Air purification method and device, terminal equipment and storage medium

Abstract

The invention provides an air purification method and device, terminal equipment and a storage medium, and is suitable for the technical field of data processing.The method comprises the steps that initial indoor pollutant concentration information is obtained according to current indoor air environment information, current operation state information and a target indoor pollutant concentration prediction model; screening the initial indoor pollutant concentration information to obtain target indoor pollutant concentration information; and according to the target indoor pollutant concentration information and the indoor volume information, indoor ventilation quantity information is obtained, and indoor air purification treatment is carried out. According to the method, the internal relation among the indoor air environment information, the operation state information and the indoor air pollutant concentration change in the operating room is mined through the target indoor pollutant concentration prediction model, and the pollutant concentration change in the operating room is accurately predicted, so that the indoor ventilation quantity information is dynamically calculated for timely air purification; the timeliness and effectiveness of air purification in the operating room are improved, and the infection risk of a patient is reduced.

Description

Technical Field

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

[0002] For an operating room, air purification work is essential. During surgery, the patient's immune system is relatively weak. Once microorganisms and dust particles in the air enter the wound, it is extremely easy to cause infection, and in severe cases, it can endanger life. And the purified air can reduce the microbial content and the risk of infection, providing a stable environmental guarantee for the success of the surgery.

[0003] In the prior art, the air purification method for the operating room during the surgery process usually filters the air through a filter and regularly introduces the filtered air into the operating room, so that the dust and pathogenic microorganisms in the operating room are discharged from the operating room along with the air flow; or by regularly adjusting the temperature, humidity, and air pressure of the air in the operating room to circulate the air in the operating room. However, whether it is the method of regularly introducing filtered gas or regularly adjusting the temperature, humidity, and air pressure in the operating room to achieve air circulation, it is impossible to flexibly adjust the ventilation volume according to the real-time indoor pollutant concentration, thereby reducing the air purification efficiency and effect in the operating room, and it is extremely easy to cause pollutants such as bacteria, viruses, and dust in the air to enter the patient's wound, resulting in postoperative infection, prolonging the wound healing time, and causing serious complications, and even endangering the patient's life. Summary of the Invention

[0004] In view of this, the embodiments of this application provide an air purification method, device, terminal device, and storage medium, aiming to solve the problems in the prior art that the monitoring and response to the indoor air pollutant concentration are relatively lagging, resulting in low air purification efficiency and poor effect during the surgery process, and greatly increasing the probability of patients being infected by pollutants such as bacteria and viruses.

[0005] The first aspect of the embodiments of this application provides an air purification method, including: Obtain the current indoor air environment information, the current surgical state information, and the indoor volume information; According to the current indoor air environment information, the current surgical state information, and the target indoor pollutant concentration prediction model, obtain the initial indoor pollutant concentration information; Perform screening processing on the initial indoor pollutant concentration information to obtain the target indoor pollutant concentration information; According to the target indoor pollutant concentration information and the indoor volume information, calculate the indoor ventilation volume information to perform air purification processing on the indoor.

[0006] The second aspect of the embodiments of the present application provides an air purification device, including: An information acquisition module, configured to acquire current indoor air environment information, current surgical state information, and indoor volume information; An initial indoor pollutant concentration information determination module, configured to obtain initial indoor pollutant concentration information according to the current indoor air environment information, current surgical state information, and a target indoor pollutant concentration prediction model; A target indoor pollutant concentration information determination module, configured to perform screening processing on the initial indoor pollutant concentration information to obtain target indoor pollutant concentration information; and An indoor ventilation volume information determination module, configured to calculate indoor ventilation volume information according to the target indoor pollutant concentration information and indoor volume information, so as to perform air purification processing on the indoor environment.

[0007] The 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.

[0008] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, including: a stored computer program, and when the computer program is executed by a processor, the steps of the air purification method described in the first aspect above are implemented.

[0009] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: The present application comprehensively considers multiple factors affecting the change of pollutant concentration in the operating room. During the operation, through the target indoor pollutant concentration prediction model, the relationship between the current indoor air environment information, surgical state information, and the dynamic change of pollutant concentration in the operating room is deeply explored, so as to accurately predict and calculate the pollutant concentration information in the operating room. Then, through screening processing, abnormal data and interference data in the prediction results are filtered out, further improving the accuracy and reliability of the prediction results. By combining the pollutant concentration information in the operating room obtained through prediction calculation with the indoor volume information, the indoor ventilation volume is calculated in real time, realizing the intelligent and refined management of indoor air purification during the operation. Therefore, by fully considering the different pollutants generated by different types of surgeries and the impact of personnel activities and time changes during the operation on the indoor pollutant concentration, the air purification function of the operating room can timely adapt to various complex surgical scenarios and indoor air environment changes, providing a more stable and reliable air purification guarantee for the operation process, effectively removing microorganisms such as bacteria, viruses, and fungi in the air during the operation, reducing the incidence of postoperative infections, reducing the surgical risk of patients, and improving the efficiency and effect of patients' postoperative recovery. Description of the Drawings

[0010] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in 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.

[0011] Figure 1 It is a schematic flowchart of the implementation of the air purification method provided in the first embodiment of the present application; Figure 2 It is a schematic flowchart of the implementation of the air purification method provided in the second embodiment of the present application; Figure 3 It is a schematic flowchart of the implementation of the air purification method provided in the third embodiment of the present application; Figure 4 It is a schematic flowchart of the implementation of the air purification method provided in the fourth embodiment of the present application; Figure 5 It is a schematic flowchart of the implementation of the air purification method provided in the fifth embodiment of the present application; Figure 6 It is a schematic flowchart of the implementation of the air purification method provided in the sixth embodiment of the present application; Figure 7 It is a schematic structural diagram of the air purification device provided in the embodiments of the present application; Figure 8 It is a schematic diagram of the terminal device provided in the embodiments of the present application. Detailed implementation manners

[0012] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are presented 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.

[0013] To illustrate the technical solutions described in the present application, the following will be described through specific embodiments.

[0014] Figure 1 The following shows the implementation flowchart of the air purification method provided in the first embodiment of the present application, and is described in detail as follows: Step S101, obtain the current indoor air environment information, the current surgical state information, and the indoor volume information.

