TW202348937A - Method and computing device of controlling a cohort of ozone gas generating devices - Google Patents

Abstract

A method and a computing device of controlling a cohort of ozone gas generating devices. The method comprises identifying, at a computing device, a plurality of ozone gas generating devices that constitute the cohort, detecting, via at least one remote ozone gas sensor device located in a spatial area associated with the cohort in conjunction with one or more processors of the computing device, a concentration of ozone gas constituent of ambient air within the spatial area, and instructing, responsive to detecting the concentration of the ozone gas constituent as being one of above and below a predetermined threshold concentration, at least one ozone gas generating device of the cohort to perform one of increasing and decreasing a rate of ozone gas generation associated therewith.

Description

Method and computing device for controlling a group of ozone gas generating devices

This application is a continuation-in-part of, and claims priority to, U.S. Patent Application No. 17/699,488, filed March 21, 2022, the entire contents of which are incorporated herein by reference. The present disclosure relates to controlling ozone gas generating devices, including cloud-based control.

Ozone is a trace gas in the Earth's atmosphere. It is formed from a molecule composed of 3 oxygen atoms (O3) and is a powerful oxidant that has been proven to be very effective in killing bacteria, fungi and mold, and inactivating viruses. . Ozone can be used to treat potentially contaminated surfaces, water, and ambient air because of its powerful bactericidal effect on a broad spectrum of microorganisms. The ozone produced by various ozone generators can spread throughout every corner of the environment in a single room or larger space without leaving any unwanted residue. The effectiveness of ozone in treating microorganisms, especially bacteria and viruses, is related to a variety of factors, such as ozone concentration, ambient temperature, ambient humidity and contact time.

Therefore, an object of the present invention is to provide a method and a computing device for controlling a group of ozone gas generating devices.

Therefore, the present invention is a method of controlling a group of ozone gas generating devices, including: identifying at a computing device a plurality of ozone gas generating devices forming a group; The ozone gas sensor device together with one or more processors of the computing device detects a concentration of the ozone gas component of the ambient air in the spatial area; and in response to detecting that the concentration of the ozone gas component is higher and lower than One of a predetermined threshold concentration, using one or more processors, instructs at least one ozone gas generating device in the group to perform one of increasing and decreasing a rate of ozone gas generation associated therewith.

Furthermore, the present invention provides a computing device that includes a processor and a non-transitory memory including instructions that, when executed by the processor, cause the processor to perform operations including the following operations: Identifying a plurality of ozone gas generating devices forming a group; detecting, via at least one remote ozone gas sensor device located in a spatial region associated with the group together with one or more processors of the computing device, a concentration of an ozone gas component of the ambient air in the spatial region; and in response to detecting that the concentration of the ozone gas component is above one of a predetermined threshold concentration and below a predetermined threshold concentration, using one or more processors to instruct the group At least one ozone gas generating device in the group performs one of increasing and decreasing a rate of ozone gas generation associated therewith.

Before the present invention is described in detail, it should be noted that in the following description, similar elements are designated with the same numbering.

The embodiments herein recognize the need to advantageously utilize the antiviral and antimicrobial properties of ozone gas in at least partially enclosed living space environments while controlling ozone gas concentrations within acceptable levels to avoid adverse effects on humans and other organisms. influence. Embodiments herein also recognize the need for an ozone gas generator operable to increase and quickly achieve a desired ozone gas concentration in a given living space without compromising the safety of any organisms occupying that living space. In particular, embodiments herein provide an ozone gas generating device capable of operating in both a regular operating mode and a higher order operating mode characterized by an increased rate of ozone gas production, somewhat similar to a "turbo" mode of operation, but only When it is determined or felt that it is safe to do so to avoid excessive and unsafe high concentration levels that could adversely affect organisms currently residing in at least partially enclosed rooms or similar living spaces.

A method of generating ozone gas is provided. The method includes receiving an ambient air stream containing gaseous oxygen, generating ozone gas based on applying ultraviolet (UV) radiation provided at a wavelength of 185 nanometers (nm) to at least a portion of the gaseous oxygen in the ambient air stream, the ultraviolet (UV) radiation passing through An optical light module powered by a direct current (DC) battery source provides a modified airflow based on the generation and discharge of modified airflow, with the modified airflow having the ability to generate higher levels of ozone gas compared to the trace amounts of ozone gas formed in the ambient airflow. concentration of ozone gas. In one embodiment with a high safety protocol, a remote motion sensor device may be used to detect ozone gas in the surrounding environment before switching to a second mode of operation with increased ozone gas production or production rates. There is no human or biological activity in a closed room in which the generating device is located. A second altered airflow produced in this higher order or "turbocharged" mode of operation may include a higher concentration of ozone gas than the first altered airflow, and optionally at a higher concentration than the first altered airflow. High exhaust flow rates are produced. In this way, higher rates of ozone gas can be produced over a given period of time to be safely dissipated into the surrounding environment while avoiding potential adverse effects on the occupants of the space.

An ozone gas generation system is also provided that includes a processor and a non-transitory memory containing instructions. When the processor executes the instructions, the instructions cause the processor to perform operations including receiving an ambient airflow containing gaseous oxygen and applying ultraviolet (UV) irradiation with a wavelength of 185 nanometers (nm) to a portion of the gaseous oxygen constituting the ambient airflow. And produce ozone gas. UV irradiation is provided through an optical lamp module powered by a direct current (DC) battery source. The generation of ozone gas creates a modified airflow composed of ozone-rich air having a higher concentration of ozone gas than the trace amounts of ozone gas that make up the ambient airflow and is discharged to the environment through the exhaust port 110 .

