Machine learning based human aerosol online monitoring system

Abstract

The present application relates to aerosol concentration monitoring technical field, specifically to a kind of human aerosol online monitoring system based on machine learning;According to non-humidity abnormal time and concentration time sequence obtains historical concentration benchmark;According to historical concentration benchmark and concentration value of current time, the range of preset particle size grade obtains concentration abnormality;According to concentration abnormality and humidity abnormal time, judge whether need to correct, if need to correct, for any concentration time sequence corresponding to minimum preset particle size grade and maximum preset particle size grade: according to the humidity of the last preset number of humidity abnormal time of current time and the concentration value of the same time of the correlation characteristics, abnormal duration characteristics of the last preset number of humidity abnormal time obtain humidity influence degree.The present application corrects concentration value according to humidity influence degree and humidity abnormal characteristics, obtains corrected concentration value, improves the accuracy of aerosol concentration.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of aerosol concentration monitoring, in particular to a human-derived aerosol online monitoring system based on machine learning. BACKGROUND

[0002] Human-derived aerosol mainly refers to a complex gaseous dispersion system generated by the respiratory tract of the human body, which contains some biological characteristic molecules generated by human metabolism; in medicine, the particle size distribution, concentration and chemical composition of human-derived aerosol can be used to quickly and accurately diagnose and monitor the condition of diseases such as asthma in patients. However, the collection and monitoring process of human-derived aerosol is easily affected by environmental humidity. If the humidity is too high or too low, the particle size in the aerosol will change, causing the concentration of different particle size ranges to deviate from the actual value, affecting the analysis accuracy of human-derived aerosol. SUMMARY

[0003] In order to solve the technical problem that the above environmental humidity will cause the particle size in the human-derived aerosol to change and affect the analysis accuracy of the human-derived aerosol, the purpose of the present application is to provide a human-derived aerosol online monitoring system based on machine learning, and the technical solution adopted is as follows:

[0004] A data acquisition module is configured to acquire an environmental humidity time sequence and a concentration time sequence of all preset particle size levels of human-derived aerosol.

[0005] A concentration analysis module is configured to obtain humidity abnormal time and non-humidity abnormal time according to the environmental humidity time sequence; obtain a historical concentration reference of a preset particle size level according to the non-humidity abnormal time and the concentration time sequence; and obtain a concentration abnormality degree according to a difference feature of the historical concentration reference and a concentration value at a current time, and a range of the preset particle size level.

[0006] A humidity analysis module is configured to determine whether the concentration value at the current time needs to be corrected according to the concentration abnormality degree and the humidity abnormal time. If correction is needed, for any concentration time sequence corresponding to the minimum preset particle size level and the maximum preset particle size level: obtain a humidity influence degree of the any concentration time sequence according to a correlation feature of the humidity at the historical most recent preset number of humidity abnormal time and the concentration value at the same time in the any concentration time sequence, and an abnormal duration feature of the historical most recent preset number of humidity abnormal time.

[0007] A concentration correction module is configured to correct the concentration value at the current time according to the humidity influence degree and humidity abnormality feature at the current time, and obtain a corrected concentration value of human-derived aerosol at the latest time in the any concentration time sequence.

[0008] Further, the step of obtaining humidity abnormal time and non-humidity abnormal time according to the environmental humidity time sequence comprises:

[0009] The time when the humidity in the environment humidity time sequence is within the preset standard humidity range is taken as the non-humidity abnormal time, and the time when the humidity in the environment humidity time sequence is not within the preset standard humidity range is taken as the humidity abnormal time.

[0010] Further, the step of obtaining a historical concentration reference of a preset particle size level according to the non-humidity abnormal time and the concentration time sequence comprises:

[0011] The average value of the concentration values of all non-humidity abnormal times in the concentration time sequence of the preset particle size level is calculated to obtain the historical concentration reference of the preset particle size level.

