Control method of negative oxygen ion generator

Abstract

The invention discloses a control method of a negative oxygen ion generator, and relates to the technical field of intelligent control of the negative oxygen ion generator, and the method comprises the steps: carrying out the anti-interference processing of collected environment data, and forming anti-interference data; analyzing the anti-interference data to obtain an analysis environment result, and recording preference information set by a user at the same time; generating a working scheme according to an environment analysis result and user preference information, and predicting an optimal working state; and optimizing a negative oxygen ion generation mode according to the optimal working state, detecting an ozone generation index, and generating a safety state report. According to the method, the graphical user interface is loaded, the sensor network is started to collect the environment data, and the random forest classifier is used for anti-interference processing, so that efficient and accurate data collection and preprocessing are realized, then the reliability and accuracy of subsequent analysis are ensured, and finally the effect of improving stability and data quality is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of intelligent control of negative oxygen ion generators, in particular to a control method of a negative oxygen ion generator. Background Art

[0002] As a device that can improve indoor air quality and enhance human health, negative oxygen ion generators have received widespread attention and rapid development in recent years. As people's requirements for the quality of living environment continue to increase, negative oxygen ion generators are not only widely used in home environments, but also play an important role in health care, air purification and other fields. Early negative oxygen ion generators mainly relied on simple corona discharge or plasma technology. Although these methods can generate negative oxygen ions to a certain extent, they have many limitations, such as the generation of ozone byproducts, unstable concentration of negative oxygen ions, and poor anti-interference ability.

[0003] In recent years, with the advancement of sensor technology and intelligent control, negative oxygen ion generators have gradually developed towards intelligence and high precision. Modern negative oxygen ion generators are usually equipped with various types of sensors for real-time monitoring of environmental parameters (such as temperature, humidity, air quality, etc.), and adjust the working mode through built-in control programs to optimize the generation efficiency of negative oxygen ions. In addition, the application of machine learning and artificial intelligence algorithms enables the device to automatically adjust the working state according to environmental changes, further improving the performance of the device and user experience. However, despite significant technological progress, the existing technology still has some shortcomings, especially in anti-interference processing and adaptation to user personalized needs. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a control method for a negative oxygen ion generator to solve the problems of anti-interference processing of environmental data and insufficient adaptation to user personalized needs.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a control method for a negative oxygen ion generator, which includes performing anti-interference processing on collected environmental data to form anti-interference data; analyzing the anti-interference data to obtain environmental analysis results, and simultaneously recording preference information set by the user; generating a work plan based on the environmental analysis results and the user preference information, and predicting an optimal working state; optimizing the negative oxygen ion generation mode based on the optimal working state, detecting ozone generation indicators, and generating a safety status report.

[0008] As a preferred solution of the control method of the negative oxygen ion generator of the present invention, wherein: the collected environmental data is subjected to anti-interference processing to form anti-interference data, and the specific steps are as follows:

[0009] Load the graphical user interface, set parameters through the graphical user interface, and start the sensor network to collect environmental data;

[0010] Use historical data to train a random forest classifier, and use the trained random forest classifier to perform anti-interference processing on environmental data. The expression is:

[0011]

[0012] Among them, Y is the environmental data after anti-interference processing, F(x i ,θ) is the application of the trained random forest classifier to the input environmental data x i The probability score obtained when making a prediction, w i is the importance weight of the i-th sensor data, n is the number of sensor data, θ is the parameter set of the random forest classifier, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, and γ is the observed average value of the current environmental condition.

[0013] As a preferred solution of the control method of the negative oxygen ion generator of the present invention, wherein: the pre-processed environmental data is analyzed and user preference information is recorded at the same time, the specific steps are as follows:

[0014] The environmental data after anti-interference processing is obtained through sensors, and a comprehensive evaluation function is introduced to analyze the environmental data after anti-interference processing. The expression is:

[0015]

[0016] Among them, A is the comprehensive evaluation score, Y is the environmental data after anti-interference processing, n is the number of sensor data, and w i is the importance weight of the i-th sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, and γ is the average value of the current environmental condition observation;

[0017] Enter the graphical user interface by starting an application on the device, enter the preference setting page through the graphical user interface, set preference information in the preference setting page, and record the user's preference information.

