A windowed oxygen intervention parameter recommendation and cabin control system for personnel working in a closed environment

Abstract

This invention relates to the field of life support and intelligent control technology in special environments, and discloses a windowed oxygen intervention parameter recommendation and chamber control system for personnel working in confined environments. The system includes a multi-dimensional fatigue perception and fusion diagnosis module, an intelligent parameter recommendation and dynamic planning module, an adaptive oxygen chamber precision control system, and a dynamic efficacy evaluation and feedback module. By collecting physiological data, cognitive behavioral data, and subjective evaluation data of personnel on long-haul flights, it generates fatigue indices and fatigue types; based on efficacy prediction models, it generates oxygen intervention parameters and performs scheduling processing in conjunction with task time windows to form an intervention execution plan; it further controls the pressure, oxygen concentration, and operating time of the oxygen chamber to achieve automatic execution of the oxygen intervention process, and ensures safety during the intervention process through real-time safety monitoring; after intervention, it performs efficacy evaluation and provides feedback to correct parameters, achieving closed-loop optimization. The system realizes the transformation of oxygen intervention from experience-driven to data-driven, improving the personalization, execution accuracy, and safety of the intervention, and is suitable for health protection scenarios for personnel in confined environments such as closed environments.

Description

Technical Field

[0001] This invention relates to the field of life support and intelligent control technology in special environments, and in particular to a windowed oxygen intervention parameter recommendation and cabin control system for personnel working in confined environments. Background Technology

[0002] Hyperbaric oxygen therapy, as an effective means to improve hypoxia, promote metabolic recovery, and enhance nervous system function, has been widely used in medical rehabilitation and special environmental work support. In special work environments such as confined spaces, high pressure, and disrupted circadian rhythms, long-haul voyage personnel are subjected to high-intensity workloads and complex stress conditions, easily leading to cumulative physiological fatigue and cognitive decline, which in turn affects operational efficiency and navigation safety. Therefore, using hyperbaric oxygen chambers for periodic or phased interventions for long-haul voyage personnel has become an important technical means to improve personnel health and mission support capabilities.

[0003] In existing technologies, hyperbaric oxygen intervention typically employs pre-set, fixed treatment protocols, meaning that workers are uniformly intervened according to predetermined pressure values, oxygen inhalation durations, and treatment cycles. These protocols are mostly derived from clinical medical experience or general guidelines, and while they possess a certain degree of stability, they lack the ability to adapt to individual differences. In manned submersible operations, different personnel on long-distance voyages exhibit significant differences in fatigue types and recovery needs due to variations in age, physical condition, job responsibilities, and sources of fatigue. Existing technologies struggle to differentiate these needs based on individual conditions, resulting in limited intervention effectiveness and even inadequate resource utilization.

[0004] Furthermore, existing hyperbaric oxygen intervention programs rely primarily on the experience and judgment of medical staff or operators in parameter selection and intervention timing, lacking objective assessment and decision support methods based on multidimensional data. Due to the lack of comprehensive analysis of multi-source information such as physiological indicators, cognitive state, and subjective feelings of long-haul travelers, it is difficult to accurately characterize the degree and trend of fatigue, thus affecting the scientific validity and accuracy of the intervention program and limiting further improvement in the effectiveness of hyperbaric oxygen intervention.

[0005] Furthermore, existing oxygen intervention systems typically operate as standalone devices, failing to effectively coordinate with the manned submersible mission management system. Manned submersible missions are highly planned and dynamically changing, with strict constraints on the work schedules and rest windows of personnel on long-haul voyages. Traditional intervention methods lack a coupling mechanism with mission time windows, easily leading to conflicts between intervention time and critical tasks, or failure to implement intervention within the optimal recovery window, thus reducing overall intervention efficiency.

[0006] In terms of control and safety, existing hyperbaric oxygen chambers largely rely on manual parameter setting and process monitoring, resulting in low levels of automation and intelligence. The vital signs and behavioral status of personnel inside the chamber are typically monitored through manual observation or simple instruments, limiting the ability to identify early abnormalities and posing certain safety risks. Furthermore, the lack of a dynamic adjustment mechanism based on real-time monitoring results during intervention makes it difficult to respond to and handle abnormal situations in a timely manner.

[0007] In summary, current technologies lack an integrated solution that comprehensively considers individual personnel conditions, mission time constraints, and the oxygen chamber control process, making it difficult to achieve personalized, dynamic, and safe control of oxygen intervention. Therefore, a new technical solution is urgently needed to achieve accurate assessment of fatigue status of personnel on long-haul flights, intelligent generation of intervention parameters, coordinated optimization of the intervention process and mission scheduling, and automation and safety of oxygen chamber control, thereby improving the overall effectiveness of oxygen intervention and the reliability of system operation. Summary of the Invention

[0008] In view of this, the purpose of this invention is to provide a window-based oxygen intervention parameter recommendation and cabin control system for workers in confined environments, so as to solve the problems of fixed oxygen intervention schemes, lack of individual adaptability, reliance on human experience, disconnection from task arrangement and insufficient safety monitoring in the prior art, and to achieve personalized, adaptive and safe controllable oxygen intervention process.

