A harmful gas monitoring and alarm system and method in an operating room based on the Internet of Things

By analyzing sensor deployment and monitoring image data in the operating room, target sensors are identified and early warning compensation is implemented, solving the problem of sensor interference caused by personnel, achieving accurate gas monitoring and early warning, and improving the safety of the operating room.

CN118430198BActive Publication Date: 2024-11-15CHANGZHOU CHILDRENS HOSPITAL
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311142739.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-09-06
Publication Date
2024-11-15
Estimated Expiration
2043-09-06

AI Technical Summary

Technical Problem

Existing operating room gas monitoring sensors are affected by the location and number of people in the operating room, leading to measurement deviations, reducing the sensitivity of early warning responses, and potentially causing incalculable harm to personnel.

Method used

By using an IoT-based operating room hazardous gas monitoring and alarm system, the area of ​​the operating room and the types of gas emitted are analyzed to determine the location and number of sensors. Combined with monitoring image data, target monitoring sensors are identified, and visual early warning compensation is performed through correlation to reduce the impact of personnel and improve the sensitivity of sensor early warning.

Benefits of technology

It enables accurate recording of gas sensor measurements under different personnel distribution conditions, improves the sensor's early warning sensitivity, avoids situations where the response is not timely or not at all due to objective reasons, and ensures the safety of personnel in the operating room.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118430198B_ABST
    Figure CN118430198B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of harmful gas monitoring in operating rooms, and specifically to an operating room harmful gas monitoring and alarm system and method based on the Internet of Things, comprising a sensor deployment module, a measurement data recording module, a target monitoring sensor determination module, a correlation analysis module and a visual early warning module; the sensor deployment module is used to deploy gas sensors in the operating room to be monitored based on the area size of the operating room to be monitored and the type of harmful gas emissions recorded; the measurement data recording module is used to put the operating room to be monitored with the gas sensors deployed into use and record the measurement data of the gas sensors; the target monitoring sensor determination module is used to determine the target monitoring sensor in the operating room to be monitored; the correlation analysis module is used to analyze the correlation between monitoring image data and effective measurement data; the visual early warning module is used to perform visual early warning compensation on the target sensor in the operating room to be monitored based on the correlation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of harmful gas monitoring in operating rooms, and in particular to an operating room harmful gas monitoring and alarm system and method based on the Internet of Things. Background Art

[0002] With the development of science and technology and the application of the Internet of Things, visual monitoring of data in the operating room is becoming more and more common. With the widespread use of modern operating room electrosurgical equipment, lasers and other electric tools in surgery, these high-temperature equipment produces more and more smoke when they come into contact with tissues. For example, a large amount of irritating odor is released during the preparation of bone cement, and there is smoke during the process of electric knife cutting tissue to stop bleeding. The smoke contains many harmful chemical components, active viruses, active cells, inactive particles, etc. The long-term exposure of operating room staff to harmful smoke poses a great potential threat to their health. Therefore, gas monitoring sensors are usually installed in the operating room to visually monitor the gas in the operating room and trigger a response or start the exhaust device when the warning conditions are met.

[0003] However, most sensors of existing devices are diffusion sensors, which will be affected by the position and number of people in the operating room during the gas diffusion process, causing the values ​​measured by the sensors to deviate from normal values, thereby reducing the sensitivity of the sensor's early warning response, which may cause immeasurable damage to people in the operating room. Summary of the invention

[0004] The purpose of the present invention is to provide an operating room harmful gas monitoring and alarm system and method based on the Internet of Things to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for monitoring and alarming harmful gases in an operating room based on the Internet of Things, comprising the following steps:

[0006] Step S100: deploying gas sensors in the operating room to be monitored based on the size of the operating room to be monitored and the types of harmful gas emissions to be recorded, putting the operating room to be monitored with the gas sensors deployed into use, and recording the measurement data of the gas sensors;

[0007] Step S200: acquiring monitoring image data of the operating room to be monitored when the gas sensor generates measurement data records after being put into use, and determining the target monitoring sensor in the operating room to be monitored based on the measurement data and monitoring image data recorded by the gas sensor in the operating room to be monitored;

[0008] Step S300: Mark the target monitoring sensor to record the surgical parameters and the measurement data corresponding to the surgical events of the same type as valid measurement data; based on the valid measurement data, analyze the correlation between the monitoring image data and the valid measurement data; analyzing the surgical parameters and the surgical events of the same type is to avoid differences in gas generation types and gas concentrations due to objective reasons;

[0009] Step S400: Based on the association relationship, visual warning compensation is performed on the target sensor in the monitored operating room.

