Biological safety laboratory digital analysis method and system based on Internet of Things

Abstract

The invention relates to the technical field of biosafety laboratories, and discloses a biosafety laboratory digital analysis method and system based on the Internet of Things, and the method comprises the following steps: carrying out the matching detection step according to a first sensor and a second sensor of a current detection scene; respectively acquiring state data of a first key object and a second key object through two sensors, wherein the first key object is located in a previous level unit of the second key object; extracting action time and action data from the state data, and calculating an action time period, an action time difference, an action continuous value and an action associated value; calculating a first correlation value, a second correlation value and a comprehensive correlation value according to the values; and finally, comparing the comprehensive association value with a preset reference association value, and if the comprehensive association value is small, performing abnormal state early warning. According to the method, the operation state of the biosafety laboratory can be accurately analyzed in real time, abnormity can be found in time, early warning is carried out, and the biosafety of the laboratory is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of biosafety laboratories, and in particular to a digital analysis method and system for biosafety laboratories based on the Internet of Things. Background Art

[0002] With the rapid development of biotechnology, laboratory biosafety, as a key component of biosafety, plays a crucial role in the overall layout of national and public security. In actual operation, biosafety laboratories are directly related to the health and life safety of laboratory personnel, and also have a significant impact on the safety of the surrounding environment.

[0003] The increasing diversity of biosafety laboratory applications and research content poses significant challenges to laboratory biosafety management. The management workload has increased significantly, encompassing multiple aspects, including personnel qualification review, laboratory equipment maintenance, biological sample storage and transportation, and laboratory environmental monitoring. Each step requires meticulous management to ensure compliance with biosafety standards.

[0004] Currently, the generally low level of digitization in biosafety laboratory management is a prominent issue. Traditional access control, laboratory environmental monitoring, and supervision of laboratory and personnel violations rely primarily on manual record-keeping and regular inspections. This inability to accurately monitor and analyze laboratory risk factors, such as pathogen concentration, equipment operating status, and ambient temperature and humidity, prevents real-time monitoring and early warning of risk factors. Consequently, when safety hazards arise, they are not immediately identified and actionable, potentially leading to the occurrence and escalation of accidents. Summary of the Invention

[0005] In order to improve the digital level of biosafety laboratories and provide early warning of safety hazards, this application provides a digital analysis method and system for biosafety laboratories based on the Internet of Things.

[0006] In the first aspect, the present application provides a digital analysis method for a biosafety laboratory based on the Internet of Things, which adopts the following technical solutions:

[0007] A digital analysis method for a biosafety laboratory based on the Internet of Things comprises the following steps:

[0008] Matching the current detection step based on the first sensor and the second sensor in the current detection scene;

[0009] Acquire first state data of a first key object based on a first sensor, and acquire second state data of a second key object based on a second sensor; wherein, in the current detection step, the first key object is located at a previous unit of the second key object;

[0010] Acquire a first action time and first action data from the first state data, and acquire a second action time and second action data from the second state data;

[0011] An action time period and an action time difference are calculated based on the first action time and the second action time; wherein the action time period is used to record the duration of the change of the sensor data of the first sensor and the second sensor, and the action time difference is used to record the difference in the speed of change of the sensor data of the first sensor and the second sensor;

[0012] Calculating an action continuity value and an action association value based on the first action data and the second action data; wherein the action continuity value is used to record the action sequence of the first sensor and the second sensor in the current detection scene, and the action association value is used to record the action association between the first sensor and the second sensor in the current detection scene;

[0013] Calculating a first correlation value based on the action time period and the action continuity value, calculating a second correlation value based on the action time difference and the action correlation value, and calculating a comprehensive correlation value based on the first correlation value and the second correlation value;

[0014] The comprehensive correlation value is compared with a preset reference correlation value, and if the comprehensive correlation value is less than the reference correlation value, an abnormal state warning is issued.

[0015] By employing the above technical solution, by setting up a first sensor and a second sensor to collect status data for the first and second key objects at different levels in the current detection scenario, respectively, the execution sequence of biosafety laboratory experimental steps can be accurately monitored. For example, at the beginning of an experiment, the first protective door of the biosafety laboratory is the first key object, and the disinfection equipment is the second key object. According to the normal process, the door should be opened and closed before the disinfection equipment is activated. By identifying the first and second action times and calculating the action continuity value, it is possible to accurately determine whether these two steps are carried out in the expected order, effectively avoiding the safety hazards caused by the reversal of steps and reducing the occurrence of missed or incorrect experimental steps. Through multi-dimensional quantitative analysis and comprehensive comprehensive evaluation, the probability of abnormal situations during the experiment is significantly reduced. Moreover, this method is applicable to various experimental scenarios in biosafety laboratories, from the initial stage of the experiment to complex experimental processes. In addition, relying on Internet of Things technology, it realizes automatic data collection, efficient transmission, and intelligent analysis, reducing human intervention while significantly improving the safety and overall management efficiency of biosafety laboratory experiments.

[0016] Optionally, the step of calculating the action time period and the action time difference according to the first action time and the second action time includes the following sub-steps:

[0017] The action time period is obtained by subtracting the first action time from the second action time;

[0018] The absolute value of the time interval between the first action time and the second action time is calculated to obtain an action time difference.

[0019] By employing the above technical solution, the duration of the action period can be accurately measured from the start of the first key object action to the start of the second key object action by subtracting the first action time from the second action time. In biosafety laboratories, strict time intervals are imposed between different experimental steps. For example, during sample incubation, a time interval that is too long or too short between inoculating the sample (the first key object action) and activating the incubator temperature control system (the second key object action) can affect experimental results. By accurately calculating the action period, experimenters can promptly detect any timing anomalies, ensuring that experimental steps proceed according to the predetermined timeline, thereby improving the accuracy and repeatability of the experiment. The absolute value of the time interval between the first and second action times is calculated to obtain the action time difference, a metric that reflects the difference in the speed of the two key objects. In the automated operation process of a biosafety laboratory, the operating speeds of different devices should maintain a relatively stable relationship. For example, in a sample transport system, a sudden increase in the time difference between sample collection by the sample collection device (the first key object) and the start of testing by the sample testing device (the second key object) may indicate a blockage in the sample transport process or a slowdown in the speed of a particular device. By monitoring the action time difference, abnormal changes in the equipment's operating speed can be discovered in a timely manner so that timely measures can be taken for adjustment and maintenance.

