A laboratory safety management method and system based on Internet of Things

Abstract

The present application provides a laboratory safety management method and system based on the Internet of Things, by determining the ventilation characteristics of the target laboratory, extracting the early warning domain based on the ventilation characteristics and the humidity monitoring data of the laboratory; collecting the current humidity information of each area of ​​the laboratory, identifying the suspicious early warning area of ​​the target laboratory according to the early warning domain and the current humidity information, determining the humidity fluctuation, and determining the first confidence early warning value based on the humidity fluctuation and the humidity distribution gradient; extracting the humidity difference and the humidity variation index from the humidity monitoring data, and determining the trend compensation amount according to the concentration trend of the humidity difference and the humidity variation index; obtaining the second confidence early warning value through the trend compensation amount and the first confidence early warning value, and sending an early warning signal to the laboratory safety management center when the second confidence early warning value is greater than the preset early warning value. The above scheme can monitor the humidity of the laboratory in real time in multiple dimensions, and timely discover potential management risks, and improve the intelligent level of laboratory safety management.

Description

Technical Field

[0001] The present application relates to the technical field of laboratory safety management, and more specifically, to a laboratory safety management method and system based on the Internet of Things. Background Art

[0002] The concept of laboratory safety management was first proposed in the 1960s. In the late 1970s, the first generation of laboratory information management systems appeared internationally. At that time, the system had single functions, high costs, and was difficult to popularize and apply. With the development of information technology and the Internet of Things, the limitations of this management method have become increasingly obvious. Since the mid-to-late 1990s, laboratory safety management methods based on the Internet of Things can collect various types of environmental data in real time. Through big data analysis and artificial intelligence technology, these data can be quickly processed to identify potential management risks and issue early warnings. Laboratory safety management not only improves the safety level of experiments, but also makes management more efficient and accurate, and can proactively respond to safety challenges in a constantly changing environment.

[0003] Existing laboratory safety management widely combines Internet of Things technology to improve monitoring and management capabilities. Internet of Things sensors deployed in the laboratory, such as temperature and humidity sensors, can collect environmental data in real time. These data are transmitted to the central system via wireless networks for real-time monitoring and management. Then, combined with big data and artificial intelligence technologies, the system can perform pattern recognition on the data, evaluate potential management risks and generate early warning information; however, the experimental environment of different laboratories is complex. When monitoring the environmental humidity of the laboratory, it is difficult for the management system to quickly adapt and respond to these changes, resulting in potential management risks that are difficult to be discovered in time, thereby reducing the level of intelligence in laboratory management. Therefore, how to monitor laboratory humidity in real time in multiple dimensions, so as to timely discover potential management risks and improve the level of intelligence in laboratory safety management has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a laboratory safety management method and system based on the Internet of Things, which can monitor the laboratory humidity in real time in multiple dimensions, so as to timely discover potential management risks and improve the intelligence level of laboratory safety management.

[0005] In a first aspect, the present application provides a laboratory safety management method based on the Internet of Things, comprising the following steps:

[0006] Monitor the humidity of the target laboratory and automatically collect humidity monitoring data of the target laboratory;

[0007] Determine the ventilation characteristics of the target laboratory at the current moment, and extract the warning domain of the laboratory humidity warning based on the ventilation characteristics and the humidity monitoring data;

[0008] Collect current humidity information of each experimental partition of the target laboratory, identify multiple suspicious warning areas according to the warning domain and the current humidity information of each experimental partition, determine the humidity fluctuation of each suspicious warning area, and determine the first confidence warning value of the target laboratory based on all humidity fluctuations and the humidity distribution gradient of the target laboratory;

[0009] Extracting the humidity difference and humidity variation index between different humidity at various temperatures in the target laboratory from the humidity monitoring data, and determining the trend compensation amount when performing monitoring error trend compensation on humidity under the influence of temperature according to the central tendency of all humidity differences and the humidity variation index;

[0010] The first confidence warning value is trend compensated by the trend compensation amount to obtain a second confidence warning value of the target laboratory. When the second confidence warning value is greater than a preset warning value, a humidity warning signal is sent to the laboratory safety management center through the Internet of Things platform.

[0011] In some embodiments, determining the ventilation characteristics of the target laboratory at the current moment specifically includes:

[0012] Obtaining a geometric feature set of a target laboratory;

[0013] The ventilation characteristics of the target laboratory at the current moment are determined based on the wind speed at the current moment and the geometric feature set.

[0014] In some embodiments, determining the ventilation characteristics of the target laboratory at the current moment based on the wind speed at the current moment and the geometric feature set specifically includes:

[0015] Extracting the spatial volume and ventilation opening cross-sectional area of ​​the target laboratory from the geometric feature set;

[0016] Determine the air supply characteristic quantity of the target laboratory by the wind speed and the cross-sectional area of ​​the ventilation opening;

[0017] The ventilation characteristics of the target laboratory at the current moment are determined based on the air supply characteristic quantity and the space volume.

[0018] In some embodiments, the warning domain of extracting the laboratory humidity warning based on the ventilation characteristics combined with the humidity monitoring data specifically includes:

[0019] Extracting the false warning lower limit and false warning upper limit of the laboratory humidity warning according to the humidity monitoring data;

[0020] The warning domain of the laboratory humidity warning is determined based on the ventilation characteristics, the false warning lower limit and the false warning upper limit.