[0012] Further, the step of obtaining a concentration abnormality degree according to the difference feature of the historical concentration reference and the concentration value at the current time and the range of the preset particle size level comprises:

[0013] The reciprocal of the difference between the maximum value and the minimum value of any preset particle size level is calculated to obtain a particle size range weight; the absolute value of the difference between the concentration value of the any preset particle size level at the current time and the historical concentration reference is calculated to obtain a concentration difference value; and the sum of the products of the concentration difference values corresponding to all preset particle size levels and the particle size range weights is calculated and normalized to obtain the concentration abnormality degree at the current time.

[0014] Further, the step of judging whether the concentration value at the current time needs to be corrected according to the concentration abnormality degree and the humidity abnormal time comprises:

[0015] If the current time is a humidity abnormal time and the concentration abnormality degree exceeds a preset abnormal threshold, the concentration value at the current time needs to be corrected.

[0016] Further, the step of obtaining a humidity influence degree of the any concentration time sequence according to the correlation feature of the humidity of the historical most recent preset number of humidity abnormal times at the current time and the concentration value at the same time in the any concentration time sequence and the abnormal duration feature of the historical most recent preset number of humidity abnormal times comprises:

[0017] The absolute value of the Pearson correlation coefficient of the humidity of the historical most recent preset number of humidity abnormal times and the concentration value at the same time in the any concentration time sequence is calculated to obtain a correlation degree value; for any humidity abnormal time in the historical most recent preset number of humidity abnormal times, the number of other humidity abnormal times connected to the any humidity abnormal time is calculated to obtain a duration feature value of the any humidity abnormal time; the sum of the squares of the duration feature values of the historical most recent preset number of humidity abnormal times is calculated and normalized to obtain a humidity abnormal coefficient; and the product of the correlation degree value and the humidity abnormal coefficient is calculated to obtain the humidity influence degree.

[0018] Further, the step of correcting the concentration value at the current time according to the humidity influence degree and the humidity anomaly feature at the current time to obtain the corrected concentration value of the human-derived aerosol at the latest time in the arbitrary concentration time sequence comprises:

[0019] calculating the absolute value of the difference between the humidity value at the current time and the median of the preset standard humidity range and normalizing to obtain a humidity difference degree; calculating the product of the humidity difference degree, the humidity influence degree and a preset constant to obtain a concentration adjustment reference; calculating the sum of constant 1 and the concentration adjustment reference to obtain a first concentration adjustment coefficient; calculating the difference between constant 1 and the concentration adjustment reference to obtain a second concentration adjustment coefficient;

[0020] if the humidity value at the current time exceeds the preset standard humidity range, calculating the product of the concentration value at the current time corresponding to the maximum preset particle size grade and the second concentration adjustment coefficient to obtain the corrected concentration; calculating the product of the concentration value at the current time corresponding to the minimum preset particle size grade and the first concentration adjustment coefficient to obtain the corrected concentration;

[0021] if the humidity value at the current time is lower than the preset standard humidity range, calculating the product of the concentration value at the current time corresponding to the maximum preset particle size grade and the first concentration adjustment coefficient to obtain the corrected concentration; calculating the product of the concentration value at the current time corresponding to the minimum preset particle size grade and the second concentration adjustment coefficient to obtain the corrected concentration.

[0022] The present application has the following beneficial effects:

