Micro hyperbaric oxygen chamber oxygen supply adjusting system based on artificial intelligence assistance

Abstract

The invention discloses a micro hyperbaric oxygen chamber oxygen supply adjusting system based on artificial intelligence assistance, and relates to the technical field of medical equipment control. The system comprises a data acquisition module for acquiring operation state parameters of a micro hyperbaric oxygen chamber and physiological state parameters of an oxygen receiving object to generate an original data set; the data processing module is used for carrying out time sequence synchronization processing on the original data set to obtain a characterization state parameter and a channel uncertainty index; the level construction module is used for forming a comprehensive oxygen metabolism load index through multi-level processing based on the characterization state parameters and the uncertainty indexes of the channels, and dividing oxygen metabolism load levels; and the strategy adjusting module is used for making an oxygen supply adjusting decision according to the oxygen metabolism load level and the characterization state parameter, determining a target adjusting quantity and generating an adjusting instruction. A comprehensive oxygen metabolism load index is constructed through high-precision state evaluation, and safe, intelligent and personalized oxygen supply regulation is realized based on the index.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical equipment control, in particular to a micro-high pressure oxygen cabin oxygen supply regulation system based on artificial intelligence assistance. BACKGROUND

[0002] As an equipment for improving the oxygen supply capacity of the human body, the micro-high pressure oxygen cabin is widely used in rehabilitation and health care, sports recovery and auxiliary treatment of specific physiological state. The existing micro-high pressure oxygen cabin generally adjusts the cabin pressure, oxygen concentration and ventilation volume to improve the cabin environment, so that the oxygen receiving object can obtain higher oxygen partial pressure. However, the operation and adjustment mode of the traditional micro-high pressure oxygen cabin depends on fixed parameter setting or artificial experience judgment, and the adjustment process often lacks real-time analysis capability of the correlation between the cabin environment state and the physiological response of the oxygen receiving object.

[0003] Although there are monitoring systems in the prior art that use various sensors to collect cabin pressure, gas concentration and physiological information of the oxygen receiving object, they usually focus on the judgment and alarm of a single parameter, and it is difficult to extract comprehensive indicators reflecting physiological load and gas exchange state from multi-source data. In addition, in the case of time deviation, insufficient sampling consistency, noise interference and channel uncertainty variation of multi-source monitoring data, the traditional processing method has certain limitations in state estimation accuracy and robustness.

[0004] At the same time, the existing oxygen cabin regulation strategy generally does not form a dynamic regulation mechanism based on comprehensive physiological load changes, and it is difficult to reflect the response difference of the oxygen receiving object to the cabin environment change in time, and also lacks the ability to fine-tune the regulation according to the environment-physiological coupling characteristics. Therefore, under the premise of ensuring the safety of the cabin operation, realizing the effective processing of multi-source data, constructing evaluation indicators reflecting oxygen metabolism load, and based on the evaluation indicators, more accurate oxygen supply regulation is the direction of continuous attention of related technical personnel. SUMMARY

[0005] Based on the shortcomings of the prior art described above, the purpose of the present application is to provide a micro-high pressure oxygen cabin oxygen supply regulation system based on artificial intelligence assistance to solve the above technical problems.

[0006] To achieve the above purpose, the present application provides the following technical scheme: a micro-high pressure oxygen cabin oxygen supply regulation system based on artificial intelligence assistance, comprising: a data acquisition module, a data processing module, a level construction module and a strategy adjustment module; The data acquisition module acquires the micro-high pressure oxygen cabin operation state parameters and the physiological state parameters of the oxygen receiving object to generate an original data set; The data processing module performs time series synchronization processing on the original data set to obtain state parameter and channel uncertainty indicators; Grade construction module: based on the state parameter and the uncertainty index of the channel, a comprehensive oxygen metabolism load index is formed through multi-stage processing, and the oxygen metabolism load grade is divided; Strategy adjustment module: according to the oxygen metabolism load grade and the state parameter, the oxygen supply adjustment decision is made, the target adjustment amount is determined, and the adjustment instruction is generated.