[0021] In some embodiments, identifying multiple suspicious warning areas according to the warning domain and the current humidity information of each experimental partition specifically includes:

[0022] Determine the regional characteristic humidity of each experimental partition based on the current humidity information of each experimental partition;

[0023] Obtain ventilation characteristics of the target laboratory;

[0024] Determine the humidity coefficient of each experimental zone based on the ventilation characteristics combined with the regional characteristic humidity of each experimental zone;

[0025] A plurality of suspicious warning areas of the target laboratory are determined according to the warning domain and the humidity coefficient of each experimental partition.

[0026] In some embodiments, determining the first confidence warning value of the target laboratory based on all humidity fluctuations and the humidity distribution gradient of the target laboratory specifically includes:

[0027] Determine the regional humidity gradient between every two suspicious warning areas;

[0028] Determine the humidity distribution gradient of the target laboratory based on all regional humidity gradients;

[0029] The first confidence warning value of the target laboratory is determined by all humidity fluctuations and the humidity distribution gradient of the target laboratory.

[0030] In some embodiments, determining the trend compensation amount for monitoring error trend compensation of humidity under the influence of temperature according to the concentration trend of all humidity differences and the humidity variation index specifically includes:

[0031] Determine the central tendency of all moisture differences;

[0032] The trend compensation amount when trend compensation is performed on humidity under the influence of temperature is determined according to the central tendency and the humidity variation index.

[0033] In a second aspect, the present application provides a laboratory safety management system based on the Internet of Things, comprising:

[0034] A collection module, used to monitor the humidity of the target laboratory and automatically collect humidity monitoring data of the target laboratory;

[0035] A processing module, used to determine the ventilation characteristics of the target laboratory at the current moment, and extract the warning domain of the laboratory humidity warning based on the ventilation characteristics and the humidity monitoring data;

[0036] The processing module is further used to collect current humidity information of each experimental partition of the target laboratory, identify multiple suspicious warning areas according to the warning domain and the current humidity information of each experimental partition, determine the humidity fluctuation of each suspicious warning area, and determine the first confidence warning value of the target laboratory based on all humidity fluctuations and the humidity distribution gradient of the target laboratory;

[0037] The processing module is further used to extract the humidity difference and humidity variation index between different humidity at various temperatures in the target laboratory from the humidity monitoring data, and determine the trend compensation amount when performing monitoring error trend compensation on humidity under the influence of temperature according to the central tendency of all humidity differences and the humidity variation index;

[0038] The execution module is used to perform trend compensation on the first confidence warning value through the trend compensation amount to obtain a second confidence warning value of the target laboratory. When the second confidence warning value is greater than a preset warning value, a humidity warning signal is sent to the laboratory safety management center through the Internet of Things platform.

[0039] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned laboratory safety management method based on the Internet of Things.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned laboratory safety management method based on the Internet of Things.

[0041] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0042] In the laboratory safety management method and system based on the Internet of Things provided in the present application, first, the humidity of the target laboratory is monitored, and the humidity monitoring data of the target laboratory is automatically collected; further, the ventilation characteristics of the target laboratory at the current moment are determined, and the warning domain of the laboratory humidity warning is extracted based on the ventilation characteristics and the humidity monitoring data; then, the current humidity information of each experimental partition of the target laboratory is collected, and multiple suspicious warning areas are identified according to the warning domain and the current humidity information of each experimental partition, and the humidity fluctuation degree of each suspicious warning area is determined, and the first confidence warning value of the target laboratory is determined based on all humidity fluctuation degrees and the humidity distribution gradient of the target laboratory; secondly, the humidity difference and humidity variation index between different humidities of the target laboratory at various temperatures are extracted from the humidity monitoring data, and the trend compensation amount when the humidity is monitored under the influence of temperature. Error trend compensation is determined according to the concentration trend of all humidity differences and the humidity variation index; finally, the first confidence warning value is trend compensated by the trend compensation amount to obtain a second confidence warning value of the target laboratory, and when the second confidence warning value is greater than the preset warning value, a humidity warning signal is sent to the laboratory safety management center through the Internet of Things platform.

[0043] It can be seen that the present application can monitor the laboratory humidity in real time in multiple dimensions, so as to timely discover potential management risks and improve the intelligent level of laboratory safety management; firstly, the automatic collection of humidity monitoring data of the target laboratory provides data support for the safety management of the target laboratory; further, the early warning domain is determined in combination with the ventilation characteristics, so as to realize dynamic control of the target laboratory environment to ensure that the environmental humidity is maintained at an appropriate level, thereby ensuring the safety and reliability of the experiment; then, the suspicious early warning area is identified according to the early warning domain and the current humidity information to identify the experimental areas that may be at risk, so as to further analyze these areas; secondly, the target laboratory is determined based on all humidity fluctuations and the humidity distribution gradient of the target laboratory. The first confidence warning value of the standard laboratory can provide a reference standard for the laboratory's humidity monitoring, which is conducive to the timely identification and handling of humidity problems; in addition, the second confidence warning value is determined by monitoring the error trend compensation to eliminate the systematic deviation of laboratory safety management or the influence of external factors on the change of laboratory humidity, thereby improving the reliability of laboratory safety management; finally, the Internet of Things platform sends a warning signal to the safety management center based on the second confidence warning value and the preset warning value to improve the intelligent level of laboratory safety management; in summary, the technical solution provided by the present application can monitor the laboratory humidity in real time in multiple dimensions, so as to timely discover potential management risks and improve the intelligent level of laboratory safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1is an exemplary flow chart of a laboratory safety management method based on the Internet of Things according to some embodiments of the present application;

[0045] Figure 2 is an exemplary flow chart for determining the ventilation characteristics of a target laboratory at the current moment according to some embodiments of the present application;