Embodiments herein further recognize that when multiple ozone gas generating devices are portable and deployed individually for operation within a given space area, there is a need for human safety to ensure overall collateral effects with respect to ozone gas concentration within the space area. Optimized to advantageously utilize antiviral and antimicrobial properties simultaneously. Embodiments herein further provide methods and systems for optimizing control of a group of ozone gas generating devices that communicate at least in part through a wireless coupling with a computing device by integrating the group of devices present at any given time. Considered a self-organized ozone gas generating network of the device. In this manner, individuals in the portable ozone gas generating device can freely join or leave the self-organizing network as their physical location transitions into or out of a given spatial region. In embodiments, once the model is properly trained, the network of ozone gas generating devices can be controlled using an artificial intelligence or machine learning neural network model. In some embodiments, the control scheme may be implemented via a cloud-based server computing device, where individual ozone gas generating devices are treated as individual Internet of Things (IoT) nodes within a given ad hoc network.

A method of controlling a population of ozone gas generating devices is also provided. The method includes identifying in a computing device a plurality of ozone gas generating devices forming a group via at least one ozone gas sensor device located in a spatial region associated with the group in conjunction with one or more of the computing device a processor to detect the concentration of the ozone gas component of the ambient air in the spatial area, and using one or more processors in response to detecting that the concentration of the ozone gas component is above and below one of a predetermined threshold concentration. Indicates that at least one ozone gas generating device in the group performs one of increasing and decreasing ozone gas generating rates associated therewith. In embodiments in which the plurality of ozone gas sensor devices are located within a spatial region associated with the group, the method further includes using, at least in part, a trained machine learning model in conjunction with the plurality of ozone gas sensor devices. Detect the concentration of ozone gas components in ambient air.

A computing device is also provided, which in one embodiment may be a server computing device. The computing device includes a processor and a non-transitory memory containing instructions. When executed by the processor, the instructions cause the processor to perform operations including identifying, in a computing device, a plurality of ozone gas generating devices that constitute a group, via an ozone gas generating device located in a spatial region associated with the group. At least one ozone gas sensor device together with one or more processors of the computing device detects the concentration of the ozone gas component of the ambient air in the spatial area, and uses one or more parameters responsive to the detected concentration of the ozone gas component. The processor instructs at least one ozone gas generating device in the group to perform one of increasing and decreasing an ozone gas generating rate associated therewith above and below a predetermined threshold concentration. In embodiments where a plurality of ozone gas sensor devices are located within the spatial region associated with the group, the instructions may further execute to combine the plurality of ozone gas sensing devices using, at least in part, a trained machine learning model device to detect the concentration of ozone gas components in the ambient air.

Programmed modules may be used to implement the embodiments described herein through the use of instructions executable by one or more processors. A programmed module may include a program, a subroutine, a portion of a program, or a software component or a hardware component capable of performing one or more specified tasks or functions. As used herein, a programmed module may exist on a hardware component independently of other modules or components, or may be a shared component of other modules, programs, or machines.

One or more embodiments described herein provide methods, techniques, and actions performed in an ozone generating device and system that are performed programmatically, or as a computer-implemented method. As used herein, programmatically refers to through the use of code or computer-executable instructions. These instructions may be stored in one or more memory resources accessible to the ozone gas generating device.

FIG. 1 illustrates, in a diagram not necessarily drawn to scale, an embodiment of an ozone gas generating device 101 (also variously referred to herein as "ozone generating device 101"). In one embodiment, ozone generating device 101 includes a housing 109 having an inlet 106 for ambient air flow 107 and an exhaust 110 for exhausting ozone-enriched air flow 111. The controller module 103 may be present in a printed circuit board electrically connected to one or more optical radiation lamps 102 providing ultraviolet radiation at a wavelength of 185 nanometers (nm) and having a direct current (DC) battery 104 to provide a power source and is at least partially enclosed within a protective cylindrical housing 112 . In an embodiment, ozone generating device 101 operates at a substantially constant voltage provided by DC battery 104 . The regional ozone gas concentration sensor 108 may be electrically connected to the controller module 103 . One or more airflow pressure differential pressure-sensing fans or similar devices 105 may be deployed near the inlet 106 and capable of operating at a variable airflow pressure rate that separates higher or lower ambient air. The air flow is introduced into the ozone generating device 101 through the inlet portion 106 and affects the exiting air flow 111 at least partially at correspondingly higher and lower flow rates.

Figure 2 illustrates an ozone generation system 200 including an ozone generation device 101 in an exemplary embodiment. In related embodiments, it is contemplated that a group or group of ozone gas generating devices 101a...n (not shown) may be deployed in a given spatial region, where "n" is an integer greater than 1, representing any number of additional ozone Gas generating device. The ozone generating device 101 is communicably coupled to a mobile device 202, which may be, for example, a mobile phone or a tablet computing device. In a cloud-based system as shown in the figure, the ozone generating device 101 can also be communicatively coupled to the server computing device 203 through a communication network 204. In some embodiments, the communication network 204 can be the Internet or the like. wide area or telecommunications-based connections. In an embodiment, the mobile device 202 may be linked to the ozone generating device 101 through wireless communication protocols including but not limited to Bluetooth, Wi-Fi, LoRa, or RFID. In some embodiments, the mobile phone device 102 may include a software application capable of communicating with the ozone gas generating device 101 directly via wireless communication or via the cloud-based system 200 over the communication network 204 to set up or The application requires a threshold or acceptable range of ozone gas concentration, such as that sensed by the local ozone gas concentration sensor device 108 . In related embodiments, it is further contemplated that a deployed group of ozone gas generating devices 101a...n may be communicatively coupled to corresponding mobile devices 202a...n (not shown).