[0020] Optionally, the step of calculating the action continuity value and the action association value according to the first action data and the second action data includes the following sub-steps:

[0021] Normalizing the first motion data and the second motion data;

[0022] Matching a preset number according to the corresponding actions of the first action data and the second action data;

[0023] Compare the sequence numbers corresponding to the first action data and the second action data; if the sequence number of the second action is 1 greater than the sequence number of the first action, it is determined that the actions are continuous, and the action continuity value is recorded as 1;

[0024] If the sequence number of the second action is 2 or more greater than the sequence number of the first action, it is considered that the required step is skipped, and the action continuity value is recorded as 0.5;

[0025] If the sequence number of the second action is smaller than the sequence number of the first action, it means that the order of the actions is reversed, and the action continuity value is recorded as 0.

[0026] By employing the above technical solution, normalizing the first and second motion data can eliminate the effects of data dimension and value range. In a biosafety laboratory, motion data generated by different experimental equipment or operations may have different units and magnitudes. For example, data from a temperature sensor may range from a few degrees Celsius to tens of degrees Celsius, while data from a pressure sensor may range from hundreds of Pascals to several kilopascals. Normalization can unify these different types of data onto the same scale, making subsequent comparisons and analyses more accurate and reliable, and avoiding misjudgments caused by differences in data scales. Each action is assigned a unique identifier based on its matching preset number. This allows different actions to be clearly identified and distinguished within the complex operational processes of a biosafety laboratory. Whether manual operations by the experimenter or automated equipment, actions can be uniformly managed using numbers. This standardized management approach improves data processing efficiency, reduces errors caused by human factors, and facilitates the recording and traceability of experimental operations.

[0027] Optionally, the step of calculating the first correlation value according to the action time period and the action continuity value, and calculating the second correlation value according to the action time difference and the action correlation value includes the following sub-steps:

[0028] performing normalization processing on the action time period and the action continuous value;

[0029] The first correlation value V1=wT×T+wC×C; T is the action time period, its weight is wT; C is the action continuity value, its weight is wC;

[0030] performing normalization processing on the action time difference and the action association value;

[0031] The second correlation value V2 = wD×D+wR×R; D is the action time difference, and its weight is wD; R is the action correlation value, and its weight is wR.

[0032] By adopting the above technical solution, the action time periods, continuous values, time differences and correlation values ​​in the biosafety laboratory are normalized to eliminate differences in data dimensions and value ranges, ensuring data comparability and accurate analysis. The first and second correlation values ​​are obtained using a weighted calculation method, and the weights of each factor can be flexibly allocated according to experimental requirements, dynamically adapting to experimental changes. The finally calculated correlation value can fully reflect the object's action status, accurately judge anomalies, and assist in timely warning. It can also optimize the experimental process based on the correlation value feedback, improve experimental efficiency and safety, and ensure stable laboratory operation.

[0033] Optionally, the method further comprises the following steps:

[0034] Based on the temperature sensor in the biosafety laboratory, obtain the temperature data within the set time period;

[0035] Calculate the temperature dispersion coefficient based on the temperature data; if the temperature dispersion coefficient exceeds a set threshold, issue a maintenance reminder;

[0036] The maintenance cycle of the biological laboratory is adjusted according to the temperature dispersion coefficient; the larger the temperature dispersion coefficient is, the shorter the maintenance cycle is; the smaller the temperature dispersion coefficient is, the longer the maintenance cycle is.

[0037] By adopting this technical solution, a large temperature dispersion coefficient indicates poor equipment operation, shortening the maintenance cycle and enabling timely inspection and repair of the equipment, reducing the risk of equipment failure. A small temperature dispersion coefficient indicates relatively stable equipment operation, and appropriately extending the maintenance cycle can reduce unnecessary maintenance costs and downtime. Dynamic and intelligent adjustment of the maintenance cycle of biological laboratories based on the temperature dispersion coefficient improves the refinement and scientific level of biological laboratory equipment management and provides a solid guarantee for the efficient and stable operation of the laboratory.

[0038] Optionally, both the first sensor and the second sensor are image sensors; the method further comprises the following steps:

[0039] Acquire image data of a biosafety laboratory access control area based on a first sensor;

[0040] identifying a plurality of specific features from the image data;

[0041] Match the corresponding identity information one by one according to the multiple specific features; if there is any mismatch between all the identity information and the preset identity information, an alarm prompt will be issued;

[0042] If all the identity information matches the preset identity information, obtaining a protective operation image based on the second sensor;

[0043] identifying a plurality of protection features from the protection operation image;

[0044] Determine whether each of the protection features matches the corresponding preset protection reference feature; if there is a protection feature that does not match, issue an irregular operation reminder; otherwise, issue an irregular operation reminder.

[0045] By adopting the above technical solution, a strict verification mechanism can promptly detect abnormal situations such as identity fraud and illegal intrusion. The alarm prompt can promptly notify laboratory security personnel or management personnel to take measures to prevent illegal personnel from entering the laboratory and ensure the safety and order of the laboratory. After the identity verification is passed, the protective operation image is continued to be obtained and the protective features are identified, and matched with the preset protective reference features, which can effectively supervise whether the personnel's protective operations are standardized. Biosafety laboratories have extremely high requirements for personnel protection, and the correct wearing of protective equipment (such as masks, gloves, protective clothing, etc.) is the key to preventing exposure to biohazards. Through this real-time supervision mechanism, irregular operations of personnel can be discovered and corrected in a timely manner, reducing the risk of personnel being exposed to biohazards.

[0046] In a second aspect, the present application provides a digital analysis system for biosafety laboratories based on the Internet of Things, which adopts the following technical solutions:

[0047] A digital analysis system for a biosafety laboratory based on the Internet of Things comprises a processor, wherein the processor executes the steps of any one of the above-mentioned digital analysis methods for a biosafety laboratory based on the Internet of Things.