[0046] Figure 3 is an exemplary flow chart for determining multiple suspicious warning areas according to some embodiments of the present application;

[0047] Figure 4 It is a schematic diagram of exemplary hardware and / or software of a laboratory safety management system based on the Internet of Things according to some embodiments of the present application;

[0048] Figure 5 It is a structural diagram of a computer device for implementing a laboratory safety management method based on the Internet of Things as shown in some embodiments of the present application. DETAILED DESCRIPTION

[0049] The core of this application is to monitor the humidity of the target laboratory and automatically collect the humidity monitoring data of the target laboratory; determine the ventilation characteristics of the target laboratory at the current moment, and extract the warning domain of the laboratory humidity warning based on the ventilation characteristics and the humidity monitoring data; collect the current humidity information of each experimental partition of the target laboratory, identify multiple suspicious warning areas according to the warning domain and the current humidity information of each experimental partition, determine the humidity fluctuation of each suspicious warning area, and determine the first confidence warning value of the target laboratory based on all humidity fluctuations and the humidity distribution gradient of the target laboratory; extract the humidity difference and humidity variation index between different humidity at each temperature of the target laboratory from the humidity monitoring data, and determine the trend compensation amount when the humidity is monitored under the influence of temperature according to the concentration trend of all humidity differences and the humidity variation index; the first confidence warning value is trend compensated by the trend compensation amount to obtain the second confidence warning value of the target laboratory, and when the second confidence warning value is greater than the preset warning value, the humidity warning signal is sent to the laboratory safety management center through the Internet of Things platform. Based on the second confidence warning value, the above scheme can monitor the humidity of the laboratory in real time in multiple dimensions, so as to timely discover potential management risks and improve the intelligent level of laboratory safety management.

[0050] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a laboratory safety management method based on the Internet of Things according to some embodiments of the present application. The laboratory safety management method 100 based on the Internet of Things mainly includes the following steps:

[0051] In step 101, the humidity of the target laboratory is monitored, and humidity monitoring data of the target laboratory is automatically collected.

[0052] In the specific implementation, the humidity of the target laboratory is monitored, and the humidity monitoring data of the target laboratory is automatically collected, that is: the humidity monitoring data of the target laboratory is automatically collected through a capacitive humidity sensor, and the collected humidity monitoring data is uploaded to the environmental monitoring database, thereby realizing the humidity monitoring of the experimental environment of the target laboratory. In addition, in other embodiments, other humidity sensors can also be used to automatically collect the humidity monitoring data of the target laboratory, such as impedance humidity sensors, optical humidity sensors, etc., which are not limited here.

[0053] It should be noted that the environmental monitoring database in this embodiment refers to a database specifically used to record, store and manage the environmental parameters of the target laboratory. It usually integrates real-time data from various environmental monitoring equipment and provides data support for the safety management of the target laboratory. It will not be repeated here.

[0054] It should also be noted that the humidity monitoring data in the present application represents information about the air humidity collected by the humidity sensor in the target laboratory. The humidity monitoring data includes multiple humidity values ​​at different experimental times and different experimental temperatures. By collecting humidity monitoring data, it can be ensured that the humidity of the target laboratory remains within the set range, which is conducive to the management system to promptly detect and deal with abnormal humidity conditions, thereby avoiding the impact of environmental humidity on the experimental results.

[0055] In step 102, the ventilation characteristics of the target laboratory at the current moment are determined, and the warning domain of the laboratory humidity warning is extracted based on the ventilation characteristics and the humidity monitoring data.

[0056] In some embodiments, the ventilation characteristics of the target laboratory at the current moment may be determined in the following manner, namely:

[0057] Obtaining a geometric feature set of a target laboratory;

[0058] The ventilation characteristics of the target laboratory at the current moment are determined based on the wind speed at the current moment and the geometric feature set.

[0059] In specific implementation, the geometric feature set of the target laboratory can be obtained through the environmental monitoring database. The geometric feature set represents the spatial geometric shape, size and other physical characteristics of the target laboratory. The geometric feature set includes the spatial volume and vent cross-sectional area of ​​the target laboratory. In other embodiments, the geometric feature set may also include other physical characteristics, which are not limited here. By obtaining the geometric feature set, the geometric characteristics of the target laboratory can be more comprehensively understood and analyzed, thereby better managing the safety of the target laboratory.

[0060] In some embodiments, reference Figure 2 As shown, this figure is an exemplary flow chart of determining the ventilation characteristics of the target laboratory at the current moment according to some embodiments of the present application. In this embodiment, the ventilation characteristics of the target laboratory at the current moment based on the wind speed at the current moment and the geometric feature set can be determined by the following steps:

[0061] First, in step 1021, the spatial volume and ventilation opening cross-sectional area of ​​the target laboratory are extracted from the geometric feature set;

[0062] Then, in step 1022, the air supply characteristic quantity of the target laboratory is determined by the wind speed and the cross-sectional area of ​​the ventilation opening;

[0063] Finally, in step 1023, the ventilation characteristics of the target laboratory at the current moment are determined based on the air supply characteristic quantity and the space volume.

[0064] In specific implementation, the air supply characteristic quantity of the target laboratory is determined by the wind speed and the cross-sectional area of ​​the vent, that is, the product of the wind speed and the cross-sectional area of ​​the vent is used as the air supply characteristic quantity of the target laboratory. In addition, in other embodiments, the air supply characteristic quantity can also be calculated by other methods, which are not limited here.