[0010] Furthermore, the deployment of gas sensors in the operating room to be monitored includes the following analysis steps:

[0011] Step S101: Obtain the type of harmful gas emission, calculate the ratio of the molecular weight of the harmful gas medium to the molecular weight of the ambient air, mark the harmful gas with a ratio greater than or equal to 1.0 as the first harmful gas, and mark the harmful gas with a ratio less than 1.0 as the second harmful gas;

[0012] Step S102: Setting the type of gas sensor to a diffusion composite sensor, which means that the sensor is installed in the operating room and the measured gas is in direct contact with the sensor detection element through natural diffusion and multiple gases can be monitored simultaneously; based on the principle that each type of harmful gas corresponds to at most one gas sensor, N types of gas sensors that can be loaded in the operating room to be monitored are constructed; each type means that the actual gas sensor under the premise of the first harmful gas or the second harmful gas classification corresponds to a type of detectable gas;

[0013] The gas sensor for the first harmful gas is set at a distance of [a1, a2] cm from the ground, and the gas sensor for the second harmful gas is set at a distance of [a1, a2] cm from the ceiling, with the sensor part facing downward;

[0014] The types of gas sensors in the operating room are arranged based on the properties of the gas and the characteristics of the gas sensors. This not only avoids detection anomalies caused by installation errors due to differences in the density of gas and air, but also improves the distinction between the types of detected gases, making the visualization data richer and more diverse.

[0015] Step S103: Obtain the area size S1 of the operating room to be monitored and the area corresponding sensor configuration standard, the area corresponding sensor configuration standard means that one gas sensor is set for every S0 square meters; when S1>S0, calculate the minimum installation quantity s, s = "S1 / S0" "S1 / S0" means that the value of S1 / S0 is rounded, and when the remainder is greater than or equal to S0 / 2, the integer part is increased by one, and when the remainder is less than S0 / 2, only the integer part is retained; the minimum installation quantity refers to the number of each type of gas sensors installed in the operating room to be monitored, and each type of gas sensor is installed according to the principle of uniform distribution;

[0016] When S1≤S0, one gas sensor of each type is installed in the operating room to be monitored, and the installation position is set according to the actual scenario while meeting the distance standard.

[0017] Further, determining the target monitoring sensor in the operating room to be monitored includes the following analysis process:

[0018] Step S201: The measurement data of the gas sensor is recorded with each operation performed in the operating room to be monitored as a monitoring period; when the number of each type of gas sensor deployed in the operating room to be monitored is one, the corresponding gas sensor of each type is output as the target monitoring sensor; when the number of each type of gas sensor deployed in the operating room to be monitored is not one, the following analysis is performed;

[0019] Step S202: The monitoring image data is the monitoring screen corresponding to the period t minutes before the gas sensor generates the measurement data, and the number of medical staff in the monitoring screen is recorded; the surgical events corresponding to the different number of medical staff recorded in the monitoring screen are extracted, using the formula:

[0020] W i =G1 / G0;

[0021] Calculate the efficiency index W of the i-th gas sensor in each type of gas sensor i , where G1 represents the fastest number of times the i-th gas sensor generates measurement data in surgical events with different numbers of medical staff, and G0 represents the number of surgical events with different numbers of medical staff; different numbers of medical staff may lead to different concentrations of gas diffusion to the sensor, because medical staff will cause gas obstruction. In the operating room, medical staff surround the operating table, and the gas begins to diffuse on the operating table. The people around the operating table will affect the gas to a certain extent; therefore, the operations are classified based on the number of medical staff to preliminarily judge the data impact of the sensor in different environments, so as to determine the most effective and efficient sensor;

[0022] Step S203: Select the maximum efficiency index W of each type of gas sensor imax The corresponding gas sensor is the target monitoring sensor; if the maximum value is not unique, any gas sensor is selected as the target sensor.

[0023] The maximum efficiency index indicates that the installation location of the sensor is suitable for the detection environment of harmful gases when personnel interference diffusion occurs in the operating room and that it is more efficient than other gas sensors of the same type;

[0024] Furthermore, step S300 includes the following analysis steps:

[0025] Step S301: sorting the valid measurement data according to the numerical value to generate a first sequence; the valid measurement data represents the maximum data of the gas sensor within t minutes after the record is generated;

[0026] Step S302: taking the maximum number of people on the target side recorded in the monitoring image data before each valid measurement data in the first sequence as the horizontal coordinate and the corresponding valid measurement data as the vertical coordinate, obtaining all pairs of coordinate values ​​recorded in the first sequence; performing fitting based on the coordinate values ​​to generate a first fitting curve; analyzing the maximum number of people on the target side is to maximize the consideration of the influence of people on gas diffusion; then outputting the correlation relationship between the monitoring image data and the valid measurement data as the fitting relationship;

[0027] Step S303: The target edge represents the edge of the operating table corresponding to the minimum value of the spatial distance between the target sensor and the four edges of the operating table; when the maximum number of people recorded on the target edge is 0, the valid measurement data corresponding to the coordinate value is obtained as the reference measurement data; when the maximum number of people recorded on the target edge does not exist and is 0, the intersection value of the first fitting curve and the ordinate axis is obtained as the reference measurement data. If it exists and is 0, it means that the data detected by the target sensor at this time is least likely to be affected by people, and if it does not exist and is 0, the measurement data corresponding to the horizontal coordinate of 0 on the image can be obtained according to the fitting curve to achieve the sensor measurement data under the minimum influence.