[0048] In a third aspect, the present application provides a storage medium that adopts the following technical solution:

[0049] A storage medium stores a program, which, when executed by a processor, implements the steps of the above-mentioned digital analysis method for biosafety laboratories based on the Internet of Things.

[0050] In summary, this application includes at least one of the following beneficial technical effects:

[0051] Accurately monitor experimental steps: By setting the first and second sensors to collect status data of key objects at different levels, combined with calculations such as action time and continuous values, the execution order of experimental steps in the biosafety laboratory can be accurately monitored to avoid reversal, omission or incorrect execution of steps, thereby reducing safety hazards.

[0052] Multi-dimensional abnormality warning: Using multi-dimensional quantitative analysis such as action time period, time difference, continuous value, and correlation value, the comprehensive correlation value is calculated and compared with the preset value. It can comprehensively evaluate the experimental status, timely discover and warn of abnormal situations, and significantly reduce the probability of abnormalities during the experiment.

[0053] Scientific and efficient data processing: All types of data are normalized to eliminate the influence of dimension and value range. Combined with weighted calculation method, weights can be flexibly assigned according to experimental requirements, dynamically adapting to experimental changes, making data analysis more accurate and reliable, and improving data processing efficiency.

[0054] Intelligent optimization of equipment management: Dynamically adjust the maintenance cycle of biological laboratories based on the temperature dispersion coefficient. When the equipment is not operating well, the cycle is shortened for timely maintenance. When the operation is stable, the cycle is extended to save costs, thereby improving the refinement and scientific level of equipment management.

[0055] Tight and reliable security protection: Image sensors are used to build access control identity verification and protective operation supervision mechanisms, strictly verifying identities to prevent illegal intrusion, and real-time monitoring of protective equipment wearing standards, reducing the risk of biohazards to personnel and ensuring laboratory safety and order. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a step-by-step diagram of a digital analysis method for biosafety laboratories based on the Internet of Things.

[0057] Figure 2 This is a step diagram for calculating an action continuity value and an action association value based on first action data and second action data.

[0058] Figure 3 The invention is a step diagram for calculating a first correlation value based on an action time period and an action continuity value, and calculating a second correlation value based on an action time difference and an action correlation value. DETAILED DESCRIPTION

[0059] Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings.

[0060] Throughout this specification, reference to the terms "certain embodiments," "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0061] The present application embodiment discloses a digital analysis method for a biosafety laboratory based on the Internet of Things, referring to Figure 1 , including the following steps:

[0062] Based on the first and second sensors in the current detection scene, advanced algorithms and a preset detection step database are used to quickly and accurately match the current detection step.

[0063] The first state data of the first key object is obtained based on the first sensor, and the second state data of the second key object is obtained based on the second sensor; wherein, in the current detection step, the first key object is located in the previous unit of the second key object. For example, in an experimental scenario involving sample processing, the sample collection device can be used as the first key object, and the sample analysis instrument as the second key object. Through this setup, the experimental process can be carefully monitored from different levels and links. In addition, it can also be other continuous steps in the biosafety laboratory to test the accuracy of experimental steps.

[0064] The first action time and first action data are obtained from the first state data, and the second action time and second action data are obtained from the second state data. The action time records the specific moment of the action, while the action data covers various operating parameters of key objects, such as temperature, pressure, speed, etc.

[0065] The action time period and the action time difference are calculated based on the first action time and the second action time; wherein the action time period is used to record the duration of the change of the sensor data of the first sensor and the second sensor, and the action time difference is used to record the difference in the change speed of the sensor data of the first sensor and the second sensor.

[0066] An action continuity value and an action association value are calculated based on the first action data and the second action data; wherein the action continuity value is used to record the action sequence of the first sensor and the second sensor in the current detection scene, and the action association value is used to record the action association between the first sensor and the second sensor in the current detection scene.

[0067] The first correlation value is calculated based on the action time period and the action continuity value. The second correlation value is calculated based on the action time difference and the action correlation value. The comprehensive correlation value is calculated based on the first and second correlation values. The comprehensive correlation value comprehensively reflects the execution of the experimental steps and the degree of coordination between key objects.

[0068] The comprehensive correlation value is strictly compared with the preset reference correlation value. If the comprehensive correlation value is less than the reference correlation value, the abnormal state warning mechanism is immediately activated. Warning methods can include audible and visual alarms, SMS notifications, system pop-up windows, and other methods to ensure that laboratory managers are notified of abnormal conditions immediately.

[0069] By setting up a first sensor and a second sensor to collect status data for the first and second key objects at different levels in the current detection scenario, respectively, the execution sequence of biosafety laboratory experimental steps can be accurately monitored. Taking the initial stage of an experiment as an example, the first protective door of the biosafety laboratory is the first key object, and the disinfection equipment is the second key object. According to normal process, the door should be opened and closed before the disinfection equipment is activated. By accurately identifying the first and second action times and calculating the action continuity value, it is possible to accurately determine whether the two steps are performed in the expected order, effectively avoiding the safety hazards caused by the reversal of steps and greatly reducing the possibility of missing or incorrect experimental steps. Through multi-dimensional quantitative analysis and comprehensive comprehensive evaluation, the probability of abnormal situations during the experiment is significantly reduced. Moreover, this method is highly versatile and flexible, suitable for a variety of experimental scenarios in biosafety laboratories, from basic operations in the initial stage of an experiment to fine-grained control during complex experimental processes. In addition, leveraging Internet of Things technology, it enables automatic data collection, efficient transmission, and intelligent analysis, reducing manual intervention while significantly improving the safety and overall management efficiency of biosafety laboratory experiments, providing strong support for the stable operation of biosafety laboratories and scientific research.