[0009] To achieve the above objectives, the present invention provides the following technical solution: In one embodiment of the present invention, a windowed oxygen intervention parameter recommendation and chamber control system for personnel working in confined environments is provided, comprising: a multidimensional fatigue perception and fusion diagnosis module, an intelligent parameter recommendation and dynamic planning module, an adaptive oxygen chamber precision control system, and a therapeutic effect dynamic evaluation and feedback module; wherein, the multidimensional fatigue perception and fusion diagnosis module is used to collect physiological data, cognitive behavioral data, and subjective evaluation data of long-haul personnel, and to fuse the data to generate a fatigue index and fatigue type; the intelligent parameter recommendation and dynamic planning module is communicatively connected to the multidimensional fatigue perception and fusion diagnosis module, and is used to receive the fatigue index and fatigue type, and to generate oxygen intervention parameters based on a therapeutic effect prediction model, wherein the oxygen intervention parameters include at least oxygen chamber pressure and pressurization rate. The intelligent parameter recommendation and dynamic planning module is used to obtain mission time window information provided by the manned submersible mission management system, and to perform time matching and scheduling processing on the oxygen intervention parameters based on the mission time window information to generate an intervention execution plan. The adaptive oxygen chamber precision control system is communicatively connected to the intelligent parameter recommendation and dynamic planning module, and is used to control the pressure, pressure rise and fall rate, oxygen concentration and running time of the oxygen chamber according to the intervention execution plan to execute the oxygen intervention operation. The efficacy dynamic evaluation and feedback module is used to collect the status data of long-distance voyage personnel after the oxygen intervention operation and generate efficacy evaluation results, and feed the efficacy evaluation results back to the intelligent parameter recommendation and dynamic planning module to correct subsequent oxygen intervention parameters.

[0010] Furthermore, the efficacy prediction model is a machine learning model trained based on historical fatigue data, oxygen intervention parameter data, and corresponding recovery effect data. The input of the model includes fatigue index, fatigue type, and individual baseline data, and the output includes oxygen intervention parameters used to control the operation of the oxygen chamber.

[0011] Furthermore, the intelligent parameter recommendation and dynamic planning module is used to evaluate and screen multiple candidate oxygen intervention parameter combinations under the constraints of the task time window, so as to generate at least one executable intervention scheduling scheme.

[0012] Preferably, the multidimensional fatigue perception and fusion diagnosis module includes: a multi-source data acquisition unit for acquiring at least one of the following data: heart rate data, heart rate variability data, sleep quality data, reaction time data, working memory data, subjective fatigue score data, and biochemical index data; and a data fusion unit for preprocessing, dimensionality reduction, and feature extraction of the multi-source data to generate the fatigue index and fatigue type.

[0013] Furthermore, it also includes an individualized baseline database for storing historical physiological and cognitive data of long-haul voyage personnel; the fatigue index is determined based on the degree of deviation of the currently collected data from the corresponding baseline data in the individualized baseline database.

[0014] Preferably, the adaptive oxygen chamber precision control system includes: a parameter control unit for generating an oxygen chamber control signal according to the intervention execution plan; and an execution unit for responding to the control signal and controlling the pressure regulating device, oxygen supply device, and exhaust device of the oxygen chamber to achieve pressure regulation, oxygen supply regulation, and duration control.

[0015] Furthermore, it also includes a real-time safety monitoring unit, which is used to collect vital sign data and behavioral status data of the personnel inside the cabin, and generate a safety control signal when an abnormal state is detected, so as to control the execution unit to reduce pressure or stop oxygen intervention operation.

[0016] Optionally, the real-time safety monitoring unit includes at least one of the following: bio-radar, infrared imaging device, or audio acquisition device, for identifying abnormal breathing, abnormal heart rate, or abnormal behavior.

[0017] Furthermore, the efficacy dynamic assessment and feedback module is used to input the efficacy assessment results into the efficacy prediction model to update the model parameters or correct the subsequent oxygen intervention parameters.

[0018] In one embodiment of the present invention, an electronic device is also provided, including a memory and a processor, wherein when the processor executes a computer program stored in the memory, it implements the functions of each module in the above system.

[0019] In one embodiment of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the functions of the modules in the above-described system.

[0020] Based on the above technical solution, the present invention provides a windowed oxygen intervention parameter recommendation and cabin control system for personnel working in confined environments. By constructing a multi-dimensional fatigue perception and fusion diagnosis module, it comprehensively collects and integrates physiological data, cognitive behavior data, and subjective evaluation data of long-haul personnel, and generates a fatigue index and fatigue type that reflect the individual's real-time state, thereby achieving a refined and quantitative assessment of fatigue status.