[0028] Furthermore, step S400 includes the following analysis steps:

[0029] Step S401: sort the maximum number of people recorded on the target side in the first sequence in step S302 to generate a second sequence, and calculate the measurement deviation value U corresponding to the maximum number of people on each target side in the second sequence, U=V1-V0, V1 represents the reference measurement data, V0 represents the valid measurement data in the first sequence corresponding to the maximum number of people on the target side;

[0030] Step S402: construct a data pair (A, U) from the maximum number of people on the target side in the second sequence A and the corresponding measurement deviation value U, obtain all data pairs (A, U) in the second sequence and perform fitting to generate a second fitting curve;

[0031] Step S403: Based on the second fitting curve, when the target sensor in the monitored operating room generates measurement data for the corresponding surgical parameters and surgical events of the same type, obtain the maximum number of people A0 on the target side within t minutes before the measurement data is generated, substitute A0 into the second fitting curve, match the corresponding vertical coordinate value to perform visual early warning compensation for the real-time target sensor recording measurement data, and the visual early warning compensation means that the recorded measurement data is displayed through the visualization system and the compensation value is responded to in the event of an early warning.

[0032] Early warning compensation is to reduce the degree to which the target sensor is affected by the gas diffusion caused by medical staff in the operating room, improve the early warning sensitivity of the target sensor, and avoid the situation where the sensor responds untimely or does not respond due to objective reasons.

[0033] The harmful gas monitoring and alarm system in the operating room includes a sensor deployment module, a measurement data recording module, a target monitoring sensor determination module, a correlation analysis module and a visual early warning module;

[0034] The sensor deployment module is used to deploy gas sensors in the operating room to be monitored based on the size of the operating room to be monitored and the types of harmful gas emissions;

[0035] The measurement data recording module is used to put the operating room to be monitored, where the gas sensor is deployed, into use to record the measurement data of the gas sensor;

[0036] The target monitoring sensor determination module is used to determine the target monitoring sensor in the operating room to be monitored;

[0037] The correlation analysis module is used to analyze the correlation between monitoring image data and effective measurement data;

[0038] The visual warning module is used to perform visual warning compensation for the target sensor in the monitored operating room based on the association relationship.

[0039] Further, the target monitoring sensor determination module includes a type sensor quantity distinction unit, an efficiency index calculation unit and a target sensor output unit;

[0040] The type sensor quantity distinguishing unit is used to distinguish the quantity of each type of gas sensor, and when the quantity is one, a signal is transmitted to the target sensor output unit; when the quantity is not one, a signal is transmitted to the efficiency index calculation unit;

[0041] The efficiency index calculation unit is used to calculate the efficiency index of each gas sensor in each type of gas sensor;

[0042] The target sensor output unit is used to output the target sensor, and based on the efficiency index, a gas sensor corresponding to the maximum efficiency index in each type of gas sensor is selected as the target monitoring sensor.

[0043] Further, the association relationship analysis module includes a first sequence generation unit, a target edge analysis unit and a fitting relationship output unit;

[0044] The first sequence generating unit is used to sort the valid measurement data according to the numerical value to generate a first sequence;

[0045] The target edge analysis unit is used to determine the edge of the operating table corresponding to the minimum value of the spatial distance between the target sensor and the four edges of the operating table. When the maximum value of the number of people recorded on the target edge is 0, the valid measurement data corresponding to the coordinate value is obtained as the reference measurement data; when the maximum value of the number of people recorded on the target edge does not exist and is 0, the intersection value of the first fitting curve and the ordinate axis is obtained as the reference measurement data;

[0046] The fitting relationship output unit is used to obtain all pairs of coordinate values ​​recorded in the first sequence with the maximum number of people recorded on the target side in the monitoring image data before each valid measurement data in the first sequence as the horizontal coordinate and the corresponding valid measurement data as the vertical coordinate; fit based on the coordinate values ​​to generate a first fitting curve, and output the association relationship between the monitoring image data and the valid measurement data as the fitting relationship.

[0047] Further, the visual warning module includes a measurement deviation value calculation unit, a second fitting curve generation unit and a warning compensation unit;

[0048] The measurement deviation value calculation unit is used to sort the maximum number of people recorded on the target side to generate a second sequence, and respectively calculate the measurement deviation value corresponding to the maximum number of people on each target side in the second sequence;

[0049] The second fitting curve generating unit is used to construct a data pair with the maximum number of people on the target side and the corresponding measurement deviation value U in the second sequence, obtain all data pairs in the second sequence and perform fitting to generate a second fitting curve;

[0050] The early warning compensation unit is used to obtain the maximum number of people around the target within t minutes before the measurement data is generated, substitute the maximum value into the second fitting curve, and match the corresponding ordinate value to perform visual early warning compensation for the measurement data recorded by the real-time target sensor.