[0070] The step of calculating the action time period and the action time difference according to the first action time and the second action time includes the following sub-steps:

[0071] The action time period is calculated by subtracting the first action time from the second action time. In the rigorous scientific research environment of a biosafety laboratory, strict time intervals are imposed between different experimental steps. For example, in a sample culture experiment, inoculating the sample is the first critical action, while activating the incubator temperature control system is the second critical action. In an ideal experimental workflow, these two actions are precisely timed. If the interval between inoculating the sample and activating the temperature control system is too long, the sample may be exposed to an unsuitable environment for too long, resulting in reduced sample activity and affecting subsequent culture results. If the interval is too short, the incubator may not have reached a stable, optimal temperature, also adversely affecting sample culture. By accurately calculating the action time period, laboratory personnel can compare it with the preset standard time to promptly identify any timing anomalies. If deviations are detected, the operation rhythm can be quickly adjusted to ensure that experimental steps are carried out according to the predetermined time sequence, greatly improving the accuracy and reproducibility of the experiment.

[0072] The action time difference is calculated by calculating the absolute value of the time interval between the first and second action times. The action time difference reflects the difference in the speed of the two key objects. In the increasingly automated operational processes of biosafety laboratories, the operating speeds of different equipment should maintain a relatively stable relationship. Taking the sample transport system as an example, the sample collection device is the first key object, and the sample testing device is the second key object. Under normal circumstances, there is a relatively stable time difference between sample collection and testing. However, if this time difference suddenly increases, it may indicate a blockage in the sample transport process, such as a blockage in the transport pipeline by impurities in the sample; or a slowdown in the operating speed of a device may be caused by aging, malfunction, or external interference. By continuously monitoring the action time difference, laboratory managers can promptly detect abnormal changes in equipment operating speed. Once an anomaly is detected, technicians can quickly arrange for equipment inspection and maintenance, adjusting equipment operating parameters, and ensuring the smooth operation of the entire automated process.

[0073] In biosafety laboratories, timing control of experimental steps is crucial for ensuring safety. Abnormalities in the time intervals and time differences between experimental steps may indicate potential risks during the experiment. For example, in the inactivation of biological samples, activating the heating device is the first critical action, and reaching the predetermined temperature is the second. If the time interval between activating the heating device and reaching the predetermined temperature is too long, incomplete sample inactivation may occur, allowing infectious biological samples to remain active, significantly increasing biosafety risks. By monitoring the time intervals and time differences in real time, the system can set corresponding thresholds. When the calculated time intervals or time differences exceed the thresholds, a timely warning is issued, which can include audible and visual alarms, text message notifications, and system pop-up notifications. These warnings quickly alert laboratory personnel to take appropriate measures, such as checking equipment operating status and adjusting operating procedures, to prevent accidents and establish a solid safety barrier for biosafety laboratories.

[0074] Reference Figure 2 The step of calculating the action continuity value and the action association value according to the first action data and the second action data includes the following sub-steps:

[0075] Normalize the first and second motion data. In a biosafety laboratory, different experimental equipment or operations generate diverse motion data, potentially covering various physical quantities such as temperature, pressure, flow, and velocity. These data often have varying units and magnitudes. For example, temperature sensor data typically fluctuates between a few degrees Celsius and tens of degrees Celsius, while pressure sensor data can vary between hundreds of Pascals and several kilopascals. Without normalization, comparisons and analyses of these data at different scales can result in significant errors due to differences in data dimensions and value ranges, impacting subsequent judgments and decisions. Normalization can unify these different types of data onto the same scale. Common normalization methods include linear normalization and Z-score normalization. For example, linear normalization maps data to the interval [0, 1], making different data comparable. This ensures more accurate and reliable comparisons and analyses, avoiding misjudgments caused by data scale differences.

[0076] A preset number is generated based on the first and second action data, matching the corresponding actions. The complex operational processes in biosafety laboratories involve numerous experimental steps and equipment actions, including manual operations by the experimenter and the operation of automated equipment. Without unified numbering management, these actions would be difficult to clearly identify and distinguish, easily leading to management confusion and inefficient data processing. The preset numbering system is pre-established based on the standard operating procedures and specifications for biosafety experiments, with each action assigned a specific number. For example, sample collection is numbered 1, sample transportation is numbered 2, sample testing is numbered 3, and so on. By matching the actual collected action data with the preset numbers, each action can be quickly and accurately identified. This standardized management approach improves data processing efficiency and reduces errors caused by human factors. It also facilitates the recording and tracing of experimental operations. When querying the specific operations of a particular experimental step, the action number can be used to quickly locate the relevant information.

[0077] Compare the sequence numbers corresponding to the first action data and the second action data; if the sequence number of the second action is 1 greater than the sequence number of the first action, it is judged that the action is continuous, and the action continuity value is recorded as 1. When the sequence number of the second action is 1 greater than the sequence number of the first action, it indicates that the action is continuous, and the action continuity value is recorded as 1. This means that the experimental operations are carried out in sequence according to the preset order, and each step is executed correctly. For example, in the sample processing process, sample pretreatment is performed first (action number 1), followed by sample separation (action number 2). This order conforms to the standard process, indicating that the continuity of the experimental operation is good.

[0078] If the sequence number of the second action is 2 or more greater than the sequence number of the first action, it is judged that the step that needs to be executed is skipped, and the action continuity value is recorded as 0.5. If the sequence number of the second action is 2 or more greater than the sequence number of the first action, it is judged that the step that needs to be executed is skipped, and the action continuity value is recorded as 0.5. In biosafety experiments, each step may have a significant impact on the experimental results. Skipping certain key steps may cause the experiment to fail or even cause a safety accident. For example, during the sample processing process, if the disinfection step is skipped (assuming the disinfection step is numbered 2) and the next step of testing (testing step numbered 3) is directly performed, the sample may be contaminated, affecting subsequent testing and analysis results. The setting of an action continuity value of 0.5 can intuitively reflect the situation of such step omissions, reminding experimenters to take corrective measures in a timely manner, such as supplementing the missed steps, to ensure the accuracy and safety of the experiment.

