A method and system for monitoring and warning of spatial anomalies under the influence of anesthetic gas

Abstract

The present invention relates to a method and system for monitoring and early warning of spatial anomalies under the influence of anesthetic gas, and relates to the field of data processing. A sensor array is deployed in a target space to monitor the anesthetic gas concentration in real time, and when the concentration does not exceed the standard, operation characteristic parameters are further collected to predict low-altitude operations and anesthetic gas distribution. Finally, the low-altitude operation parameters are combined with the predicted distribution to analyze the impact of anesthetic gas inhalation. This solves the technical problem of insufficient accuracy and inability to comprehensively assess the exposure risk of medical staff when relying on simple threshold judgment for anesthetic gas monitoring. It achieves accurate judgment and early warning, significantly improves the accuracy and timeliness of anesthetic gas leakage monitoring, and comprehensively assesses the exposure risk of medical staff, providing a strong guarantee for the safety management of target spaces such as operating rooms.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method and system for monitoring and warning of spatial anomalies under the influence of anesthetic gas. Background Art

[0002] In the medical field, the operating room is a vital location for various surgical procedures, and the use of anesthetic gases is crucial for ensuring smooth surgical procedures and a painless patient experience. However, anesthetic gases are volatile and diffuse rapidly. Leaks not only pose a direct health threat to medical staff within the operating room, such as causing headaches and nausea, with the potential for more serious health problems with long-term exposure, but can also pollute the surgical environment, impacting the smooth progress of surgery and the patient's postoperative recovery.

[0003] Anesthetic gas diffusion scenarios differ from general gas leak warnings in that they exhibit localized accumulation, behavioral correlation, and latency. In enclosed environments, such as operating rooms, laminar flow ventilation is limited by equipment distribution and ventilation setup, resulting in inefficient gas replacement in blind spots. Conventional gas monitoring, however, focuses on single-point monitoring and early warning, lacking a deep understanding of the specific needs of anesthetic gas use scenarios, such as the correlation between exposure risk, behavioral characteristics, and latency.

[0004] Existing anesthetic gas monitoring methods mostly rely on simple threshold judgments, that is, when the detected anesthetic gas concentration exceeds the preset safety threshold, the system triggers an alarm. However, this method has obvious limitations. On the one hand, a single concentration threshold judgment cannot fully reflect the actual environmental conditions in the operating room. Factors such as airflow dynamics and temperature changes may affect the diffusion and distribution of anesthetic gases, thereby affecting the accuracy of concentration monitoring. On the other hand, existing methods often ignore the exposure risks of medical staff during actual operations, especially when working at low altitudes. Due to their proximity to the ground, medical staff may be more likely to inhale leaked anesthetic gases, and this is often overlooked in existing monitoring methods. In addition, with the continuous advancement of medical technology and the increasing complexity of the operating room environment, higher requirements are placed on the accuracy and real-time performance of anesthetic gas monitoring. Simple threshold judgments can no longer meet the safety management needs of modern operating rooms. Summary of the Invention

[0005] The present invention addresses the technical problem that the existing technology relies on simple threshold judgment to monitor anesthetic gas, resulting in insufficient accuracy and inability to comprehensively assess the exposure risk of medical staff. It provides a spatial anomaly monitoring and early warning method and system under the influence of anesthetic gas to solve the problem.

[0006] The technical solution of the present invention to solve the above technical problems is as follows:

[0007] In a first aspect, the present invention provides a method for monitoring and warning of spatial anomalies under the influence of anesthetic gas, the method comprising: monitoring and collecting anesthetic gas concentrations at multiple positions through a sensor array arranged in a target space, performing discrimination and warning, and issuing a warning when the warning conditions are met; when the warning conditions are not met, collecting operation characteristic parameters in the target space, performing low-altitude operation prediction, and obtaining low-altitude operation parameters; predicting the anesthetic gas distribution in the target space based on multiple anesthetic gas concentrations, and obtaining a predicted anesthetic gas distribution; performing anesthetic gas inhalation effect analysis based on the low-altitude operation parameters and the predicted anesthetic gas distribution, obtaining anesthetic gas effect parameters, performing discrimination and warning, and issuing a warning when the inhalation warning conditions are met.

[0008] In a second aspect, the present invention provides a spatial anomaly monitoring and early warning system under the influence of anesthetic gas, the system comprising: a sensor monitoring module, for monitoring and collecting anesthetic gas concentrations at multiple locations through a sensor array arranged in the target space, performing discrimination and early warning, and issuing an early warning when the early warning conditions are met; a parameter acquisition module, for collecting operation characteristic parameters in the target space when the early warning conditions are not met, performing low-altitude operation prediction, and obtaining low-altitude operation parameters; a distribution prediction module, for predicting the anesthetic gas distribution in the target space based on multiple anesthetic gas concentrations, and obtaining predicted anesthetic gas distribution; an analysis and early warning module, for performing anesthetic gas inhalation effect analysis based on the low-altitude operation parameters and the predicted anesthetic gas distribution, obtaining anesthetic gas influence parameters, performing discrimination and early warning, and issuing an early warning when the inhalation warning conditions are met.