[0015] In this embodiment, the current indoor air environment information may refer to a series of physical, chemical, and biological indicators that can reflect the air environment quality and state in the operating room during the operation, which can be measured by sensors installed inside the operating room and automatically transmitted to the server. The current surgical state information may refer to a series of real-time changing information closely related to the operation itself and the personnel situation in the operating room environment during the operation, used to reflect the specific situation of the operation and the personnel dynamics in the operating room, which can be obtained by reading the records of the operating room management system within the hospital. The indoor volume information of the operating room refers to the three-dimensional space size occupied by the internal space of the operating room, usually obtained by measuring the length, width, and height of the operating room and multiplying the three values. It can be that the length, width, and height information of the operating room is manually entered into the computer by the staff, and the computer automatically calculates the volume of the operating room. It can also be to obtain the accurate dimensions and volume information of the operating room using BIM technology, or to measure the space dimensions inside the operating room with sensors such as laser rangefinders and ultrasonic rangefinders and automatically transmit them to the computer, and the computer automatically calculates the indoor volume information of the operating room.

[0016] In this embodiment, optionally, the current indoor air environment information may include current air particulate matter concentration information, current microorganism concentration information, current temperature and humidity information, and current air flow velocity information. Among them, the air particulate matter concentration information can be used to reflect the content of solid and liquid particles in the air of the operating room, and can be measured by a light scattering dust sensor set in the operating room. Among them, the particulate matter may include dust, pollen, smoke, etc.; the microorganism concentration information can be used to reflect the number of microorganisms such as bacteria, viruses, and fungi in the air, which is obviously closely related to the surgical infection risk; the temperature and humidity information can be used to describe the temperature and humidity conditions of the air, and can be measured by a dry and wet bulb thermometer or an electronic temperature and humidity sensor; the air flow velocity information can be used to characterize the speed of air flow, and can be measured by thermal anemometers set at different positions in the operating room. Appropriate air flow velocity helps to keep the air fresh and prevent the accumulation of pollutants. The current surgical state information may include current surgical type information, current surgical duration information, current number of surgical personnel information, and current number of times surgical personnel enter and exit information. Among them, the current surgical type information is used to reflect the complexity and risk level of the surgery, and can indirectly reflect the severity of the air purification requirements in the operating room. For example, surgical types such as cardiac surgery, neurosurgery, and organ transplantation surgery have extremely high air purification requirements during the surgery. In comparison, for example, surgical types such as superficial mass resection, breast fibroadenoma resection, and simple debridement and suture surgery have relatively low air purification requirements in the operating room during the surgery. The current surgical type information can be obtained by reading the hospital's scheduling system. The current surgical duration information can be used to reflect the progress of the surgery and the patient's condition, and can be measured by a timing device in the operating room. The timing starts automatically when the surgery begins and stops automatically when the surgery ends. The current number of surgical personnel information can be measured by an infrared induction counter or a face recognition counter set at the entrance of the operating room. When surgical personnel enter or leave the operating room, the device will automatically record and update the number of personnel. The current number of times surgical personnel enter and exit information can be used to reflect the personnel flow in the operating room, which will indirectly affect the air environment and infection risk in the operating room, and can be obtained by reading the statistical information of the personnel counting device or the access control system at the entrance of the operating room.

[0017] Step S102, according to the current indoor air environment information, the current surgical state information, and the target indoor pollutant concentration prediction model, obtain the initial indoor pollutant concentration information.

[0018] In this embodiment, the target indoor pollutant concentration prediction model can be an artificial neural network model, a support vector machine model, a BERT model, or an LLM model. The target indoor pollutant concentration prediction model is default to have been trained, and is used to mine the non-linear correlation between the current indoor air environment information, the current surgical state information, and the current indoor pollutant concentration information, and is used to accurately predict the indoor pollutant concentration information during the operation. The current indoor air environment information and the current surgical state information are used as the input information of the target indoor pollutant concentration prediction model, and the information calculated by the target indoor pollutant concentration prediction model is used as the initial indoor pollutant concentration information for further screening in the subsequent process.

[0019] Step S103: Screen and process the initial indoor pollutant concentration information to obtain the target indoor pollutant concentration information.

[0020] In this embodiment, by filtering out the abnormal values and noise information in the initial indoor pollutant concentration information, the normal values are screened out, and the abnormal values can be filled by the mean imputation method to obtain the target indoor pollutant concentration information, which is used to avoid the abnormal values and noise information in the initial indoor pollutant concentration information causing calculation errors in the subsequent indoor ventilation volume information, resulting in too large or too small ventilation volume, and thus over-purification or insufficient purification effect. The screening method can be to set multiple thresholds, and screen the initial indoor pollutant concentration information according to the multiple thresholds. The values not within the range composed of the thresholds are judged as abnormal values, and the abnormal values are discarded, and then the mean imputation method can be used to fill the position where the value is located.

[0021] Step S104: Calculate the indoor ventilation volume information according to the target indoor pollutant concentration information and the indoor volume information to purify the air in the room.

[0022] In this embodiment, the product operation can be performed on the target indoor pollutant concentration information and the indoor volume information, and the calculation result is used as the indoor ventilation volume information, which is used to represent the air volume flow rate that needs to enter and exit the operating room through the ventilation system within a certain period of time. It can be to use an intelligent ventilation control system to adjust the operating frequency and air volume of the ventilation equipment in real time according to the indoor ventilation volume information. For example, when the number of people in the operating room begins to increase or the activities of the people in the operating room begin to be frequent, which will lead to an increase in the indoor pollutant concentration, the prediction result has been obtained in time through the prediction calculation of the indoor pollutant concentration, and then the prediction result is multiplied by the indoor volume information to obtain the indoor ventilation volume information. Then, the intelligent ventilation control system adjusts the operating frequency and the number of operating fans in time, so as to increase the actual ventilation volume to ensure the stability of the air quality in the operating room.