[0079] If the sequence number of the second action is smaller than the sequence number of the first action, it means that the order of actions is reversed, and the action continuity value is recorded as 0. When the sequence number of the second action is smaller than the sequence number of the first action, it means that the order of actions is reversed, and the action continuity value is recorded as 0. In biosafety laboratories, experimental operations usually have strict sequence requirements, and reversing the sequence may undermine the scientific nature and safety of the experiment. For example, when conducting cell culture, the correct order is to add nutrient solution first (action number 1) and then inoculate cells (action number 2). If the order is reversed, inoculating cells first and then adding nutrient solution may affect cell growth and survival. Recording the action continuity value as 0 can promptly alert the experimenter that there is a serious error in the action sequence, and the operation needs to be stopped immediately and adjusted to avoid causing greater losses.

[0080] By normalizing the first action data and the second action data, matching preset numbers, and comparing sequential numbers, the action continuity value can be accurately calculated, thereby promptly discovering abnormal situations during the experimental operation, ensuring that biosafety experiments are carried out in accordance with specifications and procedures, and providing strong guarantees for the success of the experiment and the safety of the laboratory.

[0081] Reference Figure 3 The steps of calculating the first correlation value according to the action time period and the action continuity value, and calculating the second correlation value according to the action time difference and the action correlation value include the following sub-steps:

[0082] The action time period and the action continuity value are normalized; the first correlation value V1 = wT×T+wC×C; T is the action time period, and its weight is wT; C is the action continuity value, and its weight is wC.

[0083] The action time difference and the action association value are normalized; the second association value V2 = wD×D+wR×R; D is the action time difference, and its weight is wD; R is the action association value, and its weight is wR.

[0084] Normalizing action time periods, action continuity values, action time differences, and action correlation values ​​is essential for ensuring accurate data analysis. In the complex experimental scenarios of biosafety laboratories, these data vary significantly in their original form: action time periods are typically measured in seconds, minutes, or even hours, with a wide range of values. For example, the transportation of high-risk samples may last for hours, while the equipment startup response time is only a few seconds. Action continuity values, as discrete data representing the sequence of operations, only contain three states: 0, 0.5, and 1. Action time differences are measured in time intervals, reflecting differences in equipment response speeds. Action correlation values ​​quantify the logical relationships between actions, and their value range is variable.

[0085] Through algorithms such as Z-score standardization and Min-Max normalization, all types of data are mapped to a unified interval such as [0, 1] or [-1, 1], completely eliminating interference between dimensions and value ranges. For example, in one experiment, the original value of the action time period was 120 seconds, which was converted to 0.8 after normalization (assuming the maximum expected duration in this scenario is 150 seconds), which is on the same comparable scale as the action continuity value of 0.9. This allows data of different dimensions to participate in calculations under a unified standard, avoiding analytical bias caused by differences in data magnitude and providing a reliable data foundation for subsequent correlation value calculations.

[0086] A weighted calculation method is used to construct the first correlation value V1 and the second correlation value V2, giving each factor flexible weight configuration capabilities. The weight distribution closely matches the experimental characteristics: in virus culture experiments, temperature control requires extremely high time precision. In this case, the action time period weight wT can be set to 0.7 to emphasize the critical role of time. In gene editing experimental processes, the strictness of the step sequence directly affects the success of the experiment. Therefore, the action continuity value weight wC is increased to 0.8 to ensure the accuracy of the operation sequence.

[0087] As experimental content is iterated and updated, weights can be adjusted dynamically in real time. When new automated equipment is introduced, the efficiency of inter-device collaboration becomes a key concern. At this time, the action time difference weight wD can be increased from 0.3 to 0.6 to enhance monitoring of device response speed matching. If the experiment adds a cross-step association verification link, the action association value weight wR can be increased to 0.7 to strengthen the assessment of the logical relationship between actions. This adaptive weight adjustment mechanism enables the system to accurately adapt to the core needs of different experimental scenarios, improving the pertinence and effectiveness of data analysis.

[0088] The first correlation value V1 and the second correlation value V2 integrate the time characteristics and logical correlation characteristics of the action to form a multi-dimensional experimental status assessment indicator. Through real-time comparison with preset reference correlation values, the system can keenly detect experimental anomalies: if the V1 value drops sharply, it may mean that the action time period exceeds the threshold or the sequence of steps is disordered. For example, in the sample processing process, the sterilization step takes too long, causing subsequent experiments to be delayed. When the V2 value fluctuates abnormally, it often indicates an imbalance in the equipment response speed or a weakening of the action correlation. For example, the time difference between the start-up of the ventilation system and the operation of the biosafety cabinet is too large, which may lead to the risk of harmful gas leakage.

[0089] Based on the results of correlation value analysis, the system can deeply explore potential problems in the experimental process. For example, through continuous monitoring, it was found that the V1 value in a certain experimental batch was frequently low. Further tracing back to the excessively time-consuming sample transfer operation caused it. Based on this, the transfer path can be optimized or the equipment can be upgraded. If the V2 value shows that the response delay between devices exceeds the standard, it can trigger an equipment maintenance warning and preemptively identify potential faults. This data-driven abnormal diagnosis and process optimization mechanism not only significantly improves experimental efficiency, but also effectively reduces biosafety risks and ensures the safe and stable operation of the laboratory.

[0090] Through the complete process of normalization, weighted calculation and correlation value analysis mentioned above, this method realizes full-link digital management from raw data collection to intelligent decision support, and builds an efficient and accurate risk prevention and control system for biosafety laboratories.

[0091] In the operation and management of biosafety laboratories, a stable ambient temperature is crucial to ensuring the accuracy of experiments, the safety of samples, and the normal operation of equipment. Therefore, real-time monitoring of laboratory temperature and intelligent management based on data are particularly important. Specifically, the following steps are involved:

[0092] Temperature sensors are used to obtain temperature data within a set time period. High-precision temperature sensors are evenly and strategically distributed throughout key areas of the biosafety laboratory, such as sample storage rooms, experimental rooms, and incubators. These sensors are highly sensitive and stable, continuously collecting ambient temperature data at regular intervals (e.g., every minute, every five minutes).

[0093] Taking a typical biological sample storage room as an example, strict temperature control is required to ensure sample activity and stability. Multiple temperature sensors are installed within this storage room, collecting temperature data every minute and transmitting this data in real time to the laboratory's central monitoring system via IoT technology. The time period can be flexibly adjusted to meet actual needs. For example, to analyze temperature fluctuations within a day, a 24-hour period can be set; to study temperature fluctuation trends within a week, a full week can be set.