[0065] It should be noted that, in this embodiment, the wind speed represents the speed at which the external air flows through the ventilation opening of the target laboratory, and the air supply characteristic quantity represents the amount of air supplied from the ventilation opening into the target laboratory per unit time.

[0066] In specific implementation, the ventilation characteristics of the target laboratory at the current moment are determined based on the air supply characteristic quantity and the space volume, that is, the ratio of the air supply characteristic quantity to the space volume is used as the ventilation characteristics of the experimental environment of the target laboratory at the current moment. In addition, in other embodiments, the ventilation characteristics can also be calculated by other methods, which are not limited here.

[0067] It should be noted that the ventilation characteristics in the present application represent the flow pattern parameters of the air in the target laboratory, that is, the frequency with which the air in the target laboratory is completely replaced within a period of time. By determining the ventilation characteristics, the ventilation efficiency of the target laboratory can be reflected, thereby increasing the reliability of environmental monitoring of the target laboratory.

[0068] In some embodiments, the warning domain of the laboratory humidity warning can be extracted based on the ventilation characteristics combined with the humidity monitoring data in the following manner, namely:

[0069] Extracting the false warning lower limit and false warning upper limit of the laboratory humidity warning according to the humidity monitoring data;

[0070] The warning domain of the laboratory humidity warning is determined based on the ventilation characteristics, the false warning lower limit and the false warning upper limit.

[0071] In the specific implementation, the pseudo-warning lower limit and pseudo-warning upper limit of the laboratory humidity warning are extracted according to the humidity monitoring data, that is: the humidity expected value and humidity standard deviation of the humidity monitoring data are calculated by the numpy component in Python, and the difference between the humidity expected value and the humidity standard deviation is used as the pseudo-warning lower limit of the laboratory humidity warning, and the sum of the humidity expected value and the humidity standard deviation is used as the pseudo-warning upper limit of the laboratory humidity warning. In addition, in other embodiments, other methods can also be used to calculate the pseudo-warning lower limit and the pseudo-warning upper limit, which are not limited here.

[0072] In specific implementation, the warning domain of the laboratory humidity warning is determined based on the ventilation characteristics, the pseudo-warning lower limit and the pseudo-warning upper limit, that is: the product of the ventilation characteristics and the pseudo-warning lower limit is used as the warning lower limit of the laboratory humidity warning, and the product of the ventilation characteristics and the pseudo-warning upper limit is used as the warning upper limit of the laboratory humidity warning, thereby obtaining the warning domain of the laboratory humidity warning.

[0073] It should be noted that the warning domain in this application represents a set of thresholds established based on the humidity monitoring and ventilation conditions of the target laboratory. By monitoring the warning domain, dynamic control of the target laboratory environment can be achieved, thereby ensuring that the ambient humidity remains within an appropriate range, thereby ensuring the safety of experimental operations and the reliability of experimental data.

[0074] It should also be noted that, in this embodiment, the false warning lower limit and the false warning upper limit are only used as intermediate variables in the analysis process and have no practical significance, and will not be elaborated here.

[0075] In step 103, the current humidity information of each experimental partition of the target laboratory is collected, and a plurality of suspicious warning areas are identified based on the warning domain and the current humidity information of each experimental partition, and the humidity fluctuation of each suspicious warning area is determined. Based on all humidity fluctuations and the humidity distribution gradient of the target laboratory, the first confidence warning value of the target laboratory is determined.

[0076] In some embodiments, the current humidity information of each experimental partition of the target laboratory may be collected in the following manner, namely:

[0077] Divide the physical space of the target laboratory to obtain multiple experimental partitions;

[0078] Collect the current humidity information of each experimental partition.

[0079] In specific implementation, the physical space of the target laboratory is divided to obtain multiple experimental partitions, that is: the experimental area plan of the target laboratory is obtained, and the target laboratory is divided into multiple experimental partitions according to the functional annotation information of the experimental area plan. In addition, in other embodiments, other methods of division can also be used, which are not limited here.

[0080] It should be noted that, in this embodiment, the experimental area plan view represents the plan layout of the experimental area of ​​the target laboratory, and the function labeling information represents the experimental functions of the main areas marked on the experimental area plan view.

[0081] It should also be noted that the experimental partition in this embodiment refers to an area in the working environment of the target laboratory that is specifically used for experimental operations, which is usually equipped with a laboratory bench, equipment and necessary safety monitoring facilities. By dividing the experimental partitions, it is beneficial to manage the operation of the target laboratory, thereby improving safety and ensuring that environmental conditions meet the expected experimental requirements.

[0082] In specific implementation, the current humidity information of each experimental partition is collected through a capacitive humidity sensor located in each experimental partition. The actual real-time humidity status of the experimental partition during the current experiment can be known through the current humidity information. Each experimental partition has one or more humidity sensors. The current humidity information includes one or more humidity values ​​collected by the humidity sensor of the experimental partition. By collecting the current humidity information, the humidity distribution status of the target laboratory can be monitored in real time, so as to maintain the humidity status required by the experiment within a specific range. In addition, in other embodiments, other humidity sensors can also be used to collect the current humidity information, which is not limited here.

[0083] In some embodiments, reference Figure 3 As shown, this figure is an exemplary flow chart for determining multiple suspicious warning areas according to some embodiments of the present application. In this embodiment, multiple suspicious warning areas can be identified according to the warning domain and the current humidity information of each experimental partition by using the following steps:

[0084] First, in step 1031, the regional characteristic humidity of each experimental partition is determined based on the current humidity information of each experimental partition;

[0085] Then, in step 1032, the ventilation characteristics of the target laboratory are obtained;

[0086] Next, in step 1033, the humidity coefficient of each experimental partition is determined based on the ventilation characteristics combined with the regional characteristic humidity of each experimental partition;

[0087] Finally, in step 1034, multiple suspicious warning areas of the target laboratory are determined based on the warning domain and the humidity coefficient of each experimental partition.