[0023] The air purification method provided by the embodiment of the present application comprehensively considers multiple factors affecting the change of pollutant concentration in the operating room. During the operation, through the target indoor pollutant concentration prediction model, the connection between the current indoor air environment information, the operation status information and the dynamic change of the pollutant concentration in the operating room is deeply explored, so as to accurately predict and calculate the pollutant concentration information in the operating room. Then, through screening and processing, the abnormal data and interference data in the prediction results are filtered out, further improving the accuracy and reliability of the prediction results. The indoor ventilation volume is calculated in real time by combining the pollutant concentration information in the operating room obtained by prediction calculation with the indoor volume information, realizing the intelligent and refined management of indoor air purification during the operation. Therefore, by fully considering the different pollutants generated by different types of operations and the influence of personnel activities and time changes during the operation on the indoor pollutant concentration, the air purification function of the operating room can timely adapt to various complex operation scenarios and indoor air environment changes, providing a more stable and reliable air purification guarantee for the operation process, effectively removing microorganisms such as bacteria, viruses and fungi in the air during the operation, reducing the incidence of postoperative infection, reducing the surgical risk of patients, and improving the efficiency and effect of patients' postoperative recovery.

[0024] Figure 2 The implementation flowchart of the air purification method provided by the second embodiment of the present application is shown. The difference from the first embodiment above is that: The target indoor pollutant concentration prediction model is specifically obtained through the following steps: Step S201, obtain historical indoor air environment information, historical operation status information, and historical indoor pollutant concentration information; wherein, the historical indoor air environment information includes historical air particulate matter concentration information, historical microorganism concentration information, historical temperature and humidity information, and historical air flow velocity information; the historical operation status information includes historical operation type information, historical operation duration information, historical number of operation personnel information, and historical number of times of operation personnel entering and leaving information.

[0025] In this embodiment, the historical indoor air environment information, historical surgical status information, and historical indoor pollutant concentration information can all be obtained from the hospital's intelligent management system by reading the information on the monitoring of the operating room environment over a past period. Among them, the historical air particulate matter concentration information can refer to the set of concentration data of particulate matter with different particle sizes in the air of the operating room over a past period, which is used to reflect the degree of particulate matter pollution in the air of the operating room during past surgical procedures or different time periods, and can be obtained by installing particulate matter sensors in the operating room, such as laser particulate matter sensors; the historical microorganism concentration information can refer to the concentration information of microorganisms such as bacteria, fungi, and viruses in the air of the operating room over a past period, which can be sampled using an air microorganism sampler and then the microorganism concentration can be determined by the method of culturing and counting; the historical temperature and humidity information can refer to the temperature and humidity data of the operating room at different past times, which can be measured by installing temperature and humidity sensors in the operating room, such as digital temperature and humidity sensors; the historical air flow velocity information can refer to the relevant data on the air flow velocity in the operating room in the past, which is used to describe the speed of air flow at different time points in the operating room during the surgical procedure and can be regularly measured and recorded by an anemometer placed at different positions in the operating room; the historical surgical type information can refer to the records of the names, categories, etc. of various surgeries performed in the operating room in the past, which can be obtained from the hospital's surgical information management system; the historical surgical duration information can refer to the records of the time lengths experienced by each surgery from start to end in the past. Since the surgical duration may affect the changes in the operating room air environment and the accumulation degree of pollutants, it is necessary to statistically analyze the surgical durations of a series of past surgeries, which can be obtained from the hospital's surgical information management system; the historical number of surgical personnel information can refer to the record information on the number of personnel participating in the surgery in the operating room in the past, which can be counted by personnel counting devices in the operating room, such as infrared induction counters or face recognition counters installed at the operating room door, which can automatically record the entry and exit of surgical personnel, thereby statistically obtaining the number of personnel during the surgical procedure; the historical number of times surgical personnel enter and exit information refers to the frequency and number of times surgical personnel enter and exit the operating room during past surgical procedures. It can be understood that the entry and exit of surgical personnel may bring in or take out pollutants, thereby affecting the air environment of the operating room. By the historical number of times surgical personnel enter and exit information, the entry and exit situations of personnel in all surgeries over a past period can be reflected. The card swiping or face recognition information of surgical personnel can be recorded by the access control system installed at the operating room door, thereby statistically obtaining the number of times each surgical personnel enters and exits, and then summarizing to obtain the historical number of times surgical personnel enter and exit information.Historical indoor pollutant concentration information refers to the records of the concentrations of various pollutants in the operating room at different past time points, which are used to reflect the air pollution levels and changing trends in the operating room under different past circumstances. It can be used to analyze the historical patterns and changing trends of pollutant concentrations in the operating room and can be obtained through regular detection by specific indoor pollutant detection equipment, such as laser particle sensors, air microorganism samplers, etc.

[0026] Step S202: Obtain multiple candidate indoor pollutant concentration prediction information based on the historical air particle concentration information, historical microorganism concentration information, historical temperature and humidity information, historical air flow velocity information, historical operation type information, historical operation duration information, historical number of operating personnel information, historical number of entries and exits of operating personnel information, and multiple initial indoor pollutant concentration prediction models.

[0027] In this embodiment, the initial indoor pollutant concentration prediction model can be an untrained artificial neural network model, an untrained support vector machine model, an untrained BERT model, an untrained LLM model, or an untrained random forest model. The multiple initial indoor pollutant concentration prediction models can specifically be different models. The historical air particle concentration information, historical microorganism concentration information, historical temperature and humidity information, historical air flow velocity information, historical operation type information, historical operation duration information, historical number of operating personnel information, and historical number of entries and exits of operating personnel information can be used as the input information of the multiple initial indoor pollutant concentration prediction models. After calculation by the multiple initial indoor pollutant concentration prediction models, multiple candidate indoor pollutant concentration prediction information can be obtained. It can be understood that multiple different initial indoor pollutant concentration prediction models can output multiple candidate indoor pollutant concentration prediction information.

[0028] Step S203: Calculate the indoor pollutant concentration prediction error based on the historical indoor pollutant concentration information and the candidate indoor pollutant concentration prediction information.

[0029] In this embodiment, the historical indoor pollutant concentration information can be used as the true value information, and the candidate indoor pollutant concentration prediction information can be used as the predicted value information to calculate the mean square error to obtain the indoor pollutant concentration prediction error. It can be understood that the mean absolute error can also be calculated.

[0030] Step S204: Screen the candidate indoor pollutant concentration prediction information according to the indoor pollutant concentration prediction error to obtain the corresponding indoor pollutant concentration prediction information.