[0051] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention determines the position and number of sensors installed in each operating room by analyzing the characteristics of the surgery performed in the operating room and the structure of the operating room, and after the determination is completed, after a period of data collection, determines the target gas sensor in the operating room that can effectively and quickly record the measurement data; based on the target gas sensor analysis, under the same conditions, the values ​​affected by the distribution of different personnel before the sensor recording time are recorded, a relationship model is established, and after the baseline value is determined, a fitting curve is constructed for the deviation between the corresponding measurement value and the baseline value under different numbers of personnel, so that the compensation amount that needs to be warned can be determined according to the number of target monitored people during real-time monitoring, thereby quantifying the measurement value of the precise gas sensor; the warning sensitivity of the target sensor is improved to avoid the situation where the sensor responds untimely or does not respond due to objective reasons. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0053] Figure 1 It is a structural schematic diagram of an operating room harmful gas monitoring and alarm system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] See also Figure 1 The present invention provides a technical solution: a method for monitoring and alarming harmful gases in an operating room based on the Internet of Things, comprising the following steps:

[0056] Step S100: according to the size of the operating room to be monitored and the types of harmful gas emissions, gas sensors are deployed in the operating room to be monitored, and the operating room to be monitored with the gas sensors deployed is put into use to record the measurement data of the gas sensors; the types of harmful gas emissions are recorded according to the types of surgeries that can be performed in the operating room and the corresponding medical gas sources; such as those caused by surgical electrified instruments, anesthetic waste gas, etc.;

[0057] Step S200: acquiring monitoring image data of the operating room to be monitored when the gas sensor generates measurement data records after being put into use, and determining the target monitoring sensor in the operating room to be monitored based on the measurement data and monitoring image data recorded by the gas sensor in the operating room to be monitored;

[0058] Step S300: Mark the target monitoring sensor to record the surgical parameters and the measurement data corresponding to the surgical events of the same type as valid measurement data; based on the valid measurement data, analyze the correlation between the monitoring image data and the valid measurement data; analyzing the surgical parameters and the surgical events of the same type is to avoid differences in gas generation types and gas concentrations due to objective reasons;

[0059] Step S400: Based on the association relationship, visual warning compensation is performed on the target sensor in the monitored operating room.

[0060] The deployment of gas sensors in the operating room to be monitored includes the following analysis steps:

[0061] Step S101: Obtain the type of harmful gas emission, calculate the ratio of the molecular weight of the harmful gas medium to the molecular weight of the ambient air, mark the harmful gas with a ratio greater than or equal to 1.0 as the first harmful gas, and mark the harmful gas with a ratio less than 1.0 as the second harmful gas;

[0062] Step S102: Setting the type of gas sensor to a diffusion composite sensor, which means that the sensor is installed in the operating room and the measured gas is in direct contact with the sensor detection element through natural diffusion and multiple gases can be monitored simultaneously; based on the principle that each type of harmful gas corresponds to at most one gas sensor, N types of gas sensors that can be loaded in the operating room to be monitored are constructed; each type means that the actual gas sensor under the premise of the first harmful gas or the second harmful gas classification corresponds to a type of detectable gas;

[0063] The gas sensor for the first harmful gas is set at a distance of [a1, a2] cm from the ground, and the gas sensor for the second harmful gas is set at a distance of [a1, a2] cm from the ceiling, with the sensor part facing downward; in practical applications, a1 is generally set to 30 cm and a2 is generally set to 60 cm;

[0064] As shown in the embodiment: the first harmful gas includes harmful gas 1, harmful gas 2 and harmful gas 3;

[0065] The second harmful gas includes harmful gas 4 and harmful gas 5;

[0066] If there is a gas sensor that can detect harmful gas 1 and harmful gas 3 at the same time, then set gas sensor a;

[0067] To detect harmful gas 2, set gas sensor b;

[0068] If there is a gas sensor that can monitor harmful gas 4 and harmful gas 5 at the same time, then set gas sensor c;

[0069] Based on the above harmful gases, three types of sensors are constructed that can be installed in the operating room to be monitored;

[0070] The types of gas sensors in the operating room are arranged based on the properties of the gas and the characteristics of the gas sensors. This not only avoids detection anomalies caused by installation errors due to differences in the density of gas and air, but also improves the distinction between the types of detected gases, making the visualization data richer and more diverse.