[0009] The beneficial effects of the present invention are: by deploying a sensor array in the target space to monitor the anesthetic gas concentration in real time, and further collecting operation characteristic parameters to predict low-altitude operations and anesthetic gas distribution when the concentration does not exceed the standard, finally combining the low-altitude operation parameters with the predicted distribution to analyze the impact of anesthetic gas inhalation, achieving accurate judgment and early warning, significantly improving the accuracy and timeliness of anesthetic gas leakage monitoring, and at the same time comprehensively evaluating the exposure risk of medical staff, providing a strong guarantee for the safety management of target spaces such as operating rooms. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 The present invention provides a flow chart of a method for monitoring and early warning of spatial anomalies under the influence of anesthetic gas.

[0011] Figure 2 This is a structural schematic diagram of a spatial anomaly monitoring and early warning system under the influence of anesthetic gas provided by the present invention.

[0012] Description of the accompanying drawings: sensing and monitoring module 11, parameter acquisition module 12, distribution prediction module 13, analysis and early warning module 14. DETAILED DESCRIPTION

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0014] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0015] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein. Example 1

[0016] like Figure 1 As shown, an embodiment of the present invention provides a method for monitoring and early warning of spatial anomalies under the influence of anesthetic gas, the method comprising:

[0017] S10: Through the sensor array arranged in the target space, the concentration of anesthetic gas at multiple locations is monitored and collected, and a warning is made when the warning conditions are met.

[0018] For example, in the target space, the concentration of anesthetic gas at multiple key locations is monitored and data collected in real time and continuously by using a uniformly distributed sensor array. The target space is a place related to anesthetic gas monitoring, such as an operating room, and is a limited area where the subsequent sensor array monitors and collects data on the concentration of anesthetic gas. The sensor array refers to a collection of multiple sensors uniformly distributed in the target space. These sensors work together to monitor and collect data on the concentration of anesthetic gas at multiple key locations in real time and continuously. They are distributed throughout the target space, such as the operating room. Each sensor is responsible for detecting the concentration of anesthetic gas in its vicinity. The combination of numerous sensors forms a system that can comprehensively monitor the concentration of anesthetic gas at key locations in the space. These sensors are highly sensitive and accurate, and can accurately capture subtle changes in the concentration of anesthetic gas.

[0019] The collected anesthetic gas concentration data is then transmitted to the data processing center and compared with the preset anesthetic gas concentration threshold. The preset anesthetic gas concentration threshold is set based on the prescribed range of tolerance concentration and is not specifically limited here. If the anesthetic gas concentration at any location reaches or exceeds the preset threshold, the system will immediately trigger the early warning mechanism and notify relevant personnel through sound and light alarms, so that timely measures can be taken to prevent the accident from escalating. For example, in an operating room environment, if the anesthetic gas concentration suddenly rises due to equipment failure, any position in the sensor array will quickly capture this anomaly and trigger an early warning to ensure that medical staff can respond quickly and protect the safety of patients and themselves. Threshold judgment can achieve rapid and accurate early warning, effectively reducing the safety risks caused by anesthetic gas leakage.

[0020] If the current concentration data does not meet the warning conditions, the system will continue to execute subsequent steps, including collecting operation characteristic parameters, making low-altitude operation predictions and anesthetic gas distribution predictions, to further comprehensively assess the safety conditions in the space.

[0021] S20: When the warning conditions are not met, the operation characteristic parameters in the target space are collected, low-altitude operation prediction is performed, and low-altitude operation parameters are obtained.

[0022] Specifically, when the anesthetic gas concentration within the target space does not reach the preset warning threshold, the system further collects characteristic parameters of the operation within the target space. These parameters include, but are not limited to, the type of surgery, expected surgery time, the number of instrument uses, and the amount of instrument used. These parameters are directly related to the potential demand and pattern of low-altitude operations within the operating room.

[0023] Given that the density of anesthetic gas is greater than that of air, it tends to accumulate in the 0-50cm height range above the ground after leakage. This height range is exactly the height range where medical staff's heads are located when performing low-altitude operations, such as squatting to organize instruments or adjust instruments, thereby increasing the risk of inhalation of anesthetic gas. Based on this background, the collected operation characteristic parameters are used to predict the location, time series and number of times low-altitude operations may occur through a preset low-altitude operation prediction model. For example, in a complex operation that is expected to last for a long time, based on the type of operation and the instrument usage plan, it is predicted that a large number of instruments will need to be organized in the middle of the operation, and this operation will mostly be performed under the operating table, that is, in the low-altitude operation area, and then the specific time period and frequency can be planned.

[0024] Through the above steps, not only the potential risk areas and time periods for anesthetic gas inhalation are identified in advance, but also a scientific basis is provided for subsequent safety protection measures, which effectively reduces the risk of medical staff inhaling anesthetic gas due to low-altitude operations and ensures occupational health and safety in the operating room.

[0025] S30: Predicting the distribution of anesthetic gas in the target space according to the multiple anesthetic gas concentrations to obtain a predicted anesthetic gas distribution.