[0021] Furthermore, through the intelligent parameter recommendation and dynamic planning module, the fatigue index, fatigue type, and individual baseline data are processed using the efficacy prediction model to generate oxygen intervention parameters, including oxygen chamber pressure, pressurization rate, pressure stabilization time, and oxygen concentration. Combined with the mission time window information provided by the manned submersible mission management system, the oxygen intervention parameters are time-matched and scheduled for optimization, so that the intervention plan can be coordinated with the actual mission rhythm, avoiding conflicts between intervention and mission, and improving time utilization efficiency.

[0022] Furthermore, through the adaptive oxygen chamber precision control system, the intervention execution plan is transformed into specific control signals to coordinate the control of the oxygen chamber's pressure regulation device, oxygen supply device, and exhaust device, thereby realizing the automatic execution of the oxygen intervention process, reducing the intensity of manual operation, and improving control accuracy and execution consistency.

[0023] Furthermore, by setting up a real-time safety monitoring unit, the vital signs and behavioral status of the personnel in the chamber are continuously monitored during the oxygen intervention process. When an abnormal state is detected, the safety control mechanism is automatically triggered to realize the dynamic adjustment or intervention stoppage of the oxygen chamber operation status, thereby effectively reducing the safety risks caused by insufficient human supervision and improving the safety and reliability of the system operation.

[0024] Furthermore, through the dynamic efficacy assessment and feedback module, data on the status changes of long-distance voyage personnel are obtained after each or phased intervention, and compared and analyzed with the data before the intervention. The obtained efficacy assessment results are fed back to the efficacy prediction model to correct the model parameters or subsequent intervention strategies, thereby forming a closed-loop optimization mechanism that enables the system to have continuous learning and adaptive adjustment capabilities.

[0025] In summary, this invention organically combines multi-source fatigue sensing, intelligent parameter generation, task window coupling, automatic oxygen chamber control, and therapeutic effect feedback mechanisms. This achieves a shift in oxygen intervention from "experience-driven" to "data-driven," from "fixed plans" to "personalized dynamic plans," and from "manual control" to "automatic safety control." It solves the problems of existing oxygen intervention plans lacking individual adaptability, relying on human experience, being disconnected from task scheduling, and having insufficient safety monitoring. This significantly improves the accuracy, timeliness, and safety of oxygen intervention, and enhances personnel health protection and overall operational efficiency in confined environments. Attached Figure Description

[0026] Figure 1The present invention provides an overall structural block diagram of a windowed oxygen intervention parameter recommendation and chamber control system for workers in confined environments, showing the connection relationship between the multidimensional fatigue perception and fusion diagnosis module, the intelligent parameter recommendation and dynamic planning module, the adaptive oxygen chamber precision control system, the therapeutic effect dynamic evaluation and feedback module, and the data interaction relationship with the manned submersible mission management system. Figure 2 This is a schematic diagram of the workflow of a windowed oxygen intervention parameter recommendation and chamber control method provided in an embodiment of the present invention. It shows a closed-loop processing flow from multi-dimensional data acquisition, fatigue assessment, parameter generation, task window matching, oxygen chamber control execution to efficacy feedback update.

[0027] Explanation of reference numerals in the attached figures: Figure labeling: 100, Multidimensional fatigue perception and fusion diagnosis module; 110, Multi-source data acquisition unit; 120, Data fusion and feature extraction unit; 200, Intelligent parameter recommendation and dynamic planning module; 210, Therapeutic effect prediction unit; 220, Task window coupling unit; 230, Scheduling optimization unit; 300, Adaptive oxygen chamber precision control system; 310, Parameter control unit; 320, Execution unit; 330, Real-time safety monitoring unit; 400, Therapeutic effect dynamic evaluation and feedback module; 500, Manned submersible mission management system; 600, Individualized baseline database. Detailed Implementation

[0028] To make the technical problem to be solved by the present invention, the technical solution adopted, and the beneficial effects obtained clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the scope of protection of the present invention.

[0029] It should be noted that, in the description of this invention, the terms "comprising" and "including" are intended to cover non-exclusive inclusion, such that a system, apparatus, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to the system, apparatus, or method. Unless otherwise specified, the various embodiments of this invention and the technical features thereof can be combined with each other.

[0030] Furthermore, to clearly illustrate the technical concept of the present invention, the following specific embodiments will be presented in a logical order of "system structure implementation method - method flow implementation method - scalable implementation method". Firstly, in conjunction with... Figure 1 The overall composition of the system of the present invention, the structural arrangement of each functional module, and their cooperative relationship are described; secondly, in conjunction with Figure 2The execution flow of the windowed oxygen intervention parameter recommendation and cabin control method implemented based on the system is described. Finally, the scalable forms of the present invention in terms of sensing methods, model types, control strategies, monitoring methods and application scenarios are described so that those skilled in the art can more fully understand and implement the present invention.