[0018] As a preferred solution of the control method of the negative oxygen ion generator of the present invention, wherein: the working plan is generated according to the environmental analysis results and the user preference information, and the specific steps are as follows:

[0019] Based on the environmental analysis results and user preference information, the grid search method is used to generate different parameter combinations of negative oxygen ion generation modes, the candidate work plans are formed, the comprehensive work plan scoring function is designed, and the comprehensive work plan score is predicted. The expression is:

[0020]

[0021] Among them, S is the comprehensive work plan score, w i is the importance weight of the i-th sensor data, n is the number of sensor data, A i is the comprehensive evaluation score, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, γ is the observed average value of the current environmental condition, U(u,p) is the user preference information, u is the user identifier, and p is the environmental parameter.

[0022] The comprehensive work plan scoring function is used to calculate the comprehensive work plan scores of the candidate work plans, and the candidate work plan with the highest score is selected from the work plan scores as the work plan.

[0023] As a preferred solution of the control method of the negative oxygen ion generator of the present invention, the specific steps of predicting the optimal working state are as follows:

[0024] Collect performance data through sensors, use the deep learning framework to define the architecture of the deep Q network DQN, input the performance data into the architecture of the deep Q network DQN, use the back propagation algorithm and Adam to get the trained deep Q network DQN, input the work plan into the trained deep Q network DQN to predict the best working state, the expression is:

[0025]

[0026] Among them, O i is the equipment parameter corresponding to the i-th sensor data under the predicted optimal working state, S is the comprehensive working plan score, and s t is the environmental data at time t, a t is the equipment parameter at time t, w i is the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, γ is the average value of the current environmental condition observation, Q(s t ,a t ) is the expected return of the equipment parameters taken under the environmental state at time t;

[0027] Record the device parameters corresponding to the sensor data under the predicted optimal working state to form the optimal working state.

[0028] As a preferred solution of the control method of the negative oxygen ion generator of the present invention, wherein: the negative oxygen ion generation mode is optimized according to the optimal working state, and the specific steps are as follows:

[0029] The actual values ​​of the equipment parameters corresponding to the sensor data are collected in real time through sensors, and the comprehensive work plan score function is used to calculate the comprehensive work plan score of the current work plan. The dynamic adjustment value function is defined based on the optimal working state. The expression is:

[0030]

[0031] Among them, D is the dynamic adjustment value, O i is the target value of the equipment parameter corresponding to the i-th sensor data under the predicted optimal working state, C i is the actual value of the equipment parameter corresponding to the i-th sensor data, S is the comprehensive work plan score, and w i is the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, and γ is the average value of the current environmental condition observation;

[0032] Calculate the dynamic adjustment value of the negative oxygen ion generation mode;

[0033] Define a dynamic adjustment threshold τ according to the dynamic adjustment value;

[0034] If the absolute value of the dynamic adjustment value |D| is greater than the dynamic adjustment threshold τ, the parameters of the negative oxygen ion generation mode are adjusted;

[0035] If the absolute value |D| of the dynamic adjustment value is not greater than the dynamic adjustment threshold τ, the parameters of the negative oxygen ion generation mode are not adjusted.

[0036] As a preferred solution of the control method of the negative oxygen ion generator of the present invention, the specific steps of detecting the ozone generation index are as follows:

[0037] The actual value of the device parameter corresponding to each sensor data after adjustment is obtained from the optimized negative oxygen ion generation mode. Based on the optimized negative oxygen ion generation mode, an ozone generation detection function is introduced to quantify the ozone generation situation. The expression is:

[0038]

[0039] Among them, Z t is the ozone generation index at time t, is the actual value of the device parameter corresponding to the i-th sensor data after adjustment, w iis the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of environmental conditions, γ is the average value of current environmental conditions, δ is the adjustment coefficient of ozone generation efficiency, μ is the expected optimal performance value, and s t is the environmental data at time t;

[0040] The ozone generation detection function is used to calculate the ozone generation index at each time point and record the ozone generation index.

[0041] As a preferred solution of the control method of the negative oxygen ion generator of the present invention, the specific steps of generating a safety status report are as follows:

[0042] The ozone generation indicators are summarized to form a detection data set, and the comprehensive risk assessment indicators are used to assess the ozone generation risk. The expression is:

[0043]

[0044] Among them, R is the comprehensive risk assessment index, Z t is the ozone generation index at time t, w i is the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, γ is the average value of the current environmental condition observation, μ is the expected optimal performance value, and s t is the environmental data at time t, κ is the risk sensitivity coefficient;

[0045] Calculate comprehensive risk assessment indicators in real time and record them;

[0046] Defining the comprehensive risk assessment threshold R based on the comprehensive risk assessment index th , when the comprehensive risk assessment index is greater than the comprehensive risk assessment threshold R th When the negative oxygen ion generator is turned off, the user is reminded that the device has stopped running and the window has been opened;

[0047] At the same time, it checks the ozone generation index, calculates the comprehensive evaluation score, and generates a safety status report.

