Oxygen supply pressure dynamic adjusting system based on medical oxygen cabin

Abstract

The invention relates to the technical field of oxygen supply pressure dynamic adjustment. The invention relates to an oxygen supply pressure dynamic adjusting system based on a medical oxygen cabin. The system comprises a data acquisition unit, a reference setting unit, a prediction physiological analysis unit, a dynamic updating unit and an auxiliary pressure adjusting unit. The data acquisition unit is used for acquiring real-time physiological data and individual health records of a user and synchronously acquiring historical oxygen supply records; the reference setting unit integrates historical oxygen supply records and industry health data, establishes a health big data sharing platform, screens adaptive oxygen supply reference data on the health big data sharing platform in combination with individual health records, and sets target physiological data and oxygen cabin pressure parameters in combination with the oxygen supply reference data; through the synergistic effect of multi-dimensional data deep fusion, pre-judgment type dynamic accurate adjustment and whole-process safety guarantee design, the effect of comprehensively improving scientificity, adaptability and safety of medical oxygen cabin oxygen supply pressure adjustment is achieved.

Description

Technical Field

[0001] This invention relates to the field of dynamic oxygen supply pressure regulation technology, and more specifically, to a dynamic oxygen supply pressure regulation system based on a medical oxygen chamber. Background Technology

[0002] As a key device for treating hypoxic diseases and assisting rehabilitation, the precise adjustment of the oxygen supply pressure of a medical oxygen chamber is directly related to the effect of oxygen therapy and patient safety. Its core function is to provide patients with an oxygen supply that meets their basic treatment needs by setting fixed or phased oxygen chamber pressure parameters. Currently, oxygen supply pressure regulation mainly relies on fixed scenarios combined with empirical parameter settings. For example, a single and fixed pressure value is set for patients with the same condition based on the past experience of medical staff. During treatment, parameters are only passively adjusted when the patient's physiological data shows significant abnormalities. This results in a lack of individualized parameter settings, leading to one-sided regulation and difficulty in adapting to the physiological characteristics and treatment needs of different patients. Furthermore, the passive and delayed adjustment method cannot predict the trend of changes in the patient's physiological data in advance. Adjustments are often initiated only after physiological indicators deviate from the target range, which may delay the optimal adjustment time and even cause risks such as excessive fluctuations in blood oxygen and adverse reactions, affecting the oxygen therapy effect and patient safety. To reduce this situation, a dynamic oxygen supply pressure regulation system based on a medical oxygen chamber is proposed. Summary of the Invention

[0003] The purpose of this invention is to provide a dynamic oxygen supply pressure regulation system based on a medical oxygen chamber to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, a dynamic oxygen supply pressure regulation system based on a medical oxygen chamber is provided, including a data acquisition unit, a reference setting unit, a predictive physiological analysis unit, a dynamic update unit, and an auxiliary pressure regulation unit. The data acquisition unit is used to collect users’ real-time physiological data and individual health records, and simultaneously acquire historical oxygen supply records. The reference setting unit integrates historical oxygen supply records and industry health data to establish a health big data sharing platform. At the same time, it combines individual health records to select suitable oxygen supply reference data on the health big data sharing platform and sets target physiological data and oxygen chamber pressure parameters based on the oxygen supply reference data. The predictive physiological analysis unit is used to compare real-time physiological data and target physiological data to extract deviation data, and at the same time, it combines the trend analysis of deviation data curves to predict physiological data, and divides the predicted physiological data into correction nodes according to data fluctuations. The dynamic update unit combines the predicted physiological data, target physiological data and oxygen chamber pressure parameters of each correction node to match the corresponding correction pressure parameters, and substitutes the correction pressure parameters into the predicted physiological data in chronological order to dynamically update the correction nodes. The auxiliary pressure regulation unit inputs the corresponding correction pressure parameters based on the correction node and deviation data. After inputting the parameters, it compares the deviation data of real-time physiological data with the predicted physiological data of the same period. Based on the comparison results, it selects the appropriate correction node and corresponding correction pressure parameters across the time dimension to regulate the oxygen chamber pressure.

[0005] Preferably, the data acquisition unit establishes an intelligent control module within the medical oxygen chamber, which manages the data transmission of physiological monitoring sensors and oxygen supply equipment within the oxygen chamber, while simultaneously collecting the user's individual health records and historical oxygen supply data from the patient information management terminal. The physiological monitoring sensor is used to collect real-time physiological data.