In some embodiments, the usage metrics and reporting module 206 of the server 203 within the system 200 may obtain data from the controller module 103 of the ozone generating device 101 during or after a usage session. For example, data transmission from the controller module 103 of the ozone generating device 101 may include information such as, but not limited to, user or device account information, geolocation information, timestamp information, recent and accumulated historical ozone gas production metrics during deployment, among others. One or more items. In embodiments, server 203 may be maintained at a remotely located provider service or monitoring organization that communicates over communication network 204 . It is contemplated that, in some variations, at least part of the usage metrics and reporting functionality due to usage metrics and the reporting module 206 of the server computing device 203 as described herein may be stored in a memory on the mobile computing device 202 Deployed in the body with software applications running on it. In some embodiments, the mobile computing device 202 can communicatively access the server 203 through the communication network 204 .

3 illustrates an example architecture 300 of a controller module 103 of an ozone generating device 101 deployed within an ozone generating system 200 in one embodiment. In an embodiment, the controller module 103 may include a processor 301, a memory 302 and be electrically connected to the UV radiation lamp 102 and a power supply DC battery 304. The power supply DC battery 304 may be, for example, a low power DC battery or a battery operating at 1.2V and A similar power supply operating in a range between 20V, and a communication interface 307 communicatively coupled to the communication network 204 . In some embodiments, processor 301 may be implemented in an application specific integrated circuit (ASIC) device or a field programmable gate array (FPGA) device. The memory 302 may be, for example but not limited to, a random access memory. The controller module 103 may also be coupled to ozone gas concentration sensor devices, including a local ozone gas concentration sensor device 305 positioned within the housing 109 and a remote ozone gas concentration sensor device 305 positioned external to the housing 109 , such as at the ozone generating device 101 A remote ozone gas concentration sensor device 306 is located and deployed within a room. In embodiments, the controller module 103 may also be coupled with a remote motion sensor device 308 to detect the presence of humans in the area surrounding the ozone generating device 101, such as inferred from motion or the absence of motion. Disposed in a cloud connection network including the remote motion sensor device 308 and the local ozone gas concentration sensor device 305 of the ozone gas generating device 101a...n and the server computing device 203, remote ozone gas concentration sensing The controller device 306 and the remote motion sensor device 308 may be communicatively coupled to the controller module 103 through wireless communication using Wi-Fi or similar wireless communication protocols as described herein. In some embodiments, the cloud connectivity solution can be implemented through a cloud-based server computing device 203, where the respective ozone gas generating devices 101a...n are considered to be in a given ad hoc network as a mesh or Internet of Things (IoT) nodes arranged in a star network configuration.

The controller module 103 may also include the ability to communicatively access wireless communication signals, including but not limited to any of Bluetooth, Wi-Fi, LoRa, RFID, and Global Positioning System (GPS) signals, and include a communication interface 307 communicatively coupled to the communications network 104, such as by sending and receiving data transmissions. In some embodiments, the controller module 103 may also incorporate GPS positioning functionality based on GPS receiver and transmitter circuitry for accessing and enabling the transmission of operational indicators related to the deployment of the ozone generating device 101, such as, but not It is limited to account information, location information, time stamp information related to the ozone generating device 101 and ozone gas operation data related to the ozone generating device 101 . The controller module 103 can be communicatively connected with the fan/airflow device 309. In the embodiment, the fan/airflow device 309 can be an airflow pressure differential pressure-sensing fan or device 105, as shown in FIG. 1 .

In embodiments, the ozone generator logic module 310 of the controller module 103 may be comprised of computer processor executable code stored in the memory 302 that may be executed in the processor 301 to implement as described herein The ozone gas generating functions associated with the use or deployment of the ozone gas generating device 101. In one embodiment, the software instructions or routines that make up the ozone generator logic module 310, including any updates thereto, may be processed from a remote server computing device via the communications network 204, including from the server 203 or by using the software described herein. The wireless communication protocol is accessed and downloaded from the mobile computing device 202 and downloaded to the memory 202 .

In an embodiment, the ozone generator logic module 310 of the controller module 103 enables the ozone gas generator 101 to be deployed within the ozone gas generation system 200 and is included in the non-transitory memory 302 in the processor 301 Logic instructions to execute. The instructions, when executed by the processor 301, will cause the processor 301 to perform operations including receiving an ambient airflow containing gaseous oxygen, forming a gaseous state based on applying ultraviolet (UV) radiation with a wavelength of 185 nanometers (nm) to the ambient airflow. At least a portion of the oxygen to produce ozone gas is generated and exhausted via ultraviolet irradiation provided by an optical lamp module powered by a direct current (DC) battery source to produce a modified airflow in response to the modified airflow entering through the inlet 106 The altered air flow has a higher concentration of ozone gas than a trace concentration of ozone gas formed in the ambient air flow.

In some embodiments, the ozone generator logic module 310 of the controller module 103 also contains logic instructions in the non-transitory memory 302 that are executable in the processor 301 according to the local ozone gas concentration sensor device. 305 and the remote ozone gas concentration sensor device 306 and also adjust the speed of generating ozone gas based on the remote motion sensor device 308 . In embodiments, multiple remote motion sensor devices 308 or occupancy sensors may be deployed within an area of space and communicatively coupled to the server computing device 203 and ozone gas generating sensors 101a...n. In one embodiment in accordance with an enhanced safety protocol, the remote motion sensor device 308 may be used to detect the absence of human or biological activity before switching to a second mode of operation with increased ozone gas production or rates of production. The surrounding environment, for example, is a closed room in which the ozone gas generating device is located. In embodiments, remote motion sensor device 308 may be a proximity-based sensor or may include similar sensors that are deployed to detect or infer the presence of organisms in an area of space or the surrounding environment. For example, in addition to motion sensors, ultrasonic sensors that detect movement or changes in sound waves that may be associated with the presence of living things may be deployed to infer the presence or absence of a living being within a given space around the ozone gas generating device 101 biology. Infrared radiation sensors that detect heat generated by organisms can also be deployed to infer the presence of organisms in a given space around the ozone gas generating device 101 . In some embodiments, camera imaging may be deployed to detect or infer the presence or absence of organisms. The second or alternative altered air flow produced in this higher order or "turbocharged" mode of operation may contain a higher concentration of ozone gas than the first altered air flow, and optionally in the same manner as the first altered air flow. Higher exhaust flow rates produce altered airflow. In this manner, higher rates can be deployed for a given time interval when ozone gas concentration levels within a given living space are below a required threshold level and there is no biological activity or occupation of the space. ozone gas is produced to safely disseminate to the surrounding environment while avoiding potential adverse effects on organisms within the space. In embodiments, a safe and desired threshold level of ozone gas concentration that provides effective antiviral and antimicrobial functionality as sensed by the local ozone gas sensor device 305 or the remote ozone gas sensor device 306 may be in the range of one billion range between fifty parts per billion (ppb) and 100 ppb, although other ranges or values are expected to be achieved.