[0031] I. General Description

[0032] In one embodiment of the present invention, such as Figure 1 As shown, a windowed oxygen intervention parameter recommendation and cabin control system for personnel working in confined environments is provided. This system aims to improve fatigue recovery and operational safety for personnel on long-haul flights under confined conditions. Through real-time perception and analysis of multi-dimensional status data of personnel on long-haul flights, it achieves intelligent generation of oxygen intervention parameters, dynamic matching with task windows, and automatic control and safety monitoring of the oxygen chamber operation process, thereby constructing a closed-loop, adaptive intelligent intervention system.

[0033] Specifically, the system includes a multidimensional fatigue perception and fusion diagnosis module 100, an intelligent parameter recommendation and dynamic planning module 200, an adaptive oxygen chamber precision control system 300, and a therapeutic effect dynamic evaluation and feedback module 400. The modules interact and coordinate functions through a communication interface. In addition, the system also establishes a communication connection with the manned submersible mission management system 500 to obtain mission time windows and operation scheduling information.

[0034] Furthermore, the multidimensional fatigue perception and fusion diagnosis module 100 is used to collect and fuse data from multiple sources on the physiological state, cognitive ability and subjective fatigue feeling of long-distance voyage personnel, and generate assessment results reflecting the current fatigue level and fatigue type of long-distance voyage personnel, providing input basis for the generation of subsequent oxygen intervention parameters.

[0035] Furthermore, the intelligent parameter recommendation and dynamic planning module 200 is used to generate oxygen intervention parameters suitable for the current long-distance voyage personnel status based on the fatigue assessment results through the efficacy prediction model, and to perform time matching and scheduling processing on the oxygen intervention parameters in conjunction with the mission time window provided by the manned submersible mission management system 500, thereby forming an executable intervention plan and coordinating the oxygen intervention process with the mission arrangement.

[0036] Furthermore, the adaptive oxygen chamber precision control system 300 is used to receive the intervention plan and convert it into specific control signals to control the pressure regulating device, oxygen supply device and exhaust device of the oxygen chamber, so as to realize the automatic execution of the oxygen intervention process; at the same time, the system can be dynamically adjusted according to the operating status to ensure the stability and accuracy of the intervention process.

[0037] Furthermore, the efficacy dynamic assessment and feedback module 400 is used to collect data on the status changes of long-distance voyage personnel after the oxygen intervention is completed, to assess the intervention effect, and to feed the assessment results back to the intelligent parameter recommendation and dynamic planning module 200, so as to correct subsequent intervention parameters or update the efficacy prediction model, thereby forming a continuously optimized closed-loop control mechanism.

[0038] Furthermore, such as Figure 2 As shown, the present invention also provides a windowed oxygen intervention control method based on the above system. The method includes steps such as multi-dimensional data acquisition, fatigue state assessment, oxygen intervention parameter generation, task time window matching, oxygen chamber control execution, and efficacy assessment and feedback. Each step is executed sequentially according to a predetermined logical order, and dynamic optimization is achieved through data feedback.

[0039] Through the above technical solutions, this invention realizes full-process automation and intelligence from the identification of fatigue status of long-haul personnel to the execution of oxygen intervention and feedback of effects. It transforms the oxygen intervention process from the traditional experience-driven mode to a data-driven and model-driven mode, and can be dynamically adjusted according to task requirements, thereby improving the intervention effect, reducing the intensity of manual intervention and enhancing the safety of system operation.

[0040] II. System Structure and Implementation

[0041] 1. Multidimensional fatigue perception and fusion diagnosis module 100

[0042] In one embodiment of the present invention, the multidimensional fatigue perception and fusion diagnosis module 100 is used to collect, process and comprehensively analyze multidimensional state data of long-distance voyage personnel to generate fatigue assessment results for subsequent intervention decisions.

[0043] Furthermore, the multidimensional fatigue perception and fusion diagnosis module 100 includes a multi-source data acquisition unit 110 and a data fusion and feature extraction unit 120.

[0044] Specifically, the multi-source data acquisition unit 110 is used to collect various types of data from long-distance voyage personnel, including but not limited to: Physiological data, such as heart rate, heart rate variability (HRV), blood oxygen saturation, and sleep quality parameters; Cognitive behavioral data, such as reaction time, attention level, and working memory test results; Subjective evaluation data, such as fatigue scores and emotional state scores; Biochemical indicators, such as salivary cortisol or other stress-related indicators.