[0006] Preferably, the reference setting unit includes a platform establishment module and an oxygen supply setting module; The platform establishment module is used to acquire industry health data, then integrate historical oxygen supply records and industry health data to establish a health big data sharing platform. At the same time, reference conditions are set, and oxygen supply reference data that meets the reference conditions is screened on the health big data sharing platform based on the reference conditions and individual health records. The oxygen supply reference module is used to set target physiological data and oxygen chamber pressure parameters by combining oxygen supply reference data.

[0007] Preferably, in the process of setting reference conditions, the reference setting unit can set the reference conditions as a similarity matching threshold and a quantity threshold, and at the same time calculate the similarity based on the user's individual health record and the historical oxygen supply records of the health big data sharing platform belonging to the user's individual health record; Based on the similarity matching threshold, only oxygen supply reference data that meets the similarity matching threshold will be retained in the health big data platform; Based on the quantity threshold, only oxygen supply reference data whose similarity ranking falls within the quantity threshold range will be retained in the health big data platform. The oxygen supply reference data includes the individual health records of the user and the corresponding historical oxygen supply records.

[0008] Preferably, when the reference setting unit sets the target physiological data and oxygen chamber pressure parameters, it evaluates the treatment effect on the user by combining the oxygen supply reference data, selects the physiological data corresponding to the oxygen supply reference data with the best treatment effect as the target physiological data, and then matches the pressure parameters by combining the individual health data with the target physiological data to obtain the oxygen chamber pressure parameters, thus providing a basis for subsequent input and correction of pressure parameters.

[0009] Preferably, the predictive physiological analysis unit includes a deviation extraction module and a correction node division module; The deviation extraction module is used to divide healthy nodes based on the fluctuation of real-time physiological data, compare the real-time physiological data of each healthy node with the target physiological data to extract deviation data, and obtain the deviation data corresponding to each healthy node. The correction node division module is used to sort the deviation data according to the recording time corresponding to the health node, and then combine the sorted deviation data with oxygen supply reference data to establish a physiological prediction model. The physiological prediction model curve trend analysis is used to predict physiological data, obtain the user's predicted physiological data, and then divide the predicted physiological data into correction nodes according to the data fluctuation.

[0010] Preferably, the dynamic update unit includes a parameter matching module and a node update module; The parameter matching module is used to analyze the correction pressure parameters by combining the predicted physiological data of each correction node with the target physiological data, using the oxygen chamber pressure parameters as the basic parameters, and to obtain the correction pressure parameters corresponding to each correction node. By supplementing and correcting the pressure parameters of the oxygen chamber, the predicted physiological data can be adjusted to the target physiological data. The node update module is used to substitute the correction pressure parameters into the predicted physiological data according to the time sequence, and then return them to the physiological prediction model. The physiological prediction model then outputs the predicted physiological data again, thus completing the dynamic update of the correction node.

[0011] Preferably, the auxiliary pressure regulating unit includes a parameter input module and an update regulating module; The parameter input module is set to determine the deviation threshold for parameter input. The deviation data is compared and analyzed with the deviation threshold. When the deviation data is less than the deviation threshold, no correction pressure parameter is input. Conversely, when the deviation data is greater than the deviation threshold, the correction pressure parameter is input according to the correction node of the corresponding time period. The update adjustment module is used to compare the deviation data of real-time physiological data with the deviation data of predicted physiological data in the same period after the parameters are input into the parameter input module. If the deviation data of real-time physiological data is greater than the deviation data of predicted physiological data in the same period, the correction pressure parameters for subsequent prediction times are reselected based on the deviation data of real-time physiological data, and the pressure is adjusted by the reselected correction pressure parameters. At the same time, the subsequent correction nodes are adjusted according to the selected correction pressure parameters. Conversely, if the deviation data of real-time physiological data is less than the deviation data of predicted physiological data in the same period, monitoring is maintained.