[0031] In this embodiment, it may be by setting a prediction error threshold for the indoor pollutant concentration. When the prediction error of the indoor pollutant concentration is less than the prediction error threshold for the indoor pollutant concentration, the candidate indoor pollutant concentration prediction information corresponding to the prediction error of the indoor pollutant concentration is screened out as the response indoor pollutant concentration prediction information.

[0032] Step S205: According to the response indoor pollutant concentration prediction information, perform a screening process on the multiple initial indoor pollutant concentration prediction models to obtain a target indoor pollutant concentration prediction model.

[0033] In this embodiment, it may be to determine the initial indoor pollutant concentration prediction model corresponding to the response indoor pollutant concentration prediction information as the target indoor pollutant concentration prediction model. It may also be to further train the initial indoor pollutant concentration prediction model corresponding to the response indoor pollutant concentration prediction information through historical indoor air environment information, historical surgical state information, and historical indoor pollutant concentration information, and use the trained indoor pollutant concentration prediction model as the target indoor pollutant concentration prediction model.

[0034] The air purification method provided by the embodiments of the present application fully considers the complex situation of the dynamic changes in the air environment, comprehensively considers the multi-dimensional information that affects the indoor air pollutant concentration during the surgical process, provides comprehensive and effective information for the training of multiple initial indoor pollutant concentration prediction models through historical indoor air environment information, historical surgical state information, and historical indoor pollutant concentration information, generates different candidate indoor pollutant concentration prediction information through multiple initial indoor pollutant concentration prediction models respectively, gives full play to the advantages of different prediction models, avoids the limitations of a single prediction model, screens the initial indoor pollutant concentration prediction models by calculating the prediction error of the indoor pollutant concentration, enables the models with poor prediction effects to be eliminated, makes the prediction results of the screened indoor pollutant concentration prediction models more in line with the actual situation, provides a comprehensive and highly robust target indoor pollutant concentration prediction model for real-time indoor pollutant concentration prediction during subsequent actual surgical processes, ensures the accuracy and reliability of the real-time prediction results of the indoor pollutant concentration in the operating room, and improves the effectiveness of air purification.

[0035] Figure 3 The flowchart showing the implementation of the air purification method provided by Embodiment 3 of the present application is different from Embodiment 1 above in that: The indoor pollutant concentration prediction model includes multiple indoor pollutant concentration prediction sub-models and multiple sub-model selection probability calculation functions; among them, the indoor pollutant concentration prediction sub-models and the sub-model selection probability calculation functions are in one-to-one correspondence; The specific steps of step S102 include: Step S301: Perform position encoding processing on the current indoor air environment information and the current surgical state information to obtain the current indoor air environment encoding information and the current surgical state encoding information.

[0036] In this embodiment, one-hot encoding or embedding encoding can be used to perform position encoding processing on the current indoor air environment information and the current surgical state information, so as to convert the current indoor air environment information and the current surgical state information into a vector format for subsequent multi-dimensional calculations. The vectors obtained after the position encoding processing are used as the current indoor air environment encoding information and the current surgical state encoding information.

[0037] Step S302: According to the current indoor air environment encoding information, the current surgical state encoding information, and multiple preset encoding feature mapping vectors, obtain the current indoor air environment feature encoding information and the current surgical state feature encoding information.

[0038] In this embodiment, multiple preset encoding feature mapping vectors can be set manually and are used to perform feature extraction processing on the current indoor air environment encoding information and the current surgical state encoding information in different spatial dimensions. The extracted features are used to represent the component features in different spatial dimensions. It can be to perform convolution operations on the current indoor air environment encoding information and multiple encoding feature mapping vectors respectively, and the results after the convolution operations are summarized and integrated as the current indoor air environment feature encoding information and the current surgical state feature encoding information.

[0039] Step S303: According to the current indoor air environment feature encoding information, the current surgical state feature encoding information, and the sub-model selection probability calculation function, calculate the selection probability information of multiple indoor pollutant concentration prediction sub-models.

[0040] In this embodiment, the indoor pollutant concentration prediction model can be composed of multiple Transformer models. Therefore, the Transformer model can be used as the indoor pollutant concentration prediction sub-model, and the sub-model selection probability calculation function is used to determine the reference degree of the output results of each indoor pollutant concentration prediction sub-model. It can be to first use the current indoor air environment feature encoding information and the current surgical state encoding information as the independent variables of the sub-model selection probability calculation function, and the function values calculated are used as the selection probability information of the indoor pollutant concentration prediction sub-models to determine the reference degree of the output results of each indoor pollutant concentration prediction sub-model for the current input information.

[0041] Step S304: Normalize the multiple pieces of selection probability information to obtain the allocation probability information of multiple indoor pollutant concentration prediction sub-models.

[0042] In this embodiment, the normalization process is used to limit the range of the selection probability information within (0, 1) to avoid calculation errors caused by variables exceeding the dimension during subsequent calculations. The normalization process can be performed through the softmax function. Taking the selection probability information as the independent variable of the softmax function, the calculated function value is used as the allocation probability information.

[0043] Step S305: Obtain multiple initial indoor pollutant concentration intermediate variable information based on the current indoor air environment information, the current surgical state information, and multiple indoor pollutant concentration prediction sub-models.

[0044] In this embodiment, the current indoor air environment information and the current surgical state information can be used as the input information of multiple indoor pollutant concentration prediction sub-models. Through the calculations of multiple indoor pollutant concentration prediction sub-models, multiple initial indoor pollutant concentration intermediate variable information is respectively output by the multiple indoor pollutant concentration prediction sub-models.

[0045] Step S306: Calculate the initial indoor pollutant concentration information based on the multiple pieces of allocation probability information and the multiple initial indoor pollutant concentration intermediate variable information.

[0046] In this embodiment, the allocation probability information can be used as weights to perform a weighted sum calculation on the initial indoor pollutant concentration intermediate variable information, and the calculation result is used as the initial indoor pollutant concentration information.

