An air purification method, device and terminal device

Abstract

The present application provides an air purification method, device and terminal device, which are applicable to the field of data processing technology. The method includes: calculating target pollutant concentration prediction information according to historical pollutant concentration information, indoor space information, randomly generated initial weight information, initial bias information, non-linear mapping function, prediction calculation iteration number threshold, current pollutant concentration information, indoor space information, initial weight information, initial bias information, preset gradient attenuation rate, learning rate and variable iteration number threshold; calculating cleaning air velocity adjustment amount information and air supply adjustment amount information according to the target pollutant concentration prediction information, indoor space information, indoor activity personnel situation information, fan parameter information, pollutant concentration calibration information, air velocity adjustment experience coefficient and air cleaning amount per unit time, so as to perform air purification treatment. By predicting the pollutant concentration, the parameters of the air purification equipment are dynamically adjusted to ensure the accuracy and effectiveness of purification.

Description

Technical Field

[0001] This application belongs to the technical field of data processing, and particularly relates to an air purification method, device, and terminal device. Background Art

[0002] Operating room air purification refers to reducing pollutants such as dust and microorganisms in the indoor air through certain technical means, so that the operating room reaches a certain cleanliness standard, thereby reducing foreign body interference and preventing cross-infection, and creating a stable operating environment for medical staff and patients.

[0003] In the prior art, during the use of the operating room, the air in the operating room is circulated with the outside air by setting an air purifier and a fan in a fixed mode, thereby realizing the purification of the air in the operating room.

[0004] However, in the prior art, operating the air purifier and the fan in a fixed mode cannot flexibly adjust to the dynamically changing air quality in the operating room, and it is difficult to ensure that the air quality in the operating room meets the cleanliness standard requirements for a long time, thereby increasing the risk of medical staff and patients being infected with diseases. Summary of the Invention

[0005] In view of this, the embodiments of this application provide an air purification method, device, and terminal device, aiming to solve the problems in the prior art that it is impossible to adapt to the dynamically changing air quality in the operating room, it is difficult to monitor and flexibly adjust the air quality in the operating room in real time, it is impossible to ensure that the air quality in the operating room remains within the cleanliness standard range during use, and the risk of disease infection of medical staff and patients increases.

[0006] The first aspect of the embodiments of this application provides an air purification method, including:

[0007] Obtain historical pollutant concentration information, current pollutant concentration information, indoor space information, indoor activity personnel situation information, and fan parameter information;

[0008] Randomly generate initial weight information and initial bias information;

[0009] According to the historical pollutant concentration information, indoor space information, initial weight information, initial bias information, preset non-linear mapping function, and preset prediction calculation iteration number threshold, calculate initial pollutant concentration prediction information;

[0010] According to the current pollutant concentration information, initial pollutant concentration prediction information, indoor space information, initial weight information, initial bias information, preset gradient attenuation rate, preset learning rate, and preset variable iteration number threshold, calculate target weight information and target bias information;

[0011] Calculate predicted target pollutant concentration information based on the current pollutant concentration information, target weight information, target bias information, indoor space information, preset non-linear mapping function, and preset prediction calculation iteration count threshold;

[0012] Calculate clean air velocity adjustment information and air supply adjustment information based on the predicted target pollutant concentration information, indoor space information, information on indoor occupants, fan parameter information, preset pollutant concentration calibration information, preset air velocity adjustment experience coefficient, and preset unit-time air cleaning volume, so as to perform air purification on the indoor environment.

[0013] A second aspect of the embodiments of the present application provides an air purification device, including:

[0014] An information acquisition module, configured to acquire historical pollutant concentration information, current pollutant concentration information, indoor space information, information on indoor occupants, and fan parameter information;

[0015] An initial weight information and initial bias information generation module, configured to randomly generate initial weight information and initial bias information;

[0016] An initial predicted pollutant concentration information calculation module, configured to calculate initial predicted pollutant concentration information based on the historical pollutant concentration information, indoor space information, initial weight information, initial bias information, preset non-linear mapping function, and preset prediction calculation iteration count threshold;

[0017] A target weight information and target bias information calculation module, configured to calculate target weight information and target bias information based on the current pollutant concentration information, initial predicted pollutant concentration information, indoor space information, initial weight information, initial bias information, preset gradient attenuation rate, preset learning rate, and preset variable iteration count threshold;

[0018] A predicted target pollutant concentration information calculation module, configured to calculate predicted target pollutant concentration information based on the current pollutant concentration information, target weight information, target bias information, indoor space information, preset non-linear mapping function, and preset prediction calculation iteration count threshold; and

[0019] An air purification processing module, configured to calculate clean air velocity adjustment information and air supply adjustment information based on the predicted target pollutant concentration information, indoor space information, information on indoor occupants, fan parameter information, preset pollutant concentration calibration information, preset air velocity adjustment experience coefficient, and preset unit-time air cleaning volume, so as to perform air purification on the indoor environment.

[0020] A third aspect of the embodiments of the present application provides a terminal device, which includes a memory and a processor. A computer program that can run on the processor is stored on the memory. When the processor executes the computer program, the steps of the air purification method described in the first aspect above are implemented.

[0021] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: Considering the dynamic change of the indoor air quality caused by the activities of personnel in the operating room, combining the historical pollutant concentration information and the current pollutant concentration information collected by the sensors in the operating room, accurately predicting the change of the indoor pollutant concentration, and then calculating the cleaning air speed adjustment amount information and the air supply adjustment amount information according to the prediction result of the indoor pollutant concentration in combination with the fan parameters and the activities of the operating room users, and further adjusting the air speed of the air purifier and the air supply volume of the fan to achieve the purification of the air in the operating room. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 It is a schematic flowchart of the implementation of the air purification method provided in Embodiment 1 of the present application;

[0024] Figure 2 It is a schematic flowchart of the implementation of the air purification method provided in Embodiment 2 of the present application;

[0025] Figure 3 It is a schematic flowchart of the implementation of the air purification method provided in Embodiment 3 of the present application;

[0026] Figure 4 It is a schematic flowchart of the implementation of the air purification method provided in Embodiment 4 of the present application;

[0027] Figure 5 It is a schematic flowchart of the implementation of the air purification method provided in Embodiment 5 of the present application;

[0028] Figure 6 It is a schematic flowchart of the implementation of the air purification method provided in Embodiment 6 of the present application;

[0029] Figure 7 It is a schematic flowchart of the implementation of the air purification method provided in Embodiment 7 of the present application;

[0030] Figure 8It is a schematic flowchart of the implementation process of the air purification method provided in the eighth embodiment of the present application;

[0031] Figure 9 It is a schematic structural diagram of the air purification device provided in the embodiment of the present application;

[0032] Figure 10 It is a schematic diagram of the terminal device provided in the embodiment of the present application. Detailed implementation manners

[0033] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0034] In order to illustrate the technical solutions described in the present application, specific embodiments are used for illustration below.