[0012] Preferably, when the update adjustment module reselects the correction node and correction pressure parameter in subsequent prediction times, it prioritizes selecting the correction pressure parameter closest to the real time. Simultaneously, based on the selected calibration pressure parameters, the corresponding calibration node is determined, and then this node is taken as the latest calibration node. Its time distance is then compared with the time distance of all calibration nodes, and only calibration nodes whose time distance is greater than the time distance of the latest calibration node are retained. The time distance is the difference between the real-time time and the corresponding predicted time of the correction node.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This dynamic oxygen supply pressure regulation system based on a medical oxygen chamber achieves a comprehensive improvement in the scientific nature, adaptability, and safety of oxygen supply pressure regulation through the synergistic effect of deep integration of multi-dimensional data, predictive dynamic precision regulation, and full-process safety assurance design.

[0014] 2. In this dynamic oxygen supply pressure regulation system based on a medical oxygen chamber, the data acquisition unit integrates real-time physiological data, individual health records, and historical oxygen supply records. Combined with the reference setting unit, it links industry health data to build a shared platform and selects suitable reference data to solve the problem of the one-sidedness of single data. This lays a solid scientific data foundation for regulation. Then, the predictive physiological analysis unit divides health nodes and correction nodes, builds a physiological prediction model to predict data trends, and the dynamic update unit matches exclusive correction pressure parameters for each correction node, forming a closed loop of "parameter input - model feedback - node update". This breaks through the limitations of traditional passive regulation and achieves precise and node-based dynamic adaptation of pressure parameters.

[0015] 2. In this dynamic oxygen supply pressure regulation system based on a medical oxygen chamber, the auxiliary pressure regulation unit inputs parameters as needed according to the deviation threshold. The regulation effect is evaluated by comparing real-time data and predicted data, and the parameters are optimized across time dimensions. At the same time, data is screened from three dimensions of clinical effectiveness, safety, and adaptability during the reference setting stage. Personalized correction coefficients are introduced during the parameter calculation stage. The entire process takes into account both treatment effect and individual tolerance, and ultimately achieves the comprehensive effect of improving the accuracy, adaptability, and safety of oxygen therapy and optimizing the user's treatment experience. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the overall structure of a dynamic oxygen supply pressure regulation system based on a medical oxygen chamber according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figure 1 As shown, the purpose of this embodiment is to provide a dynamic oxygen supply pressure regulation system based on a medical oxygen chamber, including a data acquisition unit, a reference setting unit, a predictive physiological analysis unit, a dynamic update unit, and an auxiliary pressure regulation unit. The data acquisition unit is used to collect users' real-time physiological data and individual health records, and simultaneously obtain historical oxygen supply records; By integrating three core data types—real-time physiological data, health records, and historical oxygen supply records—it solves the problem of one-sided regulation caused by insufficient data dimensions. At the same time, through the intelligent control module, it realizes multi-device data transmission management, ensuring the real-time, complete, and accurate data collection, and laying a solid data foundation for all subsequent analysis stages. The data acquisition unit establishes an intelligent control module within the medical oxygen chamber. This module manages the data transmission of physiological monitoring sensors and oxygen supply equipment within the chamber. Simultaneously, it collects individual health records (such as medical history, allergy history, and basic physical indicators) and historical oxygen supply data (such as pressure parameters, duration, and physiological data changes from previous oxygen therapies) from the patient information management terminal. Physiological monitoring sensors are used to collect real-time physiological data (such as blood oxygen, heart rate, respiratory rate, etc.).

[0019] The reference setting unit integrates historical oxygen supply records and industry health data to establish a health big data sharing platform. At the same time, it combines individual health records to select suitable oxygen supply reference data on the health big data sharing platform, and sets target physiological data and oxygen chamber pressure parameters based on the oxygen supply reference data. By leveraging a health big data sharing platform and dual threshold screening, we can accurately match the oxygen supply reference data of suitable users, improve the individual adaptability of target physiological data and initial pressure parameters, and use the best treatment effect as the core screening criterion to ensure that the set targets and parameters have clinical effectiveness, providing scientific guidance for subsequent pressure regulation. The reference setting unit includes a platform establishment module and an oxygen supply setting module; The platform establishes a module to acquire industry health data, then integrates historical oxygen supply records and industry health data to establish a health big data sharing platform. At the same time, reference conditions are set, and oxygen supply reference data that meets the reference conditions is filtered on the health big data sharing platform based on the reference conditions and individual health records. This involves collecting general health data through medical industry databases, authoritative medical guidelines, and clinical research literature. This includes the normal physiological index ranges for different populations (such as blood oxygen saturation and standard heart rate ranges) and standard parameters for oxygen therapy corresponding to various diseases (such as pressure range and recommended treatment duration). At the same time, the collected industry health data is structured and integrated with the historical oxygen supply records accumulated by the system (including basic user information, oxygen chamber pressure parameters during treatment, corresponding physiological data changes, and treatment effect evaluations) to establish a health big data sharing platform, enabling the classified storage, unified management, and efficient retrieval of data.