[0026] Furthermore, given the limited number of sensors, it is impossible to directly cover and monitor anesthetic gas concentrations at every location. Therefore, interpolation prediction technology is used to enhance comprehensive monitoring. Specifically, a sensor array deployed at key locations collects anesthetic gas concentration data from multiple monitoring points. Subsequently, based on these discrete concentration data points and combined with the three-dimensional spatial coordinate system of the target space, mathematical interpolation algorithms (such as kriging interpolation and inverse distance weighted interpolation) are used to estimate and predict concentration values ​​at locations within the space that are not directly monitored.

[0027] The interpolation estimation relies on multiple anesthetic gas concentration values ​​monitored by sensors as input. An interpolation algorithm is used to construct a continuous anesthetic gas concentration distribution field, thereby obtaining a predicted anesthetic gas distribution. For example, in a rectangular operating room, if sensors are placed only at the four corners, the concentration data from these four points can be used to predict the anesthetic gas concentration in the center, edges, and other areas not directly monitored.

[0028] Predicting concentration diffusion through interpolation can not only fill the blank areas monitored by sensors and provide a comprehensive anesthetic gas concentration distribution map, but also provide data support for subsequent risk assessment, ventilation control, and personnel protection measures, effectively improving the scientific nature and safety of anesthetic gas management in target spaces such as operating rooms.

[0029] S40: Analyze the impact of anesthetic gas inhalation based on the low-altitude operation parameters and the predicted anesthetic gas distribution, obtain anesthetic gas impact parameters, perform judgment and early warning, and issue an early warning when the inhalation early warning conditions are met.

[0030] Specifically, after obtaining low-altitude work parameters (covering the number of low-altitude work operations, specific locations, and the duration of each squat) and predicting the anesthetic gas distribution, the anesthetic gas inhalation impact analysis process is executed. The anesthetic gas inhalation impact analysis process uses the predicted anesthetic gas distribution data, combined with low-altitude work parameters, to calculate the cumulative inhaled anesthetic gas concentration of medical staff in different work positions and different work time periods. For example, if the prediction shows that the anesthetic gas concentration in a low-altitude work area in the operating room is high, and the medical staff performs multiple and long squatting operations in this area, the system will comprehensively consider these factors and quantify the cumulative inhaled concentration through a specific algorithm model (which may involve concentration-time integral calculation).

[0031] Furthermore, the cumulative inhalation concentration is combined with the number of low-altitude operations to analyze the impact level of anesthetic gas on medical staff. This impact level is used as the anesthetic gas impact parameter to evaluate the health risks that medical staff may suffer from inhaling anesthetic gas, such as dizziness and impact on the normal functioning of blood vessels, especially considering that dizziness may be aggravated by changes in blood circulation when medical staff stand up from a squatting position.

[0032] After completing the above analysis, the anesthetic gas impact parameters are compared with the preset inhalation warning conditions. Once it is found that the impact parameters reach or exceed the warning threshold, the warning mechanism is immediately triggered to remind relevant personnel to take necessary protective measures, such as adjusting the work plan, strengthening ventilation or providing personal protective equipment.

[0033] By comprehensively considering the distribution of anesthetic gas concentration and the characteristics of low-altitude operations, accurate assessment and timely warning of the risk of anesthetic gas inhalation for medical staff are achieved, effectively ensuring the occupational health and safety of medical staff in target spaces such as operating rooms.

[0034] In a preferred embodiment, a sensor array is arranged in the target space to monitor and collect the anesthetic gas concentration at multiple locations, perform a judgment and early warning, and issue an early warning when the early warning conditions are met, including:

[0035] By deploying a sensor array in the target space, the concentration of anesthetic gas at multiple locations is monitored and collected.

[0036] Determine whether any anesthetic gas concentration is greater than or equal to the anesthetic gas concentration threshold. If so, the warning condition is met and a warning is issued. If not, the warning condition is not met and no warning is issued.

[0037] Optionally, a sensor array deployed within the target space serves as the core component of the monitoring system, responsible for collecting real-time and accurate anesthetic gas concentration data at multiple key locations. These sensors are carefully arranged to ensure full coverage of the target space without wasting resources to capture any possible changes in anesthetic gas concentration.

[0038] The collected concentration data is then transmitted to the data processing center for rapid comparison and analysis using a pre-set discrimination algorithm. The system then determines, one by one, whether the anesthetic gas concentration at each monitoring point has reached or exceeded the pre-set anesthetic gas concentration threshold. For example, in an operating room environment, if a sensor detects that the anesthetic gas concentration has suddenly risen to or exceeded a safety threshold (e.g., 50 ppm), the system will immediately determine that a warning condition has been met and trigger the corresponding warning mechanism.

[0039] The early warning mechanism may include sound and light alarms, automatic notifications to relevant personnel, etc., to ensure a quick response and take necessary measures, such as starting the ventilation system, evacuating personnel, etc., so as to effectively prevent safety accidents caused by anesthetic gas leakage.

[0040] If the anesthetic gas concentration at all monitoring points is lower than the threshold, the system determines that the warning conditions are not met, continues to maintain the monitoring status, and does not trigger the warning.