[0035] Figure 1 The implementation flowchart of the air purification method provided in the first embodiment of the present application is shown and described in detail as follows:

[0036] Step S101, obtain historical pollutant concentration information, current pollutant concentration information, indoor space information, indoor occupant situation information, and fan parameter information.

[0037] In this embodiment, the pollutants may be pollutants such as dust and microorganisms in the air. The historical pollutant concentration information refers to the pollutant concentration information at multiple spatial points in the operating room at multiple different moments in the past time period, which is used to characterize the indoor pollutant concentration distribution in the past time period. The current pollutant concentration information refers to the pollutant concentration information at multiple spatial points in the operating room at the current moment, which is used to characterize the indoor pollutant concentration distribution at the current moment. The historical pollutant concentration information and the current pollutant concentration information can be collected by sensors set in the operating room and sent to the computer terminal, so as to achieve acquisition. The indoor space information may be the volume information of the operating room, which is calculated by measuring the length, width and height inside the operating room. The indoor space information may also be the spatial rectangular coordinates of each spatial point in the operating room, and the horizontal axis coordinate, vertical axis coordinate and vertical axis coordinate are used to represent the positions of each spatial point in the operating room. The fan parameter information may be the air supply volume per unit time, the pollutant concentration of the supplied air, the exhaust air volume per unit time and the indoor air exchange frequency. Among them, the air supply volume per unit time may be the volume of fresh air supplied by the fan per hour, which can be retrieved by referring to the fan product manual; the pollutant concentration of the supplied air may be the pollutant concentration in the fresh air supplied by the fan, which can be collected and obtained by outdoor environmental detection equipment; the indoor air exchange frequency may be the number of times of indoor and outdoor air exchange by the fan per hour. Operating rooms with different cleanliness levels have different air exchange rate standards, which need to be set according to the cleanliness level of the operating room where it is located. The information on the situation of indoor moving personnel may include the information on the number of indoor moving personnel, the average pollution amount per person per unit time, and the personnel activity intensity coefficient information. Among them, the information on the number of indoor moving personnel may refer to the number of personnel in the operating room. The average pollution amount per person per unit time may refer to the amount of pollutants generated by a single person per unit time, which can be obtained through experimental measurement or by referring to relevant standards. The personnel activity intensity coefficient information can be determined by image acquisition using image acquisition equipment set in the operating room, analyzing the collected images to judge the specific activity state of the personnel, and then quantifying according to the specific activity state of the personnel. It can also be determined by monitoring inspectors judging the activity state of indoor personnel based on the monitoring screen and scoring the activity state of indoor personnel, and inputting the scoring result into the computer as the personnel activity intensity coefficient information. The value range of the personnel activity intensity coefficient information can be between 0 and 1, 0 when the personnel are stationary, and 1 when the personnel are vigorously active.

[0038] Step S102, randomly generate initial weight information and initial bias information.

[0039] In this embodiment, the initial weight information and the initial bias information are parameter information used for preliminary prediction calculation of the air pollutant concentration subsequently, and can be randomly generated by a computer. Among them, the initial weight information is used to quantify the importance degree of each information feature in the historical pollutant concentration information in the non-linear space, and the initial bias information is used to quantify the displacement of each information feature in the historical pollutant concentration information in the non-linear space, so as to widen the distance between each information feature, facilitate full analysis of each information feature, and improve the accuracy of the prediction result of the pollutant concentration.

[0040] Step S103: Calculate the initial pollutant concentration prediction information according to the historical pollutant concentration information, the indoor space information, the initial weight information, the initial bias information, the preset non-linear mapping function, and the preset prediction calculation iteration number threshold.

[0041] In this embodiment, the preset non-linear mapping function can be the ReLU function or the Tanh function. The preset prediction calculation iteration number threshold can be set manually. It can be to combine the historical pollutant concentration information with the indoor space information to generate a data matrix, and then perform weighted summation on the data matrix through the initial weight information and add the initial bias information. Then, take the calculation result as the independent variable of the non-linear mapping function, and take the function value obtained by calculation as the intermediate variable. Then, perform weighted summation on the data matrix composed of the intermediate variables with the initial weight information and add the initial bias information for calculation. Furthermore, take the calculation result as the independent variable of the non-linear mapping function to calculate the function value, so as to realize iterative calculation. The result finally output after multiple iterative calculations is used as the initial pollutant concentration prediction information, and the number of iterations can be the preset prediction calculation iteration number threshold.

[0042] Step S104: Calculate the target weight information and the target bias information according to the current pollutant concentration information, the initial pollutant concentration prediction information, the indoor space information, the initial weight information, the initial bias information, the preset gradient attenuation rate, the preset learning rate, and the preset variable iteration number threshold.

[0043] In this embodiment, the preset gradient attenuation rate, the preset learning rate, and the preset variable iteration number threshold can be set manually. It can be to first calculate the prediction error value through the current pollutant concentration information and the initial pollutant concentration prediction information, and then, through the prediction error value, combine the indoor space information, the preset gradient attenuation rate, the preset learning rate, and the preset variable iteration number threshold to perform multiple iterative updates on the weight information and the bias information, and then output the target weight information and the target bias information, which are used to predict the concentration change of indoor pollutants at future moments according to the current indoor pollutant concentration.

[0044] Step S105: Calculate the predicted target pollutant concentration information based on the current pollutant concentration information, target weight information, target bias information, indoor space information, preset non-linear mapping function, and preset prediction calculation iteration count threshold.

[0045] In this embodiment, it may be to combine the current pollutant concentration information with the indoor space information to generate a data matrix, and then perform weighted summation on the data matrix with the target weight information and add the target bias information. Then, use the calculation result as the independent variable of the non-linear mapping function, and the function value obtained as the intermediate variable. Then, perform weighted summation on the data matrix composed of the intermediate variables with the target weight information and add the target bias information for calculation. Furthermore, use the calculation result as the independent variable of the non-linear mapping function to calculate the function value, so as to achieve iterative calculation. The result finally output after multiple iterative calculations is used as the predicted target pollutant concentration information, and the number of iterations can be the preset prediction calculation iteration count threshold.

[0046] Step S106: Calculate the cleaning air velocity adjustment amount information and air supply adjustment amount information based on the predicted target pollutant concentration information, indoor space information, indoor personnel activity situation information, fan parameter information, preset pollutant concentration calibration information, preset air velocity adjustment experience coefficient, and preset unit time air cleaning amount, so as to perform air purification treatment on the indoor environment.