[0020] In setting reference conditions, the reference setting unit can set similarity matching thresholds and quantity thresholds. Simultaneously, it calculates similarity based on the user's individual health record and historical oxygen supply records belonging to the user's individual health record on the health big data sharing platform. The specific steps are as follows: Key features are extracted from the current user's individual health record and compared with the user's health record associated with historical oxygen supply records in the health big data sharing platform. The similarity is calculated to obtain the similarity between the user who needs oxygen supply analysis and other users in the past. Then, one of the following two methods is selected for screening to finally obtain oxygen supply reference data that meets the reference conditions. Key characteristics include age, medical history, basic physiological indicators, and previous oxygen therapy responses. Based on the similarity matching threshold (e.g., 80%, used to limit the lower limit of similarity with the current user's health record), only oxygen supply reference data that meets the similarity matching threshold will be retained in the health big data platform; Based on the quantity threshold (e.g., 50 records, used to limit the maximum number of reference data to be selected, to avoid the data volume being too large and affecting the analysis efficiency), only oxygen supply reference data whose similarity ranking is within the quantity threshold range will be retained in the health big data platform. The oxygen supply reference data includes the individual health records of the user and the corresponding historical oxygen supply records.

[0021] The oxygen supply reference module is used to set target physiological data and oxygen chamber pressure parameters by combining oxygen supply reference data.

[0022] When setting target physiological data and oxygen chamber pressure parameters using the reference setting unit, the treatment effect is evaluated by combining oxygen supply reference data with the target physiological data. The physiological data corresponding to the oxygen supply reference data with the best treatment effect is selected as the target physiological data. Then, the pressure parameters are matched by combining individual health data with the target physiological data to obtain the oxygen chamber pressure parameters. This provides a basis for subsequent input and correction of pressure parameters. The specific steps are as follows: First, from the selected oxygen supply reference data, the user's physiological data, oxygen chamber pressure parameters and treatment effect evaluation results corresponding to each data point are extracted. For each oxygen supply reference data point, the evaluation is carried out from three dimensions: clinical effectiveness, safety and adaptability. The treatment effect of each data point is quantified by comprehensive scoring. User physiological data includes blood oxygen saturation and heart rate change curves during treatment; Oxygen chamber pressure parameters include the pressure value during treatment and the frequency of pressure adjustment; The evaluation results of treatment effectiveness include the degree of symptom relief and the speed of recovery of physiological indicators; The clinical effectiveness score is based on the degree to which physiological indicators have recovered to a healthy range, scored on a scale of 0-10. For example, 10 points are awarded for complete recovery of physiological indicators, and partial recovery is scored according to the recovery ratio. The safety score is based on the incidence and severity of adverse reactions, scored on a scale of 0-10. 10 points are awarded for no adverse reactions, and the more severe and higher the incidence of adverse reactions, the lower the score. The adaptability score is based on the similarity to the current user's health record, scored on a scale of 0-10. The higher the similarity, the higher the score. Then, medical experts or managers pre-set the weights of the importance of clinical effectiveness, safety, and adaptability to the treatment effect, so that the sum of the three weights is 1. Finally, the scores of each dimension are multiplied by the corresponding weight coefficient and then summed to obtain the comprehensive treatment effect score for each oxygen supply reference data. Next, the oxygen supply reference data with the highest treatment effect score was selected, and the stable physiological data achieved by the user after treatment (such as blood oxygen saturation of 98% and heart rate of 70 beats / minute) was extracted from this data. This data was determined as the target physiological data for the current user and served as the ideal physiological state benchmark for subsequent treatment. Combining the current user's individual health data with the determined target physiological data, and referring to the correspondence between pressure parameters and physiological data in the selected high-quality oxygen supply reference data, the initial oxygen chamber pressure parameters (such as pressure value and initial pressure maintenance duration) suitable for the current user to achieve the target physiological data were matched through medical expert experience models or historical data fitting. These parameters served as the basis for subsequent pressure adjustment. The process involves extracting pressure parameters from the reference data showing the best treatment effect, determining an individual health difference correction coefficient (based on the difference between the current user's and the reference data user's health records; for example, a correction coefficient of 0.2 for every 10-year age difference), obtaining the quantitative values ​​of the current user's individual health characteristics and those of the corresponding user in the reference data, calculating the difference between the two and multiplying it by the individual health difference correction coefficient to obtain the individual health difference correction value, then determining the target physiological data difference correction coefficient based on the difference between the current target and the reference data target (for example, an increase of 0.1 for every 1% difference in blood oxygen target), simultaneously obtaining the quantitative values ​​of the current user's and the corresponding user's target physiological data, calculating the difference between the two and multiplying it by the target physiological data difference correction coefficient to obtain the target physiological data difference correction value, and finally adding the pressure parameters from the reference data, the individual health difference correction value, and the target physiological data difference correction value to obtain the initial oxygen chamber pressure parameters matched for the current user.