[0088] In the specific implementation, the regional characteristic humidity of each experimental partition is determined based on the current humidity information of each experimental partition, that is: an experimental partition is selected, and the average of all humidity values ​​in the current humidity information corresponding to the experimental partition is used as the regional characteristic humidity of the experimental partition, and then the regional characteristic humidity of each experimental partition is determined. In addition, in other embodiments, other calculation methods can also be used to calculate the regional characteristic humidity, which is not limited here.

[0089] It should be noted that, in this embodiment, the regional characteristic humidity represents the humidity level measured and recorded in a specific experimental partition. By determining the regional characteristic humidity, the reliability and safety of the safety management of the target laboratory can be increased.

[0090] In specific implementation, the humidity coefficient of each experimental zone is determined based on the ventilation characteristics combined with the regional characteristic humidity of each experimental zone, that is: the ventilation characteristics are multiplied by the regional characteristic humidity of each experimental zone, and each product result is used as the humidity coefficient of each experimental zone. In addition, in other embodiments, other calculation methods can also be used to calculate the humidity coefficient, which is not limited here.

[0091] It should be noted that the humidity coefficient in this embodiment represents a dimensionless number that describes the humidity level of the experimental partition. By determining the humidity coefficient, the humidity environment of the target laboratory can be monitored, thereby better performing laboratory safety management.

[0092] In specific implementation, multiple suspicious warning areas of the target laboratory are determined based on the warning domain and the humidity coefficients of each experimental partition, that is: a humidity coefficient is selected, and the humidity coefficient is compared with the warning domain. If the humidity coefficient is within the warning domain, the experimental partition corresponding to the humidity coefficient is taken as a suspicious warning area, and the remaining humidity coefficients are continued to be compared with the warning domain, thereby obtaining multiple suspicious warning areas of the target laboratory.

[0093] It should be noted that the suspicious warning area in this application refers to the area where there may be risks that are identified based on the humidity conditions during the environmental monitoring of the target laboratory. These areas often require further analysis. By determining the suspicious warning area, data support can be provided for subsequent safety analysis, thereby ensuring the management safety of the target laboratory.

[0094] In specific implementation, the humidity fluctuation degree of each suspicious warning area can be determined in the following manner, namely: select a suspicious warning area, obtain the regional characteristic humidity of the suspicious warning area, and use the ratio of the standard deviation of all humidity values ​​in the suspicious warning area to the regional characteristic humidity of the suspicious warning area as the humidity fluctuation degree of the suspicious warning area, thereby obtaining the humidity fluctuation degree of each suspicious warning area. In addition, in other embodiments, other methods can be used to calculate the humidity fluctuation degree, which is not limited here.

[0095] It should be noted that the humidity fluctuation in this application represents the stability of the humidity level in the suspicious warning area. The greater the humidity fluctuation, the worse the stability of the corresponding humidity level in the suspicious warning area. The smaller the humidity fluctuation, the better the stability of the corresponding humidity level in the suspicious warning area. Determining the humidity fluctuation helps to evaluate the stability of the experimental environment, thereby further identifying potential experimental risks.

[0096] In some embodiments, the first confidence warning value of the target laboratory may be determined based on all humidity fluctuations and the humidity distribution gradient of the target laboratory in the following manner, namely:

[0097] Determine the regional humidity gradient between every two suspicious warning areas;

[0098] Determine the humidity distribution gradient of the target laboratory based on all regional humidity gradients;

[0099] The first confidence warning value of the target laboratory is determined by all humidity fluctuations and the humidity distribution gradient of the target laboratory.

[0100] In some embodiments, the regional humidity gradient between every two suspicious warning areas may be determined in the following manner, namely:

[0101] Select two suspicious warning areas as the first warning area and the second warning area respectively;

[0102] Acquire the regional characteristic humidity of the first warning area as the first humidity, and acquire the regional characteristic humidity of the second warning area as the second humidity;

[0103] Determine the regional distance between the first warning area and the second warning area;

[0104] determining a regional humidity gradient between a first warning area and a second warning area based on the regional distance, the first humidity, and the second humidity;

[0105] Continue to determine the regional humidity gradient between every two suspicious warning areas in the remaining suspicious warning areas.

[0106] In specific implementation, the regional distance between the first warning area and the second warning area can be determined by using the Euclidean distance calculation method. In addition, in other embodiments, other calculation methods can be used to obtain the regional distance, which is not limited here.

[0107] In addition, the regional humidity gradient between the first warning area and the second warning area is determined based on the regional distance, the first humidity and the second humidity, that is, the difference between the first humidity and the second humidity is calculated, and the ratio of the difference result to the regional distance is used as the regional humidity gradient between the first warning area and the second warning area. In addition, in other embodiments, other calculation methods can also be used to obtain the regional humidity gradient, which is not limited here.

[0108] It should be noted that, in this embodiment, the regional humidity gradient represents the degree of change of the humidity value between two suspicious warning areas with the target laboratory space.

[0109] In specific implementation, the humidity distribution gradient of the target laboratory is determined based on all regional humidity gradients, that is: the total area of ​​every two suspicious warning areas is obtained from the environmental monitoring database, and the humidity gradient of each region is multiplied by the corresponding total area, and the ratio of the cumulative sum of all product results to the cumulative sum of all regional total areas is used as the humidity distribution gradient of the target laboratory. In addition, in other embodiments, other calculation methods can also be used to obtain the humidity distribution gradient, which is not limited here.