[0047] In this embodiment, the preset pollutant concentration calibration information refers to the indoor pollutant concentration threshold set according to the cleanliness standard of the operating room. That is, when the pollutant concentration in the operating room is higher than this pollutant concentration calibration information, the air quality in the operating room will be judged as unqualified, which will pose a threat to the physical health of medical staff and patients. The preset air velocity adjustment experience coefficient can be set manually or obtained through multiple experimental measurements. The preset unit time air cleaning amount can refer to the volume of air that the air purifier can clean per hour, which can be uniformly set by the technical department where the operating room is located to facilitate unified management of the working state of the air purifier. The cleaning air velocity adjustment amount information refers to the air velocity adjustment amount of the air purifier, and the air supply adjustment amount information refers to the air supply adjustment amount of the fan. It can be understood that by adjusting the air velocity of the air purifier and the air supply volume of the fan, the air in the operating room can be purified. It can be to calculate the air velocity adjustment amount of the air purifier and the air supply adjustment amount of the fan according to the predicted result of the indoor pollutant concentration in combination with the fan parameters and the activity situation of the operating room users.

[0048] The air purification method provided by the embodiments of the present application takes into account the dynamic changes in indoor air quality caused by the activities of personnel in the operating room. By combining the historical pollutant concentration information and the current pollutant concentration information collected by sensors in the operating room, it accurately predicts the changes in indoor pollutant concentration. Then, based on the prediction results of indoor pollutant concentration, combined with the fan parameters and the activities of operating room users, it calculates the wind speed adjustment amount of the air purifier and the air supply adjustment amount of the fan, and further adjusts the wind speed of the air purifier and the air supply volume of the fan to achieve the purification of the air in the operating room.

[0049] Figure 2 The flowchart showing the implementation of the air purification method provided by Embodiment 2 of the present application is different from that of Embodiment 1 above in that:

[0050] The indoor space information includes indoor space abscissa information, indoor space ordinate information, and indoor space vertical coordinate information;

[0051] Step S103 specifically includes:

[0052] Step S201: Generate an initial indoor pollution information matrix according to the historical pollutant concentration information, indoor space abscissa information, indoor space ordinate information, and indoor space vertical coordinate information.

[0053] In this embodiment, it can be understood that the historical pollutant concentration information is used to represent the indoor pollutant concentration distribution at each moment in the past time period. The historical pollutant concentration information contains the pollutant concentrations at the spatial points represented by the indoor space abscissa information, indoor space ordinate information, and indoor space vertical coordinate information corresponding to each time point. Therefore, each value in the historical pollutant concentration information can be extracted and corresponding one by one with the current indoor space abscissa information, indoor space ordinate information, and indoor space vertical coordinate information, and then the corresponding values are combined to generate the initial indoor pollution information matrix.

[0054] Step S202: Perform weighted summation on the initial indoor pollution information matrix according to the initial weight information to obtain an indoor pollution information characterization variable matrix.

[0055] In this embodiment, through the weighted summation calculation of the initial weight information and the initial indoor pollution information matrix, the calculation result is the indoor pollution information characterization variable matrix, which is used for subsequent further prediction calculation of indoor pollutant concentration.

[0056] Step S203: Calculate an indoor pollution information intermediate variable matrix according to the indoor pollution information characterization variable matrix and the initial bias information.

[0057] In this embodiment, it may be to sum the indoor pollution information characterization variable matrix and the initial bias information, and the sum result is the intermediate indoor pollution information matrix.

[0058] Step S204: Generate a target indoor pollution information matrix according to the intermediate indoor pollution information matrix, a preset non-linear mapping function, and a preset prediction calculation iteration number threshold.

[0059] In this embodiment, it may be to use the intermediate indoor pollution information matrix as the independent variable of the non-linear mapping function, calculate the function value, and then perform operations with the initial weight information and the initial bias information, and then perform operations through the non-linear mapping function to achieve iterative calculation. The number of iterative calculations may be the prediction calculation iteration number threshold, and the result output after the iteration is the target indoor pollution information matrix.

[0060] Step S205: Calculate the initial pollutant concentration prediction information according to the target indoor pollution information matrix.

[0061] In this embodiment, extract the values in the target indoor pollution information matrix, extract the numerical values of the concentration part, and extract the spatial values corresponding to the concentration values, so as to obtain the initial pollutant concentration prediction information, which is used to calculate the error with the current pollutant concentration information in the subsequent process to adjust the weights and biases.

[0062] The air purification method provided by the embodiment of the present application preliminarily predicts the pollutant concentration based on the historical pollutant concentration information and the operating room space information, maps and identifies the data features in the historical pollutant concentration information through a non-linear mapping function, simulates the complex pollutant diffusion situation through the iterative transformation of the data features in the non-linear space, and then adjusts the weights and biases through the preliminary prediction results, so as to provide accurate and effective data support for subsequent air purification decisions.

[0063] Figure 3 The implementation flowchart of the air purification method provided by the third embodiment of the present application is shown. The difference from the second embodiment above is that step S204 specifically includes:

[0064] Step S301: Perform a mapping transformation on the intermediate indoor pollution information matrix according to a preset non-linear mapping function to generate an intermediate indoor pollution information matrix.

[0065] In this embodiment, it may be to use the intermediate indoor pollution information matrix as the independent variable of the non-linear mapping function, and the calculated function value is the intermediate indoor pollution information matrix.

[0066] Step S302: Count the generation times of the intermediate indoor pollution information matrix to obtain the prediction variable iteration number.

[0067] In this embodiment, each time the pollution information matrix in the intermediate chamber is generated, a counting operation can be performed to obtain a statistical value of the number of times the pollution information matrix in the intermediate chamber is generated, which is used as the iteration number of the prediction variable for subsequent judgment on whether the iteration should end.

[0068] Step S303: Determine whether the iteration number of the prediction variable is less than a preset iteration number threshold for prediction calculation; if so, proceed to step S304; if not, proceed to step S305.

[0069] In this embodiment, when the iteration number of the prediction variable is less than the preset iteration number threshold for prediction calculation, it indicates that the calculation result has not converged, and thus iterative calculation should continue to improve the non-linear fitting ability of the prediction calculation result and the accuracy of the pollutant prediction result; when the iteration number of the prediction variable is greater than or equal to the preset iteration number threshold for prediction calculation, it indicates that the calculation result has approached convergence, and thus iterative calculation is stopped, and the pollution information matrix in the intermediate chamber is output as the iteration calculation result.