[0023] The predictive physiological analysis unit is used to compare real-time physiological data and target physiological data to extract deviation data. At the same time, it combines the trend analysis of deviation data curves to predict physiological data and divides the predicted physiological data into correction nodes according to data fluctuations. By dividing health nodes and extracting deviations, the difference between real-time data and target data can be accurately located, avoiding the omission of details caused by overall data comparison. Physiological data trends can be predicted in advance and correction nodes can be divided to achieve predictive adjustment, avoid passively responding to data fluctuations, and improve the foresight of adjustment. The predictive physiological analysis unit includes a deviation extraction module and a correction node division module; The deviation extraction module is used to divide healthy nodes based on the fluctuation of real-time physiological data, compare the real-time physiological data of each healthy node with the target physiological data to extract deviation data, and obtain the deviation data corresponding to each healthy node. By analyzing the fluctuation characteristics of real-time physiological data (such as the fluctuation amplitude and frequency of blood oxygen and heart rate), the relatively stable period of physiological state is divided into different health nodes. Each node corresponds to a continuous segment of real-time physiological data. For each health node, the real-time physiological data in that node is compared with the target physiological data one by one, and the difference between the two is calculated to obtain the deviation data corresponding to each health node.

[0024] The calibration node partitioning module sorts the deviation data according to the recording time corresponding to the health node, then combines the sorted deviation data with oxygen supply reference data to build a physiological prediction model. The physiological prediction model's curve trend analysis predicts physiological data, obtaining the user's predicted physiological data. Finally, the predicted physiological data is partitioned into calibration nodes based on data fluctuations. The specific steps are as follows: According to the chronological order of the records corresponding to the health nodes, the deviation data of each node are sorted to form a deviation dataset arranged in time series. The sorted deviation data is combined with oxygen supply reference data (including historical physiological data, pressure parameters, treatment effects, etc.) and a physiological prediction model is constructed using an LSTM neural network to simulate the changing trend of physiological data with time and pressure parameters. Then, using the established physiological prediction model, the curve trend analysis of physiological data in future periods is performed to output the user's predicted physiological data. After that, the fluctuation of the predicted physiological data is analyzed, and the time periods when the data fluctuation exceeds the preset threshold (such as the predicted blood oxygen fluctuation amplitude ≥2%) are divided into correction nodes to determine the time anchor point for subsequent pressure adjustment.