[0048] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the control method of the negative oxygen ion generator as described in the first aspect of the present invention is implemented.

[0049] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the control method of the negative oxygen ion generator as described in the first aspect of the present invention is implemented.

[0050] The beneficial effects of the present invention are as follows: by loading a graphical user interface, starting the sensor network to collect environmental data and using a random forest classifier for anti-interference processing, efficient and accurate data collection and preprocessing are achieved, and then the reliability and accuracy of subsequent analysis are ensured, and finally the effect of improving stability and data quality is achieved. By defining a dynamic adjustment value function, and defining a dynamic adjustment threshold τ according to the dynamic adjustment value, the negative oxygen ion generation mode parameters that exceed the threshold are adjusted, and intelligent working mode optimization is achieved, and then the device is always in the optimal working state, and finally the effect of improving the negative oxygen ion generation efficiency, reducing resource waste and reducing the risk of harmful by-product generation is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0052] Figure 1 This is a flow chart of the control method of the negative oxygen ion generator in Example 1.

[0053] Figure 2 This is a schematic diagram of optimizing the negative oxygen ion generation mode according to the optimal working state in Example 1. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0055] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0056] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0057] Example 1, reference Figure 1 and Figure 2, which is the first embodiment of the present invention, provides a control method for a negative oxygen ion generator, comprising the following steps:

[0058] S1: Perform anti-interference processing on the collected environmental data to form anti-interference data;

[0059] Load the graphical user interface, set parameters through the graphical user interface, and start the sensor network to collect environmental data;

[0060] Use historical data to train a random forest classifier, and use the trained random forest classifier to perform anti-interference processing on environmental data. The expression is:

[0061]

[0062] Among them, Y is the environmental data after anti-interference processing, F(x i ,θ) is the application of the trained random forest classifier to the input environmental data x i The probability score obtained when making a prediction, w i is the importance weight of the i-th sensor data, n is the number of sensor data, θ is the parameter set of the random forest classifier, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, and γ is the observed average value of the current environmental condition.

[0063] It should also be noted that the use of a trained random forest classifier to perform anti-interference processing on environmental data can cope with complex and changeable environmental conditions, thereby improving the stability and performance of the entire negative oxygen ion generator.

[0064] S2: Analyze the anti-interference data to obtain an analysis environment result, and simultaneously record the preference information set by the user;

[0065] The environmental data after anti-interference processing is obtained through sensors, and a comprehensive evaluation function is introduced to analyze the environmental data after anti-interference processing. The expression is:

[0066]

[0067] Among them, A is the comprehensive evaluation score, Y is the environmental data after anti-interference processing, n is the number of sensor data, and w i is the importance weight of the i-th sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, and γ is the average value of the current environmental condition observation;

[0068] Enter the graphical user interface by starting an application on the device, enter the preference setting page through the graphical user interface, set preference information in the preference setting page, and record the user's preference information.

[0069] It should also be noted that: through in-depth analysis of the environmental data after anti-interference processing, a comprehensive evaluation score was obtained. The comprehensive evaluation score quantifies the quality of the environmental data and ensures that subsequent decisions are based on high-quality data;

[0070] The user's preference information, including user identification and environment parameters, is recorded through the graphical user interface.

[0071] S3: Generate a work plan based on the environmental analysis results and user preference information;

[0072] Based on the environmental analysis results and user preference information, the grid search method is used to generate different parameter combinations of negative oxygen ion generation modes, the candidate work plans are formed, the comprehensive work plan scoring function is designed, and the comprehensive work plan score is predicted. The expression is:

[0073]

[0074] Among them, S is the comprehensive work plan score, w i is the importance weight of the i-th sensor data, n is the number of sensor data, A is the comprehensive evaluation score, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, γ is the observed average value of the current environmental condition, U(u,p) is the user preference information, u is the user identifier, and p is the environmental parameter.