[0070] Step S304: Use the pollution information matrix in the intermediate chamber as the initial pollution information matrix in the chamber and return to step S202.

[0071] In this embodiment, when the iteration number of the prediction variable is less than the preset iteration number threshold for prediction calculation, it indicates that the calculation result has not converged, and thus iterative calculation should continue to improve the non-linear fitting ability of the prediction calculation result and the accuracy of the pollutant prediction result.

[0072] Step S305: Generate a target pollution information matrix in the chamber according to the pollution information matrix in the intermediate chamber.

[0073] In this embodiment, when the iteration number of the prediction variable is greater than or equal to the preset iteration number threshold for prediction calculation, it indicates that the calculation result has approached convergence, and thus iterative calculation is stopped, and the pollution information matrix in the intermediate chamber is output as the iteration calculation result.

[0074] The air purification method provided by the embodiment of the present application performs multiple iterative calculations on the historical pollutant concentration information, extracts deep-level features of the complex information in the historical pollutant concentration information, and discovers the potential laws behind the historical pollutant concentration information, thereby improving the prediction accuracy of the pollutant concentration and providing reliable data support for the precise regulation of the purification equipment.

[0075] Figure 4 The flowchart showing the implementation of the air purification method provided by the fourth embodiment of the present application is different from that of the first embodiment above in that:

[0076] The preset gradient decay rate includes a preset first gradient decay rate and a preset second gradient decay rate;

[0077] Step S104 specifically includes:

[0078] Step S401: Calculate the predicted loss value information according to the current pollutant concentration information, the initial pollutant concentration prediction information, and the indoor space information.

[0079] In this embodiment, it may be to calculate the variance between the current pollutant concentration information and the initial pollutant concentration prediction information to obtain the data constraint loss, and then discretize the operating room space through the indoor space information. Specifically, it may be to divide the length, width, and height directions of the operating room at a certain interval respectively, so as to divide multiple grids in three directions respectively, and then calculate the residuals between the initial pollutant concentration prediction information and the current pollutant concentration information at each grid point, and then sum the multiple residual values to obtain the physical constraint loss, and then add the data constraint loss and the physical constraint loss to obtain the predicted loss value information.

[0080] Step S402: Calculate the weight gradient variable and the bias gradient variable according to the predicted loss value information, the initial weight information, and the initial bias information.

[0081] In this embodiment, it may be to use an automatic differentiation tool, such as tensorflow or pytorch, and take the predicted loss value information, the initial weight information, and the initial bias information as input data to calculate the weight gradient variable and the bias gradient variable.

[0082] Step S403: Calculate the weight gradient mean and the bias gradient mean according to the weight gradient variable, the bias gradient variable, and the preset first gradient decay rate.

[0083] In this embodiment, it may be to first use an automatic differentiation tool, such as tensorflow or pytorch, to calculate the first moment estimation values of the weight gradient variable and the bias gradient variable, and then multiply the first gradient decay rate by the weight gradient variable and the bias gradient variable respectively, and then add the multiplied results to the first moment estimation values of the weight gradient variable and the bias gradient variable respectively to obtain the weight gradient mean and the bias gradient mean.

[0084] Step S404: Calculate the weight gradient variance and the bias gradient variance according to the weight gradient variable, the bias gradient variable, and the preset second gradient decay rate.

[0085] In this embodiment, it is possible to first use an automatic differentiation tool, such as tensorflow or pytorch, to calculate the second moment estimates of the weight gradient variable and the bias gradient variable, and then multiply the second gradient decay rate by the weight gradient variable and the bias gradient variable respectively. Furthermore, add the multiplication results to the second moment estimates of the weight gradient variable and the bias gradient variable respectively to obtain the weight gradient variance and the bias gradient variance.

[0086] Step S405: Calculate the intermediate weight variable and the intermediate bias variable according to the weight gradient mean, the bias gradient mean, the weight gradient variance, the bias gradient variance, and a preset learning rate.

[0087] In this embodiment, the preset learning rate can be set manually. First, take the square root of the weight gradient variance and the bias gradient variance respectively, and then use the square root results as the denominators and the preset learning rate as the numerators to form two fractions. Multiply the two fractions by the weight gradient mean and the bias gradient mean respectively to obtain the multiplication results. Then, subtract the two multiplication results from the initial weight information and the initial bias information respectively. The subtraction results are the intermediate weight variable and the intermediate bias variable.

[0088] Step S406: Calculate the target weight information and the target bias information according to the intermediate weight variable, the intermediate bias variable, and a preset variable iteration count threshold.

[0089] In this embodiment, first combine the intermediate weight variable and the intermediate bias variable with the historical pollutant concentration information to predict and calculate the pollutant concentration again. Then, calculate the loss value again through the concentration prediction calculation result. Furthermore, calculate the intermediate weight variable and the intermediate bias variable again through this loss value to achieve iteration. The number of iterations is determined by the preset variable iteration count threshold. When the iterative calculation ends, the output results are the target weight information and the target bias information, which are used to take the current pollutant concentration information as the input data for the prediction calculation to predict and calculate the future change situation of the pollutant concentration.

[0090] The air purification method provided by the embodiment of the present application optimizes the operation parameters in the prediction calculation process by calculating the prediction error value and updating the weight information and the bias information, making the prediction result of the indoor pollutant concentration closer to the true value. It is used to enable the air purification device to adjust the operation parameters according to a more accurate prediction result in the subsequent process, effectively improving the indoor air purification effect.

[0091] Figure 5 The flowchart showing the implementation of the air purification method provided by the fifth embodiment of the present application is different from the fourth embodiment above in that step S401 specifically includes:

[0092] Step S501, count the data volume information of the current pollutant concentration information.

[0093] In this embodiment, the data volume information of the current pollutant concentration information, that is, the number of actually collected data points, can also be the total number of pollutant concentration data collected at different spatial positions in the room at the current time point.

[0094] Step S502, calculate the first intermediate prediction loss value according to the data volume information, the current pollutant concentration information, and the initial pollutant concentration prediction information.

[0095] In this embodiment, the variance can be calculated through the current pollutant concentration information and the initial pollutant concentration prediction information, and then the calculated variance value is divided by the data volume information to obtain the first intermediate prediction loss value, which is used to measure the difference between the predicted output result and the actually collected data.

[0096] Step S503, calculate the second intermediate prediction loss value according to the indoor space information and the initial pollutant concentration prediction information.