[0071] Step S103: Obtain the area size S1 of the operating room to be monitored and the sensor configuration standard corresponding to the area, the area corresponding to the sensor configuration standard means that one gas sensor is set for every S0 square; when S1>S0, calculate the minimum installation quantity s, s = "S1 / S0" "S1 / S0" means rounding the value of S1 / S0, adding one to the integer part when the remainder is greater than or equal to S0 / 2, and only retaining the integer part when the remainder is less than S0 / 2; the minimum installation quantity refers to the number of each type of gas sensors installed in the operating room to be monitored, and each type of gas sensor is installed according to the principle of uniform distribution; uniform distribution means that if there are 2 types of gas sensors, and each type of gas sensor has 2, then the two types of gas sensors can be installed on the east wall of the operating room and one of each can be installed at the corresponding distance position, and one of each of the remaining two types of gas sensors can be installed on the west wall; as long as the space uniform distribution is met, it can be adjusted based on the layout of the operating room;

[0072] When S1≤S0, the monitored operating room is set to install one gas sensor of each type and the installation position is set according to the actual scene under the premise of meeting the distance standard. In practical applications, S0=20 is generally set. When there is only one gas sensor, it can be set according to the specific situation without restriction.

[0073] Determining the target monitoring sensors in the operating room to be monitored includes the following analysis process:

[0074] Step S201: The measurement data of the gas sensor is recorded with each operation performed in the operating room to be monitored as a monitoring period; when the number of each type of gas sensor deployed in the operating room to be monitored is one, the corresponding gas sensor of each type is output as the target monitoring sensor; when the number of each type of gas sensor deployed in the operating room to be monitored is not one, the following analysis is performed;

[0075] Step S202: The monitoring image data is the monitoring screen corresponding to the period t minutes before the gas sensor generates the measurement data, and the number of medical staff in the monitoring screen is recorded; the surgical events corresponding to the different number of medical staff recorded in the monitoring screen are extracted, using the formula:

[0076] W i =G1 / G0;

[0077] Calculate the efficiency index W of the i-th gas sensor in each type of gas sensor i, where G1 represents the fastest number of times the i-th gas sensor generates measurement data in surgical events with different numbers of medical staff, and G0 represents the number of surgical events with different numbers of medical staff; different numbers of medical staff may lead to different concentrations of gas diffusion to the sensor, because medical staff will cause gas obstruction. In the operating room, medical staff surround the operating table, and the gas begins to diffuse on the operating table. The people around the operating table will affect the gas to a certain extent; therefore, the operations are classified based on the number of medical staff to preliminarily judge the data impact of the sensor in different environments, so as to determine the most effective and efficient sensor;

[0078] Step S203: Select the maximum efficiency index W of each type of gas sensor imax The corresponding gas sensor is the target monitoring sensor; if the maximum value is not unique, any gas sensor is selected as the target sensor.

[0079] The maximum efficiency index indicates that the installation location of the sensor is suitable for the detection environment of harmful gases when personnel interference diffusion occurs in the operating room and that it is more efficient than other gas sensors of the same type;

[0080] Step S300 includes the following analysis steps:

[0081] Step S301: sorting the valid measurement data according to the numerical value to generate a first sequence; the valid measurement data represents the maximum data of the gas sensor within t minutes after the record is generated;

[0082] Step S302: taking the maximum number of people on the target side recorded in the monitoring image data before each valid measurement data in the first sequence as the horizontal coordinate and the corresponding valid measurement data as the vertical coordinate, obtaining all pairs of coordinate values ​​recorded in the first sequence; performing fitting based on the coordinate values ​​to generate a first fitting curve; analyzing the maximum number of people on the target side is to maximize the consideration of the influence of people on gas diffusion; then outputting the correlation relationship between the monitoring image data and the valid measurement data as the fitting relationship;

[0083] Step S303: The target edge represents the edge of the operating table corresponding to the minimum value of the spatial distance between the target sensor and the four edges of the operating table; when the maximum number of people recorded on the target edge is 0, the valid measurement data corresponding to the coordinate value is obtained as the reference measurement data; when the maximum number of people recorded on the target edge does not exist and is 0, the intersection value of the first fitting curve and the ordinate axis is obtained as the reference measurement data. If it exists and is 0, it means that the data detected by the target sensor at this time is least likely to be affected by people, and if it does not exist and is 0, the measurement data corresponding to the horizontal coordinate of 0 on the image can be obtained according to the fitting curve to achieve the sensor measurement data under the minimum influence.