[0047] The air purification method provided by the embodiment of the present application extracts features of different dimensions in a non-linear space for the current indoor air environment information and the current surgical state information through multiple encoded feature mapping vectors, fully excavates the key features of the current indoor air environment information and the current surgical state information, and avoids any subtle key features being omitted during subsequent prediction calculations. The key features of the current indoor air environment information and the current surgical state information are operated through the sub-model selection probability calculation function to adaptively calculate the matching degree for different indoor pollutant concentration prediction sub-models, thereby giving full play to the calculation advantages of each indoor pollutant concentration prediction sub-model to adapt to the dynamic changes of the air environment during the operation, improving the accuracy and reliability of the prediction of indoor pollutant concentration information, providing precise data decision support for the air purification of the operating room, and effectively reducing the infection risk during the operation.

[0048] Figure 4 The implementation flowchart of the air purification method provided by the fourth embodiment of the present application is shown. The difference from the third embodiment above is that: The multiple preset encoding feature mapping vectors include a preset search feature mapping vector, a preset index feature mapping vector, and a preset content feature mapping vector; Step S302 specifically includes: Step S401: According to the current indoor air environment encoding information, the current surgical state encoding information, the preset search feature mapping vector, the preset index feature mapping vector, and the preset content feature mapping vector, obtain the current indoor air environment search feature information, the current indoor air environment index feature information, the current indoor air environment content feature information, the current surgical state search feature information, the current surgical state index feature information, and the current surgical state content feature information.

[0049] In this embodiment, the preset search feature mapping vector, the preset index feature mapping vector, and the preset content feature mapping vector can all be set artificially and are used to perform feature extraction on different dimensions of the current indoor air environment encoding information and the current surgical state encoding information. It can be understood that both the current indoor air environment encoding information and the current surgical state encoding information are calculated in the form of matrices. It can be to perform inner product operations on the current indoor air environment encoding information with the preset search feature mapping vector, the preset index feature mapping vector, and the preset content feature mapping vector respectively, and the inner product operation results obtain the current indoor air environment search feature information, the current indoor air environment index feature information, and the current indoor air environment content feature information; it can be to perform inner product operations on the current surgical state encoding information with the preset search feature mapping vector, the preset index feature mapping vector, and the preset content feature mapping vector respectively, and the inner product operation results obtain the current surgical state search feature information, the current surgical state index feature information, and the current surgical state content feature information.

[0050] Step S402: According to the current indoor air environment search feature information, the current indoor air environment index feature information, the current surgical state search feature information, and the current surgical state index feature information, obtain the current indoor air environment mapping feature information and the current surgical state mapping feature information.

[0051] In this embodiment, it can be to first perform transposition processing on the current indoor air environment index feature information and the current surgical state index feature information, multiply the current indoor air environment search feature information by the transposed current indoor air environment index feature information to obtain the current indoor air environment mapping feature information; multiply the current surgical state search feature information by the transposed current surgical state index feature information to obtain the current surgical state mapping feature information.

[0052] Step S403: Obtain the current indoor air environment mapping feature weight information and the current surgical state mapping weight information based on the current indoor air environment mapping feature information, the current surgical state mapping feature information, and multiple preset mapping feature offset matrices.

[0053] In this embodiment, the preset mapping feature offset matrices can be set manually and are used to cause multi-dimensional displacements of the current indoor air environment mapping feature information and the current surgical state mapping feature information in the non-linear space, thereby increasing the logical distances of each key feature in the non-linear space. It can be to add the current indoor air environment mapping feature information to multiple preset mapping feature offset matrices respectively to increase the logical distances of the key features represented by each current indoor air environment mapping feature information in the non-linear space, and the addition results are used as the current indoor air environment mapping feature weight information. It can be to add the current surgical state mapping feature information to multiple preset mapping feature offset matrices to increase the logical distances of the key features represented by each current surgical state mapping feature information in the non-linear space, and the addition results are used as the current surgical state mapping weight information.

[0054] Step S404: Randomly generate multiple mapping feature mask matrices according to the dimension information of the current indoor air environment mapping feature weight information and the dimension information of the current surgical state mapping weight information.

[0055] In this embodiment, first determine the dimension information of the current indoor air environment mapping feature weight information and the dimension information of the current surgical state mapping weight information, and use the dimension information of the current indoor air environment mapping feature weight information and the dimension information of the current surgical state mapping weight information as the dimension information of the randomly generated mapping feature mask matrices, that is, the dimension of the randomly generated mapping feature mask matrices is the same as the dimension of the current indoor air environment mapping feature weight information and is also the same as the dimension of the current surgical state mapping weight information. All the element values in the mapping feature mask matrices can be defaulted to 0.

[0056] Step S405: Obtain the current indoor air environment mask feature weight information and the current surgical state mask weight information based on the current indoor air environment mapping feature weight information, the current surgical state mapping weight information, and multiple mapping feature mask matrices.

[0057] In this embodiment, according to a specific matrix value filling rule, the mapping feature mask matrix may be filled with values first, the values at the filling positions are changed to 1, and the filled mapping feature mask matrix is respectively subjected to convolution calculation or inner product calculation with the current indoor air environment mapping feature weight information and the current surgical state mapping weight information, and the calculation results are used as the current indoor air environment mask feature weight information and the current surgical state mask weight information.

[0058] Step S406: Obtain the current indoor air environment feature encoding information and the current surgical state feature encoding information according to the current indoor air environment mask feature weight information, the current surgical state mask weight information, the current indoor air environment content feature information, and the current surgical state content feature information.

[0059] In this embodiment, the current indoor air environment mask feature weight information may be multiplied by the current indoor air environment content feature information, and the calculation result is used as the current indoor air environment feature encoding information. The current surgical state mask weight information may be multiplied by the current surgical state content feature information, and the calculation result is used as the current surgical state feature encoding information.

[0060] The air purification method provided by the embodiment of the present application performs different-dimensional feature depth extraction on the current indoor air environment information and the current surgical state information through multiple feature mapping vectors to comprehensively capture the key information in the current indoor air environment information and the current surgical state information, so that the potential association between the current indoor air environment information, the current surgical state information, and the current indoor pollutant concentration can be fully explored. The mapping feature offset matrix is used to enhance the influence of important features and weaken the role of secondary features, avoiding the omission of important features and preventing secondary features from interfering with the prediction calculation results. Through multiple mapping feature mask matrices, features closely related to the prediction of indoor pollutant concentration are further extracted and amplified during the calculation process, while filtering out irrelevant or redundant features, avoiding full-scale calculation of all features, reducing the calculation amount, and improving the operation efficiency. While ensuring the prediction accuracy of indoor pollutant concentration information, the prediction timeliness of indoor pollutant concentration information is improved, thereby enhancing the timeliness and effectiveness of indoor air purification processing.