[0097] In this embodiment, the operating room space is discretized through the indoor space information. Specifically, the length, width, and height directions of the operating room can be divided at a certain interval respectively, so as to divide multiple grids in three directions respectively. Then, the residual between the initial pollutant concentration prediction information and the current pollutant concentration information at each grid point is calculated, and then the multiple residual values are summed. The summation result is divided by the data volume information to obtain the second intermediate prediction loss value, which is used to constrain the output result of the prediction loss value information and avoid falling into a feature mapping relationship that does not conform to physical reality and generating a large error.

[0098] Step S504, calculate the prediction loss value information according to the first intermediate prediction loss value and the second intermediate prediction loss value.

[0099] In this embodiment, the first intermediate prediction loss value and the second intermediate prediction loss value are added together to obtain the prediction loss value information, which is used to characterize the error between the predicted value of the pollutant concentration and the true value of the pollutant concentration.

[0100] The air purification method provided by the embodiment of the present application calculates the first intermediate prediction loss value and the second intermediate prediction loss value respectively. While effectively characterizing the gap between the predicted value of the pollutant concentration and the actual value of the pollutant concentration, it ensures that the fitting data follows physical laws at the same time, avoids the output value exceeding the dimension and being unable to perform subsequent operations, thereby improving the prediction effectiveness and accuracy of the pollutant concentration, and facilitating providing more reliable data support for efficient and scientific indoor air purification means.

[0101] Figure 6 The flowchart showing the implementation of the air purification method provided in the sixth embodiment of the present application is different from that of the fourth embodiment above in that step S406 specifically includes:

[0102] Step S601: Count the number of calculation times of the intermediate weight variable and the intermediate bias variable to obtain the intermediate variable iteration times.

[0103] In this embodiment, it may be that a counting operation is performed each time the intermediate weight variable and the intermediate bias variable are calculated, so as to obtain the intermediate variable iteration times.

[0104] Step S602: Determine whether the intermediate variable iteration times are less than a preset variable iteration times threshold; if so, proceed to step S603; if not, proceed to step S604.

[0105] In this embodiment, when the intermediate variable iteration times are less than the preset variable iteration times, it indicates that the update times of the weight information and the bias information are not enough, and the effectiveness of the weight information and the bias information is still insufficient, so iterative calculation needs to be continued to update the weight information and the bias information. When the intermediate variable iteration times are greater than or equal to the preset variable iteration times, it indicates that the update times of the weight information and the bias information are sufficient to ensure the effectiveness of the weight information and the bias information, so iterative calculation does not need to be continued, and the update of the weight information and the bias information is stopped.

[0106] Step S603: Use the intermediate weight variable as the initial weight information and the intermediate bias variable as the initial bias information, and return to step S103.

[0107] In this embodiment, when the intermediate variable iteration times are less than the preset variable iteration times, it indicates that the update times of the weight information and the bias information are not enough, and the effectiveness of the weight information and the bias information is still insufficient, so iterative calculation needs to be continued to update the weight information and the bias information.

[0108] Step S604: Use the intermediate weight variable and the intermediate bias variable as the target weight information and the target bias information.

[0109] In this embodiment, when the number of iterations of the intermediate variable is greater than or equal to the preset number of variable iterations, it indicates that the number of updates for the weight information and the bias information is sufficient to ensure the effectiveness of the weight information and the bias information. Then, there is no need to continue the iterative calculation, so as to stop updating the weight information and the bias information. Therefore, the currently calculated weight information and bias information are output as the target weight information and the target bias information, which are used for subsequent prediction calculations of the pollutant concentration to predict the change of the indoor pollutant concentration.

[0110] The air purification method provided by the embodiment of the present application realizes multiple updates of the weight information and the bias information through multiple iterative calculations, thereby optimizing the operation parameters in the prediction calculation process, making the prediction result of the indoor pollutant concentration closer to the true value, and thus improving the accuracy and effectiveness of predicting the indoor air quality situation, enabling the air purification device to adjust the operation parameters according to a more accurate prediction result, and effectively improving the indoor air purification effect.

[0111] Figure 7 The flowchart of the air purification method provided by the seventh embodiment of the present application is shown. The difference from the first embodiment above is that:

[0112] The indoor space information includes indoor space volume information;

[0113] The indoor occupant situation information includes the number of indoor occupants, the average pollution amount per person per unit time, and the activity intensity coefficient information of the occupants;

[0114] The fan parameter information includes the air supply volume per unit time, the pollutant concentration of the air supply, the exhaust air volume per unit time, and the indoor air exchange frequency;

[0115] Step S106 specifically includes:

[0116] Step S701: Calculate the adjustment amount of the air purification efficiency according to the target pollutant concentration prediction information and the preset pollutant concentration calibration information.

[0117] In this embodiment, first calculate the difference between the target pollutant concentration prediction information and the pollutant concentration calibration information, then use the difference as the numerator and the pollutant concentration calibration information as the denominator, and the result of the fractional operation is the adjustment amount of the air purification efficiency.

[0118] Step S702: Calculate the cleaning air velocity adjustment amount information according to the air purification efficiency adjustment amount and the preset air velocity adjustment experience coefficient.

[0119] In this embodiment, the preset air velocity adjustment experience coefficient may include a first air velocity experience coefficient and a second air velocity experience coefficient. First, the difference between the air purification efficiency adjustment amount and the first air velocity experience coefficient may be calculated, and then the difference may be divided by the second air velocity experience coefficient. The division result is the cleaning air velocity adjustment amount information.

[0120] Step S703: Calculate the pollutant generation rate of the active personnel according to the indoor active personnel quantity information, the average pollutant quantity per person per unit time information, and the personnel activity intensity coefficient information.

[0121] In this embodiment, the indoor active personnel quantity information, the average pollutant quantity per person per unit time information, and the personnel activity intensity coefficient information are multiplied, and the multiplication result is the pollutant generation rate of the active personnel.

[0122] Step S704: Calculate the air supply adjustment amount information according to the target pollutant concentration prediction information, the indoor space volume information, the indoor air exchange frequency, the pollutant generation rate of the active personnel, the air supply quantity per unit time, the air supply pollutant concentration, the preset air cleaning quantity per unit time, and the preset pollutant concentration calibration information.