[0075] The comprehensive work plan scoring function is used to calculate the comprehensive work plan scores of the candidate work plans, and the candidate work plan with the highest score is selected from the work plan scores as the work plan.

[0076] S4: Predict optimal working state;

[0077] Collect performance data through sensors, use the deep learning framework to define the architecture of the deep Q network DQN, input the performance data into the architecture of the deep Q network DQN, use the back propagation algorithm and Adam to get the trained deep Q network DQN, input the work plan into the trained deep Q network DQN to predict the best working state, the expression is:

[0078]

[0079] Among them, O i is the equipment parameter corresponding to the i-th sensor data under the predicted optimal working state, S is the comprehensive working plan score, and s t is the environmental data at time t, a t is the equipment parameter at time t, w i is the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, γ is the average value of the current environmental condition observation, Q(s t,a t ) is the expected return of the equipment parameters taken under the environmental state at time t;

[0080] Record the device parameters corresponding to the sensor data under the predicted optimal working state to form the optimal working state.

[0081] It should also be noted that the trained deep Q network DQN can automatically learn and adjust in a complex and changing environment, find the optimal working state, and ensure that the negative oxygen ion generator is always in an efficient and safe operation mode.

[0082] S5: Optimizing the negative oxygen ion generation mode according to the optimal working state;

[0083] The actual values ​​of the equipment parameters corresponding to the sensor data are collected in real time through sensors, and the comprehensive work plan score function is used to calculate the comprehensive work plan score of the current work plan. The dynamic adjustment value function is defined based on the optimal working state. The expression is:

[0084]

[0085] Among them, D is the dynamic adjustment value, O i is the target value of the equipment parameter corresponding to the i-th sensor data under the predicted optimal working state, C i is the actual value of the equipment parameter corresponding to the i-th sensor data, S is the comprehensive work plan score, and w i is the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, and γ is the average value of the current environmental condition observation;

[0086] Calculate the dynamic adjustment value of the negative oxygen ion generation mode;

[0087] Define a dynamic adjustment threshold τ according to the dynamic adjustment value;

[0088] If the absolute value of the dynamic adjustment value |D| is greater than the dynamic adjustment threshold τ, the parameters of the negative oxygen ion generation mode are adjusted;

[0089] If the absolute value |D| of the dynamic adjustment value is not greater than the dynamic adjustment threshold τ, the parameters of the negative oxygen ion generation mode are not adjusted.

[0090] It should also be noted that: the value of the dynamic adjustment threshold τ is set to 0.2. If |D| is greater than τ and D is less than 0, the voltage output, fan speed and the working intensity of the negative oxygen ion generator are gradually increased. Each voltage output adjustment is 0.1V, each fan speed adjustment is 50RPM, and each negative oxygen ion generator The working intensity adjustment range is one thousand negative oxygen ions per cubic centimeter. If |D| is greater than τ and D is greater than 0, the voltage output, fan speed and the working intensity of the negative oxygen ion generator are gradually reduced. Each voltage output adjustment range is 0.1V, each fan speed adjustment range is 50RPM, and each negative oxygen ion generator The working intensity adjustment range is one thousand negative oxygen ions per cubic centimeter, until |D| is less than τ.

[0091] S6: Detect ozone generation indicators;

[0092] The actual value of the device parameter corresponding to each sensor data after adjustment is obtained from the optimized negative oxygen ion generation mode. Based on the optimized negative oxygen ion generation mode, an ozone generation detection function is introduced to quantify the ozone generation situation. The expression is:

[0093]

[0094] Among them, Z t is the ozone generation index at time t, is the actual value of the device parameter corresponding to the i-th sensor data after adjustment, w i is the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of environmental conditions, γ is the average value of current environmental conditions, δ is the adjustment coefficient of ozone generation efficiency, μ is the expected optimal performance value, and s t is the environmental data at time t;

[0095] The ozone generation detection function is used to calculate the ozone generation index at each time point and record the ozone generation index.

[0096] It should also be noted that the introduction of the ozone generation detection function can monitor and evaluate the ozone generation of the negative oxygen ion generator in different working modes in real time.

[0097] S7: Generate a security status report.