In some embodiments, when a higher level or "turbo boost" mode is deployed, one or more ozone gas generating devices 101a...n or server computing device 203 may activate a warning or alarm indicating that entry into this area of space is hazardous to a Individually it is unsafe. For example, in one embodiment where the spatial area is a hotel room, a flashing LED warning light may warn an intruder trying to enter that the room is unsafe. In some variations, the warning may be further advanced to initiate a locked state of the hotel room through the existing door lock, so that the visitor will not be able to enter the room or similar enclosed area while one or more ozone gas generating devices 101a... n Operates in "Turbo" mode. Related to warnings or alerts, in one embodiment, the warning or alert may be a "Cleaning in Progress - Do Not Enter" message displayed to entrants attempting to enter the room. In related embodiments, the warning or alarm may also include a smoke alarm or piezoelectric-based buzzer that has been deployed in the hotel room through existing wireless communications, including through a WiFi connection. In other embodiments, if an unsafe ozone condition above a threshold ozone gas concentration is detected, a cloud-based alarm system, including but not limited to a smoke or fire alarm, may be triggered by the server computing device 203 .

FIG. 4 illustrates a method 400 of operation of the ozone generating device 101 in an exemplary embodiment. Examples of method steps described herein are related to the deployment and use of ozone generating device 101 as described herein. According to one embodiment, the technology is executed in a processor 301 that executes one or more software logic instruction programs that constitute the ozone generator logic module 310 of the controller module 103 . In an embodiment, instructions constituting the ozone generator logic module 310 may be read into the memory 302 from a machine-readable medium, such as a memory storage device. Execution of the instructions of the ozone generator logic module 310 stored in the memory 302 causes the processor 301 to perform the process steps described herein. In alternative implementations, at least some hardwired circuitry may be used in place of or in combination with software logic instructions to implement the examples described herein. Accordingly, the examples described herein are not limited to any specific combination of hardware circuitry and software instructions.

At step 410, an ambient airflow containing gaseous oxygen is received through an inlet in a housing of the ozone generating device.

At step 420, ozone gas is generated by applying ultraviolet (UV) irradiation with a wavelength of 185 nanometers (nm) to at least a portion of the gaseous oxygen of the ambient air flow through an optical lamp module powered by a direct current (DC) battery source. group provided. The shorter 185 nanometer wavelength ultraviolet radiation produces ozone by reacting with oxygen in the ambient air stream and breaking it down into atomic oxygen, thereby providing a highly unstable oxygen atom that then combines with oxygen in the ambient air stream to form ozone. .

At step 430, a modified airflow is generated based on the generation. In some embodiments, either the local ozone gas sensor device 305 or the remote ozone gas sensor device 306 may sense the ozone concentration produced by the ozone generator device 101 and if the sensed ozone gas concentration levels above a predetermined threshold level, the processor 301 may operate the optical lamp module 102 using an intermittent, duty cycle-based, on/off power mode that regulates ozone gas production to a more acceptable range. , and then maintain it within this range. In some example embodiments, between 50 and 500 ppb may be predetermined as such an acceptable range, although other ppb values may be used. In embodiments, the threshold level considered acceptable may be set or changed by the mobile phone device 202 from one or more pre-existing values.

In step 440, the modified airflow is discharged through an exhaust portion of the housing, the modified airflow having a higher concentration of ozone gas compared to a trace concentration of ozone gas formed in the ambient airflow.

In yet another variation, the method may include transmitting one or more of account information, location information, and timestamp information associated with ozone generator device 101 to a computing device, such as a remote server computing device. Details of its operation in ozone gas generation system 200.

Figure 5 illustrates another method of operation 500 of the ozone generating device 101 in yet another exemplary embodiment. In one embodiment in accordance with an enhanced safety protocol, the remote motion sensor device 308 may be used to detect the absence of persons or organisms in the environment before switching to a second mode of operation with increased ozone gas production or production rates. Activities, such as activities in an environment such as a closed room where an ozone gas generating device is located. The second or alternative altered air flow produced in this higher order or "turbocharged" mode of operation may contain a higher concentration of ozone gas than the first altered air flow, and optionally in the same manner as the first altered air flow. Higher exhaust flow rates produce altered airflow. In this manner, if the ozone gas concentration level within a given living space is below a required threshold level and there is no biological activity or no living organisms occupying the space as determined by the remote motion sensor device 308, the A higher production rate of deploying ozone gas over a given period of time to safely dissipate into the surrounding environment while avoiding potential adverse effects on the occupants of the space. In embodiments, a safe and desired threshold level of ozone gas concentration that provides effective antiviral and antimicrobial functionality as sensed by one of the local ozone gas sensor device 305 or the remote ozone gas sensor device 306 may In the range between 50 parts per billion (ppb) and 100 ppb. However, it is contemplated that other ranges or values may be employed; for example, within an ozone gas concentration range of 50 ppb to 500 ppb.