[0110] It should be noted that the humidity distribution gradient in the present application represents the overall trend of humidity changes in the target laboratory with spatial position. By determining the humidity distribution gradient, the intensity of humidity differences between different locations in the target laboratory can be reflected, which is more conducive to identifying humidity anomalies in the target laboratory, thereby improving the effectiveness and safety of laboratory safety management.

[0111] In some embodiments, the first confidence warning value of the target laboratory can be determined by all humidity fluctuations and the humidity distribution gradient of the target laboratory in the following manner, namely:

[0112] Perform early warning correlation analysis on all humidity fluctuations and the humidity distribution gradient of the target laboratory to obtain the confidence coefficient for early warning of environmental humidity;

[0113] The first confidence warning value of the target laboratory is determined by the feature set of all humidity fluctuations and the confidence coefficient.

[0114] In specific implementation, the Pearson correlation coefficient method can be used to perform warning correlation analysis on all humidity fluctuations and the humidity distribution gradient of the target laboratory to obtain a confidence coefficient for warning of environmental humidity. In addition, in other embodiments, other analysis methods can be used to obtain the confidence coefficient, for example, regression analysis method, etc., which is not limited here.

[0115] It should be noted that the confidence coefficient in this embodiment represents a numerical value used to represent the reliability of a variable value in statistical analysis. It should also be noted that the Pearson correlation coefficient method in this embodiment is an existing technology for statistical analysis, and the specific analysis process will not be repeated here.

[0116] In specific implementation, the first confidence warning value of the target laboratory is determined by the feature set of all humidity fluctuations and the confidence coefficient, that is: the feature set of all humidity fluctuations is determined by the numpy component of Python, the feature set includes the humidity fluctuation mean and the humidity fluctuation standard deviation of all humidity fluctuations, the humidity fluctuation mean and the humidity fluctuation standard deviation are extracted from the feature set, the confidence coefficient and the humidity fluctuation standard deviation are multiplied, and the sum of the product result and the humidity fluctuation mean is used as the first confidence warning value of the target laboratory.

[0117] It should be noted that the first confidence warning value in the present application represents a humidity threshold value used to determine whether the humidity environment of the target laboratory requires further intervention analysis at a reliable confidence level. By determining the first confidence warning value, a reference standard can be provided for laboratory humidity monitoring, which is conducive to timely identification and processing of humidity problems.

[0118] In step 104, the humidity difference and humidity variation index between different humidities at various temperatures in the target laboratory are extracted from the humidity monitoring data, and the trend compensation amount for humidity monitoring error trend compensation under the influence of temperature is determined based on the central tendency of all humidity differences and the humidity variation index.

[0119] In some embodiments, the humidity difference and humidity variation index between different humidities at different temperatures in the target laboratory can be extracted from the humidity monitoring data in the following manner, namely:

[0120] Performing isothermal analysis on the humidity monitoring data to obtain the humidity difference between different humidities at various temperatures in the target laboratory;

[0121] A humidity variation index of a target laboratory is extracted from the humidity monitoring data.

[0122] In specific implementation, the humidity monitoring data is subjected to isothermal analysis to obtain the humidity difference between different humidities at various temperatures in the target laboratory, that is, the different humidity values ​​at the same temperature in the humidity monitoring data are matched to form humidity pairs, and for each group of humidity pairs, the humidity difference is calculated to obtain the humidity difference between different humidities at various temperatures in the target laboratory. In addition, in other embodiments, other methods may be used to perform isothermal analysis on the humidity monitoring data to obtain the humidity difference, which is not limited here.

[0123] In specific implementation, the humidity variation index of the target laboratory is extracted from the humidity monitoring data, that is, principal component analysis (PCA) is performed on the humidity monitoring data to reduce the dimension, and the principal component of the humidity change in the target laboratory is obtained, and the mean of all elements in the principal component is used as the humidity variation index of the target laboratory. The PCA dimension reduction is a data processing technology for refining and summarizing a large amount of data. The principal component is the result of PCA dimension reduction. Each element in the principal component represents the degree of influence of different humidity information in the target laboratory on the overall humidity environment change. In addition, in other embodiments, other methods can be used to obtain the humidity variation index, which is not limited here.

[0124] It should be noted that the humidity variation index in this embodiment represents an indicator for measuring the degree of influence of all humidity information in the target laboratory on changes in the laboratory environment. Determining the humidity variation index can help evaluate the stability of humidity changes.

[0125] In some embodiments, the trend compensation amount for monitoring error trend compensation of humidity under the influence of temperature can be determined according to the concentration trend of all humidity differences and the humidity variation index in the following manner, namely:

[0126] Determine the central tendency of all moisture differences;

[0127] The trend compensation amount when performing monitoring error trend compensation on humidity under the influence of temperature is determined according to the central tendency and the humidity variation index.

[0128] In the specific implementation, the central tendency of all humidity differences is determined, that is, all humidity differences are averaged, and the calculated average value is used as the central tendency of all humidity differences. In addition, in other embodiments, other calculation methods can also be used to calculate the central tendency, which is not limited here.

[0129] It should be noted that the centralization trend in this application represents the centralized distribution of humidity in the target laboratory under the same temperature conditions. By determining the centralization trend, the concentration degree of ambient humidity under fluctuation can be reflected, which is beneficial to optimize the experimental environment and thus increase the reliability of laboratory management.