[0023] In the present application, the humidity anomaly time and the non-humidity anomaly time are obtained to determine the aerosol concentration feature without interference from external factors; the historical concentration reference is obtained to determine the normal level of human-derived aerosol under historical normal conditions without interference, thereby facilitating the judgment of whether the concentration is abnormal. The concentration anomaly degree is obtained to judge whether the overall aerosol concentration feature at the current time is abnormal, and then combined with the environmental humidity feature to judge whether correction is needed. The humidity influence degree is obtained to represent the influence degree of aerosol concentration by environmental humidity according to the change correlation feature between humidity and aerosol concentration and the duration of humidity feature, thereby improving the correction accuracy of aerosol concentration according to the humidity influence degree. Finally, the concentration value at the current time is corrected according to the humidity influence degree and the humidity anomaly feature to obtain the corrected concentration; the corrected concentration can reduce the influence of environmental humidity on aerosol concentration, so that the obtained aerosol concentration is more accurate, thereby improving the accuracy of aerosol feature analysis. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0025] Figure 1 A machine learning-based human aerosol online monitoring system block diagram provided by an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined inventive purpose, the following will combine the drawings and the preferred embodiments to specifically describe the machine learning-based human aerosol online monitoring system according to the present application, its specific implementation, structure, features and effects in detail. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0027] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0028] The following will specifically describe the specific scheme of the machine learning-based human aerosol online monitoring system provided by the present application in combination with the drawings.

[0029] Please refer to Figure 1 which shows a machine learning-based human aerosol online monitoring system block diagram provided by an embodiment of the present application, the system includes the following modules:

[0030] The data acquisition module S1 is used to acquire the environment humidity time sequence and the concentration time sequence of all preset particle size levels of human aerosol.

[0031] In the embodiment of the present application, the implementation scenario is to correct the concentration value of human aerosol measured under abnormal humidity conditions, and to improve the accuracy of concentration measurement. First, the environment humidity time sequence and the concentration time sequence of all preset particle size levels of human aerosol are acquired, the environment humidity time sequence is collected by a humidity sensor, and the concentration of human aerosol is collected by a laser particle size analyzer. In the embodiment of the present application, five common preset particle size levels are set, the first particle size range is 6-100nm, the second particle size range is 100-300nm, the third particle size range is 300nm-1μm, the fourth particle size range is 1-5μm, and the fifth particle size range is 5-10μm. The implementer can determine it by himself according to the implementation scenario. The collection time of the environment humidity time sequence and the concentration time sequence is the same.

[0032] The concentration analysis module S2 is configured to obtain humidity abnormal time and non-humidity abnormal time according to the environment humidity time sequence, obtain historical concentration reference of a preset particle size level according to the non-humidity abnormal time and the concentration time sequence, and obtain concentration abnormality degree according to the difference feature of the historical concentration reference and the concentration value at the current time and the range of the preset particle size level.

[0033] In a normal case, the concentration value of the human-derived aerosol collected from the object is similar at different times. If the concentration of the aerosol changes, it is likely that the humidity is relatively abnormal or that more pathogens appear in the aerosol. Therefore, it is necessary to analyze the concentration of the human-derived aerosol collected from the object in a normal case, and then determine whether correction is needed. First, the humidity abnormal time and the non-humidity abnormal time are obtained according to the environment humidity time sequence, specifically including: taking the time when the humidity in the environment humidity time sequence is within a preset standard humidity range as the non-humidity abnormal time, and taking the time when the humidity in the environment humidity time sequence is not within the preset standard humidity range as the humidity abnormal time; in the embodiment of the present application, the preset standard humidity range is 48%-52%, and the particle size of the aerosol is difficult to change in the air within this range, and the implementer can determine it according to the implementation scene.

[0034] Further, the particle size of the aerosol at the non-humidity abnormal time is difficult to be affected by the outside world, so the concentration of the aerosol at the non-humidity abnormal time is relatively normal. Therefore, the historical concentration reference of the preset particle size level can be obtained according to the non-humidity abnormal time and the concentration time sequence; preferably, in the embodiment of the present application, the step of obtaining the historical concentration reference includes: calculating the average value of the concentration values of all non-humidity abnormal times in the concentration time sequence of the preset particle size level, and obtaining the historical concentration reference of the preset particle size level. The historical concentration reference represents the normal level of the aerosol concentration without external interference. Then, the concentration abnormality can be determined according to the difference feature of the current aerosol concentration and the corresponding historical concentration reference; in the normal breathing state of human beings, the exhaled aerosol has a smaller particle size; while in the deep breathing or coughing state, larger aerosol particles are produced, so the concentration data of the smaller aerosol particles is more representative under normal circumstances. Therefore, when calculating the concentration abnormality of all particle size levels, the difference feature of the concentration data of the smaller particles is more important; therefore, the concentration abnormality degree is obtained according to the difference feature of the historical concentration reference and the concentration value at the current time and the range of the preset particle size level.