[0123] In this embodiment, first, the exhaust air volume of the fan may be calculated through the indoor air exchange frequency and the indoor space volume information. Then, the air supply adjustment amount information may be calculated through the exhaust air volume, the indoor space volume information, the pollutant generation rate of the active personnel, the air supply quantity per unit time, the air supply pollutant concentration, the air cleaning quantity per unit time, and the pollutant concentration calibration information. Among them, according to the law of conservation of mass, the change in indoor air quality satisfies: where V is the indoor space volume of the operating room, in cubic meters; is the air supply quantity provided by the fan; is the air supply pollutant concentration; is the exhaust air volume of the fan, which can be calculated by multiplying the indoor air exchange frequency by the indoor volume. It can be understood that in the actual application scenario, the indoor air exchange frequency is usually fixed, and the indoor volume is also fixed. Therefore, the exhaust air volume of the fan is also fixed, which is convenient for the hospital building to uniformly control, manage, and maintain each fan; is the indoor pollutant concentration; is the pollutant generation rate of the active personnel; is the air cleaning quantity per unit time; then the additional air supply adjustment amount That is, the calculation formula for the air supply adjustment amount information can be expressed as: where represents the target pollutant concentration prediction information; represents the pollutant concentration calibration information.

[0124] The air purification method provided by the embodiments of the present application aims at the dynamic and variable air quality caused by personnel activities in the operating room environment. By calculating the wind speed adjustment amount of the air purifier and the air supply increase amount of the fan that need to be regulated in a timely manner according to the real-time prediction results of the pollutant concentration, it can adapt to the change of air quality in a timely manner, maintain the air cleanliness in the operating room, thereby improving the indoor air purification efficiency and the indoor environmental safety, increasing the surgical success rate and reducing the infection rate, and providing a reliable medical environment for medical staff and patients.

[0125] Figure 8 The flowchart showing the implementation of the air purification method provided by Embodiment 8 of the present application is different from that of Embodiment 7 above in that: Step S704 specifically includes:

[0126] Step S801: Calculate the air cleaning rate according to the target pollutant concentration prediction information, the indoor space volume information, and the preset air cleaning amount per unit time.

[0127] In this embodiment, it can be to first divide the air cleaning amount per unit time by the indoor space volume information, and then multiply the division result by the target pollutant concentration prediction information to calculate the air cleaning rate.

[0128] Step S802: Calculate the air supply purification rate according to the target pollutant concentration prediction information, the air supply volume per unit time, the air supply pollutant concentration, and the indoor space volume information.

[0129] In this embodiment, it can be to first divide the air supply volume per unit time by the indoor space volume information, and then multiply the division result by the difference between the target pollutant concentration prediction information and the pollutant concentration calibration information to calculate the air supply purification rate.

[0130] Step S803: Calculate the air purification rate according to the air cleaning rate and the air supply purification rate.

[0131] In this embodiment, it can be to add the air cleaning rate and the air supply purification rate to obtain the air purification rate, which is used for subsequent calculation of the air supply adjustment amount of the fan.

[0132] Step S804: Calculate the exhaust air volume information according to the indoor air exchange frequency and the indoor space volume information.

[0133] In this embodiment, it can be to multiply the indoor air exchange frequency by the indoor space volume information to calculate the exhaust air volume information, which is used for subsequent calculation of the air supply adjustment amount of the fan.

[0134] Step S805: Calculate the air supply adjustment information according to the target pollutant concentration prediction information, indoor space volume information, air exhaust volume information, pollutant generation rate of active personnel, air purification rate, air supply pollutant concentration, and preset pollutant concentration calibration information.

[0135] In this embodiment, it can be to first find the difference between the target pollutant concentration prediction information and the pollutant concentration calibration information as the indoor pollutant concentration adjustment amount, then multiply the indoor pollutant concentration adjustment amount by the indoor space volume information to obtain the product result of the indoor pollutant concentration adjustment amount and the indoor space volume information. Then multiply the air exhaust volume by the target pollutant concentration prediction information to obtain the product result of the air exhaust volume and the target pollutant concentration prediction information. Then add the product result of the indoor pollutant concentration adjustment amount and the indoor space volume information and the product result of the air exhaust volume and the target pollutant concentration prediction information, add the pollutant generation rate of active personnel to the sum result, subtract the air purification rate from the added result, and then divide the subtracted result by the pollutant concentration calibration information, thereby calculating the air supply adjustment amount of the fan, that is, the air supply adjustment information, which is used to increase the air supply volume of the fan, that is, to increase the fresh air supply volume of the fan to the indoor, and can be achieved by increasing the working power of the fan to achieve the purification of the indoor air.

[0136] The air purification method provided by the embodiment of the present application quantifies the processing ability of the air purifier for the pollutant concentration in the current state by calculating the air purification rate, and adjusts the wind speed of the air purifier in real time according to the calculated air purification rate, thereby improving the purification effect of the indoor air. By calculating the additional air supply volume required for the fan, it is ensured that more fresh air is introduced into the indoor to reduce the indoor pollutant concentration and promote the discharge of pollutants outdoors, so as to ensure that the air cleanliness requirements of the operating room are met in the complex and changeable indoor air quality changes, and ensure that the operating room environment always meets strict standards, so as to reduce the infection risk and improve the safety and reliability of the medical environment.

[0137] Corresponding to the method in the above embodiment, Figure 9 The structural block diagram of the air purification device provided by the embodiment of the present application is shown. For the sake of convenience of description, only the parts related to the embodiment of the present application are shown. Figure 9 The exemplary air purification device may be the execution subject of the air purification method provided in the foregoing Embodiment 1.

[0138] Refer to Figure 9 , the air purification device includes:

[0139] An information acquisition module 910, configured to acquire historical pollutant concentration information, current pollutant concentration information, indoor space information, indoor active personnel situation information, and fan parameter information;

[0140] An initial weight information and initial bias information generation module 920, configured to randomly generate initial weight information and initial bias information;

[0141] An initial pollutant concentration prediction information calculation module 930, configured to calculate initial pollutant concentration prediction information according to the historical pollutant concentration information, indoor space information, initial weight information, initial bias information, a preset non-linear mapping function, and a preset prediction calculation iteration number threshold;

[0142] A target weight information and target bias information calculation module 940, configured to calculate target weight information and target bias information according to the current pollutant concentration information, initial pollutant concentration prediction information, indoor space information, initial weight information, initial bias information, a preset gradient attenuation rate, a preset learning rate, and a preset variable iteration number threshold;

[0143] A target pollutant concentration prediction information calculation module 950, configured to calculate target pollutant concentration prediction information according to the current pollutant concentration information, target weight information, target bias information, indoor space information, a preset non-linear mapping function, and a preset prediction calculation iteration number threshold; and

[0144] An air purification processing module 960, configured to calculate a clean air speed adjustment amount information and an air supply adjustment amount information according to the target pollutant concentration prediction information, indoor space information, indoor activity personnel situation information, fan parameter information, a preset pollutant concentration calibration information, a preset air speed adjustment experience coefficient, and a preset unit time air cleaning amount, so as to perform air purification processing on the indoor environment.