[0007] The application further provides that the data acquisition module comprises: The multi-dimensional environmental sensing sensor is used to collect the micro hyperbaric oxygen chamber operating state parameters, and the micro hyperbaric oxygen chamber operating state parameters include: cabin pressure, oxygen concentration, carbon dioxide concentration, temperature and valve execution state; The physiological monitoring sensor is used to collect the physiological state parameters of the oxygen receiving object, and the physiological state parameters include: blood oxygen saturation, respiratory rate and pulse information; The original data set is generated by combining the micro hyperbaric oxygen chamber operating state parameters and the physiological state parameters.

[0008] The application further provides that the state estimation module comprises: According to the original data set, the time sequence is aligned according to the preset control period, and interpolation and down-sampling processing are performed; The processed data sequence is subjected to multi-scale filtering; Abnormal points are identified and removed by using statistical analysis and physical constraint comparison methods, and missing data is filled by using the adjacent effective data interpolation method; Based on the filled data sequence, joint state estimation is performed by using weighted fusion and recursive filtering methods to generate state parameters containing cabin operating parameters and physiological parameters of oxygen receiving objects, and uncertainty indexes of each sampling sensing channel.

[0009] The application further provides that the grade construction module comprises: a physiological load construction unit, a gas exchange efficiency evaluation unit, a dynamic coupling analysis unit and a comprehensive load index generation unit.

[0010] The application further provides that the physiological load construction unit comprises: The physiological parameters of the oxygen receiving object in the state parameter are continuously monitored and feature extracted; Through the use of sliding window statistical method, median and mean value calculation, trend line analysis and fluctuation amplitude statistical method in the preset historical time window, short-term baseline calculation, trend analysis and fluctuation amplitude evaluation are performed to identify the change trend and fluctuation characteristics of the physiological parameters; Based on the change trend and fluctuation characteristics, the physiological load index is constructed by using standardization processing and weighted synthesis method.

[0011] The application further provides that the gas exchange efficiency evaluation unit is used for: Characteristic analysis is performed on the oxygen concentration, carbon dioxide concentration and cabin pressure in the cabin operation state parameters, combined with the physiological parameters of the oxygen-receiving object in the characteristic state parameters, the initial gas exchange efficiency is obtained through trend analysis, proportional change evaluation and weighted fusion method, and integrated evaluation is performed; According to the channel uncertainty index, the evaluation result is corrected in reliability through a dynamic weighting or confidence adjustment method, and then the gas exchange efficiency index is formed.

[0012] The application further provides that the dynamic coupling analysis unit comprises: Based on the cabin operation parameters in the characteristic state parameters, the cabin environment parameter change sequence is obtained by using the time sequence arrangement method; Based on the physiological parameters of the oxygen-receiving object in the characteristic state parameters, the physiological response sequence of the oxygen-receiving object is obtained by a smoothing processing method; The cabin environment parameter change sequence and the physiological response sequence of the oxygen-receiving object are analyzed; According to the correlation analysis result and the channel uncertainty index, a dynamic coupling index is constructed by a weighted fusion method.

[0013] The application further provides that the comprehensive load index generation unit is used for: The physiological load index, the gas exchange efficiency index and the dynamic coupling index are normalized, the channel uncertainty index corresponding to each channel is taken as an adjustment factor, and data fusion is performed on each index; According to the data fusion result, a comprehensive oxygen metabolism load index is generated by using a fuzzy membership function rule and a preset grade threshold, and the oxygen metabolism load grade is divided according to the preset grade threshold.

[0014] The application further provides that the strategy adjustment module comprises an adjustment amount generation unit and an instruction generation unit; The adjustment amount generation unit comprises: When the oxygen metabolism load grade meets the preset adjustment trigger rule, the difference between the cabin operation parameters in the characteristic state parameters and the preset standard operation target is taken as an adjustment reference, and the comprehensive oxygen metabolism load index is taken as an adjustment factor, and the target adjustment amount is obtained by combining the adjustment reference.

[0015] The application further provides that the instruction generation unit comprises: The target adjustment amount is checked according to the preset minimum adjustment rate and maximum adjustment rate, the executability of the target adjustment amount under the current safety constraint is determined, and the adjustment instruction is generated when the check is passed.