[0045] Furthermore, the data fusion and feature extraction unit 120 is used to perform unified processing on the multi-source data, including data cleaning, outlier removal, normalization processing and dimensionality reduction calculation, and extract feature parameters representing the fatigue state of long-distance voyage personnel based on the processing results.

[0046] Preferably, the data fusion and feature extraction unit 120 generates a comprehensive fatigue index through statistical analysis or machine learning methods, and classifies fatigue types, including physical fatigue, cognitive fatigue, or mixed fatigue.

[0047] Furthermore, in some embodiments, the multidimensional fatigue perception and fusion diagnosis module 100 is also connected to the individualized baseline database 600 to store historical physiological and cognitive data of long-distance voyage personnel, and to dynamically correct the fatigue state based on the degree of deviation of the current data from the historical baseline data, thereby improving the accuracy of the assessment.

[0048] 2. Intelligent Parameter Recommendation and Dynamic Programming Module 200

[0049] In one embodiment of the present invention, the intelligent parameter recommendation and dynamic programming module 200 is used to generate oxygen intervention parameters based on fatigue assessment results, and generate an executable intervention plan in combination with task time constraints.

[0050] Furthermore, the intelligent parameter recommendation and dynamic planning module 200 includes a treatment efficacy prediction unit 210, a task window coupling unit 220, and a scheduling optimization unit 230.

[0051] Specifically, the efficacy prediction unit 210 is used to receive the fatigue index and fatigue type from the multidimensional fatigue perception and fusion diagnosis module 100, and input them into the efficacy prediction model in combination with individual baseline data to generate oxygen intervention parameters.

[0052] The oxygen intervention parameters include, but are not limited to: Oxygen chamber pressure; The rate of increase and the rate of decrease in voltage; Voltage stabilization time; Oxygen concentration or oxygen supply mode.

[0053] Preferably, the efficacy prediction model is a machine learning model trained based on historical data, such as a gradient boosting model or a neural network model.

[0054] Furthermore, the task window coupling unit 220 is used to obtain task time window information in the manned submersible task management system 500 through the communication interface, including the operation time period and the rest time period, and match the oxygen intervention parameters with the task time window to determine the time interval for intervention execution.

[0055] Furthermore, the scheduling optimization unit 230 is used to evaluate multiple candidate oxygen intervention schemes and select at least one executable intervention scheduling scheme under task constraints, so as to balance the intervention effect and task execution requirements.

[0056] 3. Adaptive oxygen chamber precision control system 300

[0057] In one embodiment of the present invention, the adaptive oxygen chamber precision control system 300 is used to automatically control the oxygen chamber according to the intervention scheduling scheme to perform oxygen intervention operations.

[0058] Furthermore, the adaptive oxygen chamber precision control system 300 includes a parameter control unit 310 and an execution unit 320.

[0059] Specifically, the parameter control unit 310 is used to generate corresponding control signals according to the intervention scheduling scheme, and the control signals include pressure control signals, oxygen supply control signals and time control signals.

[0060] Furthermore, the execution unit 320 is used to control relevant equipment within the oxygen chamber in response to the control signal, including: Pressure regulating device, used to realize the pressure increase and decrease process; An oxygen supply device used to regulate oxygen concentration; Exhaust system, used to regulate the gas environment inside the cabin.

[0061] Through the above controls, the operating parameters of the oxygen chamber are automatically adjusted, thereby ensuring the stability and accuracy of the oxygen intervention process.

[0062] 4. Real-time security monitoring unit 330

[0063] Furthermore, in some embodiments, the system also includes a real-time safety monitoring unit 330 for real-time monitoring of the status of personnel on long-haul voyages during oxygen intervention.

[0064] Specifically, the real-time safety monitoring unit 330 is used to collect vital sign data and behavioral status data of personnel on long-distance voyages, including heart rate, respiratory rate and abnormal behavior information.

[0065] Preferably, the real-time security monitoring unit 330 adopts a non-contact monitoring method and includes at least one of the following devices: Bio-radar equipment; Infrared imaging equipment; Audio acquisition equipment.

[0066] Furthermore, when an abnormal state is detected, the real-time safety monitoring unit 330 generates a safety control signal and sends it to the parameter control unit 310 to trigger corresponding safety control operations, including reducing pressure, pausing intervention, or stopping operation.

[0067] 5. Dynamic evaluation and feedback module for therapeutic efficacy (400)

[0068] In one embodiment of the present invention, the efficacy dynamic assessment and feedback module 400 is used to assess the effect of oxygen intervention and realize closed-loop optimization of the system.

[0069] Specifically, the efficacy dynamic assessment and feedback module 400 is used to collect the status data of long-distance voyage personnel after the oxygen intervention is completed, and to compare and analyze the status changes before and after the intervention through a preset assessment method to generate efficacy assessment results.