[0084] Step S400 includes the following analysis steps:

[0085] Step S401: sort the maximum number of people recorded on the target side in the first sequence in step S302 to generate a second sequence, and calculate the measurement deviation value U corresponding to the maximum number of people on each target side in the second sequence, U=V1-V0, V1 represents the reference measurement data, V0 represents the valid measurement data in the first sequence corresponding to the maximum number of people on the target side;

[0086] Step S402: construct a data pair (A, U) from the maximum number of people on the target side in the second sequence A and the corresponding measurement deviation value U, obtain all data pairs (A, U) in the second sequence and perform fitting to generate a second fitting curve;

[0087] Step S403: Based on the second fitting curve, when the target sensor in the monitored operating room generates measurement data for the corresponding surgical parameters and surgical events of the same type, obtain the maximum number of people A0 on the target side within t minutes before the measurement data is generated, substitute A0 into the second fitting curve, match the corresponding vertical coordinate value to perform visual early warning compensation for the real-time target sensor recording measurement data, and the visual early warning compensation means that the recorded measurement data is displayed through the visualization system and the compensation value is responded to in the event of an early warning.

[0088] Early warning compensation is to reduce the degree to which the target sensor is affected by the gas diffusion caused by medical staff in the operating room, improve the early warning sensitivity of the target sensor, and avoid the situation where the sensor responds untimely or does not respond due to objective reasons.

[0089] For example, when the gas sensor detects harmful gas with a concentration of b and issues an early warning without being affected by personnel; when there is an impact from personnel, the concentration detected by the sensor may be reduced to b1, but b1 does not reach the early warning limit of the sensor, causing the sensor to fail to transmit an early warning signal, while the actual concentration has reached the early warning value. This error may cause serious harm to medical staff in the operating room. In this application, each type of target sensor corresponds to the same analysis method as above to obtain a corresponding compensation method. The early warning compensation is to add the ordinate value to the valid measurement data to obtain an unaffected measurement value; at the same time, when analyzing different surgical parameters and types, the corresponding analysis will be performed from steps S300-S400 to obtain the specific fitting curve and early warning compensation amount for each type of target sensor under the corresponding surgical parameters and types.

[0090] The harmful gas monitoring and alarm system in the operating room includes a sensor deployment module, a measurement data recording module, a target monitoring sensor determination module, a correlation analysis module and a visual early warning module;

[0091] The sensor deployment module is used to deploy gas sensors in the operating room to be monitored based on the size of the operating room to be monitored and the types of harmful gas emissions;

[0092] The measurement data recording module is used to put the operating room to be monitored, where the gas sensor is deployed, into use to record the measurement data of the gas sensor;

[0093] The target monitoring sensor determination module is used to determine the target monitoring sensor in the operating room to be monitored;

[0094] The correlation analysis module is used to analyze the correlation between monitoring image data and effective measurement data;

[0095] The visual warning module is used to perform visual warning compensation for the target sensor in the monitored operating room based on the association relationship.

[0096] The target monitoring sensor determination module includes a type sensor quantity distinction unit, an efficiency index calculation unit and a target sensor output unit;

[0097] The type sensor quantity distinguishing unit is used to distinguish the quantity of each type of gas sensor, and when the quantity is one, a signal is transmitted to the target sensor output unit; when the quantity is not one, a signal is transmitted to the efficiency index calculation unit;

[0098] The efficiency index calculation unit is used to calculate the efficiency index of each gas sensor in each type of gas sensor;

[0099] The target sensor output unit is used to output the target sensor, and based on the efficiency index, a gas sensor corresponding to the maximum efficiency index in each type of gas sensor is selected as the target monitoring sensor.

[0100] The association relationship analysis module includes a first sequence generation unit, a target edge analysis unit and a fitting relationship output unit;

[0101] The first sequence generating unit is used to sort the valid measurement data according to the numerical value to generate a first sequence;

[0102] The target edge analysis unit is used to determine the edge of the operating table corresponding to the minimum value of the spatial distance between the target sensor and the four edges of the operating table. When the maximum value of the number of people recorded on the target edge is 0, the valid measurement data corresponding to the coordinate value is obtained as the reference measurement data; when the maximum value of the number of people recorded on the target edge does not exist and is 0, the intersection value of the first fitting curve and the ordinate axis is obtained as the reference measurement data;

[0103] The fitting relationship output unit is used to obtain all pairs of coordinate values ​​recorded in the first sequence with the maximum number of people recorded on the target side in the monitoring image data before each valid measurement data in the first sequence as the horizontal coordinate and the corresponding valid measurement data as the vertical coordinate; fit based on the coordinate values ​​to generate a first fitting curve, and output the association relationship between the monitoring image data and the valid measurement data as the fitting relationship.

[0104] The visual warning module includes a measurement deviation value calculation unit, a second fitting curve generation unit and a warning compensation unit;

[0105] The measurement deviation value calculation unit is used to sort the maximum number of people recorded on the target side to generate a second sequence, and respectively calculate the measurement deviation value corresponding to the maximum number of people on each target side in the second sequence;

[0106] The second fitting curve generating unit is used to construct a data pair with the maximum number of people on the target side and the corresponding measurement deviation value U in the second sequence, obtain all data pairs in the second sequence and perform fitting to generate a second fitting curve;

[0107] The early warning compensation unit is used to obtain the maximum number of people around the target within t minutes before the measurement data is generated, substitute the maximum value into the second fitting curve, and match the corresponding ordinate value to perform visual early warning compensation for the measurement data recorded by the real-time target sensor.