[0016] The application provides a micro-high pressure oxygen cabin oxygen supply adjustment system based on artificial intelligence assistance, the system acquires micro-high pressure oxygen cabin operation state parameters and physiological state parameters of oxygen receiving objects through a data acquisition module to generate an original data set; a data processing module performs time sequence synchronization processing on the original data set to obtain state parameter indicators and channel uncertainty indicators; a grade construction module forms a comprehensive oxygen metabolism load index based on the state parameter indicators and the channel uncertainty indicators and divides oxygen metabolism load grades; and a strategy adjustment module makes oxygen supply adjustment decisions according to the oxygen metabolism load grades and the state parameter indicators, determines a target adjustment amount and generates adjustment instructions, which has the beneficial effects of: Improving state evaluation accuracy: through multi-dimensional processing such as time sequence alignment, abnormality elimination, multi-scale filtering and recursive fusion of multi-source physiological parameters and cabin environmental parameters, high-precision operation state estimation is realized, thereby reducing errors caused by sampling noise and channel uncertainty.

[0017] Realizing comprehensive evaluation of oxygen metabolism load: by constructing three types of indicators of physiological load, gas exchange efficiency and environmental-physiological dynamic coupling, and combining the comprehensive load index generated by the membership function and the grade threshold, the oxygen metabolism changes of the oxygen receiving object are more completely reflected, and accurate load grade division is realized.

[0018] Supporting intelligent oxygen supply adjustment decisions: the target adjustment amount is automatically generated according to the comprehensive oxygen metabolism load index and the operation parameter deviation, and the executable adjustment instructions are output within the safety constraints, realizing intelligent and personalized oxygen supply regulation of the micro-high pressure oxygen cabin, and improving oxygen supply efficiency and use safety.

[0019] The above description is only a summary of the technical solutions of the application, in order to more clearly understand the technical means of the application, the application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor. In the drawings: Figure 1 A structure schematic diagram of a micro-high pressure oxygen cabin oxygen supply adjustment system based on artificial intelligence assistance is shown for an exemplary embodiment of the application. DETAILED DESCRIPTION

[0021] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0022] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0023] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0024] Example: An AI-assisted oxygen supply regulation system for a micro hyperbaric oxygen chamber, such as Figure 1 As shown, it includes: Data acquisition module: Collects operational status parameters of the hyperbaric oxygen chamber and physiological status parameters of the oxygen recipients, and generates raw datasets; Data processing module: performs time-series synchronization processing on the original dataset to obtain state parameters and channel uncertainty indices; The classification module: Based on the uncertainty index of the characterizing state parameters and channels, after multi-level processing, a comprehensive oxygen metabolism load index is formed, and oxygen metabolism load levels are classified. Strategy adjustment module: Makes oxygen supply adjustment decisions based on oxygen metabolism load level and characterization state parameters, determines target adjustment amount and generates adjustment instructions.

[0025] The present invention is further configured such that the data acquisition module includes: Multidimensional environmental sensors are used to collect the operating status parameters of the micro hyperbaric oxygen chamber, which include: chamber pressure, oxygen concentration, carbon dioxide concentration, temperature, and valve operation status. Physiological state parameters of the oxygen-receiving object are collected using physiological monitoring sensors, including blood oxygen saturation, respiratory rate, and pulse information. The original data set is generated in combination with the operating state parameters and the physiological state parameters of the micro high-pressure oxygen cabin. The multi-group multi-dimensional environmental sensor nodes convert the original signals into digital quantities and transmit them to the processing terminal via the cabin body control bus. The physiological monitoring sensors are worn on the surface of the oxygen-receiving object, and the blood oxygen saturation, respiratory frequency and pulse wave signals are generated in real time through the photoelectric detection method and the respiratory waveform analysis method, and are transmitted to the processing terminal after preliminary filtering and artifact rejection in the local preset processing module. The processing terminal first performs validity verification on the two types of data, removes distorted data through signal amplitude threshold judgment, continuity check and abnormal jump identification, then performs timestamp calibration according to the data arrival time, and ensures that the environmental parameter sequence and the physiological parameter sequence are aligned on the same time axis. Subsequently, the aligned data is input into a unified data fusion process, the sampling gaps are supplemented through linear interpolation method, and the complete environmental and physiological information is ensured in each time window through sliding window method, so as to form a continuous original data set. The environmental parameters are analyzed according to the pressure change trend, gas concentration change speed and valve execution action in the fusion process, and the physiological data are analyzed according to the waveform form, cycle stability and response amplitude in the fusion process.