[0070] Furthermore, the efficacy evaluation results are fed back to the intelligent parameter recommendation and dynamic programming module 200 to correct subsequent oxygen intervention parameters or update the efficacy prediction model, thereby achieving continuous optimization of the intervention strategy.

[0071] III. Method Flow and Implementation

[0072] In one embodiment of the present invention, such as Figure 2 As shown, a method for recommending windowed oxygen intervention parameters and controlling cabin conditions for workers in confined environments is provided. This method is based on the aforementioned system and includes the following steps: Step S1: Multidimensional Data Acquisition In this step, multidimensional status data of the long-distance voyage personnel are collected.

[0073] Specifically, the multi-source data acquisition unit 110 in the multi-dimensional fatigue perception and fusion diagnosis module 100 acquires physiological data, cognitive behavior data and subjective evaluation data of long-distance voyage personnel. The data includes, but is not limited to, heart rate, heart rate variability, sleep quality, reaction time, working memory test results and subjective fatigue scores.

[0074] Furthermore, in some embodiments, biochemical indicators, such as salivary cortisol levels, may also be collected to enhance the ability to assess stress states.

[0075] Step S2: Fatigue Status Assessment

[0076] In this step, the collected multidimensional data is fused and analyzed to generate fatigue assessment results.

[0077] Specifically, the multidimensional data is preprocessed by the data fusion and feature extraction unit 120, including data cleaning, outlier removal, normalization and dimensionality reduction analysis, and key feature parameters are extracted.

[0078] Furthermore, a fatigue index is generated based on the characteristic parameters, and the fatigue types are classified, including physical fatigue, cognitive fatigue, or mixed fatigue.

[0079] Preferably, in some embodiments, the current data is compared with historical data in the individualized baseline database 600 to determine the degree of deviation of the current fatigue state from the baseline, thereby improving the accuracy of the assessment.

[0080] Step S3: Generation of oxygen intervention parameters

[0081] In this step, oxygen intervention parameters are generated based on the fatigue assessment results.

[0082] Specifically, the fatigue index, fatigue type, and individual baseline data are input into the efficacy prediction unit 210 in the intelligent parameter recommendation and dynamic programming module 200, and the oxygen intervention parameters are calculated through the efficacy prediction model.

[0083] The oxygen intervention parameters include, but are not limited to: Oxygen chamber pressure; The rate of increase and the rate of decrease in voltage; Voltage stabilization time; Oxygen concentration or oxygen supply mode.

[0084] Furthermore, in some embodiments, the efficacy prediction model is trained based on historical intervention data and recovery effect data to improve the accuracy of parameter generation.

[0085] Step S4: Task window matching and scheduling generation

[0086] In this step, the generated oxygen intervention parameters are matched with the task time window to form an executable intervention plan.

[0087] Specifically, the task time information in the manned submersible task management system 500, including the operation time period and the rest time period, is obtained through the task window coupling unit 220.

[0088] Furthermore, the oxygen intervention parameters are time-matched and scheduled by the scheduling optimization unit 230. Under the premise of meeting the task execution constraints, the execution time and execution order of oxygen intervention are determined, thereby generating an intervention scheduling plan.

[0089] Preferably, in some embodiments, multiple candidate solutions can be evaluated and screened to select the optimal or feasible implementation solution.

[0090] Step S5: Oxygen Chamber Control Execution

[0091] In this step, the oxygen chamber is controlled to perform oxygen intervention operations according to the intervention scheduling plan.

[0092] Specifically, the parameter control unit 310 in the adaptive oxygen chamber precision control system 300 generates control signals, and the execution unit 320 controls the oxygen chamber related equipment, including pressure regulating device, oxygen supply device and exhaust device, to achieve the regulation of oxygen chamber pressure, oxygen concentration and running time.

[0093] Furthermore, during the oxygen intervention process, the vital signs and behavioral status of the long-haul voyage personnel are continuously monitored through the real-time safety monitoring unit 330.

[0094] When an abnormal state is detected, a safety control signal is generated, and corresponding safety control operations are executed, including reducing pressure, suspending intervention, or stopping operation, to ensure personnel safety.

[0095] Step S6: Efficacy Assessment and Feedback Optimization

[0096] In this step, the effectiveness of oxygen intervention is evaluated, and subsequent intervention strategies are optimized.

[0097] Specifically, the efficacy dynamic assessment and feedback module 400 collects the status data of the long-distance voyage personnel after the intervention and compares and analyzes it with the data before the intervention to generate efficacy assessment results.

[0098] Furthermore, the efficacy assessment results are fed back to the intelligent parameter recommendation and dynamic programming module 200 to correct subsequent oxygen intervention parameters or update the efficacy prediction model, thereby achieving continuous optimization of the intervention strategy.

[0099] IV. Expandable Implementation Methods

[0100] In one embodiment of the present invention, the system and method can be extended and modified in various forms without departing from the core technical concept of the present invention.