At step 510, conditions outside the enclosure are sensed via one or more remote ozone gas concentration sensor devices 306. In one embodiment, one or more remote motion sensor devices 308 may be used to determine the condition outside the enclosure as there are no people within a predetermined area around the enclosure.

In a further variation, using one or more remote ozone gas concentration sensor devices 306 , conditions outside the enclosure may be determined to have an ozone gas concentration below a predetermined threshold concentration, such as at the ozone gas generating device 101 In a predetermined area around the enclosure, the ozone gas concentration is in the range of 50 to 500 ppb.

At step 520, in response to the detection, switching to a second operating mode that produces a second altered air flow, the second altered air flow including at least one of the following: (i) a higher concentration of ozone than the first altered air flow gas, and (ii) a higher exhaust flow rate compared to the first altered gas flow. In this way, a higher rate of ozone gas production can be generated within a given period of time and subsequently dispersed into the surrounding environment. In one embodiment with an enhanced safety protocol, the remote motion sensor device 308 may be used to detect the absence of human activity or occupancy before switching to a second mode of operation in which ozone gas production or production rates are increased. The surrounding environment, such as a closed room where the ozone gas generating device 101 is located.

In one embodiment, the optical lamp module includes one or more optical lamps, and the second mode of operation includes activating at least one additional optical lamp of the optical lamp module.

In another variation, the second modified higher flow rate of the air flow is achieved based on changing an operating state of one or more differential pressure sensing devices at least partially disposed within the housing. This change in operating status may be accomplished in accordance with a higher order, or "turbo boost" mode, as described herein, by enabling additional fans, accelerated deployment of fans, or any combination thereof, whereby additional fans and/or Fans operating at high speeds achieve higher ozone production rates and a faster time to reach a given ozone gas concentration.

In yet another embodiment, the method includes terminating at least the second mode of operation in response to detecting that a concentration of ozone gas exceeds a predetermined threshold concentration in ppb in a region surrounding the enclosure.

Figure 6 illustrates, in one exemplary embodiment, a computing device architecture 600 incorporating an artificial intelligence machine learning based system for controlling a set of ozone gas generating devices 101a...n. As used herein, the term group refers to a group of ozone gas generating devices deployed within a given spatial area for the common or separate purpose of producing ozone gas in the ambient air of that spatial area. The spatial area can be a room, a hall, an enclosed or partially enclosed area, and can be defined in terms of location coordinates, either local or global (x,y) coordinates that define the boundaries of the spatial area or Periphery.

In a cloud-based embodiment, the server computing device 203 includes a processor 601, a memory 602, a display screen 605, an input device 604 (such as a keyboard or a touch screen input function implemented by software) and a device for communicating through a communication network. 204 communicates with the communication interface 607. Remote ozone sensor devices 606a...n are physically located in the spatial area associated with the group of ozone gas generating devices 101a...n, but communicate with server computing via wireless communication network 204 and communication interface 607 The processor 601 of the device 203 communicates communicatively. Memory 602 may include any type of non-transitory system memory that stores instructions executable in processor 601, including, for example, a static random access memory (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), read-only memory (ROM), or any combination thereof.

In a cloud-based embodiment, the ozone generation control logic module 610 includes processor-executable instructions stored in the memory 602 of the server computing device 203 , and the instructions are executable in the processor 601 . The ozone generation control logic module 610 may include portions or sub-modules including a group device identification module 611 , an artificial intelligence (AI) neural network module 612 and a group device indication module 613 .

In one embodiment, processor 201 uses executable instructions stored in group device identification module 611 to identify, at server computing device 203, a plurality of ozone gas generating devices 101a...n that form a group. Some of the ozone gas generating devices 101a...n operating within a given spatial area may be classified or assigned to belong to a group based on their physical location sensed by the server computing device 203. The spatial area may be designated as a location or perimeter based on predetermined coordinates (x, y), such as a room, a hall, or the like. The physical location of each ozone gas generating device 101a...n may be determined or estimated using a global positioning system in conjunction with a GPS receiver in the ozone generating device 101a...n, or may be estimated by wireless communication with a mobile phone 202a...n corresponds to a location corresponding to a mobile phone. In some embodiments, the ozone gas generating devices 101a...n can wirelessly communicate with a fixed wireless communication access point device in the spatial area by estimating the coordinate (x, y) position in the spatial area based on the received wireless signal strength. , such as but not limited to Bluetooth protocol.

The processor 201 uses executable instructions stored in the AI or machine learning neural network module 612 to combine operations through at least one of the ozone gas sensor devices 606a...n located in a spatial region associated with the group. One or more processors of the device 203 detect the concentration of an ozone gas component of the ambient air in the spatial area. In embodiments, detecting the concentration of ozone gas components in ambient air may be based at least in part on using a trained machine learning model in conjunction with a plurality of ozone gas sensor devices 606a...n.

In one embodiment, a neural network is configured with a set of input layers, an output layer, and one or more intermediate layers connecting the input and output layers. In embodiments, the input layers are associated with input features or input attributes related to digital advertising data, such as, but not limited to, digital advertising data acquired, created or accessed via the mobile computing device 103 . The output attribute generation module 212 may present the resulting output attributes on a user interface including a display screen 203 or other display interface device capable of selecting specific attributes among the output attributes to be generated.

The trained neural network may be deployed based at least in part on adjusting an initial weight matrix when the output layer generates at least one digital advertising output attribute based on a corresponding one of the set of input layers. In some embodiments, the output attribute relates to a benefit or a result that would be a desired result from the group of ozone gas generating devices 101a...n within the spatial region. In an embodiment, adjusting includes recursively adjusting the initial weight matrix via backpropagation when generating the output attributes. The output attributes are generated based on recursive adjustments based on the reduction of an error matrix calculated at the output layer of the neural network. In an embodiment, backpropagation includes backpropagation of errors based on an error matrix computed at the output layer, with the errors being inversely distributed throughout the weights of intermediate layers of the neural network.