[0025] The dynamic update unit combines the predicted physiological data, target physiological data and oxygen chamber pressure parameters of each calibration node to match the corresponding calibration pressure parameters, and substitutes the calibration pressure parameters into the predicted physiological data in chronological order to dynamically update the calibration nodes. Each calibration node is matched with a dedicated calibration pressure parameter to achieve precise node-based optimization, avoiding the rigidity of using a single parameter throughout the entire process. At the same time, through the closed loop of parameter input to model feedback and then to data update, the prediction data and calibration nodes are continuously optimized to ensure dynamic adaptation of parameters to the user's physiological state. The dynamic update unit includes a parameter matching module and a node update module; The parameter matching module uses oxygen chamber pressure parameters as the basic parameters, combines the predicted physiological data of each calibration node with the target physiological data to perform calibration pressure parameter analysis, and obtains the calibration pressure parameters corresponding to each calibration node. The specific steps are as follows: The initial oxygen chamber pressure parameters were determined as the basis for analysis. At the same time, the predicted physiological data and the preset target physiological data corresponding to each calibration node were extracted and organized into data pairs (prediction and target) for each calibration node. Then, for each calibration node, the difference between the predicted physiological data and the target physiological data of that node was analyzed to determine the pressure adjustment range. When the predicted physiological data is lower than the target physiological data (such as low blood oxygen), calculate the pressure value that needs to be increased; When the predicted physiological data is higher than the target physiological data (such as high blood oxygen), the pressure value that needs to be reduced is calculated, and finally the correction pressure parameter for each correction node is obtained. By supplementing and correcting the pressure parameters of the oxygen chamber, the predicted physiological data can be adjusted to the target physiological data. The node update module is used to substitute the correction pressure parameters into the predicted physiological data according to the time sequence, and then return them to the physiological prediction model. The physiological prediction model then re-outputs the predicted physiological data, completing the dynamic update of the correction nodes. The specific steps are as follows: According to the time sequence of the calibration nodes, the corresponding calibration pressure parameters are successively substituted into the predicted physiological data of each node, and the predicted physiological data of each time point is updated to be consistent with the target data, forming a data combination sorted by time (corrected predicted data and calibration pressure parameters). Then, the time-sorted data combination is re-inputted into the physiological prediction model. Based on the new pressure parameters and the corrected data, the model recalculates and outputs the predicted physiological data for future periods. According to the fluctuation of the new predicted data, the calibration nodes are re-divided or adjusted to complete the dynamic update of the calibration nodes.

[0026] The auxiliary pressure regulation unit inputs the corresponding correction pressure parameters based on the correction node and deviation data. After inputting the parameters, it compares the deviation data of real-time physiological data with the predicted physiological data of the same period. Based on the comparison results, it selects the appropriate correction node and corresponding correction pressure parameters across the time dimension to regulate the oxygen chamber pressure.

[0027] Setting deviation thresholds enables on-demand adjustment, avoiding meaningless frequent adjustments, improving adjustment stability and user experience. Furthermore, it optimizes parameter selection across time dimensions and dynamically adjusts based on real-time data feedback, ensuring both timely adjustment and avoiding redundant parameter interference through node filtering, thereby improving adjustment efficiency and safety. The auxiliary pressure regulation unit includes a parameter input module and an update regulation module; The parameter input module is set to determine the deviation threshold for parameter input. The deviation data is compared and analyzed with the deviation threshold. If the deviation data is less than the deviation threshold, the correction pressure parameter is not input. Conversely, if the deviation data is greater than the deviation threshold, the correction pressure parameter is input according to the correction node of the corresponding time period. The parameter is then input into the oxygen supply equipment of the oxygen chamber to adjust the oxygen supply pressure of the oxygen chamber. The update adjustment module is used to compare the deviation data of real-time physiological data with the predicted physiological data of the same period after the parameters are input into the parameter input module. By inputting the correction pressure parameter, the module synchronously collects real-time physiological data and predicted physiological data of the same period, calculates the deviation data between the two, and analyzes the degree of difference between the actual physiological state and the predicted state. If the deviation of real-time physiological data is greater than the deviation of predicted physiological data for the same period, it indicates that the current parameter adjustment effect has not met expectations. Therefore, based on the deviation of real-time physiological data, a new correction pressure parameter is selected from the correction pressure parameters for subsequent prediction times, and pressure adjustment is performed using the newly selected correction pressure parameter. At the same time, subsequent correction nodes are adjusted according to the selected correction pressure parameter. Conversely, if the deviation of real-time physiological data is less than the deviation of predicted physiological data during the same period, monitoring should continue, indicating that the current parameters are well-suited and there is no need to reselect parameters. When the update adjustment module reselects the correction node and correction pressure parameter in subsequent prediction times, it prioritizes the correction pressure parameter that is closest to the real time. Simultaneously, based on the selected calibration pressure parameters, the corresponding calibration node is determined, and then this node is taken as the latest calibration node. Its time distance is then compared with the time distance of all calibration nodes, and only calibration nodes whose time distance is greater than the time distance of the latest calibration node are retained. By adjusting the time distribution of subsequent correction nodes according to the correction nodes corresponding to the new parameters, it is ensured that subsequent adjustments can continuously adapt to changes in the user's physiological state. The time distance is the difference between the real-time time and the prediction time corresponding to the correction node, where the system operation formula is as follows: ; Among them, P implement The final output oxygen supply pressure parameters to the oxygen chamber are defined by P0, where P0 is the initial oxygen chamber pressure parameter, n is the total number of calibration nodes after dynamic updates, and K is the final output oxygen supply pressure parameter. j Let T be the pressure-physiological data response coefficient for the j-th calibration node, and T be the target physiological data. For the predicted physiological data of the j-th correction node, Priority(P) j ) represents the selection priority of the correction pressure parameter corresponding to the j-th correction node. A larger value indicates a higher priority, ensuring that near-real-time node parameters are selected first. D real D represents the absolute value of the deviation between real-time physiological data and predicted physiological data from the same period. threshodl This is a preset deviation threshold used to determine whether a correction pressure parameter needs to be input. ; Among them, R realReal-time physiological data of users collected by physiological monitoring sensors. To predict physiological data; ; Among them, t rael t represents the real-time time for pressure regulation. j The prediction time corresponding to the j-th correction node; Each unit forms a closed loop through a progressive logic of data support, goal setting, predictive analysis, parameter updates, and execution adjustment. This not only ensures the accuracy and dynamic adaptability of pressure regulation, but also improves the system's ability to adapt to individual user differences and the safety of treatment.