[0035] Preferably, in the embodiments of the present application, the step of obtaining the concentration abnormality degree comprises: calculating the reciprocal of the difference between the maximum value and the minimum value of any preset particle size grade to obtain a particle size range weight; the smaller the particle size, the more representative the aerosol concentration, so the smaller the preset particle size grade range, the greater the particle size range weight. Calculate the absolute value of the difference between the concentration value of any preset particle size grade at the current time and the historical concentration reference to obtain a concentration difference value; the greater the concentration difference value means the greater the abnormality of the concentration value of the arbitrary preset particle size grade at the current time. Calculate the sum of the products of the concentration difference values corresponding to all preset particle size grades and the particle size range weights and normalize to obtain the concentration abnormality degree at the current time; the greater the concentration abnormality degree means the greater the abnormality of the concentration of human-derived aerosols collected at the current time.

[0036] The humidity analysis module S3 is used to determine whether the concentration value at the current time needs to be corrected according to the concentration abnormality degree and the humidity abnormal time; if it needs to be corrected, for any concentration time sequence corresponding to the minimum preset particle size grade and the maximum preset particle size grade: obtain the humidity influence degree of the arbitrary concentration time sequence according to the correlation characteristics of the humidity at the historical most recent preset number of humidity abnormal times and the concentration value at the same time in the arbitrary concentration time sequence, and the abnormal duration characteristics of the historical most recent preset number of humidity abnormal times.

[0037] If the concentration abnormality degree at the current time is large, and the greater the difference between the humidity and the preset standard humidity range, the more likely it is that the aerosol concentration at the current time is affected by the environmental humidity rather than an increase in pathogenic organisms. Therefore, it is determined whether the concentration value at the current time needs to be corrected according to the concentration abnormality degree and the humidity abnormal time; specifically including: if the current time is a humidity abnormal time and the concentration abnormality degree exceeds the preset abnormal threshold, the concentration value at the current time needs to be corrected; in the embodiments of the present application, the preset abnormal threshold is 0.6, and the implementer can determine it according to the implementation scene.

[0038] Further, when the ambient humidity increases, the aerosol particles will absorb water, causing the particle size to increase, the size of the aerosol particles in the smaller particle size range exhaled by the human body will increase several times or even dozens of times, resulting in a higher concentration of aerosol in the larger particle size range; for example, the aerosol particles in the first particle size range become large to the second particle size range, the aerosol particles in the second particle size range become large to the third particle size range, and the aerosol particles in the fourth particle size range become large to the fifth particle size range; ultimately, the concentration of aerosol in the first particle size range decreases, while the concentration of aerosol in the fifth particle size range increases, and the concentration of aerosol in other particle size ranges does not change significantly. When the ambient humidity decreases, the water in the aerosol particles will evaporate, causing the particle volume to shrink, resulting in a decrease in the particle size of the aerosol particles in the larger particle size range; for example, the aerosol particles in the fifth particle size range will decrease to the fourth particle size range, the aerosol particles in the fourth particle size range will decrease to the third particle size range, and the aerosol particles in the second particle size range will decrease to the first particle size range; ultimately, the concentration of aerosol in the first particle size range increases, while the concentration of aerosol in the fifth particle size range decreases, and the concentration of aerosol in other particle size ranges does not change significantly. Therefore, the more abnormal the ambient humidity is, the more likely it is to affect the concentration of aerosol in the first particle size range and the fifth particle size range, so the correlation between the humidity anomaly and the aerosol concentration can be analyzed, and the more correlation between the two changes means the more obvious the influence of humidity on the concentration. And the humidity condition is usually stable, the longer the duration of the ambient humidity, the more it can reflect the correlation between the humidity anomaly and the aerosol concentration change characteristics; the shorter the duration of the humidity anomaly, the more likely the concentration anomaly is caused by non-humidity anomaly, which may be caused by human factors to change the aerosol particle size.