[0094] Calculate the temperature coefficient of dispersion based on the collected temperature data. The temperature coefficient of dispersion is a statistical indicator that reflects the degree of dispersion of a set of data relative to its mean. In biosafety laboratory temperature management, the temperature coefficient of dispersion can intuitively reflect temperature fluctuations. Its calculation formula is: Temperature coefficient of dispersion = Temperature standard deviation / Average temperature.

[0095] When the calculated temperature coefficient of variation exceeds a set threshold, the system immediately issues a maintenance reminder. This threshold is predetermined based on the laboratory's specific requirements and the equipment's performance parameters. For example, for cell culture experiments with extremely high temperature requirements, the threshold might be relatively low, such as a temperature coefficient of variation not exceeding 0.05. Once the temperature coefficient of variation exceeds this threshold, the central monitoring system issues an alert through various means, including audible and visual alarms and text messages notifying laboratory managers and equipment maintenance personnel.

[0096] For example, in a cell culture room in a biosafety laboratory, temperature data collected over a set period of one day shows an average temperature of 25°C, but with significant temperature fluctuations. The calculated temperature dispersion coefficient is 0.08, exceeding the set threshold of 0.05. At this point, the system quickly issues a maintenance reminder, alerting staff to inspect and maintain the room's temperature control equipment.

[0097] Adjust the maintenance cycle of biological laboratories based on the temperature dispersion coefficient. The specific rule is: a larger temperature dispersion coefficient indicates poor equipment operation and large temperature fluctuations. In this case, the maintenance cycle should be shortened to enable timely inspection and repair of the equipment and reduce the risk of equipment failure. A smaller temperature dispersion coefficient indicates relatively stable equipment operation and small temperature fluctuations. Appropriately extending the maintenance cycle can reduce unnecessary maintenance costs and downtime.

[0098] For example, in a small biosafety laboratory, the initial maintenance cycle was set at monthly. During a period of monitoring, it was found that the temperature coefficient of variation in a certain experimental operation room remained at a low level, such as 0.02, far below the set threshold. Based on the adjustment rules, the maintenance cycle for this operation room was extended to once every two months. Conversely, if the temperature coefficient of variation in another sample storage room remained consistently high, reaching 0.1, significantly exceeding the set threshold, the maintenance cycle for that storage room was shortened to once every two weeks.

[0099] By dynamically and intelligently adjusting the maintenance cycle of biological laboratories based on the temperature dispersion coefficient, precise management of laboratory equipment can be achieved. This approach avoids the blindness and inefficiency of traditional fixed-cycle maintenance methods, improves the refinement and scientific level of biological laboratory equipment management, and provides a solid guarantee for the efficient and stable operation of the laboratory. For example, in the laboratories of some large biopharmaceutical companies, the implementation of this dynamic maintenance management method has significantly reduced equipment failure rates, greatly improved experimental success rates, and saved a considerable amount of maintenance costs and time.

[0100] In the safety protection system of the biosafety laboratory, the first sensor and the second sensor are both image sensors. The specific steps and effects of the safety management method based on this are as follows:

[0101] The first image sensor captures high-definition image data from the biosafety laboratory access control area in real time. This sensor utilizes high-resolution, low-light imaging technology, enabling it to clearly capture facial details and ID information even in dimly lit environments. The system utilizes advanced image enhancement algorithms to reduce noise and sharpen the captured raw images, further improving image quality and paving the way for subsequent feature recognition.

[0102] Subsequently, deep learning algorithms are used to accurately identify multiple specific features from the processed image data. For facial feature recognition, a convolutional neural network (CNN) is used to extract key facial features, such as the position, shape, and relative proportions of the eyes, nose, mouth, and cheekbones, to construct a unique facial feature vector. For work card feature recognition, optical character recognition (OCR) technology is used to automatically extract information such as the text, number, and barcode on the work card. Image segmentation technology is then used to separate the photo from the text on the work card for more accurate feature extraction and comparison.

[0103] The system matches the identified features against the identity information stored in the database. The system has established a comprehensive database of personnel identity information, including facial feature templates, ID card details, department affiliation, position, and authority level of authorized personnel. During the matching process, a multimodal fusion algorithm is used to compare facial features with ID card information, improving the accuracy and reliability of identity verification.

[0104] If any of the identity information does not match the preset identity information, the system immediately triggers a multi-level alarm mechanism. First, the audio and visual alarm at the access control station emits a shrill alarm and flashes a red warning light, deterring illegal intruders. Second, the system automatically sends an alarm message to the laboratory security personnel's handheld terminal, the monitoring center computer, and the management personnel's mobile phone app. The message contains a real-time image of the abnormal person, the time of intrusion, the access control location, and other details. In addition, the access control system automatically locks the door to prevent illegal entry. At the same time, it connects to surrounding cameras to track and record the abnormal person throughout the process, providing strong evidence for subsequent investigation and handling.

[0105] If all identity information matches the preset one, the person's identity verification is successful. At this point, a second image sensor captures the protective operation image. This sensor, conveniently located inside the access control, clearly captures the protective gear worn by the person entering the laboratory. The sensor's wide-angle image and autofocus capabilities allow it to capture the entire person's body, ensuring every detail of their protective gear is captured.

[0106] Image semantic segmentation technology is used to identify multiple protective features in protective operation images. For masks, the system detects features such as the edge contour, coverage, and wearing position to determine whether they are correctly worn. For gloves, the system identifies features such as glove color, material, and completeness of wear. For protective clothing, the system analyzes features such as whether the zipper is properly closed, the cuffs and trouser legs are sealed, and whether the protective mask is worn correctly.

[0107] Each identified protective feature is precisely matched to the corresponding preset protective reference feature. These reference features are pre-set based on biosafety laboratory safety standards and operating procedures, and include detailed characteristic parameters for the correct wearing of various protective equipment. For example, masks should fully cover the mouth, nose, and chin, with the edges fitting tightly against the face; gloves should be undamaged and fully cover the hands.