[0028] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A dynamic oxygen supply pressure regulation system based on a medical oxygen chamber, characterized in that: It includes a data acquisition unit, a reference setting unit, a predictive physiological analysis unit, a dynamic update unit, and an auxiliary pressure regulation unit; The data acquisition unit is used to collect users’ real-time physiological data and individual health records, and simultaneously acquire historical oxygen supply records. The reference setting unit integrates historical oxygen supply records and industry health data to establish a health big data sharing platform. At the same time, it combines individual health records to select suitable oxygen supply reference data on the health big data sharing platform and sets target physiological data and oxygen chamber pressure parameters based on the oxygen supply reference data. The predictive physiological analysis unit is used to compare real-time physiological data and target physiological data to extract deviation data, and at the same time, it combines the trend analysis of deviation data curves to predict physiological data, and divides the predicted physiological data into correction nodes according to data fluctuations. The dynamic update unit combines the predicted physiological data, target physiological data and oxygen chamber pressure parameters of each correction node to match the corresponding correction pressure parameters, and substitutes the correction pressure parameters into the predicted physiological data in chronological order to dynamically update the correction nodes. The auxiliary pressure regulation unit inputs the corresponding correction pressure parameters based on the correction node and deviation data. After inputting the parameters, it compares the deviation data of real-time physiological data with the predicted physiological data of the same period. Based on the comparison results, it selects the appropriate correction node and corresponding correction pressure parameters across the time dimension to regulate the oxygen chamber pressure.

2. The oxygen supply pressure dynamic adjustment system based on a medical oxygen chamber according to claim 1, characterized in that: The data acquisition unit establishes an intelligent control module within the medical oxygen chamber. This module manages the data transmission of physiological monitoring sensors and oxygen supply equipment within the oxygen chamber, while simultaneously collecting individual health records and historical oxygen supply data from users to the patient information management terminal. The physiological monitoring sensor is used to collect real-time physiological data.

3. The oxygen supply pressure dynamic adjustment system based on a medical oxygen chamber according to claim 1, characterized in that: The reference setting unit includes a platform establishment module and an oxygen supply setting module; The platform establishment module is used to acquire industry health data, then integrate historical oxygen supply records and industry health data to establish a health big data sharing platform. At the same time, reference conditions are set, and oxygen supply reference data that meets the reference conditions is screened on the health big data sharing platform based on the reference conditions and individual health records. The oxygen supply reference module is used to set target physiological data and oxygen chamber pressure parameters by combining oxygen supply reference data.