[0061] Figure 5 The implementation flowchart of the air purification method provided by the fifth embodiment of the present application is shown. The difference from the fourth embodiment above is that step S405 specifically includes: Step S501: Obtain the internal position information of the mask matrix and the edge position information of the mask matrix according to the multiple mapping feature mask matrices.

[0062] In this embodiment, it can be understood that the mapping feature mask matrix is calculated in the form of a multi-dimensional matrix. Assuming that the number of rows of the mapping feature mask matrix is m and the number of columns is n, the positions of the elements with row numbers 1 and m and the positions of the elements with column numbers 1 and n in the mapping feature mask matrix are the edge position information of the mask matrix, and the positions of the remaining elements are the internal position information of the mask matrix.

[0063] Step S502: According to the internal position information of the mask matrix, perform odd-bit filling processing on the multiple mapping feature mask matrices to obtain multiple intermediate variables of the mapping feature mask matrices.

[0064] In this embodiment, it can be to perform numerical filling processing on the elements at the internal position information of the mask matrix. It can be to perform numerical filling on the elements with both odd row numbers and odd column numbers, that is, replace the value of the element with both odd row numbers and odd column numbers with 1. The matrix after the odd-bit filling processing is used as the intermediate variable of the mapping feature mask matrix for subsequent re-filling.

[0065] Step S503: According to the edge position information of the mask matrix, perform segmented filling processing on the multiple intermediate variables of the mapping feature mask matrices to obtain multiple mapping feature mask transformation matrices.

[0066] In this embodiment, it can be to perform numerical filling processing on the elements at the edge position information of the mask matrix. For the elements with row numbers 1 and m, fill the elements with column numbers less than m / 2, that is, replace the element with 1; for the elements with column numbers 1 and n, fill the elements with row numbers greater than n / 2, that is, replace the element with 1. It can also be that for the elements with row numbers 1 and m, fill the elements with column numbers greater than m / 2, that is, replace the element with 1; for the elements with column numbers 1 and n, fill the elements with row numbers less than n / 2, that is, replace the element with 1. The matrix after the segmented filling processing is used as the mapping feature mask transformation matrix for subsequent masking processing of the current indoor air environment mapping feature weight information and the current surgical state mapping weight information.

[0067] Step S504: According to the multiple mapping feature mask transformation matrices, perform masking processing on the current indoor air environment mapping feature weight information and the current surgical state mapping weight information to obtain the current indoor air environment masked feature weight information and the current surgical state masked weight information.

[0068] In this embodiment, it may be to multiply the current indoor air environment mapping feature weight information by multiple mapping feature mask transformation matrices respectively, and the result of the multiplication is used as the current indoor air environment mask feature weight information. It may be to multiply the current surgical state mapping weight information by multiple mapping feature mask transformation matrices respectively, and the result of the multiplication is used as the current surgical state mask weight information.

[0069] The air purification method provided by the embodiment of the present application fills the mapping feature mask matrix, and uses the filled mapping feature mask transformation matrix to perform mask processing on the feature information of the current indoor air environment information and the current surgical state information, so that a large number of irrelevant processes are filtered out, reducing unnecessary calculations, and avoiding interference of the prediction calculation process by irrelevant information, improving the calculation efficiency and the accuracy of predicting the indoor pollutant concentration, and ensuring the timeliness and effectiveness of the indoor air purification process during the operation.

[0070] Figure 6 The flowchart of the implementation of the air purification method provided by the sixth embodiment of the present application is shown. The difference from the first embodiment above is that step S103 specifically includes: Step S601: Obtain an indoor pollutant concentration classification variable according to the initial indoor pollutant concentration information and a preset classification weight matrix.

[0071] In this embodiment, the preset classification weight matrix can be set manually. The result of multiplying with other matrices can be 1 or 0, and it is used to classify the initial indoor pollutant concentration information. Among them, the initial indoor pollutant concentration information can be divided into two categories. One category is valid information, which can be represented by the function value 1, and the other category is invalid information, which can be represented by the function value 0. The invalid information can refer to the abnormal information and noise information in the initial indoor pollutant concentration information and can be directly discarded. The classification weight matrix processing can be to multiply the initial indoor pollutant concentration information by the classification weight matrix, and the valid information after being processed by the classification weight matrix is used as the indoor pollutant concentration classification variable for the next calculation process.

[0072] Step S602: Obtain an indoor pollutant concentration classification offset conversion variable according to the indoor pollutant concentration classification variable and a preset classification offset matrix.

[0073] In this embodiment, the preset classification offset matrix can be set manually and is used to adjust the decision boundary for the indoor pollutant concentration classification variable. It can be to multiply the indoor pollutant concentration classification variable by the classification offset matrix, and the result of the multiplication is used as the indoor pollutant concentration classification offset conversion variable.

[0074] Step S603: Perform probability interval mapping processing on the indoor pollutant concentration classification offset conversion variable to obtain indoor pollutant concentration classification probability information.

[0075] In this embodiment, the probability interval mapping processing can be performed through the ReLU function. The indoor pollutant concentration classification offset conversion variable can be used as the independent variable of the ReLU function, and the calculated function value is used as the indoor pollutant concentration classification probability information.

[0076] Step S604: Screen the initial indoor pollutant concentration information according to the indoor pollutant concentration classification probability information and the preset indoor pollutant concentration classification probability threshold information to obtain the target indoor pollutant concentration information.

[0077] In this embodiment, the preset indoor pollutant concentration classification probability threshold information can be set manually and is used to determine the validity of the initial indoor pollutant concentration information represented by the indoor pollutant concentration classification probability information. When the indoor pollutant concentration classification probability information is greater than the indoor pollutant concentration classification probability threshold information, it indicates that the initial indoor pollutant concentration information corresponding to the indoor pollutant concentration classification probability information has high validity, and the initial indoor pollutant concentration information corresponding to the indoor pollutant concentration classification probability information is output as the target indoor pollutant concentration information. When the indoor pollutant concentration classification probability information is less than or equal to the indoor pollutant concentration classification probability threshold information, it indicates that the initial indoor pollutant concentration information corresponding to the indoor pollutant concentration classification probability information has insufficient validity, and the initial indoor pollutant concentration information corresponding to the indoor pollutant concentration classification probability information is discarded.