In a specific embodiment of a convolutional neural network model, the convolution operation typically contains two parts of input: (i) input feature map data, and (ii) a weight, also called an output filter or kernel. Given input channel data with W(width) x H(height) x IC data cube and RxSxIC filter, the output of direct convolution can be expressed as: Among them: Output data/output features/output feature map W = filter/kernel/weight

Machine learning inference and training networks are often configured to contain many convolutional layers. Typically, the output of one convolutional layer becomes the input of the next convolutional layer. For each input channel, a filter or weight is convolved with the data and produces output data. Sums the data at the same location for all input channels and produces the channel output data. Based on an input data stream of digital parameters, weights are used to detect a specific defect characteristic or type.

Each output channel of a convolutional model is represented by an output filter or weight that is used to detect a specific feature or pattern in the input feature data stream. A convolutional network can be composed of many output filters or weights for each layer of the convolutional model that correspond to individual features or patterns in the input attribute data stream.

Although the example embodiments herein relate to a convolutional neural network, it is contemplated that other neural network models may be applied, including a recurrent neural network model, including hybrid models that combine aspects of the neural network models.

The processor 201 uses executable instructions stored in the group device instruction module 613 to instruct the ozone gas generating device in response to detecting that the concentration of the ozone gas component is above or below one of a predetermined threshold concentration. At least one ozone gas generating device in the group 101a...n increases or decreases its ozone gas generation rate. In an embodiment, the instructions may be implemented by processor 601 transmitting one or more encoded commands to one or more ozone gas generating devices 101a...n, such as via communication interface 607 and over communication network 204.

Figure 7 illustrates, in an exemplary embodiment, a method 700 of controlling a population of ozone gas generating devices 101a...n, which incorporates a system based on artificial intelligence machine learning neural networks.

At step 710, a plurality of ozone gas generating devices 101a...n forming a group are identified at the computing device 203.

At step 720, ambient air in a spatial region associated with the group is detected via at least one remote ozone gas sensor device 606a...n located in the spatial region in conjunction with one or more processors 601 of the computing device 203. A concentration of the ozone gas component.

At step 730, in response to detecting that the concentration of the ozone gas component is above and below one of a predetermined threshold concentration, one or more processors 601 are used to instruct at least one ozone gas generating device of the group of ozone gas generating devices 101a...n Performs an increase and decrease associated with one of the ozone gas production rates.

In an embodiment, the at least one remote ozone gas sensor device includes a plurality of remote ozone gas sensor devices 606a...n located within a spatial region associated with the group, but not necessarily within the ozone gas generating device 101a...n, which is distinct from the local ozone gas concentration sensor 108, and the method further includes detecting ambient air using, at least in part, a trained machine learning model in conjunction with a plurality of ozone gas sensor devices 606a...n The concentration of the ozone gas component in the In one aspect, the trained machine learning model includes one of a trained convolutional neural network and a trained recurrent neural network.

In one variation, in response to the instruction, at least one ozone gas generating device of the group of ozone gas generating devices 101a...n increases its associated ozone gas in response to switching from a first mode to a second mode of ozone gas generation. The second ozone gas generation mode has a higher ozone gas generation rate compared to the first mode.

In one aspect, at least one ozone generating device includes an optical lamp module composed of a plurality of optical lamps 102 , and the second mode of ozone gas generation includes activating at least one additional optical lamp of the plurality of optical lamps 102 .

In yet another aspect, in response to the instruction, at least one ozone gas generating device in the group of ozone gas generating devices 101a...n reduces its associated ozone gas generation rate according to at least one of the following two points, (i) from a second mode switching to a first mode of ozone gas generation, and (ii) switching from an operating state to a non-operating state, where the operating state refers to a state of actively generating ozone gas, and the non-operating state may be a power outage or no generation Inactive state of ozone gas.

In yet another embodiment, at least one ozone generating device includes an optical lamp module composed of a plurality of optical lamps 102, and the first mode of ozone gas generation includes deactivating at least one of the plurality of optical lamps 102.

Figure 8 illustrates, in an exemplary embodiment 800, input data sets 801 and output attributes 802 of an artificial intelligence machine learning based system including a neural network model for controlling a set of ozone gas generating devices 101a...n Group 612. In one aspect, the input data set 801 includes one or more of the following: an ozone gas generating capability in a normal operating mode, an ozone gas generating capability in an advanced operating mode, position coordinates defining the outer boundary or perimeter of a given spatial region, in The coordinate position of the ozone gas generating device in the spatial area, the model identification of the ozone gas generating device, the device operation reliability index, the device wireless communication reliability index and the historical and accumulated ozone gas generation index of the device. In an embodiment, the output attribute 802 includes a desired concentration of ozone gas formed in the ambient airflow of the spatial region.

Figure 9 illustrates a method 900 of training an artificial intelligence machine learning based system to control a set of ozone gas generating devices 101a...n in one embodiment. It is contemplated that, in embodiments, training may implement supervised learning techniques, unsupervised learning techniques, or some combination thereof.

At step 910, a corresponding one of a plurality of input layers of a neural network that is instantiated in one or more processors and has a set of input data via an intermediate layer receives a plurality of input data sets. An output layer connected to a plurality of input layers, each of the plurality of input data sets including an input attribute associated with some of the plurality of ozone gas generating devices, some of the intermediate set of layers configured according to an initial weight matrix of.