[0026] The state estimation module comprises: The original data set is aligned in time according to a preset control period, and interpolation and down-sampling processing are performed; The processed data sequence is subjected to multi-scale filtering; Abnormal points are identified and removed by using statistical analysis and physical constraint comparison methods, and missing data is supplemented by using adjacent valid data interpolation method; The state estimation module first extracts the environmental parameter and physiological parameter records of the same time period from the original data set according to the preset control period, realizes time alignment through timestamp comparison, compensates for the gaps caused by inconsistent sampling intervals by using linear interpolation method, and uses downsampling strategy to compress the signals with excessively high frequency into data sequences with uniform sampling rate according to the control period requirement. Then, the aligned data is input into the multi-scale filtering process, and the system selects smoothing filter, sliding mean filter and wavelet decomposition filter according to the change speed and noise characteristics of different parameters to extract slow varying trend and rapid disturbance characteristics, thereby forming data sequences with low noise and maintaining dynamic response characteristics. The filtered data enters the abnormality recognition step, the system calculates the short-term mean and change range of each data sequence using statistical analysis method, and combines the physical boundary conditions of the cabin operation law and physiological response to determine the mutation point, data drift and out-of-bound sampling. All the data points judged to be distorted are excluded, and the continuous supplementary segment is constructed using the normal data at both ends by using the adjacent effective data interpolation method. The data sequence after filling is input into the joint state estimation process, the system uses the coupling relationship between the environmental parameters and the physiological parameters to improve the estimation accuracy by weighted fusion, and then uses the recursive filtering method to update the continuous time sequence data step by step, so that each time the state value depends on the current sampling information and the state value at the last time. Finally, the state value is generated, which can completely represent the cabin operating pressure, gas concentration, temperature, valve action characteristics, and the oxygen saturation of the oxygen receiver, breathing frequency, and pulse dynamic change. At the same time, the module calculates the uncertainty index of each sampling channel according to the participation degree of multiple sampling channels in the process, the residual size before and after filtering, the proportion of the filled segment and the noise sensitivity, which is used to reflect the credibility of each channel in the current state estimation result.

[0027] The application is further configured to have the grade construction module comprising a physiological load construction unit, a gas exchange efficiency evaluation unit, a dynamic coupling analysis unit and a comprehensive load index generation unit. Specifically, the physiological load construction unit constructs a physiological load index by monitoring physiological state parameters of the oxygen-receiving object, analyzing the change trend and fluctuation thereof, and providing a basis for oxygen regulation decision-making to ensure that the oxygen supply meets physiological needs, wherein the physiological load index is used to reflect the current physiological load level of the oxygen-receiving object; the gas exchange efficiency evaluation unit is used to analyze parameters such as oxygen concentration, carbon dioxide concentration and cabin pressure in the cabin, and evaluate the gas exchange efficiency in combination with physiological reactions to ensure smooth gas exchange in the cabin and timely adjustment of the oxygen supply mode; the dynamic coupling analysis unit identifies the response mode between environmental regulation actions and physiological feedback by analyzing the correlation between the cabin environment and physiological parameters, thereby evaluating the effect of oxygen supply regulation and optimizing the regulation strategy; the comprehensive load index generation unit combines physiological load, gas exchange efficiency and dynamic coupling analysis results to generate a comprehensive oxygen metabolism load index through weighted fusion to provide real-time feedback and help optimize oxygen supply regulation decision-making, wherein the oxygen metabolism load index can reflect physiological load, gas exchange efficiency and dynamic coupling state, and also considers the reliability and uncertainty of the sensing channel.