[0108] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0109] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A harmful gas monitoring and alarm method for operating rooms based on the Internet of Things. It is characterized in that The following steps are involved: Step S100: deploying gas sensors in the operating room to be monitored based on the size of the operating room to be monitored and the types of harmful gas emissions to be recorded, putting the operating room to be monitored with the gas sensors deployed into use, and recording the measurement data of the gas sensors; The deployment of gas sensors in the operating room to be monitored includes the following analysis steps: Step S101: Obtain the type of harmful gas emission, calculate the ratio of the molecular weight of the harmful gas medium to the molecular weight of the ambient air, mark the harmful gas with a ratio greater than or equal to 1.0 as the first harmful gas, and mark the harmful gas with a ratio less than 1.0 as the second harmful gas; Step S102: Setting the type of gas sensor to a diffusion composite sensor, wherein the diffusion composite sensor refers to a sensor installed in an operating room where the measured gas is in direct contact with the sensor detection element through natural diffusion and multiple gases can be monitored simultaneously; based on the principle that each type of harmful gas corresponds to at most one gas sensor, constructing N types of gas sensors that can be loaded in the operating room to be monitored; each type refers to a type of detectable gas corresponding to the actual gas sensor under the premise of the first harmful gas or the second harmful gas classification; The gas sensor for the first harmful gas is arranged at a distance from the ground [a 1 ,a 2 ]cm, the gas sensor for the second harmful gas is arranged at a distance of [a 1 ,a 2 ]cm, with the sensor facing downward; Step S103: Obtain the area size S of the operating room to be monitored 1 And the area corresponding to the sensor configuration standard, the area corresponding to the sensor configuration standard refers to each S 0 Square set a gas sensor; when S 1 >S 0 When calculating the minimum installation quantity s, s = "S 1 / S 0 "S 1 / S 0 "S 1 / S 0 The value is rounded, and the remainder is greater than or equal to S 0 / 2, the integer part is increased by 1, and the remainder is less than S 0 / 2, only the integer part is retained; the minimum installation quantity refers to the number of each type of gas sensors installed in the operating room to be monitored, and each type of gas sensor is installed according to the principle of uniform distribution; When S 1 ≤S 0 When setting up the monitored operating room, install one gas sensor of each type and the installation position should be set according to the actual scene under the premise of meeting the distance standard; Step S200: acquiring monitoring image data of the operating room to be monitored when the gas sensor generates measurement data records after being put into use, and determining the target monitoring sensor in the operating room to be monitored based on the measurement data and monitoring image data recorded by the gas sensor in the operating room to be monitored; Determining the target monitoring sensor in the operating room to be monitored includes the following analysis process: Step S201: The measurement data of the gas sensor is recorded with each operation performed in the operating room to be monitored as a monitoring period; when the number of each type of gas sensor deployed in the operating room to be monitored is one, the corresponding gas sensor of each type is output as the target monitoring sensor; when the number of each type of gas sensor deployed in the operating room to be monitored is not one, the following analysis is performed; Step S202: The monitoring image data is the monitoring screen corresponding to the period t minutes before the gas sensor generates the measurement data, and the number of medical staff in the monitoring screen is recorded; the surgical events corresponding to the different number of medical staff recorded in the monitoring screen are extracted, using the formula: W i =G 1 / G 0 ; Calculate the efficiency index W of the i-th gas sensor in each type of gas sensor i , where G 1 G represents the fastest number of times the i-th gas sensor generates measurement data during a surgical event with different numbers of medical staff. 0 It indicates the number of surgical events with different number of medical staff; Step S203: Select the maximum efficiency index W of each type of gas sensor imax The corresponding gas sensor is the target monitoring sensor; If the maximum value is not unique, any gas sensor is selected as the target sensor; Step S300: marking the target monitoring sensor recording the surgical parameters and the measurement data corresponding to the surgical events of the same type as valid measurement data; Based on the effective measurement data, analyze the correlation between the monitoring image data and the effective measurement data; The step S300 includes the following analysis steps: Step S301: sorting the valid measurement data according to the numerical value to generate a first sequence; the valid measurement data represents the maximum data of the gas sensor within t minutes after the record is generated; Step S302: taking the maximum number of people on the target side recorded in the monitoring image data before each valid measurement data in the first sequence as the horizontal coordinate and the corresponding valid measurement data as the vertical coordinate, obtaining all pairs of coordinate values ​​recorded in the first sequence; performing fitting based on the coordinate values ​​to generate a first fitting curve; then outputting the correlation relationship between the monitoring image data and the valid measurement data as the fitting relationship; Step S303: the target edge represents the edge of the operating table corresponding to the minimum value of the spatial distance between the target sensor and the four edges of the operating table; when the maximum number of people recorded on the target edge is 0, the valid measurement data corresponding to the coordinate value is obtained as the reference measurement data; when the maximum number of people recorded on the target edge does not exist and is 0, the intersection value of the first fitting curve and the ordinate axis is obtained as the reference measurement data; Step S400: Based on the association relationship, visual early warning compensation is performed on the target sensor in the operating room to be monitored; The step S400 includes the following analysis steps: Step S401: Sort the maximum number of people recorded on the target side in the first sequence in step S302 to generate a second sequence, and calculate the measurement deviation value U corresponding to the maximum number of people on each target side in the second sequence, U=V 1 -V 0 , V 1 Indicates the benchmark measurement data, V 0 Indicates that the maximum number of people on the target side corresponds to the valid measurement data in the first sequence; Step S402: construct a data pair (A, U) from the maximum number of people on the target side in the second sequence A and the corresponding measurement deviation value U, obtain all data pairs (A, U) in the second sequence and perform fitting to generate a second fitting curve; Step S403: Based on the second fitting curve, when the target sensor in the operating room to be monitored generates measurement data corresponding to the surgical parameters and the same type of surgical event, obtain the maximum number of people on the target side within t minutes before the moment of generating the measurement data A 0 , A 0 Substitute the second fitting curve and match the corresponding ordinate value to perform visual early warning compensation for the real-time target sensor recorded measurement data, wherein the visual early warning compensation means displaying the recorded measurement data through a visualization system and responding to the compensation value in the event of an early warning.