[0039] Further, if correction is needed, for any concentration time sequence corresponding to the minimum preset particle size level and the maximum preset particle size level: according to the correlation feature of the humidity at the latest preset number of humidity abnormal time points in the current moment and the concentration value at the same time in the any concentration time sequence, and the abnormal duration feature of the latest preset number of humidity abnormal time points, the humidity influence degree of the any concentration time sequence is obtained. Preferably, in the embodiment of the present application, the step of obtaining the humidity influence degree comprises: calculating the absolute value of the Pearson correlation coefficient of the humidity at the latest preset number of humidity abnormal time points and the concentration value at the same time in the any concentration time sequence, to obtain the correlation degree value; it should be noted that the Pearson correlation coefficient belongs to the prior art, and the closer the Pearson correlation coefficient is to 1, the more relevant the change features of the two data sequences are, and vice versa. In the embodiment of the present application, the latest preset number of humidity abnormal time points are the 40 humidity abnormal time points closest to the current moment, and the implementer can determine it according to the implementation scene. For any humidity abnormal time point in the latest preset number of humidity abnormal time points, the number of other humidity abnormal time points connected to the any humidity abnormal time point is calculated to obtain the duration feature value of the any humidity abnormal time point; the number of other humidity abnormal time points connected to the any humidity abnormal time point reflects the duration of continuous humidity abnormality, and the greater the duration feature value means the longer the time of the humidity abnormal period in which the any humidity abnormal time point is located, thereby indicating that the aerosol concentration is more susceptible to the influence of humidity abnormality. The sum of squares of the duration feature values of the latest preset number of humidity abnormal time points is calculated and normalized to obtain a humidity abnormality coefficient; the greater the sum of squares of the duration feature values means the longer the duration of the humidity abnormal period in which the latest preset number of humidity abnormal time points are located, and the more likely to cause aerosol concentration abnormality. The product of the correlation degree value and the humidity abnormality coefficient is calculated to obtain the humidity influence degree; the greater the humidity influence degree means that the aerosol concentration is more affected by the ambient humidity.

[0040] The concentration correction module S4 is configured to correct the concentration value at the current moment according to the humidity influence degree and the humidity abnormality feature at the current moment, to obtain the corrected concentration value of the human-derived aerosol at the latest time in the any concentration time sequence.

[0041] After the humidity influence degree of the current time is obtained, the concentration value of the current time can be corrected according to the humidity influence degree of the current time and the humidity abnormality feature, and the corrected concentration value of the human-derived aerosol at the latest time in the arbitrary concentration time sequence is obtained; preferably, in the embodiment of the present application, the step of obtaining the corrected concentration value includes: calculating the absolute value of the difference between the humidity value of the current time and the median of the preset standard humidity range and normalizing to obtain the humidity difference degree; the humidity difference degree reflects the difference between the humidity of the current time and the normal humidity, and the greater the humidity difference degree, the greater the influence on the aerosol concentration. The product of the humidity difference degree, the humidity influence degree and the preset constant is calculated to obtain the concentration adjustment benchmark; in the embodiment of the present application, the preset constant is 0.1, and the purpose is to change the range of the concentration adjustment benchmark, so that the correction result is more accurate, and the implementer can determine it according to the implementation scene; the greater the concentration adjustment benchmark, the higher the correction degree of the aerosol concentration. The sum of the constant 1 and the concentration adjustment benchmark is calculated to obtain the first concentration adjustment coefficient; the difference between the constant 1 and the concentration adjustment benchmark is calculated to obtain the second concentration adjustment coefficient.