[0145] For the process of each module in the air purification device provided by the embodiments of the present application to implement its respective functions, reference may be specifically made to the description of the foregoing Figure 1 Example 1 shown, which will not be elaborated here.

[0146] It should be understood that, in the above embodiments, the magnitudes of the sequence numbers of the steps do not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0147] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0148] It should also be understood that the term "and / or" as used in the specification and appended claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0149] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]" depending on the context.

[0150] In addition, in the description of the specification and appended claims of this application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and should not be construed as indicating or implying relative importance. It should also be understood that although the terms "first", "second", etc. are used in the text in some embodiments of this application to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, the first table can be named the second table, and similarly, the second table can be named the first table without departing from the scope of the various described embodiments. The first table and the second table are both tables, but they are not the same table.

[0151] Reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments" unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having" and their variants all mean "including but not limited to" unless otherwise specifically emphasized in another way.

[0152] The air purification method provided by the embodiments of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), etc. The embodiments of the present application do not impose any restrictions on the specific types of terminal devices.

[0153] For example, the terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device, or other processing devices connected to a wireless modem, a vehicle-mounted device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a television set-top box (STB), a customer premise equipment (CPE), and / or other devices for communicating on a wireless system, as well as next-generation communication systems. For example, a mobile terminal in a 5G network or a mobile terminal in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0154] By way of example and not limitation, when the terminal device is a wearable device, the wearable device can also be a general term for devices that apply wearable technology to the intelligent design of daily wear and develop wearable devices, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is either directly worn on the body or integrated into the user's clothes or accessories. A wearable device is not just a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable intelligent devices include those with complete functions and large sizes that can realize complete or partial functions without relying on a smart phone, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to cooperate with other devices such as smart phones, such as various smart bracelets and smart jewelry for monitoring physical signs.

[0155] Figure 10It is a schematic structural diagram of a terminal device provided by an embodiment of the present application. As Figure 10 shown, the terminal device 10 of this embodiment includes: at least one processor 1000 ( Figure 10 only one is shown in the figure), and a memory 1010. A computer program 1020 that can run on the processor 1000 is stored in the memory 1010. When the processor 1000 executes the computer program 1020, the steps in the above-mentioned embodiments of each air purification method are implemented, such as Figure 1 the steps S101 to S106 shown. Alternatively, when the processor 1000 executes the computer program 1020, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0156] The terminal device 10 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor 1000 and a memory 1010. Those skilled in the art can understand that Figure 10 this is only an example of the terminal device 10 and does not constitute a limitation on the terminal device 10. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the terminal device may further include an input and sending device, a network access device, a bus, etc.

[0157] The so-called processor 1000 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0158] In some embodiments, the memory 1010 may be an internal storage unit of the terminal device 10, such as a hard disk or memory of the terminal device 10. The memory 1010 may also be an external storage device of the terminal device 10, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the terminal device 10. Further, the memory 1010 may also include both the internal storage unit and the external storage device of the terminal device 10. The memory 1010 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as program codes of the computer program. The memory 1010 may also be used to temporarily store data that has been sent or will be sent.

[0159] In addition, in each embodiment of the present application, each functional unit may be integrated in a processing unit, may exist physically alone for each unit, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0160] The embodiment of the present application further provides a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor. When the processor executes the computer program, the terminal device implements the steps in any of the above method embodiments.

[0161] The embodiment of the present application further provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in the above various method embodiments can be implemented.

[0162] The embodiment of the present application provides a computer program product, and when the computer program product runs on a terminal device, the terminal device is caused to execute and implement the steps in the above various method embodiments.

[0163] When the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0164] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0165] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0166] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0167] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of this application, and should all be included in the protection scope of this application.

Claims

1. An air purification method, characterized in that: include: Obtain historical pollutant concentration information, current pollutant concentration information, indoor space information, indoor activity personnel information, and fan parameter information; Randomly generate initial weight information and initial bias information; Calculating initial pollutant concentration prediction information according to the historical pollutant concentration information, indoor space information, initial weight information, initial bias information, a preset nonlinear mapping function, and a preset prediction calculation iteration number threshold; Calculating target weight information and target bias information according to the current pollutant concentration information, the initial pollutant concentration prediction information, the indoor space information, the initial weight information, the initial bias information, the preset gradient decay rate, the preset learning rate, and the preset variable iteration number threshold; Calculating target pollutant concentration prediction information according to the current pollutant concentration information, target weight information, target bias information, indoor space information, a preset nonlinear mapping function, and a preset prediction calculation iteration number threshold; According to the target pollutant concentration prediction information, indoor space information, indoor active personnel situation information, fan parameter information, preset pollutant concentration calibration information, preset wind speed adjustment empirical coefficient and preset air cleaning amount per unit time, the clean wind speed adjustment amount information and the supply air adjustment amount information are calculated to perform indoor air purification.

2. The air purification method according to claim 1, characterized in that: The indoor space information includes indoor space horizontal coordinate information, indoor space vertical coordinate information and indoor space vertical coordinate information; The step of calculating the initial pollutant concentration prediction information according to the historical pollutant concentration information, the indoor space information, the initial weight information, the initial bias information, the preset nonlinear mapping function and the preset prediction calculation iteration number threshold specifically includes: Generate an initial indoor pollution information matrix according to the historical pollutant concentration information, the indoor space horizontal coordinate information, the indoor space vertical coordinate information and the indoor space vertical coordinate information; According to the initial weight information, weighted summing is performed on the initial indoor pollution information matrix to obtain an indoor pollution information representation variable matrix; Calculating an indoor pollution information intermediate variable matrix according to the indoor pollution information characterization variable matrix and initial bias information; Generate a target indoor pollution information matrix according to the indoor pollution information intermediate variable matrix, a preset nonlinear mapping function and a preset prediction calculation iteration number threshold; Initial pollutant concentration prediction information is calculated based on the target indoor pollution information matrix.

3. The air purification method according to claim 2, characterized in that: The step of generating a target indoor pollution information matrix according to the indoor pollution information intermediate variable matrix, a preset nonlinear mapping function and a preset prediction calculation iteration number threshold specifically includes: According to a preset nonlinear mapping function, mapping transformation is performed on the intermediate variable matrix of indoor pollution information to generate an intermediate indoor pollution information matrix; Counting the number of times the intermediate indoor pollution information matrix is ​​generated to obtain the number of iterations of the prediction variables; Determining whether the number of iterations of the prediction variable is less than a preset prediction calculation iteration number threshold; If yes, the intermediate indoor pollution information matrix is ​​used as the initial indoor pollution information matrix, and the process returns to the step of performing weighted summation on the initial indoor pollution information matrix according to the initial weight information to obtain an indoor pollution information characterization variable matrix; If not, a target indoor pollution information matrix is ​​generated according to the intermediate indoor pollution information matrix.