[0028] The application is further configured to have the physiological load construction unit comprising: continuous monitoring and feature extraction of physiological parameters of the oxygen-receiving object in the state parameter representation; short-term baseline calculation, trend analysis and fluctuation amplitude evaluation are performed by using a sliding window statistical method, median and mean value calculation, trend line analysis and fluctuation amplitude statistical method within a preset historical time window to identify the change trend and fluctuation characteristics of the physiological parameters; Based on the change trend and fluctuation characteristics, a physiological load index is constructed through a standardization processing and a weighted synthesis method. Specifically, the system first acquires physiological parameters of the oxygen-receiving object from the state estimation module, which specifically include blood oxygen saturation, respiratory rate and pulse information, and simultaneously performs continuous monitoring feature extraction on these physiological parameters to obtain physiological response data in the form of time series. Subsequently, the system automatically applies a sliding window statistical method to the continuous physiological response data within a preset historical time window, establishes a short-term baseline by calculating the median value and the mean value in the window, identifies the data change trend by using a trend line analysis method, and evaluates the fluctuation characteristics of the physiological parameters by using a fluctuation amplitude statistical method, thereby obtaining the change rule and stability information of the physiological parameters. Finally, based on the trend and fluctuation characteristics, the physiological response data is subjected to standardization processing for each physiological parameter, the data of different dimensions and numerical ranges are mapped to a unified scale, and a weighted synthesis method is used to synthesize multiple physiological parameters into a physiological load index, wherein the weights of different parameters are set according to the preset physiological importance. In the whole process, the sliding window statistical method realizes short-term baseline estimation by using point-by-point sliding average and variance calculation, the trend line analysis uses least square method fitting, the fluctuation amplitude evaluation is realized by calculating the standard deviation or the maximum and minimum difference, and the weighted synthesis method uses the weighted average strategy. Through the above processing, the system automatically generates a physiological load index for reflecting the current physiological load level of the oxygen-receiving object.

[0029] The application further provides that the gas exchange efficiency evaluation unit is used for: Characteristic analysis is performed on the oxygen concentration, carbon dioxide concentration and cabin pressure in the cabin operation state parameters, and the physiological parameters of the oxygen-receiving object in the state parameters are combined to obtain an initial gas exchange efficiency through trend analysis, proportional change evaluation and weighted fusion method, and integrated evaluation is performed. According to the channel uncertainty index, the evaluation result is corrected in reliability by a dynamic weighting or confidence adjustment method, and then a gas exchange efficiency index is formed. Specifically, the system first acquires cabin operating state parameters, which specifically include: cabin oxygen concentration, carbon dioxide concentration and cabin pressure, and acquires physiological parameters of the oxygen receiving object from the state estimation module, which specifically include: blood oxygen saturation and respiratory rate. Then, the system performs feature analysis on the cabin operating parameters such as oxygen concentration, carbon dioxide concentration and pressure, specifically: extracting the change trend and relative proportional change information of the time series, which is used to reflect the dynamic state of the cabin gas environment. Subsequently, the cabin environment characteristics are associated with the physiological parameters of the oxygen receiving object, and the oxygen uptake and carbon dioxide discharge efficiency are preliminarily estimated through trend analysis and proportional change evaluation to form the initial gas exchange efficiency. The initial gas exchange efficiency is further combined with the uncertainty information of each channel, and the initial gas exchange efficiency is corrected by a dynamic weighting or confidence adjustment method. The weight of the channel with high uncertainty is reduced in the fusion process, thereby reducing the influence of abnormal or noise data. After the fusion is completed, the gas exchange efficiency index is generated. The corrected gas exchange efficiency index is used to accurately reflect the influence of the cabin environment change on the physiological state of the oxygen receiving object, while considering the data reliability and sensor channel stability. In the whole specific execution process, the feature analysis uses time series trend extraction and proportional calculation method, the initial evaluation uses weighted average and mapping analysis technology, and the dynamic weighting and confidence adjustment uses existing weighted fusion and confidence correction algorithm. Finally, continuous and reliable evaluation of the gas exchange efficiency is realized.