[0101] 1. Expansion of fatigue perception modes

[0102] Furthermore, in some embodiments, the data types collected by the multidimensional fatigue perception and fusion diagnosis module 100 can be expanded according to application requirements.

[0103] Specifically, in addition to the aforementioned physiological data, cognitive behavioral data, and subjective evaluation data, the following data can also be accessed: Electroencephalogram (EEG) data is used to assess the state of neural activity; Eye-tracking data is used to analyze attention and visual fatigue levels. Electrodermal conductance data (EDA) is used to reflect mood and stress levels; Motor behavior data, such as gait or activity level data.

[0104] By introducing more dimensions of data, the accuracy and sensitivity of fatigue assessment can be further improved.

[0105] 2. Expansion of the efficacy prediction model

[0106] Furthermore, in some embodiments, the implementation of the efficacy prediction model is not limited to a specific algorithm.

[0107] Preferably, the model can be implemented in any one or more of the following ways: Gradient Boosting Decision Tree (GBDT) model; Deep Neural Network Model (DNN); Recurrent Neural Network (RNN) or Long Short-Term Memory (LSTM) network. An adaptive decision-making model based on reinforcement learning.

[0108] Alternatively, the model can be updated through online learning or incremental learning to adapt to changes in different long-haul voyage personnel and different mission environments.

[0109] 3. Extension of task coupling methods

[0110] Furthermore, in some embodiments, the task window coupling method can be extended according to the complexity of the task.

[0111] Specifically, in addition to basic time window matching, the following constraints can also be considered: Job priority; Work intensity level; Staff shift system; Emergency task insertion mechanism.

[0112] By introducing multidimensional task constraints, more refined intervention and scheduling can be achieved.

[0113] 4. Expansion of oxygen chamber control methods

[0114] Furthermore, in some embodiments, the control method of the adaptive oxygen chamber precision control system 300 can be expanded.

[0115] Specifically, in addition to basic pressure and oxygen concentration control, it may also include: Phased pressure control strategy (segmented pressure increase / decrease). Intermittent oxygen supply mode; Personalized breathing rhythm guidance; Adjustment of cabin environmental parameters (such as temperature and humidity).

[0116] The aforementioned extended control methods can further enhance the comfort and effectiveness of oxygen intervention.

[0117] 5. Expansion of security monitoring methods

[0118] Furthermore, in some embodiments, the real-time security monitoring unit 330 can be expanded into a multimodal fusion monitoring system.

[0119] Specifically, anomaly identification can be achieved by integrating the following information: Abnormal physiological signals; Abnormal behavior; Voice and emotional changes; The results are determined collaboratively by multiple sensors.

[0120] Preferably, a multi-source information fusion algorithm can be used to improve the accuracy and response speed of anomaly detection.

[0121] 6. Expansion of application scenarios

[0122] Furthermore, in some embodiments, the present invention is not only applicable to confined working environments, but can also be extended to other confined or special working environments, including but not limited to: Spacecraft or space station environment; Deep-sea operation platform; Working scenarios in high-altitude or low-oxygen environments; Mining or underground working environments.

[0123] In the above scenarios, the present invention can also be used for personnel fatigue management and oxygen intervention control.

[0124] 7. Expansion of system deployment methods

[0125] Furthermore, in some embodiments, the system can be deployed using different architectural forms.

[0126] Specifically, it may include: Centralized deployment (unified server processing); Distributed deployment (modules are distributed across different devices); Edge computing deployment (running on local equipment on manned submersibles); Collaborative deployment in the cloud and on-premises.

[0127] Different deployment methods can be used to adapt to different computing resources and communication conditions.

[0128] V. Summary

[0129] In summary, this invention provides a windowed oxygen intervention parameter recommendation and chamber control system and method for workers in confined environments. By constructing a multi-dimensional fatigue perception and fusion diagnosis module, an intelligent parameter recommendation and dynamic planning module, an adaptive oxygen chamber precision control system, and a therapeutic effect dynamic evaluation and feedback module, a closed-loop technology system integrating "state perception - intelligent decision-making - automatic control - effect feedback" is formed.

[0130] Compared to existing technologies, this invention achieves refined and quantitative assessment of fatigue status of personnel on long-distance voyages by introducing a multi-source data fusion mechanism; generates oxygen intervention parameters through a efficacy prediction model, enabling the intervention plan to be dynamically adjusted according to individual conditions; achieves coordinated matching between the intervention process and the mission time window through coupling with the manned submersible mission management system; achieves precise execution of the intervention process through the oxygen chamber automatic control system; and achieves continuous optimization of the intervention strategy through an efficacy feedback mechanism.

[0131] Furthermore, this invention achieves the synergistic integration of multiple key technical elements in its system architecture, resulting in a tight coupling between modules and ensuring the integrated operation of data flow, control flow, and feedback flow. This closed-loop structure not only improves the accuracy and adaptability of oxygen intervention but also enhances the stability and reliability of the system in complex task environments.