[0130] In specific implementation, the trend compensation amount when compensating for the error trend of humidity monitoring under the influence of temperature is determined according to the central tendency and the humidity variation index, that is, the weighted sum of the central tendency and the humidity variation index is used as the trend compensation amount when compensating for the error trend of humidity monitoring under the influence of temperature. The specific weight distribution can be set between 0 and 1 according to actual application requirements. For example, the weights of the central tendency and the humidity variation index in the present application can be set to 0.55 and 0.45, respectively, which are not limited here. In addition, in other embodiments, other calculation methods can be used to calculate the trend compensation amount, which are not limited here.

[0131] It should be noted that the trend compensation amount in the present application represents the adjustment value calculated through trend analysis of humidity monitoring data. By determining the trend compensation amount, the systematic deviation of the laboratory safety management system or the impact of external factors on laboratory humidity changes can be eliminated, thereby increasing the reliability and practicality of laboratory safety management.

[0132] It should also be noted that in laboratory environmental monitoring, when the temperature is unstable, the humidity will fluctuate with changes in temperature. This is because the saturated vapor pressure will change with changes in temperature, causing the humidity to change in different trends with changes in temperature, thereby causing monitoring errors. The process of correcting and eliminating these monitoring errors is called monitoring error trend compensation.

[0133] In step 105, the first confidence warning value is trend compensated by the trend compensation amount to obtain a second confidence warning value of the target laboratory. When the second confidence warning value is greater than the preset warning value, a humidity warning signal is sent to the laboratory safety management center through the Internet of Things platform.

[0134] In a specific implementation, the trend compensation amount is used to perform trend compensation on the first confidence warning value to obtain the second confidence warning value of the target laboratory, that is, the trend compensation amount and the first confidence warning value are added, and the addition result is used as the second confidence warning value of the target laboratory. In addition, in other embodiments, other calculation methods can also be used to perform trend compensation on the first confidence warning value, which is not limited here.

[0135] It should be noted that the second confidence warning value in the present application represents the humidity change judgment value obtained by adjusting the first confidence warning value through the introduction of a trend compensation mechanism. By determining the second confidence warning value, more accurate monitoring indicators can be provided for the environmental monitoring of the target laboratory, thereby enabling better laboratory safety management.

[0136] In specific implementation, when the second confidence warning value is greater than the preset warning value, a humidity warning signal is sent to the laboratory safety management center through the Internet of Things platform, that is: the preset warning value in the laboratory safety management system is obtained, and the second confidence warning value is compared with the preset warning value. When the second confidence warning value is greater than the preset warning value, it indicates that there is a potential abnormal or unstable risk in the humidity level in the experimental environment of the current target laboratory, such as poor ventilation, sensor equipment failure, experimental abnormality, etc. At this time, the Internet of Things platform will select an appropriate communication protocol and send a warning signal containing information such as warning type, specific warning value, warning time, warning laboratory, etc. to the laboratory safety management center. After receiving the warning signal, the laboratory safety management center will perform further emergency processing, such as triggering relevant emergency response measures, notifying the laboratory director, etc.

[0137] In addition, in another aspect of the present application, in some embodiments, the present application provides a laboratory safety management system based on the Internet of Things, referring to Figure 4 , which is a schematic diagram of exemplary hardware and / or software of a laboratory safety management system based on the Internet of Things according to some embodiments of the present application. The laboratory safety management system 200 based on the Internet of Things includes: a collection module 201, a processing module 202 and an execution module 203, which are described as follows:

[0138] The acquisition module 201 in this application is mainly used to monitor the humidity of the target laboratory and automatically collect the humidity monitoring data of the target laboratory;

[0139] Processing module 202, in this application, processing module 202 is mainly used to determine the ventilation characteristics of the target laboratory at the current moment, and extract the warning domain of the laboratory humidity warning based on the ventilation characteristics combined with the humidity monitoring data;

[0140] The processing module 202 is further used to collect current humidity information of each experimental partition of the target laboratory, identify multiple suspicious warning areas according to the warning domain and the current humidity information of each experimental partition, determine the humidity fluctuation of each suspicious warning area, and determine the first confidence warning value of the target laboratory based on all humidity fluctuations and the humidity distribution gradient of the target laboratory;

[0141] In addition, the processing module 202 is also used to extract the humidity difference and humidity variation index between different humidity at various temperatures in the target laboratory from the humidity monitoring data, and determine the trend compensation amount when performing monitoring error trend compensation on humidity under the influence of temperature according to the concentration trend of all humidity differences and the humidity variation index;

[0142] Execution module 203. In the present application, execution module 203 is mainly used to perform trend compensation on the first confidence warning value through the trend compensation amount to obtain a second confidence warning value of the target laboratory. When the second confidence warning value is greater than the preset warning value, a humidity warning signal is sent to the laboratory safety management center through the Internet of Things platform.

[0143] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned laboratory safety management method based on the Internet of Things.

[0144] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device using a laboratory safety management method based on the Internet of Things according to some embodiments of the present application. The laboratory safety management method based on the Internet of Things in the above embodiment can be Figure 5 The computer device 300 shown in the figure is implemented, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303 and at least one communication interface 304.

[0145] Processor 301 can be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC) or one or more for controlling the execution of the laboratory safety management method based on the Internet of Things in this application.

[0146] The communication bus 302 may be used to transmit information between the above-mentioned components.

[0147] The memory 303 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 303 may exist independently and be connected to the processor 301 via the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0148] Among them, the memory 303 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the program code stored in the memory 303. The program code may include one or more software modules. The determination of the laboratory safety management method based on the Internet of Things in the above embodiment can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0149] The communication interface 304 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0150] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0151] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0152] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned laboratory safety management method based on the Internet of Things.