At step 920, training the neural network based at least in part on recursively adjusting the initial weight matrix through backpropagation based on corresponding ones of the plurality of input layers based on the reduction of an error matrix calculated at the output layer of the neural network, Generate an output attribute in the output layer. When deploying a trained neural network, in one embodiment, the output attribute may be a desired target ozone gas concentration level constituted in the environment of a given spatial region relevant to training. In this way, a machine learning network is trained to predict the outcome of ozone gas concentration in ambient air for a given spatial region with a population of operating ozone gas generating devices 101a...n, using backpropagation to update the neural parameters of the network so that it can perform predictions more accurately. In a particular embodiment, the desired target ozone gas concentration corresponding to the output attribute 802 of the neural network may be predetermined to be 100 ppb, although it is contemplated that other ozone gas concentration levels within a range between 50 ppb and 500 ppb may be implemented. of.

Supervised learning as used in this article refers to a method of training a machine learning (ML) algorithm based on a labeled input data set, while guiding the ML algorithm model learning based on expert knowledge of the characteristics of the ozone gas generation device used to provide feedback. This ML algorithm learns a mapping function from input features to desired output attributes. The input data set labels through the training application can be related to characteristics related to the ozone gas generating device, such as, but not limited to, ozone gas generating capabilities in normal operating modes, ozone gas generating capabilities in high-order operating modes, and defining a given spatial area. The position coordinates of the external boundary or periphery, the coordinate position of the ozone gas generating device in the spatial area, the model identification of the ozone gas generating device, the device operation reliability index, the device wireless communication reliability index and the historical and accumulated ozone gas production of the device indicators.

In unsupervised learning embodiments, clustering techniques or algorithms may be applied to find natural groups or clusters in ozone gas generating device characteristics to interpret the input data. In one embodiment, the unsupervised learning technique employs a clustering algorithm that identifies one or more clusters in ozone gas generating device attributes and applies corresponding dataset labels to the input dataset features.

In embodiments, when a trained neural network is deployed in a production or normal use environment, the neural network can undergo and undergo continuous learning and accuracy improvements as originally trained, and thus benefit from Additional subsequent input data sets acquired during regular use.

Although embodiments are described in detail herein with reference to the accompanying drawings, it is contemplated that the disclosure herein is not limited to such literal embodiments. Accordingly, many modifications including variations in the order of method steps in combination with variations in the user interface features disclosed herein will be apparent to those skilled in the art. Accordingly, the scope of the invention is intended to be defined by the appended claims and their equivalents. Furthermore, it is contemplated that a particular feature described alone or as part of an embodiment may be combined with other individually described features or parts of other embodiments. Accordingly, the failure to describe such combinations does not preclude the inventor from claiming rights to such combinations.

However, the above are only examples of the present invention, and should not be used to limit the scope of the present invention. All simple equivalent changes and modifications made based on the patent scope of the present invention and the content of the patent specification are still within the scope of the present invention. Within the scope covered by the patent of this invention.

101: Ozone (gas) generating device 102: Optical (radiation) lamp/UV radiation lamp 103:Controller module 104: Direct current (DC) battery 105: Air flow pressure differential - induction fan or similar device 106: Entrance Department 107:Ambient airflow 108: Ozone gas concentration sensor 109: Shell 110:Exhaust part 111:Airflow 200:Ozone generation system 202:Mobile device 203:Server computing device 204:Communication network 206: Using Metrics and Reporting Modules 300: Sample architecture 301: Processor 302:Memory 304:Power supply DC battery 305: Local ozone gas concentration sensor device 306: Remote ozone gas concentration sensor device 307: Communication interface 308: Remote motion sensor device 309:Fan/airflow device 310: Ozone generator logic module 400, 500, 700, 900: Method 410, 420, 430, 440, 510, 520, 710, 720, 730, 910, 920: steps 600:Computing device architecture 601: Processor 602:Memory 604:Input device 605:Display screen 606: Remote ozone sensor device 607: Communication interface 610: Ozone generation control logic module 611: Group device identification module 612: (Artificial Intelligence (AI)) Neural Network Module 613:Group device indication module 800: Exemplary embodiment 801:Input data set 802: Output attributes

Other features and effects of the present invention will be clearly shown in the embodiments with reference to the drawings, in which: Figure 1 shows an ozone gas generating device in an exemplary embodiment. Figure 2 illustrates an ozone gas generation system including an ozone gas generation device in an exemplary embodiment. Figure 3 illustrates an example architecture of an ozone gas generating device deployed in an ozone generating system in an exemplary embodiment. Figure 4 illustrates a method of operating an ozone generating device in an exemplary embodiment. Figure 5 illustrates, in yet another exemplary embodiment, a method of operation of an ozone generating device according to a higher order method of operation. 6 illustrates, in an exemplary embodiment, a computing device architecture incorporating an artificial intelligence machine learning based system for controlling a group of ozone gas generating devices. Figure 7 illustrates, in an exemplary embodiment, a method of controlling a set of ozone gas generating devices incorporating a system based on artificial intelligence machine learning. 8 illustrates, in an exemplary embodiment, input data sets and output attributes of an artificial intelligence machine learning based system for controlling a set of ozone gas generating devices. Figure 9 illustrates, in one embodiment, a method of training a system based on artificial intelligence machine learning to control a set of ozone gas generating devices.