[0132] Furthermore, by introducing a real-time safety monitoring mechanism, this invention continuously monitors vital signs and behavioral status during the intervention process and automatically triggers safety control measures in abnormal situations, effectively reducing the risks caused by insufficient human supervision and significantly improving the system's safety assurance capabilities.

[0133] In terms of application effects, this invention has transformed oxygen intervention from the traditional "experience-driven, fixed plan, and manual control" model to a "data-driven, personalized dynamic plan, and automatic safety control" model. This not only improves the fatigue recovery efficiency of long-haul voyage personnel but also optimizes resource utilization and enhances personnel support capabilities during mission execution.

[0134] It should be noted that, without departing from the technical concept of this invention, those skilled in the art can make various modifications or equivalent substitutions to the above embodiments, and such modifications or substitutions should all fall within the protection scope defined by the claims of this invention.

Claims

1. A windowed oxygen intervention parameter recommendation and cabin control system for personnel working in confined environments, characterized in that, include: The multidimensional fatigue perception and fusion diagnosis module is used to collect physiological data, cognitive behavior data and subjective evaluation data of long-distance voyage personnel, and to fuse the data to generate fatigue index and fatigue type. The intelligent parameter recommendation and dynamic planning module is communicatively connected to the multidimensional fatigue perception and fusion diagnosis module. It is used to receive the fatigue index and fatigue type, and generate oxygen intervention parameters based on the efficacy prediction model. The oxygen intervention parameters include at least oxygen chamber pressure, pressurization rate, pressure stabilization time and oxygen supply concentration. The intelligent parameter recommendation and dynamic planning module is also used to obtain the mission time window information provided by the manned submersible mission management system, and to perform time matching and scheduling processing on the oxygen intervention parameters based on the mission time window information to generate an intervention execution plan. The adaptive oxygen chamber precision control system is connected in communication with the intelligent parameter recommendation and dynamic planning module. It is used to control the pressure, pressure rise and fall rate, oxygen supply concentration and running time of the oxygen chamber according to the intervention execution plan in order to perform oxygen intervention operations. The efficacy dynamic assessment and feedback module is used to collect the status data of long-haul voyage personnel after oxygen intervention and generate efficacy assessment results. The efficacy assessment results are then fed back to the intelligent parameter recommendation and dynamic planning module to correct subsequent oxygen intervention parameters.

2. The system according to claim 1, characterized in that, The efficacy prediction model is a machine learning model trained based on historical fatigue data, oxygen intervention parameter data, and corresponding recovery effect data. The input of the model includes fatigue index, fatigue type, and individual baseline data, and the output includes oxygen intervention parameters used to control the operation of the oxygen chamber.

3. The system according to claim 1 or 2, characterized in that, The intelligent parameter recommendation and dynamic programming module is used to evaluate and screen multiple candidate oxygen intervention parameter combinations under the constraints of the task time window, so as to generate at least one executable intervention scheduling scheme.

4. The system according to claim 1, characterized in that, The multidimensional fatigue perception and fusion diagnosis module includes: A multi-source data acquisition unit is used to collect at least one of the following data: heart rate data, heart rate variability data, sleep quality data, reaction time data, working memory data, subjective fatigue score data, and biochemical index data; The data fusion unit is used to preprocess, reduce dimensionality, and extract features from the multi-source data to generate the fatigue index and fatigue type.

5. The system according to claim 4, characterized in that, It also includes an individualized baseline database for storing historical physiological and cognitive data of long-haul voyage personnel; The fatigue index is determined based on the degree of deviation of the currently collected data from the corresponding baseline data in the individualized baseline database.

6. The system according to claim 1, characterized in that, The adaptive oxygen chamber precision control system includes: A parameter control unit is used to generate oxygen chamber control signals according to the intervention execution plan; The execution unit is used to respond to the control signal and control the pressure regulating device, oxygen supply device and exhaust device of the oxygen chamber to achieve pressure regulation, oxygen supply regulation and duration control.

7. The system according to claim 6, characterized in that, It also includes a real-time safety monitoring unit, which collects vital signs and behavioral data of personnel inside the cabin, and generates a safety control signal when an abnormal state is detected, so as to control the execution unit to reduce pressure or stop oxygen intervention operations.

8. The system according to claim 7, characterized in that, The real-time security monitoring unit includes at least one of the following: bio-radar, infrared imaging equipment, or audio acquisition equipment, used to identify abnormal breathing, abnormal heart rate, or abnormal behavior.

9. An electronic device comprising a memory and a processor, characterized in that, When the processor executes the computer program stored in the memory, it implements the functions of the system as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it performs the functions of the system as described in any one of claims 1 to 8.

Images