[0041] The above steps significantly improve the response speed and accuracy to anesthetic gas leaks through real-time monitoring and rapid identification, providing strong guarantees for the safe management of target spaces such as operating rooms.

[0042] In a preferred embodiment, when the warning conditions are not met, the operation characteristic parameters in the target space are collected to perform low-altitude operation prediction and obtain low-altitude operation parameters, including:

[0043] When the warning conditions are not met, before the operation is performed, the operation characteristic parameters in the target space are collected, where the operation characteristic parameters include the operation type and equipment usage parameters.

[0044] The operation characteristic parameters are input into a low-altitude operation prediction network for low-altitude operation prediction, and the prediction output obtains low-altitude operation parameters, wherein the low-altitude operation parameters include the number of low-altitude operations, the low-altitude operation time series and the low-altitude operation position series.

[0045] Specifically, when the anesthetic gas concentration monitoring results in the target space show that the warning conditions are not met, the system will further execute the low-altitude operation prediction process to identify potential risks.

[0046] Before the operation begins, the operation characteristic parameters in the target space are actively collected. These parameters are key factors affecting whether low-altitude operations occur and the form of low-altitude operations, including but not limited to the type of operation (such as cardiac surgery, neurosurgery, etc., different types of operations have different requirements for low-altitude operations) and instrument usage parameters (such as the frequency and duration of use of specific instruments, etc., instrument operation may require medical staff to be in a low-altitude working state).

[0047] Subsequently, the collected operation characteristic parameters are input into the pre-trained low-altitude operation prediction network. The low-altitude operation prediction network is a model built based on machine learning, which can predict and output low-altitude operation parameters based on the input operation characteristic parameters. The low-altitude operation parameters specifically include the number of low-altitude operations (i.e., the frequency at which low-altitude operations are expected to be performed during the operation), the low-altitude operation time series (i.e., the time point or time period at which each low-altitude operation is expected to occur), and the low-altitude operation position sequence (i.e., the location or area at which each low-altitude operation is expected to occur). For example, if the prediction network determines based on the input operation type and instrument usage parameters that in an operation that is expected to last a long time, medical staff will perform low-altitude operations multiple times in the middle of the operation to organize or adjust the instruments, the network will output the corresponding number of low-altitude operations, time series, and position series.

[0048] By predicting low-altitude operation parameters in advance, key data support can be provided for subsequent analysis of the impact of anesthetic gas inhalation, thereby more accurately assessing the exposure risk of medical staff and formulating corresponding protective measures, effectively improving the safety management level and occupational health protection capabilities in target spaces such as operating rooms.

[0049] In a preferred embodiment, the training step of the low-altitude operation prediction network includes:

[0050] Based on machine learning, a low-altitude operation prediction network is constructed, wherein the input features of the low-altitude operation prediction network are operation feature parameters, and the output features are low-altitude operation parameters.

[0051] According to the historical operation data in the target space, a set of sample operation feature parameters is collected as input feature training data.

[0052] The number of low-altitude operations, low-altitude operation time series, and low-altitude operation position series performed under different sample operation characteristic parameters are collected, and the sample low-altitude operation parameter set is annotated to serve as the output feature training data.

[0053] The input feature training data and the output feature training data are used to perform supervised training on the low-altitude operation prediction network, and the training is completed after the test accuracy converges.

[0054] Furthermore, in the process of constructing a low-altitude operation prediction network, a neural network model with a specific input-output structure was designed and built based on machine learning technology. The network's input features were set as operation characteristic parameters. These parameters include key information such as operation type and equipment usage parameters, which are important factors affecting the occurrence and form of low-altitude operations. The output features were set as low-altitude operation parameters, specifically including the number of low-altitude operations, low-altitude operation time series, and low-altitude operation location series. These parameters can comprehensively reflect the specific circumstances of low-altitude operations.

[0055] In order to train the low-altitude work prediction network, it is necessary to collect a large number of sample work feature parameter sets from the historical work data of the target space. These sets will serve as input feature training data to provide a basis for network learning. At the same time, it is also necessary to collect and annotate the number of low-altitude work operations, time series, and position series corresponding to each sample work feature parameter in the actual operation process, thereby forming a sample low-altitude work parameter set as output feature training data. For example, when analyzing the historical data of a heart surgery, if it is found that medical staff in this type of surgery often perform multiple low-altitude operations to organize equipment within a specific time period, this information will be annotated and included in the training data.

[0056] Finally, supervised training of the low-altitude operation prediction network is performed using the prepared input and output feature training data. During training, the network continuously adjusts its internal parameters to minimize the error between the predicted output and the actual annotations. When the test accuracy converges to a stable and high level, the network is considered to have fully learned the mapping relationship between the operation feature parameters and the low-altitude operation parameters, thus completing training.

[0057] The low-altitude operation prediction network obtained through training can accurately and efficiently predict low-altitude operation situations in future operations, providing strong support for safety management in target spaces such as operating rooms, helping to formulate protective measures in advance and reduce the exposure risk of medical staff.