[0098] The ozone generation indicators are summarized to form a detection data set, and the comprehensive risk assessment indicators are used to assess the ozone generation risk. The expression is:

[0099]

[0100] Among them, R is the comprehensive risk assessment index, Z t is the ozone generation index at time t, w iis the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, γ is the average value of the current environmental condition observation, μ is the expected optimal performance value, and s t is the environmental data at time t, κ is the risk sensitivity coefficient;

[0101] Calculate comprehensive risk assessment indicators in real time and record them;

[0102] Defining the comprehensive risk assessment threshold R based on the comprehensive risk assessment index th , when the comprehensive risk assessment index is greater than the comprehensive risk assessment threshold R th When the negative oxygen ion generator is turned off, the user is reminded that the device has stopped running and the window is opened;

[0103] At the same time, it checks the ozone generation index, calculates the comprehensive evaluation score, and generates a safety status report.

[0104] It should also be noted that: citing comprehensive risk assessment indicators to assess ozone generation risk ensures the accuracy and reliability of safety status reports;

[0105] The comprehensive risk assessment threshold R th The value of is set to 0.6;

[0106] The safety status report includes the current ozone generation index, the comprehensive evaluation score of the current environmental data and the current environmental data. The safety status report is output to the user through a graphical user interface to help the user understand the operation status and potential risks of the equipment.

[0107] This embodiment also provides a computer device, which is suitable for the control method of the negative oxygen ion generator, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the control method of the negative oxygen ion generator proposed in the above embodiment.

[0108] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0109] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by the processor, the control method of the negative oxygen ion generator proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0110] In summary, the present invention achieves efficient and accurate data collection and preprocessing by: loading a graphical user interface, starting a sensor network to collect environmental data, and using a random forest classifier for anti-interference processing, and then ensures the reliability and accuracy of subsequent analysis, and finally achieves the effect of improving stability and data quality. By defining a dynamic adjustment value function, and defining a dynamic adjustment threshold τ according to the dynamic adjustment value, the negative oxygen ion generation mode parameters that exceed the threshold are adjusted, and intelligent working mode optimization is achieved, and then the equipment is always in the optimal working state, and finally the effect of improving the efficiency of negative oxygen ion generation, reducing resource waste and reducing the risk of harmful by-product generation is achieved.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A control method for a negative oxygen ion generator, characterized in that: include, Perform anti-interference processing on the collected environmental data to form anti-interference data; Analyze the anti-interference data to obtain an analysis environment result, and simultaneously record the preference information set by the user; Generate work plans based on environmental analysis results and user preference information, and predict the best working state; The negative oxygen ion generation mode is optimized according to the optimal working state, the ozone generation index is detected, and a safety status report is generated.

2. The control method of the negative oxygen ion generator according to claim 1, characterized in that: The anti-interference processing of the collected environmental data to form anti-interference data is performed in the following specific steps: Load the graphical user interface, set parameters through the graphical user interface, and start the sensor network to collect environmental data; Use historical data to train a random forest classifier, and use the trained random forest classifier to perform anti-interference processing on environmental data. The expression is: Among them, Y is the environmental data after anti-interference processing, F(x i ,θ) is the application of the trained random forest classifier to the input environmental data x i The probability score obtained when making a prediction, w i is the importance weight of the i-th sensor data, n is the number of sensor data, θ is the parameter set of the random forest classifier, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, and γ is the observed average value of the current environmental condition.

3. The control method of the negative oxygen ion generator according to claim 2, characterized in that: The anti-interference data is analyzed to obtain the analysis environment result, and the preference information set by the user is recorded at the same time. The specific steps are as follows: The environmental data after anti-interference processing is obtained through sensors, and a comprehensive evaluation function is introduced to analyze the environmental data after anti-interference processing. The expression is: Among them, A is the comprehensive evaluation score, Y is the environmental data after anti-interference processing, n is the number of sensor data, and w i is the importance weight of the i-th sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, and γ is the average value of the current environmental condition observation; Enter the graphical user interface by starting an application on the device, enter the preference setting page through the graphical user interface, set preference information in the preference setting page, and record the user's preference information.

4. The control method of the negative oxygen ion generator according to claim 3, characterized in that: The specific steps of generating a work plan based on the environmental analysis results and user preference information are as follows: Based on the environmental analysis results and user preference information, the grid search method is used to generate different parameter combinations of negative oxygen ion generation modes, the candidate work plans are formed, the comprehensive work plan scoring function is designed, and the comprehensive work plan score is predicted. The expression is: Among them, S is the comprehensive work plan score, w i is the importance weight of the i-th sensor data, n is the number of sensor data, A is the comprehensive evaluation score, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, γ is the observed average value of the current environmental condition, U(u,p) is the user preference information, u is the user identifier, and p is the environmental parameter. The comprehensive work plan scoring function is used to calculate the comprehensive work plan scores of the candidate work plans, and the candidate work plan with the highest score is selected from the work plan scores as the work plan.