[0030] The application is further provided that the dynamic coupling analysis unit comprises: Based on the cabin operating parameters in the state parameters, the cabin environment parameter change sequence is obtained by using a time series arrangement method; Based on the physiological parameters of the oxygen receiving object in the state parameters, the physiological response sequence of the oxygen receiving object is obtained by a smoothing processing method; The cabin environment parameter change sequence and the physiological response sequence of the oxygen receiving object are associated and analyzed; According to the correlation analysis result and the channel uncertainty index, a dynamic coupling index is constructed by a weighted fusion method. Specifically, the system first acquires the state parameters from the state estimation module, including cabin operating parameters and physiological parameters of the oxygen-receiving object. First, based on the cabin operating parameters, a time series arrangement method is used to generate a cabin environment parameter change sequence, which mainly reflects the dynamic changes of parameters such as cabin pressure, oxygen concentration, carbon dioxide concentration and temperature with time. At the same time, based on the physiological parameters of the oxygen-receiving object, a smoothing processing method is used to generate a physiological response sequence. The smoothing processing of the physiological response sequence is mainly used to eliminate sampling noise and short-term fluctuations, so as to obtain more continuous and reliable physiological response information. Subsequently, the system performs correlation analysis on the cabin environment parameter change sequence and the physiological response sequence, and evaluates the influence degree of environmental change on physiological response by calculating the correlation, delay relationship and trend synchronicity between the parameters. On the basis of correlation analysis, combined with the uncertainty information of each sampling channel, the environment-physiology correlation data is integrated by a weighted fusion method. The channel with higher uncertainty corresponds to lower weight, which reduces the influence of abnormal data or noise on the analysis result, so as to generate a dynamic coupling index. In the whole process, the time series arrangement uses existing sequence rearrangement and interpolation method, the smoothing processing uses moving average or low-pass filtering technology, the correlation analysis uses correlation analysis and delay response evaluation algorithm, and the weighted fusion uses weighted average or confidence weighted method, so as to obtain a dynamic coupling index which can reflect the dynamic coupling relationship between the cabin environment change and the physiological response of the oxygen-receiving object, and realize accurate characterization of the dynamic change of oxygen metabolism load.

[0031] The application is further provided that the comprehensive load index generation unit is used for: The physiological load index, the gas exchange efficiency index and the dynamic coupling index are normalized, and the channel uncertainty index corresponding to each channel is used as an adjustment factor to fuse the data of each index. According to the data fusion result, the comprehensive oxygen metabolism load index is generated by using the fuzzy membership function rule and the preset grade threshold, and the oxygen metabolism load grade is divided according to the preset grade threshold. Specifically, the system first acquires the index data from the physiological load construction unit, the gas exchange efficiency evaluation unit and the dynamic coupling analysis unit, wherein the index data includes physiological load indexes, gas exchange efficiency indexes and environment-physiological coupling indexes, and the uncertainty information of each sampling channel is also acquired. Then, the three types of index data are normalized respectively, and the three types of index values are mapped to a unified dimension, so as to facilitate subsequent fusion. In the specific fusion process, the uncertainty information of each channel is taken as an adjustment factor to perform weighted processing on the normalized indexes, and the weight corresponding to the channel with higher uncertainty is lower, so as to reduce the influence of abnormal or noise data and realize the robust fusion of multiple source indexes, wherein the specific uncertainty index corresponds to different weights according to the specific numerical values of the preset weight corresponding table according to the look-up table method. After the fusion is completed, the fuzzy membership function rule is applied according to the fusion result to map the continuous numerical value to the membership degree of different oxygen metabolism load grades, and then the final comprehensive oxygen metabolism load index is determined according to the preset grade threshold, and the index is divided into the corresponding oxygen metabolism load grade, such as low load, medium load and high load. In the whole process, the normalization processing adopts the minimum-maximum mapping method, the multi-index fusion uses the weighted average method, and the membership function rule adopts the existing fuzzy logic algorithm to realize, so as to obtain the comprehensive oxygen metabolism load index which can reflect the physiological load, gas exchange efficiency and dynamic coupling state, and also consider the reliability and uncertainty of the sensing channel.

[0032] The application further provides that the policy adjustment module comprises an adjustment amount generation unit and an instruction generation unit. The adjustment amount generation unit comprises: When the oxygen metabolism load grade meets the preset adjustment trigger rule, the difference between the cabin operation parameter in the state parameter and the preset standard operation target is taken as an adjustment reference, and the comprehensive oxygen metabolism load index is taken as an adjustment factor to obtain a target adjustment amount in combination with the adjustment reference. Specifically, the adjustment amount generation unit is used to calculate the target amplitude of oxygen supply adjustment according to the deviation of the cabin operation parameter from the standard operation target and the comprehensive oxygen metabolism load index, so as to realize the quantitative response to the deviation degree of the cabin environment and the physiological load of the oxygen receiving object.