700:Method

710~730: steps

Claims (20)

A method of controlling a group of ozone gas generating devices, the method comprising: Identifying at a computing device a plurality of ozone gas generating devices forming a group; detecting a concentration of an ozone gas component of the ambient air in a spatial area associated with the group via at least one remote ozone gas sensor device located in the spatial area associated with the group together with one or more processors of the computing device; and In response to detecting that the concentration of the ozone gas component is above and below one of a predetermined threshold concentration, one or more processors are used to instruct at least one ozone gas generating device in the group to perform an increase and decrease associated therewith. One of the rates at which ozone gas is produced. The method of claim 1, wherein the at least one remote ozone gas sensor device includes a plurality of remote ozone gas sensor devices located within the spatial area associated with the group. , and also includes detecting the concentration of the ozone gas component in the ambient air using, at least in part, a trained machine learning model in combination with a plurality of remote ozone gas sensor devices. The method of claim 2 further includes a trained machine learning model generated through a training process, the training process including: A plurality of input data sets are received by respective ones of a plurality of input layers of a neural network implemented in one or more processors and having connections to the plurality of input layers via a set of intermediate layers. an output layer, each of the plurality of input data sets including an input attribute associated with some of the plurality of ozone gas generating devices, some of the intermediate set of layers configured according to an initial weight matrix; and Training the neural network based at least in part on recursively adjusting the initial weight matrix through backpropagation based on corresponding ones of the plurality of input layers, generating at the output layer based on the reduction of an error matrix calculated at the output layer of the neural network An output attribute. The method according to claim 3, wherein the plurality of input data sets include one or more of the following: ozone gas production capacity in normal operation mode, ozone gas production capacity in high-order operation mode, definition-given The position coordinates of the outer boundary or periphery of the space area, the coordinate position of the ozone gas generation device in the space area, the model identification of the ozone gas generation device, device operation reliability indicators, device wireless communication reliability indicators and device history, accumulation of ozone gas production indicators. The method of claim 3, wherein the output attribute includes a desired concentration of ozone gas formed in the ambient air of the spatial region. The method of claim 2, wherein the trained machine learning model includes one of a trained convolutional neural network and a trained recurrent neural network. The method of claim 1, wherein, in response to the indication, at least one ozone gas generating device of the group increases its associated ozone according to switching from a first mode of ozone gas generation to a second mode. Gas production rate, the second mode of ozone gas production has a higher ozone gas production rate compared to the first mode. The method of claim 7, wherein the at least one ozone generating device includes an optical lamp module composed of a plurality of optical lamps, and the second mode of ozone gas generation includes activating one of the plurality of optical lamps. of at least one additional optical light. The method of claim 7, wherein, in response to the indication, at least one ozone gas generating device of the group reduces its associated ozone gas generation rate according to one of the following: (i) from a second ozone gas generated mode switching to the first mode, and (ii) switching from an operating state to a non-operating state. The method of claim 9, wherein the at least one ozone generating device includes an optical lamp module composed of a plurality of optical lamps, and the first mode of ozone gas generation includes deactivating one of the plurality of optical lamps. At least one optical light. A computing device including: a processor; and A non-transitory memory containing instructions that, when executed by the processor, cause the processor to perform operations including: Identifying at a computing device a plurality of ozone gas generating devices forming a group; Detecting an ozone gas component of ambient air in a spatial area associated with the group via at least one remote ozone gas sensor device located in the spatial area associated with the group in conjunction with one or more processors of the computing device concentration; and In response to detecting that the concentration of the ozone gas component is one of above and below a predetermined threshold concentration, using one or more processors to instruct at least one ozone gas generating device in the group to perform increases and decreases associated therewith One of the rates at which ozone gas is produced. The computing device of claim 11, wherein the at least one remote ozone gas sensor device includes a plurality of remote ozone gas sensor devices located within the spatial area associated with the group, and further comprising The concentration of the ozone gas component in the ambient air is detected at least in part using a trained machine learning model in conjunction with a plurality of remote ozone gas sensor devices. The computing device of claim 12 further includes instructions executable in the processor to generate a trained machine learning model through a training process, the training process including: A plurality of input data sets are received by respective ones of a plurality of input layers of a neural network implemented in one or more processors and having connections to the plurality of input layers via a set of intermediate layers. an output layer, each of the plurality of input data sets including an input attribute associated with some of the plurality of ozone gas generating devices, some of the intermediate set of layers configured according to an initial weight matrix; and Training the neural network based at least in part on recursively adjusting the initial weight matrix through backpropagation based on corresponding ones of the plurality of input layers, generating at the output layer based on the reduction of an error matrix calculated at the output layer of the neural network An output attribute. The computing device according to claim 13, wherein the plurality of input data sets include one or more of the following: ozone gas production capacity in normal operation mode, ozone gas production capacity in high-order operation mode, definition-given The position coordinates of the outer boundary or periphery of a certain space area, the coordinate position of the ozone gas generation device in the space area, the model identification of the ozone gas generation device, the device operation reliability index, the device wireless communication reliability index and the device history, Cumulative ozone gas production indicator. The computing device of claim 13, wherein the output attribute includes a desired concentration of ozone gas formed in the ambient air of the spatial area. The computing device of claim 12, wherein the trained machine learning model includes one of a trained convolutional neural network and a trained recurrent neural network. The computing device of claim 11, wherein, in response to the instruction, at least one ozone gas generating device of the group increases its associated data according to switching from a first mode of ozone gas generation to a second mode. Ozone gas production rate, the second mode of ozone gas production has a higher ozone gas production rate compared to the first mode. The computing device of claim 17, wherein the at least one ozone generating device includes an optical lamp module composed of a plurality of optical lamps, and the second mode of ozone gas generation includes activating the plurality of optical lamps. at least one additional optical light. The computing device of claim 17, wherein, in response to the indication, at least one ozone gas generation device of the group reduces its associated ozone gas generation rate according to one of the following: (i) a first ozone gas generation device generated from ozone gas; switching from the second mode to the first mode, and (ii) switching from an operating state to a non-operating state. The computing device of claim 19, wherein the at least one ozone generating device includes an optical lamp module composed of a plurality of optical lamps, and the first mode of ozone gas generation includes deactivating one of the plurality of optical lamps. of at least one optical light.

Images