[0058] In a preferred embodiment, predicting the anesthetic gas distribution in the target space based on multiple anesthetic gas concentrations to obtain the predicted anesthetic gas distribution includes:

[0059] Obtain the spatial coordinate system in the target space.

[0060] Anesthetic gas concentration interpolation processing is performed in the spatial coordinate system according to the multiple anesthetic gas concentrations to predict and obtain a predicted anesthetic gas distribution.

[0061] Specifically, when performing the prediction of anesthetic gas distribution in the target space, the three-dimensional spatial coordinate system of the target space needs to be clarified. This coordinate system provides a basic framework for the subsequent concentration interpolation processing and ensures the spatial accuracy and locatability of the prediction results.

[0062] Then, based on the anesthetic gas concentration data collected by sensors placed at multiple key locations within the target space, the system performs interpolation of the anesthetic gas concentration within the defined spatial coordinate system. This interpolation process uses mathematical algorithms (such as kriging and spline interpolation) to estimate the concentration values ​​at unknown points based on the concentration data at known points, thereby constructing a map of the anesthetic gas concentration distribution within the entire target space. For example, in a rectangular operating room, if sensors are placed only at the four corners, the system can use interpolation to predict the anesthetic gas concentrations in the center, edges, and other areas not directly monitored, forming a complete predicted anesthetic gas distribution.

[0063] The predicted anesthetic gas distribution obtained through interpolation processing not only fills the blank areas monitored by sensors, but also provides continuous spatial distribution information of anesthetic gas, providing a scientific basis for subsequent risk assessment, ventilation control, and personnel protection measures, effectively improving the accuracy and safety of anesthetic gas management in target spaces such as operating rooms.

[0064] In a preferred embodiment, based on the low-altitude operation parameters and the predicted anesthetic gas distribution, an anesthetic gas inhalation impact analysis is performed to obtain anesthetic gas impact parameters, perform a judgment and early warning, and issue an early warning when the inhalation early warning conditions are met, including:

[0065] A low-altitude operation position sequence within the low-altitude operation parameter is obtained, the predicted anesthetic gas distribution is input for indexing, and an inhaled anesthetic gas concentration sequence is obtained.

[0066] The low-altitude operation time sequence in the low-altitude operation parameter is obtained, and the cumulative inhaled anesthetic gas concentration is calculated in combination with the inhaled anesthetic gas concentration sequence.

[0067] Anesthetic gas inhalation effects are classified according to the cumulative inhaled anesthetic gas concentration and the number of low-altitude operations within the low-altitude operation parameter to obtain an inhalation effect grade as an anesthetic gas effect parameter.

[0068] Determine whether the anesthetic gas impact parameter is greater than or equal to a preset inhalation impact level threshold. If so, the inhalation warning condition is met and a warning is issued. If not, the inhalation warning condition is not met and no warning is issued.

[0069] For example, in the analysis process for the impact of anesthetic gas inhalation in the target space, a low-altitude work position sequence is extracted from the low-altitude work parameters, and these position information are input into the obtained predicted anesthetic gas distribution data for indexing. The low-altitude work position sequence refers to an ordered arrangement of a series of low-altitude work positions extracted from the low-altitude work parameters. These position information are used to input into the predicted anesthetic gas distribution data for indexing to obtain the anesthetic gas concentration corresponding to each position, and finally form an inhaled anesthetic gas concentration sequence. For example, in an operating room space, medical staff perform operations at different low-altitude positions, and these low-altitude positions are arranged in a certain order to form a low-altitude work position sequence. Through this step, the inhaled anesthetic gas concentration corresponding to each low-altitude work position can be obtained, thereby forming an inhaled anesthetic gas concentration sequence, which records in detail the concentration of anesthetic gas inhaled when performing low-altitude operations at different positions.

[0070] Subsequently, the low-altitude operation time series in the low-altitude operation parameters is further combined with the inhaled anesthetic gas concentration series for comprehensive calculation. Specifically, based on the duration of each low-altitude operation and the anesthetic gas concentration at the corresponding location, the inhaled volume of each operation is calculated and accumulated to obtain the cumulative inhaled anesthetic gas concentration. The cumulative inhaled anesthetic gas concentration can intuitively reflect the total amount of anesthetic gas that medical personnel may inhale during the completion of all low-altitude operations.

[0071] Furthermore, a categorized analysis of the impact of anesthetic gas inhalation will be conducted based on the cumulative inhaled anesthetic gas concentration and the number of low-altitude operations in the low-altitude operation parameter. A preset algorithm or model can assess the level of inhalation impact that medical personnel may experience under different operating conditions and output this as the anesthetic gas impact parameter. For example, if the cumulative inhaled concentration is high and the number of operations is frequent, the inhalation impact level may be high, indicating that the medical personnel face a greater health risk.

[0072] Finally, the calculated anesthetic gas impact parameter is compared with the preset inhalation impact level threshold. If the impact parameter is greater than or equal to the threshold, the inhalation warning condition is determined to be met, and the system immediately triggers the warning mechanism to remind relevant personnel to take necessary protective measures. Conversely, if the impact parameter is lower than the threshold, the warning condition is determined to be not met, and the system will continue monitoring without triggering the warning.