4. The air purification method according to claim 1, characterized in that: The preset gradient decay rate includes a preset first gradient decay rate and a preset second gradient decay rate; The step of calculating the target weight information and the target bias information according to the current pollutant concentration information, the initial pollutant concentration prediction information, the indoor space information, the initial weight information, the initial bias information, the preset gradient decay rate, the preset learning rate and the preset variable iteration number threshold specifically includes: Calculating predicted loss value information based on the current pollutant concentration information, the initial pollutant concentration prediction information, and the indoor space information; Calculating a weight gradient variable and a bias gradient variable according to the predicted loss value information, the initial weight information, and the initial bias information; Calculating a weight gradient mean and a bias gradient mean according to the weight gradient variable, the bias gradient variable and a preset first gradient decay rate; Calculate the weight gradient variance and the bias gradient variance according to the weight gradient variable, the bias gradient variable and a preset second gradient decay rate; Calculate intermediate weight variables and intermediate bias variables according to the weight gradient mean, bias gradient mean, weight gradient variance, bias gradient variance and a preset learning rate; Calculate target weight information and target bias information based on the intermediate weight variable, the intermediate bias variable and a preset variable iteration number threshold.

5. The air purification method according to claim 4, characterized in that: The step of calculating the predicted loss value information according to the current pollutant concentration information, the initial pollutant concentration prediction information and the indoor space information specifically includes: Counting the data volume information of the current pollutant concentration information; Calculating a first intermediate prediction loss value according to the data volume information, current pollutant concentration information, and initial pollutant concentration prediction information; Calculating a second intermediate predicted loss value according to the indoor space information and the initial pollutant concentration prediction information; The prediction loss value information is calculated based on the first intermediate prediction loss value and the second intermediate prediction loss value.

6. The air purification method according to claim 4, characterized in that: The step of calculating target weight information and target bias information according to the intermediate weight variable, the intermediate bias variable and a preset variable iteration number threshold specifically includes: Counting the number of calculations of the intermediate weight variables and the intermediate bias variables to obtain the number of intermediate variable iterations; Determine whether the number of intermediate variable iterations is less than a preset variable iteration number threshold; If so, the intermediate weight variable is used as the initial weight information, the intermediate bias variable is used as the initial bias information, and the process returns to the step of calculating the initial pollutant concentration prediction information according to the historical pollutant concentration information, the indoor space information, the initial weight information, the initial bias information, the preset nonlinear mapping function and the preset prediction calculation iteration number threshold; If not, the intermediate weight variable and the intermediate bias variable are used as the target weight information and the target bias information.

7. The air purification method according to claim 1, characterized in that: The indoor space information includes indoor space volume information; The indoor activity personnel information includes the number of indoor activity personnel, the average pollution amount per unit time, and the personnel activity intensity coefficient information; The fan parameter information includes air supply volume per unit time, air supply pollutant concentration, air exhaust volume per unit time and indoor air exchange frequency; The step of calculating the clean wind speed adjustment amount information and the supply air adjustment amount information according to the target pollutant concentration prediction information, indoor space information, indoor activity personnel situation information, fan parameter information, preset pollutant concentration calibration information, preset wind speed adjustment experience coefficient and preset unit time air cleaning amount specifically includes: Calculating the air purification efficiency adjustment amount according to the target pollutant concentration prediction information and the preset pollutant concentration calibration information; Calculating the clean wind speed adjustment amount information according to the air purification efficiency adjustment amount and the preset wind speed adjustment empirical coefficient; Calculate the pollutant generation rate of the active personnel according to the number of active personnel information, the average pollution amount of personnel per unit time, and the personnel activity intensity coefficient information; The air supply adjustment amount information is calculated based on the target pollutant concentration prediction information, indoor space volume information, indoor air exchange frequency, pollutant generation rate of active personnel, air supply volume per unit time, air supply pollutant concentration, preset air cleaning volume per unit time and preset pollutant concentration calibration information.

8. The air purification method according to claim 7, characterized in that: The step of calculating the air supply adjustment amount information according to the target pollutant concentration prediction information, indoor space volume information, indoor air exchange frequency, pollutant generation rate of active personnel, air supply volume per unit time, air supply pollutant concentration, preset air cleaning volume per unit time and preset pollutant concentration calibration information specifically includes: Calculating the air cleaning rate according to the target pollutant concentration prediction information, the indoor space volume information and the preset air cleaning amount per unit time; Calculate the air supply purification rate according to the target pollutant concentration prediction information, the air supply volume per unit time, the air supply pollutant concentration and the indoor space volume information; Calculating an air purification rate according to the air cleaning rate and the air supply purification rate; Calculating exhaust volume information according to the indoor air exchange frequency and indoor space volume information; The air supply adjustment amount information is calculated based on the target pollutant concentration prediction information, indoor space volume information, exhaust volume information, pollutant generation rate of active personnel, air purification rate, supply air pollutant concentration and preset pollutant concentration calibration information.

9. An air purification device, characterized in that: include: An information acquisition module is used to obtain historical pollutant concentration information, current pollutant concentration information, indoor space information, indoor activity personnel information, and fan parameter information; An initial weight information and initial bias information generation module, used to randomly generate initial weight information and initial bias information; An initial pollutant concentration prediction information calculation module, used to calculate the initial pollutant concentration prediction information according to the historical pollutant concentration information, indoor space information, initial weight information, initial bias information, a preset nonlinear mapping function and a preset prediction calculation iteration number threshold; A target weight information and target bias information calculation module, used to calculate the target weight information and target bias information according to the current pollutant concentration information, the initial pollutant concentration prediction information, the indoor space information, the initial weight information, the initial bias information, the preset gradient decay rate, the preset learning rate and the preset variable iteration number threshold; A target pollutant concentration prediction information calculation module, used to calculate the target pollutant concentration prediction information according to the current pollutant concentration information, target weight information, target bias information, indoor space information, a preset nonlinear mapping function and a preset prediction calculation iteration number threshold; as well as The air purification processing module is used to calculate the clean wind speed adjustment amount information and the supply air adjustment amount information according to the target pollutant concentration prediction information, indoor space information, indoor active personnel situation information, fan parameter information, preset pollutant concentration calibration information, preset wind speed adjustment experience coefficient and preset unit time air cleaning amount, so as to perform indoor air purification.

10. A terminal device, characterized in that: The terminal device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor implements the steps of the method according to any one of claims 1 to 8 when executing the computer program.

Images