[0078] The air purification method provided by the embodiment of the present application accurately identifies abnormal values and noise information in the initial indoor pollutant concentration information through the classification weight matrix, improves the robustness and effectiveness of real-time calculation of indoor pollutant concentration information, provides a more accurate data basis for subsequent calculation of indoor ventilation volume, and further improves the effect and efficiency of air purification treatment in the operating room, ensures the quality of the air environment in the operating room during the operation, and effectively reduces the risk of surgical infection.

[0079] Corresponding to the method in the above embodiment, Figure 7 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 7 The exemplary air purification device may be the execution subject of the air purification method provided in the foregoing Embodiment 1.

[0080] Refer to Figure 7 and the air purification device includes: An information acquisition module 710, configured to acquire current indoor air environment information, current surgical state information, and indoor volume information; An initial indoor pollutant concentration information determination module 720, configured to obtain initial indoor pollutant concentration information according to the current indoor air environment information, the current surgical state information, and a target indoor pollutant concentration prediction model; A target indoor pollutant concentration information determination module 730, configured to perform screening processing on the initial indoor pollutant concentration information to obtain target indoor pollutant concentration information; and An indoor ventilation volume information determination module 740, configured to calculate indoor ventilation volume information according to the target indoor pollutant concentration information and the indoor volume information, so as to perform air purification processing on the indoor environment.

[0081] For the process of each module in the air purification device provided in the embodiments of the present application to implement its respective functions, reference may be specifically made to the description of Embodiment 1 shown above, which will not be elaborated herein. Figure 1 Shown in the above embodiment, and will not be repeated here.

[0082] It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution is prior or posterior. 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.

[0083] 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.

[0084] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0085] As used in the specification and the appended claims of the present application, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" according to the context.

[0086] In addition, in the description of the specification and the appended claims of the present 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 the present 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.

[0087] The reference to "one embodiment" or "some embodiments" etc. described in the specification of the present application means that a specific feature, structure or characteristic described in connection with that embodiment is included in one or more embodiments of the present application. Thus, the statements "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 other ways. The terms "comprise", "include", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0088] 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.

[0089] For example, the terminal device may 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-to-everything (V2X) 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, such as a mobile terminal in a 5G network or a mobile terminal in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0090] By way of example and not limitation, when the terminal device is a wearable device, the wearable device may 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 worn directly on the body or integrated into the user's clothing or accessories. A wearable device is not only 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 smartphone, 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 smartphones, such as various smart bracelets and smart jewelry for monitoring physical signs.

[0091] Figure 8 It is a schematic structural diagram of a terminal device provided by an embodiment of the present application. As Figure 8 shown, the terminal device 8 of this embodiment includes: at least one processor 80 ( Figure 8 only one is shown in the figure), and a memory 81. A computer program 82 that can run on the processor 80 is stored in the memory 81. When the processor 80 executes the computer program 82, the steps in the above embodiments of each air purification method are implemented, such as Figure 1 the steps S101 to S104 shown in the figure. Alternatively, when the processor 80 executes the computer program 82, the functions of each module / unit in the above device embodiments are implemented, such as Figure 7The functions of the modules 710 to 740 shown.

[0092] The terminal device 8 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 80 and a memory 81. Those skilled in the art can understand that Figure 8 These are merely examples of the terminal device 8 and do not constitute a limitation on the terminal device 8. It may include more or fewer components than shown in the figure, or combine certain components, or have different components. For example, the terminal device may further include an input and sending device, a network access device, a bus, etc.

[0093] The so-called processor 80 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.

[0094] In some embodiments, the memory 81 may be an internal storage unit of the terminal device 8, such as the hard disk or memory of the terminal device 8. The memory 81 may also be an external storage device of the terminal device 8, 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 8. Further, the memory 81 may also include both the internal storage unit and the external storage device of the terminal device 8. The memory 81 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program, etc. The memory 81 may also be used to temporarily store data that has been sent or will be sent.

[0095] In addition, in each embodiment of the present application, the functional units may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0096] An 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.

[0097] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, which when executed by a processor can implement the steps in each of the above method embodiments.

[0098] An embodiment of the present application provides a computer program product, which when running on a terminal device enables the terminal device to execute the steps in each of the above method embodiments.

[0099] If 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, all or part of the processes in the method embodiments of the present application can also be completed by instructing related 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 in each of the above 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 disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0100] In the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0101] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or 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. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0102] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed over 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.

[0103] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present 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 on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An air purification method, characterized in that, Including: Obtain the current indoor air environment information, the current surgical state information, and the indoor volume information; According to the current indoor air environment information, the current surgical state information, and the target indoor pollutant concentration prediction model, obtain the initial indoor pollutant concentration information; Perform screening processing on the initial indoor pollutant concentration information to obtain the target indoor pollutant concentration information; According to the target indoor pollutant concentration information and the indoor volume information, calculate the indoor ventilation volume information to perform air purification processing on the indoor environment.

2. The air purification method according to claim 1, wherein: The target indoor pollutant concentration prediction model is obtained through the following steps: Obtain the historical indoor air environment information, the historical surgical state information, and the historical indoor pollutant concentration information; wherein, the historical indoor air environment information includes the historical air particulate matter concentration information, the historical microorganism concentration information, the historical temperature and humidity information, and the historical air flow velocity information; the historical surgical state information includes the historical surgical type information, the historical surgical duration information, the historical number of surgical personnel information, and the historical number of entries and exits of surgical personnel information; According to the historical air particulate matter concentration information, the historical microorganism concentration information, the historical temperature and humidity information, the historical air flow velocity information, the historical surgical type information, the historical surgical duration information, the historical number of surgical personnel information, the historical number of entries and exits of surgical personnel information, and multiple initial indoor pollutant concentration prediction models, obtain multiple candidate indoor pollutant concentration prediction information; According to the historical indoor pollutant concentration information and the candidate indoor pollutant concentration prediction information, calculate the indoor pollutant concentration prediction error; According to the indoor pollutant concentration prediction error, perform screening processing on the candidate indoor pollutant concentration prediction information to obtain the response indoor pollutant concentration prediction information; According to the response indoor pollutant concentration prediction information, perform screening processing on the multiple initial indoor pollutant concentration prediction models to obtain the target indoor pollutant concentration prediction model.