[0033] The instruction generation unit is used for safety check on the target adjustment amount output by the adjustment amount generation unit, including checking whether the adjustment rate and the cabin parameter are within the allowed range, and generating an adjustment instruction executable by the device after passing the check, to realize safe and accurate control of the oxygen concentration and pressure in the cabin. For the specific implementation process of the adjustment amount generation unit: the system continuously acquires the cabin operating parameters and the physiological parameters of the oxygen-receiving object, and simultaneously monitors the comprehensive oxygen metabolism load index, and determines whether to trigger oxygen supply adjustment through preset levels. When the load level reaches the triggering condition, the system first collects the cabin pressure, oxygen concentration, carbon dioxide concentration and valve state, and compares them with the pre-set standard operating target item by item, and obtains the adjustment reference through item-by-item difference evaluation. Then, the comprehensive oxygen metabolism load index is used as an adjustment factor to weight and adjust the adjustment reference, and a high load index corresponds to an amplified adjustment range, and a low load index corresponds to a reduced range, so as to generate a target adjustment amount.

[0034] The application further provides that the instruction generation unit comprises: According to the target adjustment amount, the preset minimum adjustment rate and the maximum adjustment rate are checked to determine the executability of the target adjustment amount under the current safety constraint, and the adjustment instruction is generated when the check passes. Specifically, for the specific implementation process of the instruction generation unit: after the target adjustment amount is generated, the system performs safety check in sequence, first calculates the adjustment rate between the current parameter and the adjusted parameter based on the target adjustment amount, then checks whether the adjustment speed is lower than the preset minimum adjustment rate or exceeds the preset maximum adjustment rate, and automatically adjusts to the allowed interval through the over-limit rule, and then evaluates whether the cabin pressure and oxygen concentration after adjustment exceed the safety boundary, and ensures that they are within the allowed range through adjustment. After the check passes, the system converts the target adjustment amount into a device executable instruction, and realizes accurate adjustment of the oxygen concentration and pressure in the cabin through control of the oxygen valve opening degree, oxygen adjustment and exhaust action. In the whole process, multi-dimensional sensor fusion technology is used for data acquisition, item-by-item difference analysis method is used for deviation calculation, weighted adjustment strategy is used for adjustment amount generation, safety check combines interval constraint and dynamic boundary check method, and instruction generation follows the device protocol format, so as to realize safe, intelligent and dynamic oxygen supply adjustment based on real-time cabin operating state and physiological response of the oxygen-receiving object.

[0035] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An artificial intelligence assisted micro-hyperbaric oxygen chamber oxygen supply adjustment system, characterized in that, The method comprises the following steps: a data acquisition module: collect the micro-high pressure oxygen cabin operating state parameters and the physiological state parameters of the oxygen receiving object, and generate an original data set; a data processing module: time sequence synchronization processing is performed on the original data set to obtain the state parameter and the channel uncertainty index; a grade construction module: based on the state parameter and the channel uncertainty index, a comprehensive oxygen metabolism load index is formed through multi-level processing, and the oxygen metabolism load grade is divided; a strategy adjustment module: according to the oxygen metabolism load grade and the state parameter, the oxygen supply adjustment decision is made, the target adjustment amount is determined, and the adjustment instruction is generated.

2. The micro-hyperbaric oxygen chamber oxygen supply adjustment system based on artificial intelligence assistance according to claim 1, characterized in that, The data acquisition module comprises: a multi-dimensional environmental sensing sensor is used to collect the micro-high pressure oxygen cabin operating state parameters, and the micro-high pressure oxygen cabin operating state parameters comprise: cabin pressure, oxygen concentration, carbon dioxide concentration, temperature and valve execution state; a physiological monitoring sensor is used to collect the physiological state parameters of the oxygen receiving object, and the physiological state parameters comprise: blood oxygen saturation, breathing frequency and pulse information; the micro-high pressure oxygen cabin operating state parameters and the physiological state parameters are combined to generate an original data set.