4. The oxygen supply pressure dynamic adjustment system based on a medical oxygen chamber according to claim 1, characterized in that: In the process of setting reference conditions, the reference setting unit can set the reference conditions as a similarity matching threshold and a quantity threshold, and at the same time calculate the similarity based on the user's individual health record and the historical oxygen supply records of the health big data sharing platform belonging to the user's individual health record. Based on the similarity matching threshold, only oxygen supply reference data that meets the similarity matching threshold will be retained in the health big data platform; Based on the quantity threshold, only oxygen supply reference data whose similarity ranking falls within the quantity threshold range will be retained in the health big data platform. The oxygen supply reference data includes the individual health records of the user and the corresponding historical oxygen supply records.

5. The oxygen supply pressure dynamic adjustment system based on a medical oxygen chamber according to claim 1, characterized in that: When the reference setting unit sets the target physiological data and oxygen chamber pressure parameters, it evaluates the treatment effect on the user by combining the oxygen supply reference data, selects the physiological data corresponding to the oxygen supply reference data with the best treatment effect as the target physiological data, and then matches the pressure parameters by combining the individual health data with the target physiological data to obtain the oxygen chamber pressure parameters, thus providing a basis for subsequent input and correction of pressure parameters.

6. The oxygen supply pressure dynamic adjustment system based on a medical oxygen chamber according to claim 1, characterized in that: The predictive physiological analysis unit includes a deviation extraction module and a correction node division module; The deviation extraction module is used to divide healthy nodes based on the fluctuation of real-time physiological data, compare the real-time physiological data of each healthy node with the target physiological data to extract deviation data, and obtain the deviation data corresponding to each healthy node. The correction node division module is used to sort the deviation data according to the recording time corresponding to the health node, and then combine the sorted deviation data with oxygen supply reference data to establish a physiological prediction model. The physiological prediction model curve trend analysis is used to predict physiological data, obtain the user's predicted physiological data, and then divide the predicted physiological data into correction nodes according to the data fluctuation.

7. The oxygen supply pressure dynamic adjustment system based on a medical oxygen chamber according to claim 1, characterized in that: The dynamic update unit includes a parameter matching module and a node update module; The parameter matching module is used to analyze the correction pressure parameters by combining the predicted physiological data of each correction node with the target physiological data, using the oxygen chamber pressure parameters as the basic parameters, and to obtain the correction pressure parameters corresponding to each correction node. By supplementing and correcting the pressure parameters of the oxygen chamber, the predicted physiological data can be adjusted to the target physiological data. The node update module is used to substitute the correction pressure parameters into the predicted physiological data according to the time sequence, and then return them to the physiological prediction model. The physiological prediction model then outputs the predicted physiological data again, thus completing the dynamic update of the correction node.

8. The oxygen supply pressure dynamic adjustment system based on a medical oxygen chamber according to claim 1, characterized in that: The auxiliary pressure regulating unit includes a parameter input module and an update regulating module; The parameter input module is set to determine the deviation threshold for parameter input. The deviation data is compared and analyzed with the deviation threshold. When the deviation data is less than the deviation threshold, no correction pressure parameter is input. Conversely, when the deviation data is greater than the deviation threshold, the correction pressure parameter is input according to the correction node of the corresponding time period. The update adjustment module is used to compare the deviation data of real-time physiological data with the deviation data of predicted physiological data in the same period after the parameters are input into the parameter input module. If the deviation data of real-time physiological data is greater than the deviation data of predicted physiological data in the same period, the correction pressure parameters for subsequent prediction times are reselected based on the deviation data of real-time physiological data, and the pressure is adjusted by the reselected correction pressure parameters. At the same time, the subsequent correction nodes are adjusted according to the selected correction pressure parameters. Conversely, if the deviation data of real-time physiological data is less than the deviation data of predicted physiological data in the same period, monitoring is maintained.

9. A dynamic oxygen supply pressure regulation system based on a medical oxygen chamber according to claim 8, characterized in that: When the update adjustment module reselects the correction node and correction pressure parameter in subsequent prediction times, it prioritizes the correction pressure parameter that is closest to the real time. Simultaneously, based on the selected calibration pressure parameters, the corresponding calibration node is determined, and then this node is taken as the latest calibration node. Its time distance is then compared with the time distance of all calibration nodes, and only calibration nodes whose time distance is greater than the time distance of the latest calibration node are retained. The time distance is the difference between the real-time time and the corresponding predicted time of the correction node.

Images