5. The control method of the negative oxygen ion generator according to claim 4, characterized in that: The specific steps of predicting the optimal working state are as follows: Collect performance data through sensors, use the deep learning framework to define the architecture of the deep Q network DQN, input the performance data into the architecture of the deep Q network DQN, use the back propagation algorithm and Adam to get the trained deep Q network DQN, input the work plan into the trained deep Q network DQN to predict the best working state, the expression is: Among them, O i is the equipment parameter corresponding to the i-th sensor data under the predicted optimal working state, S is the comprehensive working plan score, and s t is the environmental data at time t, a t is the equipment parameter at time t, w i is the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, γ is the average value of the current environmental condition observation, Q(s t ,a t ) is the expected return of the equipment parameters taken under the environmental state at time t; Record the device parameters corresponding to the sensor data under the predicted optimal working state to form the optimal working state.

6. The control method of the negative oxygen ion generator according to claim 5, characterized in that: The specific steps of optimizing the negative oxygen ion generation mode according to the optimal working state are as follows: The actual values ​​of the equipment parameters corresponding to the sensor data are collected in real time through sensors, and the comprehensive work plan score function is used to calculate the comprehensive work plan score of the current work plan. The dynamic adjustment value function is defined based on the optimal working state. The expression is: Among them, D is the dynamic adjustment value, O i is the target value of the equipment parameter corresponding to the i-th sensor data under the predicted optimal working state, C i is the actual value of the equipment parameter corresponding to the i-th sensor data, S is the comprehensive work plan score, and w i is the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, and γ is the average value of the current environmental condition observation; Calculate the dynamic adjustment value of the negative oxygen ion generation mode; Define a dynamic adjustment threshold τ according to the dynamic adjustment value; If the absolute value of the dynamic adjustment value |D| is greater than the dynamic adjustment threshold τ, the parameters of the negative oxygen ion generation mode are adjusted; If the absolute value |D| of the dynamic adjustment value is not greater than the dynamic adjustment threshold τ, the parameters of the negative oxygen ion generation mode are not adjusted.

7. The control method of the negative oxygen ion generator according to claim 6, characterized in that: The specific steps of detecting the ozone generation index are as follows: The actual value of the device parameter corresponding to each sensor data after adjustment is obtained from the optimized negative oxygen ion generation mode. Based on the optimized negative oxygen ion generation mode, an ozone generation detection function is introduced to quantify the ozone generation situation. The expression is: Among them, Z t is the ozone generation index at time t, C i is the actual value of the device parameter corresponding to the i-th sensor data after adjustment, w i is the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of environmental conditions, γ is the average value of current environmental conditions, δ is the adjustment coefficient of ozone generation efficiency, μ is the expected optimal performance value, and s t is the environmental data at time t; The ozone generation detection function is used to calculate the ozone generation index at each time point and record the ozone generation index.

8. The control method of the negative oxygen ion generator according to claim 7, characterized in that: The specific steps of generating a security status report are as follows: The ozone generation indicators are summarized to form a detection data set, and the comprehensive risk assessment indicators are used to assess the ozone generation risk. The expression is: Among them, R is the comprehensive risk assessment index, Z t is the ozone generation index at time t, w i is the importance weight of the i-th sensor data, n is the number of sensor data, α is the adjustment coefficient of the S-type function, β is the ideal value of the environmental condition, γ is the average value of the current environmental condition observation, μ is the expected optimal performance value, and s t is the environmental data at time t, k is the risk sensitivity coefficient; Calculate comprehensive risk assessment indicators in real time and record them; Defining the comprehensive risk assessment threshold R based on the comprehensive risk assessment index th , when the comprehensive risk assessment index is greater than the comprehensive risk assessment threshold R th When the negative oxygen ion generator is turned off, the user is reminded that the device has stopped running and the window has been opened; At the same time, it checks the ozone generation index, calculates the comprehensive evaluation score, and generates a safety status report.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the control method of the negative oxygen ion generator according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the control method of the negative oxygen ion generator according to any one of claims 1 to 8 are implemented.

Images