3. The air purification method according to claim 1, wherein: The indoor pollutant concentration prediction model includes multiple indoor pollutant concentration prediction sub-models and multiple sub-model selection probability calculation functions; wherein, the indoor pollutant concentration prediction sub-models and the sub-model selection probability calculation functions are in one-to-one correspondence; The step of obtaining the initial indoor pollutant concentration information according to the current indoor air environment information, the current surgical state information, and the target indoor pollutant concentration prediction model specifically includes: Perform position encoding processing on the current indoor air environment information and the current surgical state information to obtain the current indoor air environment encoding information and the current surgical state encoding information; According to the current indoor air environment encoding information, the current surgical state encoding information, and multiple preset encoding feature mapping vectors, obtain the current indoor air environment feature encoding information and the current surgical state feature encoding information; According to the current indoor air environment characteristic coding information, the current surgical state characteristic coding information, and the sub-model selection probability calculation function, calculate the selection probability information of multiple indoor pollutant concentration prediction sub-models; Perform normalization processing on the multiple selection probability information to obtain the allocation probability information of multiple indoor pollutant concentration prediction sub-models; According to the current indoor air environment information, the current surgical state information, and multiple indoor pollutant concentration prediction sub-models, obtain multiple initial indoor pollutant concentration intermediate variable information; According to the multiple allocation probability information and the multiple initial indoor pollutant concentration intermediate variable information, calculate the initial indoor pollutant concentration information.

4. The air purification method according to claim 3, wherein The multiple preset coding feature mapping vectors include a preset search feature mapping vector, a preset index feature mapping vector, and a preset content feature mapping vector; The step of obtaining the current indoor air environment characteristic coding information and the current surgical state characteristic coding information according to the current indoor air environment coding information, the current surgical state coding information, and the multiple preset coding feature mapping vectors specifically includes: According to the current indoor air environment coding information, the current surgical state coding information, the preset search feature mapping vector, the preset index feature mapping vector, and the preset content feature mapping vector, obtain the current indoor air environment search feature information, the current indoor air environment index feature information, the current indoor air environment content feature information, the current surgical state search feature information, the current surgical state index feature information, and the current surgical state content feature information; According to the current indoor air environment search feature information, the current indoor air environment index feature information, the current surgical state search feature information, and the current surgical state index feature information, obtain the current indoor air environment mapping feature information and the current surgical state mapping feature information; According to the current indoor air environment mapping feature information, the current surgical state mapping feature information, and the multiple preset mapping feature offset matrices, obtain the current indoor air environment mapping feature weight information and the current surgical state mapping weight information; Randomly generate multiple mapping feature mask matrices according to the dimension information of the current indoor air environment mapping feature weight information and the dimension information of the current surgical state mapping weight information; According to the current indoor air environment mapping feature weight information, the current surgical state mapping weight information, and the multiple mapping feature mask matrices, obtain the current indoor air environment mask feature weight information and the current surgical state mask weight information; According to the current indoor air environment mask feature weight information, the current surgical state mask weight information, the current indoor air environment content feature information, and the current surgical state content feature information, obtain the current indoor air environment characteristic coding information and the current surgical state characteristic coding information.

5. The air purification method according to claim 4, characterized in that The step of obtaining the current indoor air environment masked feature weight information and the current surgical state masked weight information according to the current indoor air environment mapped feature weight information, the current surgical state mapped weight information, and multiple mapped feature mask matrices specifically includes: Obtaining the internal position information of the mask matrix and the edge position information of the mask matrix according to the multiple mapped feature mask matrices; Performing odd-bit filling processing on the multiple mapped feature mask matrices according to the internal position information of the mask matrix to obtain intermediate variables of the multiple mapped feature mask matrices; Performing segmented filling processing on the intermediate variables of the multiple mapped feature mask matrices according to the edge position information of the mask matrix to obtain multiple mapped feature transformation matrices; Performing mask processing on the current indoor air environment mapped feature weight information and the current surgical state mapped weight information according to the multiple mapped feature transformation matrices to obtain the current indoor air environment masked feature weight information and the current surgical state masked weight information.

6. The air purification method according to claim 1, characterized in that, The step of screening the initial indoor pollutant concentration information to obtain the target indoor pollutant concentration information specifically includes: Obtaining an indoor pollutant concentration classification variable according to the initial indoor pollutant concentration information and a preset classification weight matrix; Obtaining an indoor pollutant concentration classification offset conversion variable according to the indoor pollutant concentration classification variable and a preset classification offset matrix; Performing probability interval mapping processing on the indoor pollutant concentration classification offset conversion variable to obtain indoor pollutant concentration classification probability information; Screening the initial indoor pollutant concentration information according to the indoor pollutant concentration classification probability information and preset indoor pollutant concentration classification probability threshold information to obtain the target indoor pollutant concentration information.

7. The air purification method according to claim 1, characterized in that, The current indoor air environment information includes current air particulate matter concentration information, current microorganism concentration information, current temperature and humidity information, and current air flow velocity information; The current surgical state information includes current surgical type information, current surgical duration information, current number of surgical personnel information, and current number of entries and exits of surgical personnel information.

8. An air purification device, characterized in that, Including: An information acquisition module, configured to acquire current indoor air environment information, current surgical state information, and indoor volume information; An initial indoor pollutant concentration information determination module, configured to obtain initial indoor pollutant concentration information according to the current indoor air environment information, the current surgical state information, and a target indoor pollutant concentration prediction model; A target indoor pollutant concentration information determination module, configured to screen the initial indoor pollutant concentration information to obtain the target indoor pollutant concentration information; And An indoor ventilation volume information determination module, configured to calculate indoor ventilation volume information according to the target indoor pollutant concentration information and the indoor volume information to perform air purification processing on the indoor environment.

9. A terminal device, characterized in that, The terminal device 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 method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images