[0153] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0154] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A laboratory safety management method based on the Internet of Things, characterized in that: The steps include: Monitor the humidity of the target laboratory and automatically collect humidity monitoring data of the target laboratory; Determine the ventilation characteristics of the target laboratory at the current moment, and extract the warning domain of the laboratory humidity warning based on the ventilation characteristics and the humidity monitoring data; Collect current humidity information of each experimental partition of the target laboratory, identify multiple suspicious warning areas according to the warning domain and the current humidity information of each experimental partition, determine the humidity fluctuation of each suspicious warning area, and determine the first confidence warning value of the target laboratory based on all humidity fluctuations and the humidity distribution gradient of the target laboratory; Extract the humidity difference and humidity variation index between different humidities at various temperatures in the target laboratory from the humidity monitoring data, wherein the humidity monitoring data is subjected to principal component analysis and dimensionality reduction to obtain the principal component of the humidity change in the target laboratory, and the mean of all elements in the principal component is used as the humidity variation index of the target laboratory, and the trend compensation amount when the humidity is monitored under the influence of temperature and error trend compensation is determined according to the concentration trend of all humidity differences and the humidity variation index; The first confidence warning value is trend compensated by the trend compensation amount to obtain a second confidence warning value of the target laboratory. When the second confidence warning value is greater than a preset warning value, a humidity warning signal is sent to the laboratory safety management center through the Internet of Things platform.

2. The method according to claim 1, characterized in that Determine the ventilation characteristics of the target laboratory at the current moment, including: Obtaining a geometric feature set of a target laboratory; The ventilation characteristics of the target laboratory at the current moment are determined based on the wind speed at the current moment and the geometric feature set.

3. The method according to claim 2, characterized in that Determining the ventilation characteristics of the target laboratory at the current moment based on the wind speed at the current moment and the geometric feature set specifically includes: Extracting the spatial volume and ventilation opening cross-sectional area of ​​the target laboratory from the geometric feature set; Determine the air supply characteristic quantity of the target laboratory by the wind speed and the cross-sectional area of ​​the ventilation opening; The ventilation characteristics of the target laboratory at the current moment are determined based on the air supply characteristic quantity and the space volume.

4. The method according to claim 1, characterized in that The early warning domain for extracting laboratory humidity early warning based on the ventilation characteristics combined with the humidity monitoring data specifically includes: Extracting the false warning lower limit and false warning upper limit of the laboratory humidity warning according to the humidity monitoring data; The warning domain of the laboratory humidity warning is determined based on the ventilation characteristics, the false warning lower limit and the false warning upper limit.

5. The method according to claim 1, characterized in that According to the warning domain and the current humidity information of each experimental partition, multiple suspicious warning areas are identified, including: Determine the regional characteristic humidity of each experimental partition based on the current humidity information of each experimental partition; Obtain ventilation characteristics of the target laboratory; Determine the humidity coefficient of each experimental zone based on the ventilation characteristics combined with the regional characteristic humidity of each experimental zone; A plurality of suspicious warning areas of the target laboratory are determined according to the warning domain and the humidity coefficient of each experimental partition.

6. The method according to claim 1, characterized in that Determining the first confidence warning value of the target laboratory based on all humidity fluctuations and the humidity distribution gradient of the target laboratory specifically includes: Determine the regional humidity gradient between every two suspicious warning areas; Determine the humidity distribution gradient of the target laboratory based on all regional humidity gradients; The first confidence warning value of the target laboratory is determined by all humidity fluctuations and the humidity distribution gradient of the target laboratory.

7. The method according to claim 1, characterized in that The trend compensation amount for humidity monitoring error trend compensation under the influence of temperature is determined according to the concentration trend of all humidity differences and the humidity variation index, specifically including: Determine the central tendency of all moisture differences; The trend compensation amount when trend compensation is performed on humidity under the influence of temperature is determined according to the central tendency and the humidity variation index.

8. A laboratory safety management system based on the Internet of Things, which adopts the method described in any one of claims 1 to 7 to perform laboratory safety management, characterized in that: The IoT-based laboratory safety management system includes: A collection module, used to monitor the humidity of the target laboratory and automatically collect humidity monitoring data of the target laboratory; A processing module, used to determine the ventilation characteristics of the target laboratory at the current moment, and extract the warning domain of the laboratory humidity warning based on the ventilation characteristics and the humidity monitoring data; The processing module is further used to collect current humidity information of each experimental partition of the target laboratory, identify multiple suspicious warning areas according to the warning domain and the current humidity information of each experimental partition, determine the humidity fluctuation of each suspicious warning area, and determine the first confidence warning value of the target laboratory based on all humidity fluctuations and the humidity distribution gradient of the target laboratory; The processing module is further used to extract the humidity difference and humidity variation index between different humidity at various temperatures in the target laboratory from the humidity monitoring data, and determine the trend compensation amount when performing monitoring error trend compensation on humidity under the influence of temperature according to the central tendency of all humidity differences and the humidity variation index; The execution module is used to perform trend compensation on the first confidence warning value through the trend compensation amount to obtain a second confidence warning value of the target laboratory. When the second confidence warning value is greater than a preset warning value, a humidity warning signal is sent to the laboratory safety management center through the Internet of Things platform.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the laboratory safety management method based on the Internet of Things as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the laboratory safety management method based on the Internet of Things is implemented as described in any one of claims 1 to 7.

Images