[0108] If there is a mismatch in any of the protective features, the system will immediately issue an operational irregularity reminder. This reminder includes displaying text prompts on the display screen at the access control, such as "Your mask is not worn properly, please readjust it." At the same time, a voice reminder is issued through the voice broadcast system to inform personnel of the specific irregularities. Furthermore, the system will send a reminder message to the device bound to the personnel's work card, urging them to make timely corrections. If all protective features match the preset protective reference features, an operational standard prompt will be issued, such as "Protective equipment is worn properly, welcome to the laboratory" will be displayed on the display screen, and a voice welcome prompt will be broadcast, providing clear feedback for personnel entering the laboratory.

[0109] Through this rigorous and meticulous verification and monitoring mechanism, this method can promptly detect anomalies such as identity theft and illegal intrusion, effectively ensuring laboratory safety and order. After identity verification is successful, real-time monitoring of protective operations ensures personnel are properly wearing protective equipment, reducing the risk of biohazard exposure and providing comprehensive, multi-layered protection for the safe operation of biosafety laboratories.

[0110] In other embodiments, the first sensor is a displacement sensor for detecting the opening and closing status of the biosafety cabinet door, and the second sensor is a switch sensor for detecting the door lock status of the biosafety cabinet door, wherein the first key object is the biosafety cabinet door and the second key object is the door lock of the biosafety cabinet.

[0111] When a high-precision displacement sensor is used as the first sensor and a sensitive switch sensor is selected as the second sensor, a highly efficient monitoring system for biosafety cabinet doors and their locks can be established. Using non-contact sensing technology, the displacement sensor, installed in key locations such as the cabinet door's hinges and guide rails, captures dynamic data such as displacement distance, rotation angle, and opening and closing speed during the door's opening and closing process in real time. Even the slightest abnormal movement or incomplete closure of the cabinet door can be detected by the displacement sensor and transmitted to the laboratory's central control system.

[0112] The second sensor uses a switch sensor, which fits tightly into the door lock structure. By detecting the extension and retraction status of the lock tongue and the rotation feedback of the lock cylinder, it can accurately determine whether the door lock is locked, unlocked, or in an abnormal state. For example, when the door lock cannot fully pop out due to a mechanical failure, the switch sensor will immediately transmit the abnormal signal to the system. By correlating and analyzing the data of the displacement sensor and the switch sensor, the central control system can not only determine whether the operating status of the cabinet door and door lock is normal, but also identify logical anomalies such as "the cabinet door is not closed but the locking operation is completed", triggering the sound and light alarm in time, and sending detailed abnormal information to laboratory managers to ensure the reliability of the biosafety cabinet door, an important protective barrier.

[0113] In other embodiments, the first sensor is a temperature sensor for detecting the temperature in the biosafety laboratory, and the second sensor is a pressure sensor for detecting the pressure in the biosafety laboratory. The two sensors work together to achieve comprehensive monitoring of the core environmental parameters in the biosafety laboratory.

[0114] Scenario 1: Gas Heating Equipment Operation Monitoring

[0115] In experiments involving gas heating, the temperature and pressure changes in the gas heating equipment are subject to strict timing requirements. During the initial phase of the experiment, a temperature sensor monitors the internal temperature of the equipment in real time at a high sampling rate of 10 times per second. When the operator initiates the heating process, the temperature sensor immediately detects the rising temperature trend and transmits the data to the laboratory's central control system. For example, if the temperature begins to rise from an initial 20°C, the system accurately records the start time and the rate of temperature increase.

[0116] At the same time, the pressure sensor synchronously monitors the internal pressure status of the equipment. According to the standard operating procedures, the gas heating equipment should start to gradually increase the pressure only after the temperature reaches the predetermined value and stabilizes. The central control system calculates the action time period and the action time difference based on the first action time feedback from the temperature sensor and the second action time feedback from the pressure sensor. If the pressure sensor detects an abnormal increase in pressure when the temperature has not yet stabilized, or the action time period exceeds the preset safety threshold (such as after the temperature rises to the target temperature, the pressure should begin to rise steadily within 5 minutes, otherwise it will be considered abnormal), the system will immediately trigger an audible and visual alarm, and send a warning message containing abnormal data to the experimenter and equipment maintenance personnel, indicating that there may be problems such as uneven heating and pressure control system failure, so as to avoid safety accidents such as gas leakage and equipment explosion caused by disorder in temperature and pressure control.

[0117] Scenario 2: Centrifuge operating status monitoring

[0118] Centrifuges are commonly used in biosafety laboratories for high-speed operations, so monitoring the correlation between their rotational speed and temperature is crucial. During initial operation, a speed sensor (which can be considered the primary sensor, working in conjunction with the temperature sensor) collects real-time centrifuge speed data. Once the centrifuge is started, the speed rapidly increases from 0 to a preset speed (e.g., 5000 rpm). The system fully records the time and speed changes during this process.

[0119] The temperature sensor closely monitors the heat generation during the operation of the centrifuge. Under normal circumstances, after the centrifuge rotates at high speed for a period of time, the temperature will rise due to factors such as mechanical friction, but it should be within a safe range. The central control system calculates the action continuity value and the action association value by analyzing the data of the speed sensor and the temperature sensor. If the centrifuge has an abnormally high temperature when the speed has not yet stabilized, or the temperature rise rate exceeds the normal level (such as after the speed reaches a stable value, the temperature does not rise by more than 5°C every 10 minutes, otherwise it is considered abnormal), the system will determine that the equipment is operating abnormally. At this time, not only will an alarm be issued, but the speed of the centrifuge will also be automatically reduced until it stops to prevent dangerous situations such as equipment damage or sample splashing due to overheating. At the same time, a maintenance report containing abnormal data will be generated to provide a basis for subsequent maintenance.

[0120] Scenario 3: Comprehensive Monitoring of the Experimental Environment

[0121] Throughout the biosafety laboratory, temperature and pressure sensors collaborate to form an environmental monitoring network. Multiple temperature sensors are located in various functional areas, such as experimental operation areas, sample storage areas, and incubators, providing real-time temperature data for each area. Pressure sensors are installed in ventilation systems, gas ducts, and sealed operating chambers to monitor indoor air pressure balance and status.