[0073] By comprehensively considering low-altitude working parameters and predicting the distribution of anesthetic gas, accurate assessment and timely warning of the impact of anesthetic gas inhalation can be achieved, providing strong occupational health protection for medical staff in target spaces such as operating rooms.

[0074] In a preferred embodiment, the anesthetic gas inhalation effect is classified according to the cumulative inhaled anesthetic gas concentration and the number of low-altitude operations in the low-altitude operation parameter to obtain an inhalation effect level as the anesthetic gas effect parameter, including:

[0075] Based on the historical record data of the effects of anesthetic gas inhalation, the sample users' cumulative inhaled anesthetic gas concentration set and the sample low-altitude operation number set, as well as the sample users' sample inhalation effect level set are collected.

[0076] A decision tree is used to construct an anesthetic inhalation impact classifier based on the sample cumulative inhaled anesthetic gas concentration set, the sample low-altitude operation number set and the sample inhalation impact level set.

[0077] The cumulative inhaled anesthetic gas concentration and the number of low-altitude operations in the low-altitude operation parameter are combined and input into the anesthetic inhalation impact classifier, and the inhalation impact level is obtained by classification output as the anesthetic gas impact parameter.

[0078] Specifically, in the process of building a classification system for the effects of anesthetic gas inhalation, we systematically collect multi-dimensional information on sample users based on historical records of the effects of anesthetic gas inhalation. This includes the set of cumulative inhaled anesthetic gas concentrations, the set of low-altitude operation times, and the corresponding set of inhalation impact levels. These set data serve as the basis for training the classifier, ensuring the accuracy and reliability of the classification model. For example, by collecting the inhalation concentrations, operation times, and final impact levels of different medical staff in similar surgical environments, a representative sample data set can be constructed.

[0079] Subsequently, a decision tree algorithm was used to train a model based on the sample dataset to construct an anesthetic inhalation effect classifier. The decision tree algorithm recursively partitions the dataset into several subsets, each corresponding to a decision node, until all subsets are correctly classified or a preset stopping condition is met, thereby forming a tree-structured model capable of automatic classification. This classifier can learn the complex relationship between the cumulative inhaled anesthetic gas concentration, the number of low-altitude work attempts, and the level of inhalation effect, providing a basis for subsequent real-time classification.

[0080] In practical applications, the cumulative inhaled anesthetic gas concentration obtained through real-time monitoring is combined with the number of low-altitude work operations in the low-altitude work parameter as input features and fed into a trained anesthetic inhalation effect classifier. The classifier automatically classifies the input features based on the learned classification rules and outputs the corresponding inhalation effect level. This level serves as the anesthetic gas impact parameter and is used to assess the inhalation risk of medical personnel under current working conditions.

[0081] By constructing an anesthetic inhalation effect classifier based on a decision tree, we have achieved automated and precise classification of the effects of anesthetic gas inhalation. This not only improves the efficiency and accuracy of risk assessment, but also provides a scientific basis for the early warning mechanism, helping to take protective measures in a timely manner and reduce the occupational exposure risk of medical staff.

[0082] The embodiment of the present invention provides a method for monitoring and early warning of spatial anomalies under the influence of anesthetic gas, which has at least the following technical effects:

[0083] 1. By deploying a sensor array within the target space, real-time monitoring and early warning of anesthetic gas concentrations at multiple locations are achieved. Once the anesthetic gas concentration is detected to exceed the threshold, an early warning will be triggered immediately, effectively preventing safety accidents caused by anesthetic gas leakage and improving space safety.

[0084] 2. When the warning conditions are not met, the operation characteristic parameters in the target space can be collected, and the low-altitude operation parameters can be predicted through the low-altitude operation prediction network. Combined with the predicted anesthetic gas distribution, the impact of anesthetic gas inhalation can be further analyzed, and the inhalation impact level can be obtained as a warning basis, so that potential risks can be evaluated before the operation, providing a scientific basis for taking protective measures.

[0085] 3. An anesthetic inhalation impact classifier was constructed based on machine learning technology. It can automatically classify and output the inhalation impact level based on the cumulative inhaled anesthetic gas concentration and the number of low-altitude operations. This not only improves the accuracy and efficiency of risk assessment, but also makes the early warning mechanism more scientific and reasonable. When the inhalation impact level exceeds the preset threshold, an early warning will be automatically triggered, effectively ensuring the occupational health and safety of personnel. Example 2

[0086] like Figure 2 As shown, based on the same inventive concept as the method for monitoring and warning of spatial anomalies under the influence of anesthetic gas provided in Example 1, an embodiment of the present invention further provides a system for monitoring and warning of spatial anomalies under the influence of anesthetic gas, the system comprising:

[0087] The sensor monitoring module 11 is used to monitor and collect the anesthetic gas concentration at multiple locations through a sensor array arranged in the target space, make judgments and give early warnings, and issue early warnings when early warning conditions are met.

[0088] The parameter collection module 12 is used to collect the operation characteristic parameters in the target space when the warning conditions are not met, perform low-altitude operation prediction, and obtain low-altitude operation parameters.