3. The micro-hyperbaric oxygen chamber oxygen supply adjustment system based on artificial intelligence assistance of claim 1, wherein, The state estimation module comprises: according to the original data set, time sequence alignment is performed according to the preset control period, and interpolation and down-sampling processing are performed; multi-scale filtering is performed on the processed data sequence; abnormal points are identified and removed by using statistical analysis and physical constraint comparison methods, and missing data is filled by using the adjacent effective data interpolation method; based on the filled data sequence, joint state estimation is performed by using the weighted fusion and recursive filtering method, to generate the state parameter comprising the cabin operating parameter and the physiological parameter of the oxygen receiving object, and the uncertainty index of each sampling sensing channel.

4. The micro-hyperbaric oxygen chamber oxygen supply adjustment system based on artificial intelligence assistance of claim 1, wherein, The grade construction module comprises: a physiological load construction unit, a gas exchange efficiency evaluation unit, a dynamic coupling analysis unit and a comprehensive load index generation unit.

5. The micro-hyperbaric oxygen chamber oxygen supply adjustment system based on artificial intelligence assistance according to claim 4, characterized in that, The physiological load construction unit comprises: continuous monitoring feature extraction is performed on the physiological parameters of the oxygen receiving object in the state parameter; short-term baseline calculation, trend analysis and fluctuation amplitude evaluation are performed by using the sliding window statistical method, median value and average value calculation, trend line analysis and fluctuation amplitude statistical method in the preset historical time window, to identify the change trend and fluctuation characteristics of the physiological parameters; based on the change trend and fluctuation characteristics, the physiological load index is constructed by using the standardization processing and weighted synthesis method.

6. The micro-hyperbaric oxygen chamber oxygen supply adjustment system based on artificial intelligence assistance of claim 4, characterized in that, The gas exchange efficiency evaluation unit is used for: feature analysis is performed on the oxygen concentration, carbon dioxide concentration and cabin pressure in the cabin operating state parameter, combined with the physiological parameters of the oxygen receiving object in the state parameter, the initial gas exchange efficiency is obtained by using the trend analysis, proportional change evaluation and weighted fusion method, and integrated evaluation is performed; according to the channel uncertainty index, the evaluation result is corrected by using the dynamic weighting or confidence adjustment method, and then the gas exchange efficiency index is formed.

7. The micro-hyperbaric oxygen chamber oxygen supply adjustment system based on artificial intelligence assistance according to claim 4, characterized in that, The dynamic coupling analysis unit comprises: based on the cabin operating parameter in the state parameter, the cabin environment parameter change sequence is obtained by using the time sequence arrangement method; based on the physiological parameters of the oxygen receiving object in the state parameter, the physiological response sequence of the oxygen receiving object is obtained by using the smoothing processing method; The cabin environmental parameter change sequence and the physiological response sequence of the oxygen-receiving object are analyzed in association; According to the association analysis result and the channel uncertainty index, a dynamic coupling index is constructed by a weighted fusion method.

8. The micro-hyperbaric oxygen chamber oxygen supply adjustment system based on artificial intelligence assistance of claim 4, characterized in that, The comprehensive load index generation unit comprises: The physiological load index, the gas exchange efficiency index and the dynamic coupling index are normalized, and the channel uncertainty index corresponding to each channel is taken as an adjustment factor to perform data fusion on each index; According to the data fusion result, a comprehensive oxygen metabolism load index is generated by using a fuzzy membership function rule and a preset grade threshold, and the oxygen metabolism load grade is divided according to the preset grade threshold.

9. The micro-hyperbaric oxygen chamber oxygen supply adjustment system based on artificial intelligence assistance of claim 1, wherein, The strategy adjustment module comprises an adjustment amount generation unit and an instruction generation unit. The adjustment amount generation unit comprises: When the oxygen metabolism load grade meets a preset adjustment trigger rule, a difference between the cabin operation parameter in the state parameter and a preset standard operation target is taken as an adjustment reference, and the comprehensive oxygen metabolism load index is taken as an adjustment factor to obtain a target adjustment amount in combination with the adjustment reference.

10. The micro-hyperbaric oxygen chamber oxygen supply adjustment system based on artificial intelligence assistance of claim 9, wherein, The instruction generation unit comprises: The target adjustment amount is checked according to a preset minimum adjustment rate and a maximum adjustment rate to determine the executability of the target adjustment amount under the current safety constraint, and an adjustment instruction is generated when the checking is passed.

Images