[0042] Further, if the humidity value of the current time exceeds the preset standard humidity range, the aerosol concentration of the maximum preset particle size level will increase, and the concentration value needs to be reduced during correction; the aerosol concentration of the minimum preset particle size level will decrease, and the concentration value needs to be increased during correction. Therefore, the product of the concentration value of the current time corresponding to the maximum preset particle size level and the second concentration adjustment coefficient is calculated to obtain the corrected concentration; in the embodiment of the present application, the maximum preset particle size level is the fifth particle size range, and the corrected concentration of this preset particle size level is less than the collected concentration value. The product of the concentration value of the current time corresponding to the minimum preset particle size level and the first concentration adjustment coefficient is calculated to obtain the corrected concentration; in the embodiment of the present application, the minimum preset particle size level is the first particle size range, and the corrected concentration of this preset particle size level is greater than the collected concentration value. If the humidity value of the current time is lower than the preset standard humidity range, the aerosol concentration of the maximum preset particle size level will decrease, and the concentration value needs to be increased during correction; the aerosol concentration of the minimum preset particle size level will increase, and the concentration value needs to be reduced during correction. Therefore, the product of the concentration value of the current time corresponding to the maximum preset particle size level and the first concentration adjustment coefficient is calculated to obtain the corrected concentration; the product of the concentration value of the current time corresponding to the minimum preset particle size level and the second concentration adjustment coefficient is calculated to obtain the corrected concentration. The corrected concentration of the current time is more accurate than the collected concentration value, which weakens the influence of environmental humidity on the aerosol concentration of the minimum preset particle size level and the maximum preset particle size level, and further makes the subsequent analysis of the aerosol feature more accurate.

[0043] To sum up, the embodiment of the present application provides a human aerosol online monitoring system based on machine learning; a historical concentration reference is obtained according to a non-humidity abnormal moment and a concentration time sequence; a concentration abnormality degree is obtained according to the historical concentration reference and a concentration value of a current moment, a preset particle size level range; whether correction is needed is judged according to the concentration abnormality degree and the humidity abnormal moment, if correction is needed, for any concentration time sequence corresponding to a minimum preset particle size level and a maximum preset particle size level: a humidity influence degree is obtained according to a correlation feature of a humidity of a historical nearest preset number of humidity abnormal moments of a current moment and a concentration value of the same moment, and an abnormal duration feature of the historical nearest preset number of humidity abnormal moments. The present application corrects the concentration value of the current moment according to the humidity influence degree and the humidity abnormal feature, obtains a corrected concentration value, and improves the accuracy of the aerosol concentration acquisition.

[0044] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0045] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the difference from other embodiments.