[0089] The distribution prediction module 13 is configured to predict the anesthetic gas distribution in the target space according to multiple anesthetic gas concentrations to obtain a predicted anesthetic gas distribution.

[0090] The analysis and warning module 14 is used to analyze the impact of anesthetic gas inhalation based on the low-altitude operation parameters and the predicted anesthetic gas distribution, obtain anesthetic gas impact parameters, make judgments and give warnings, and issue warnings when the inhalation warning conditions are met.

[0091] Furthermore, the sensor monitoring module 11 is further configured to perform the following steps:

[0092] By deploying a sensor array in the target space, the concentration of anesthetic gas at multiple locations is monitored and collected; it is determined whether there is any anesthetic gas concentration greater than or equal to the anesthetic gas concentration threshold. If so, the warning condition is met and a warning is issued; if not, the warning condition is not met and no warning is issued.

[0093] Furthermore, the parameter acquisition module 12 is further configured to perform the following steps:

[0094] When the warning conditions are not met, before performing the operation, the operation characteristic parameters in the target space are collected, wherein the operation characteristic parameters include the operation type and equipment usage parameters; the operation characteristic parameters are input into a low-altitude operation prediction network for predicting low-altitude operations, and the prediction output obtains low-altitude operation parameters, wherein the low-altitude operation parameters include the number of low-altitude operations, the low-altitude operation time series and the low-altitude operation position series.

[0095] Furthermore, the parameter acquisition module 12 is further configured to perform the following steps:

[0096] Based on machine learning, a low-altitude operation prediction network is constructed, wherein the input features of the low-altitude operation prediction network are operation feature parameters, and the output features are low-altitude operation parameters; based on the historical operation data in the target space, a set of sample operation feature parameters is collected as input feature training data; the number of low-altitude operations performed under different sample operation feature parameters, the low-altitude operation time series and the low-altitude operation position series are collected, and the sample low-altitude operation parameter sets are annotated to obtain the output feature training data; the input feature training data and the output feature training data are used to perform supervised training on the low-altitude operation prediction network, and the training is completed after the test accuracy converges.

[0097] Furthermore, the distribution prediction module 13 is further configured to perform the following steps:

[0098] A spatial coordinate system in the target space is acquired; and according to the multiple anesthetic gas concentrations, anesthetic gas concentration interpolation processing is performed in the spatial coordinate system to predict and obtain a predicted anesthetic gas distribution.

[0099] Furthermore, the analysis and warning module 14 is further configured to perform the following steps:

[0100] Obtain a low-altitude operation position sequence within the low-altitude operation parameter, input the predicted anesthetic gas distribution for indexing, and obtain an inhaled anesthetic gas concentration sequence; obtain a low-altitude operation time sequence within the low-altitude operation parameter, and calculate the cumulative inhaled anesthetic gas concentration in combination with the inhaled anesthetic gas concentration sequence; classify the anesthetic gas inhalation impact according to the cumulative inhaled anesthetic gas concentration and the number of low-altitude operations within the low-altitude operation parameter, and obtain an inhalation impact level as an anesthetic gas impact parameter; determine whether the anesthetic gas impact parameter is greater than or equal to a preset inhalation impact level threshold; if so, the inhalation warning condition is met and a warning is issued; if not, the inhalation warning condition is not met and no warning is issued.

[0101] Furthermore, the analysis and warning module 14 is further configured to perform the following steps:

[0102] According to the historical record data of the impact of anesthetic gas inhalation, a set of sample cumulative inhaled anesthetic gas concentrations and a set of sample low-altitude operation times of sample users, as well as a set of sample inhalation impact levels of sample users are collected; a decision tree is used to construct an anesthetic inhalation impact classifier based on the sample cumulative inhaled anesthetic gas concentration set, the sample low-altitude operation times set and the sample inhalation impact level set; the cumulative inhaled anesthetic gas concentration and the low-altitude operation times in the low-altitude operation parameter are combined and input into the anesthetic inhalation impact classifier, and the classification output obtains the inhalation impact level as the anesthetic gas impact parameter.