[0122] The system can identify a variety of potential risks by analyzing the correlation between temperature and pressure data. For example, if the temperature in a certain area of ​​the laboratory suddenly rises and the air pressure in that area drops abnormally, the system will comprehensively determine that there may be a gas leak and a localized temperature increase. It will then initiate the emergency ventilation program, close the gas valves in the relevant area, and issue an evacuation alarm to all laboratory personnel. In addition, based on long-term monitoring data, the system can analyze the patterns of temperature and pressure changes and optimize laboratory environmental control strategies. For example, during periods of large temperature fluctuations, the system can automatically adjust the ventilation frequency to maintain a stable indoor environment, providing reliable guarantees for the smooth progress of biological experiments.

[0123] An embodiment of the present application further discloses a digital analysis system for a biosafety laboratory based on the Internet of Things, comprising a processor, wherein the processor executes the steps of any one of the above-described digital analysis methods for a biosafety laboratory based on the Internet of Things.

[0124] An embodiment of the present application further discloses a storage medium, in which a program is stored. When the program is executed by a processor, the steps of the above-mentioned method for digital analysis of biosafety laboratories based on the Internet of Things are implemented.

[0125] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A digital analysis method for biosafety laboratories based on the Internet of Things, characterized in that: The steps include: Matching the current detection step based on the first sensor and the second sensor in the current detection scene; Acquire first state data of a first key object based on a first sensor, and acquire second state data of a second key object based on a second sensor; wherein, in the current detection step, the first key object is located at a previous unit of the second key object; Acquire a first action time and first action data from the first state data, and acquire a second action time and second action data from the second state data; An action time period and an action time difference are calculated based on the first action time and the second action time; wherein the action time period is used to record the duration of the change of the sensor data of the first sensor and the second sensor, and the action time difference is used to record the difference in the speed of change of the sensor data of the first sensor and the second sensor; Calculating an action continuity value and an action association value based on the first action data and the second action data; wherein the action continuity value is used to record the action sequence of the first sensor and the second sensor in the current detection scene, and the action association value is used to record the action association between the first sensor and the second sensor in the current detection scene; Calculating a first correlation value based on the action time period and the action continuity value, calculating a second correlation value based on the action time difference and the action correlation value, and calculating a comprehensive correlation value based on the first correlation value and the second correlation value; The comprehensive correlation value is compared with a preset reference correlation value, and if the comprehensive correlation value is less than the reference correlation value, an abnormal state warning is issued.

2. The digital analysis method for biosafety laboratories based on the Internet of Things according to claim 1, characterized in that: The step of calculating the action time period and the action time difference based on the first action time and the second action time includes the following sub-steps: The action time period is obtained by subtracting the first action time from the second action time; The absolute value of the time interval between the first action time and the second action time is calculated to obtain an action time difference.

3. The digital analysis method for biosafety laboratories based on the Internet of Things according to claim 2, characterized in that: The step of calculating the action continuity value and the action association value based on the first action data and the second action data includes the following sub-steps: Normalizing the first motion data and the second motion data; Matching a preset number according to the corresponding actions of the first action data and the second action data; Compare the sequence numbers corresponding to the first action data and the second action data; if the sequence number of the second action is 1 greater than the sequence number of the first action, it is determined that the actions are continuous, and the action continuity value is recorded as 1; If the sequence number of the second action is 2 or more greater than the sequence number of the first action, it is considered that the required step is skipped, and the action continuity value is recorded as 0.5; If the sequence number of the second action is smaller than the sequence number of the first action, it means that the order of the actions is reversed, and the action continuity value is recorded as 0.

4. The digital analysis method for biosafety laboratories based on the Internet of Things according to claim 3, characterized in that: The step of calculating the first correlation value according to the action time period and the action continuity value, and calculating the second correlation value according to the action time difference and the action correlation value includes the following sub-steps: performing normalization processing on the action time period and the action continuous value; The first correlation value V1=wT×T+wC×C; T is the action time period, its weight is wT; C is the action continuity value, its weight is wC; performing normalization processing on the action time difference and the action association value; The second correlation value V2 = wD×D+wR×R; D is the action time difference, and its weight is wD; R is the action correlation value, and its weight is wR.

5. The digital analysis method for biosafety laboratories based on the Internet of Things according to claim 1, characterized in that: The method further comprises the steps of: Based on the temperature sensor in the biosafety laboratory, obtain the temperature data within the set time period; Calculate the temperature dispersion coefficient based on the temperature data; if the temperature dispersion coefficient exceeds a set threshold, issue a maintenance reminder; Adjusting the maintenance cycle of the biological laboratory according to the temperature dispersion coefficient; the larger the temperature dispersion coefficient, the shorter the maintenance cycle; The smaller the temperature dispersion coefficient is, the longer the maintenance period is.

6. The digital analysis method for biosafety laboratories based on the Internet of Things according to claim 1, characterized in that: The first sensor and the second sensor are both image sensors; the method further comprises the following steps: Acquire image data of a biosafety laboratory access control area based on a first sensor; identifying a plurality of specific features from the image data; Match the corresponding identity information one by one according to the multiple specific features; if there is any mismatch between all the identity information and the preset identity information, an alarm prompt will be issued; If all the identity information matches the preset identity information, obtaining a protective operation image based on the second sensor; identifying a plurality of protection features from the protection operation image; Determine whether each of the protection features matches the corresponding preset protection reference feature; if there is a protection feature that does not match, issue an irregular operation reminder; otherwise, issue an irregular operation reminder.

7. A digital analysis system for biosafety laboratories based on the Internet of Things, characterized in that: The method comprises a processor, wherein the processor executes the steps of the digital analysis method for a biosafety laboratory based on the Internet of Things according to any one of claims 1 to 6.

8. A storage medium, characterized in that: The medium stores a program, and when the program is executed by the processor, the steps of the digital analysis method for biosafety laboratories based on the Internet of Things according to any one of claims 1 to 6 are implemented.

Images