2. An operating room harmful gas monitoring and alarm system using the operating room harmful gas monitoring and alarm method based on the Internet of Things as described in claim 1, It is characterized in that It includes sensor deployment module, measurement data recording module, target monitoring sensor determination module, correlation relationship analysis module and visual early warning module; The sensor deployment module is used to deploy gas sensors in the operating room to be monitored based on the size of the operating room to be monitored and the types of harmful gas emissions to be recorded; The measurement data recording module is used to put the operating room to be monitored, where the gas sensor is deployed, into use and record the measurement data of the gas sensor; The target monitoring sensor determination module is used to determine the target monitoring sensor in the operating room to be monitored; The target monitoring sensor determination module includes a type sensor quantity distinction unit, an efficiency index calculation unit and a target sensor output unit; The type sensor quantity distinguishing unit is used to distinguish the quantity of each type of gas sensor, and transmits a signal to the target sensor output unit when the quantity is one; and transmits a signal to the efficiency index calculating unit when the quantity is not one; The efficiency index calculation unit is used to calculate the efficiency index of each gas sensor in each type of gas sensor; The target sensor output unit is used to output the target sensor, and based on the efficiency index, a gas sensor corresponding to the maximum efficiency index of each type of gas sensor is selected as the target monitoring sensor; The correlation analysis module is used to analyze the correlation between monitoring image data and effective measurement data; The association relationship analysis module includes a first sequence generation unit, a target edge analysis unit and a fitting relationship output unit; The first sequence generating unit is used to sort the valid measurement data according to the numerical value to generate a first sequence; The target edge analysis unit is used to determine the edge of the operating table corresponding to the minimum value of the spatial distance between the target sensor and the four edges of the operating table. When the maximum number of people recorded on the target edge is 0, the valid measurement data corresponding to the coordinate value is obtained as the reference measurement data; when the maximum number of people recorded on the target edge does not exist and is 0, the intersection value of the first fitting curve and the ordinate axis is obtained as the reference measurement data; The fitting relationship output unit is used to obtain all pairs of coordinate values ​​recorded in the first sequence by taking the maximum number of people recorded on the target side in the monitoring image data before each valid measurement data in the first sequence as the horizontal coordinate and the corresponding valid measurement data as the vertical coordinate; perform fitting based on the coordinate values ​​to generate a first fitting curve, and output the correlation relationship between the monitoring image data and the valid measurement data as the fitting relationship; The visual warning module is used to perform visual warning compensation on the target sensor in the monitored operating room based on the association relationship; The visual warning module includes a measurement deviation value calculation unit, a second fitting curve generation unit and a warning compensation unit; The measurement deviation value calculation unit is used to sort the maximum number of people recorded on the target side to generate a second sequence, and respectively calculate the measurement deviation value corresponding to the maximum number of people on each target side in the second sequence; The second fitting curve generating unit is used to construct a data pair with the maximum number of people on the target side and the corresponding measurement deviation value U in the second sequence, obtain all data pairs in the second sequence and perform fitting to generate a second fitting curve; The early warning compensation unit is used to obtain the maximum number of people around the target within t minutes before the measurement data is generated, substitute the maximum value into the second fitting curve, and match the corresponding vertical coordinate value to perform visual early warning compensation for the measurement data recorded by the real-time target sensor.