[0103] Through the above-mentioned detailed description of the spatial anomaly monitoring and early warning method under the influence of anesthetic gas in this specification, those skilled in the art can clearly understand the spatial anomaly monitoring and early warning system under the influence of anesthetic gas in this embodiment. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0104] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for monitoring and early warning of spatial anomalies under the influence of anesthetic gas, characterized in that: The method comprises: Through the sensor array deployed in the target space, the concentration of anesthetic gas at multiple locations is monitored and collected, and an early warning is issued when the early warning conditions are met; When the warning conditions are not met, the operation characteristic parameters in the target space are collected to predict low-altitude operations and obtain low-altitude operation parameters, including: When the warning conditions are not met, before the operation is carried out, the operation characteristic parameters in the target space are collected, wherein the operation characteristic parameters include the operation type and the equipment usage parameters; Inputting the operation characteristic parameters into a low-altitude operation prediction network for predicting low-altitude operations, and outputting the prediction to obtain low-altitude operation parameters, wherein the low-altitude operation parameters include the number of low-altitude operations, the time series of low-altitude operations, and the position series of low-altitude operations; predicting the distribution of anesthetic gas in the target space according to the multiple anesthetic gas concentrations to obtain a predicted anesthetic gas distribution; An anesthetic gas inhalation impact analysis is performed based on the low-altitude operation parameters and the predicted anesthetic gas distribution, anesthetic gas impact parameters are obtained, and a judgment and warning are performed. When an inhalation warning condition is met, a warning is issued, including: Obtaining a low-altitude operation position sequence within the low-altitude operation parameters, inputting the predicted anesthetic gas distribution for indexing, and obtaining an inhaled anesthetic gas concentration sequence; Obtaining a low-altitude operation time sequence within the low-altitude operation parameters, and combining the inhaled anesthetic gas concentration sequence to calculate a cumulative inhaled anesthetic gas concentration; classifying the effects of anesthetic gas inhalation according to the cumulative inhaled anesthetic gas concentration and the number of low-altitude operations within the low-altitude operation parameters to obtain an inhalation effect grade as an anesthetic gas effect parameter; Determine whether the anesthetic gas impact parameter is greater than or equal to a preset inhalation impact level threshold. If so, the inhalation warning condition is met and a warning is issued. If not, the inhalation warning condition is not met and no warning is issued.

2. The spatial anomaly monitoring and early warning method under the influence of anesthetic gas according to claim 1 is characterized in that: Through the sensor array deployed in the target space, the concentration of anesthetic gas at multiple locations is monitored and collected, and an early warning is issued when the early warning conditions are met, including: By deploying a sensor array in the target space, the concentration of anesthetic gas at multiple locations is monitored and collected; Determine whether any anesthetic gas concentration is greater than or equal to the anesthetic gas concentration threshold. If so, the warning condition is met and a warning is issued. If not, the warning condition is not met and no warning is issued.

3. The method for monitoring and early warning of spatial anomalies under the influence of anesthetic gas according to claim 1, characterized in that: The training steps of the low-altitude operation prediction network include: Based on machine learning, a low-altitude operation prediction network is constructed, wherein the input features of the low-altitude operation prediction network are operation feature parameters, and the output features are low-altitude operation parameters; Based on the historical operation data in the target space, a set of sample operation feature parameters is collected as input feature training data; The number of low-altitude operations, low-altitude operation time series, and low-altitude operation position series performed under different sample operation characteristic parameters are collected, and the sample low-altitude operation parameter set is annotated to serve as the output feature training data. The input feature training data and the output feature training data are used to perform supervised training on the low-altitude operation prediction network, and the training is completed after the test accuracy converges.

4. The method for monitoring and early warning of spatial anomalies under the influence of anesthetic gas according to claim 1, characterized in that: Predicting the distribution of anesthetic gas in the target space according to the multiple anesthetic gas concentrations to obtain the predicted anesthetic gas distribution includes: Acquire a spatial coordinate system in the target space; Anesthetic gas concentration interpolation processing is performed in the spatial coordinate system according to the multiple anesthetic gas concentrations to predict and obtain a predicted anesthetic gas distribution.

5. The method for monitoring and early warning of spatial anomalies under the influence of anesthetic gas according to claim 1, characterized in that: Anesthetic gas inhalation impact classification is performed based on the cumulative inhaled anesthetic gas concentration and the number of low-altitude operations within the low-altitude operation parameters to obtain an inhalation impact level as an anesthetic gas impact parameter, including: Based on the historical data of the effects of anesthetic gas inhalation, the sample users' cumulative inhaled anesthetic gas concentration set and the sample low-altitude operation times set, as well as the sample users' inhalation effect level set; A decision tree is used to construct an anesthetic inhalation impact classifier based on the sample cumulative inhaled anesthetic gas concentration set, the sample low-altitude operation number set, and the sample inhalation impact level set; The cumulative inhaled anesthetic gas concentration and the number of low-altitude operations within the low-altitude operation parameters are combined and input into the anesthetic inhalation impact classifier, and the inhalation impact level is obtained by classification output as the anesthetic gas impact parameter.

6. A spatial anomaly monitoring and early warning system under the influence of anesthetic gas, characterized in that: A system for implementing the spatial anomaly monitoring and early warning method under the influence of anesthetic gas according to any one of claims 1 to 5, comprising: The sensor monitoring module is used to monitor and collect the concentration of anesthetic gas at multiple locations through a sensor array arranged in the target space, make judgments and give early warnings, and issue early warnings when the early warning conditions are met; The parameter collection module is used to collect the operation characteristic parameters in the target space when the warning conditions are not met, perform low-altitude operation prediction, and obtain low-altitude operation parameters; a distribution prediction module, configured to predict the anesthetic gas distribution in the target space according to a plurality of anesthetic gas concentrations, and obtain a predicted anesthetic gas distribution; The analysis and warning module is used to analyze the impact of anesthetic gas inhalation based on the low-altitude operation parameters and the predicted anesthetic gas distribution, obtain anesthetic gas impact parameters, make judgments and give warnings, and issue warnings when the inhalation warning conditions are met.

Images