Claims

1. A human-derived aerosol online monitoring system based on machine learning, characterized in that, The system includes the following modules: The data acquisition module is used to acquire the environmental humidity time series and the concentration time series of all preset particle size classes of human-derived aerosols. The concentration analysis module is used to obtain abnormal and non-abnormal humidity times based on the environmental humidity time series; to obtain historical concentration benchmarks for a preset particle size class based on the non-abnormal humidity times and the concentration time series; and to obtain the concentration anomaly degree based on the difference characteristics between the historical concentration benchmarks and the concentration values ​​at the current time, and the range of the preset particle size class. The humidity analysis module is used to determine whether the concentration value at the current moment needs to be corrected based on the concentration anomaly degree and the humidity anomaly time. If correction is required, for any concentration time series corresponding to the minimum preset particle size level and the maximum preset particle size level: the humidity influence degree of the arbitrary concentration time series is obtained based on the correlation characteristics of the humidity at the current moment and the concentration values ​​at the same moment in the arbitrary concentration time series, and the abnormal persistence characteristics of the recent preset number of humidity anomaly times. The concentration correction module is used to correct the concentration value at the current moment based on the humidity influence and humidity anomaly characteristics at the current moment, so as to obtain the corrected concentration value of human aerosol at the latest moment in the arbitrary concentration time series. The step of obtaining the concentration anomaly based on the difference characteristics between the historical concentration benchmark and the current concentration value, and the range of the preset particle size class, includes: Calculate the reciprocal of the difference between the maximum and minimum values ​​of any preset particle size level to obtain the particle size range weight; calculate the absolute value of the difference between the concentration value of the arbitrary preset particle size level at the current moment and the historical concentration benchmark to obtain the concentration difference value; calculate the sum of the products of the concentration difference values ​​corresponding to all preset particle size levels and the particle size range weights and normalize them to obtain the concentration anomaly degree at the current moment. The step of obtaining the humidity influence of the arbitrary concentration time series based on the correlation characteristics of the humidity at the current moment and the concentration values ​​at the same moment in the arbitrary concentration time series, and the abnormal persistence characteristics of the most recent preset number of humidity anomaly moments, includes: Calculate the absolute value of the Pearson correlation coefficient between the humidity of the most recent preset number of humidity anomalies and the concentration values ​​at the same time in the arbitrary concentration time series to obtain the correlation degree value; for any humidity anomaly among the most recent preset number of humidity anomalies, calculate the number of other humidity anomalies connected to the arbitrary humidity anomaly to obtain the persistence characteristic value of the arbitrary humidity anomaly; calculate the sum of squares of the persistence characteristic values ​​of the most recent preset number of humidity anomalies and normalize them to obtain the humidity anomaly coefficient; calculate the product of the correlation degree value and the humidity anomaly coefficient to obtain the humidity influence degree. The step of correcting the concentration value at the current moment based on the humidity influence and humidity anomaly characteristics at the current moment to obtain the corrected concentration value of human-generated aerosols at the latest moment in the arbitrary concentration time series includes: Calculate the absolute value of the difference between the current humidity value and the median of the preset standard humidity range, and normalize it to obtain the degree of humidity difference; calculate the product of the degree of humidity difference, the degree of humidity influence, and a preset constant to obtain the concentration adjustment benchmark; calculate the sum of constant 1 and the concentration adjustment benchmark to obtain the first concentration adjustment coefficient; calculate the difference between constant 1 and the concentration adjustment benchmark to obtain the second concentration adjustment coefficient. If the current humidity value exceeds the preset standard humidity range, calculate the product of the current concentration value corresponding to the maximum preset particle size level and the second concentration adjustment coefficient to obtain the corrected concentration; calculate the product of the current concentration value corresponding to the minimum preset particle size level and the first concentration adjustment coefficient to obtain the corrected concentration. If the current humidity value is lower than the preset standard humidity range, calculate the product of the current concentration value corresponding to the maximum preset particle size level and the first concentration adjustment coefficient to obtain the corrected concentration; calculate the product of the current concentration value corresponding to the minimum preset particle size level and the second concentration adjustment coefficient to obtain the corrected concentration.

2. The online monitoring system for human-generated aerosols based on machine learning according to claim 1, characterized in that, The step of obtaining abnormal humidity times and non-abnormal humidity times based on the environmental humidity time series includes: The time when the humidity in the environmental humidity time series is within the preset standard humidity range is defined as the non-humidity abnormal time, and the time when the humidity in the environmental humidity time series is outside the preset standard humidity range is defined as the humidity abnormal time.

3. The online monitoring system for human-generated aerosols based on machine learning according to claim 1, characterized in that, The step of obtaining the historical concentration benchmark of the preset particle size class based on the non-humidity anomaly time and the concentration time sequence includes: Calculate the average concentration value of all non-humidity abnormal times in the concentration time series of the preset particle size class to obtain the historical concentration benchmark of the preset particle size class.

4. The online monitoring system for human-generated aerosols based on machine learning according to claim 1, characterized in that, The step of determining whether the concentration value at the current moment needs to be corrected based on the concentration anomaly and the humidity anomaly includes: If the current moment is a time of abnormal humidity and the degree of concentration abnormality exceeds a preset abnormality threshold, the concentration value at the current moment needs to be corrected.

Images