An intelligent postoperative rehabilitation management system for critically ill children

Abstract

The present invention relates to the technical field of postoperative management, and in particular to an intelligent postoperative rehabilitation management system for critically ill children. The system includes a postoperative rehabilitation EEG signal monitoring module, a postoperative rehabilitation consciousness and cognitive state analysis module, a consciousness and cognitive state rehabilitation intelligent strategy analysis module, and a child postoperative rehabilitation intelligent management module. The system can perform signal preprocessing and equipment abnormal EEG distribution calibration processing on the EEG signal feedback from the rehabilitation perception operation performed on the critically ill children after surgery through a preset rehabilitation perception signal, and generate an EEG signal distribution calibration spectrum during postoperative rehabilitation; perform consciousness and cognitive score quantitative calculation and consciousness and cognitive state division on the EEG signal distribution calibration spectrum during postoperative rehabilitation, and perform rehabilitation goal setting and rehabilitation activity project intelligent strategy analysis, and perform postoperative rehabilitation intelligent management at the same time, and obtain the intelligent management results of postoperative rehabilitation for critically ill children. The present invention can achieve the intelligent management effect of the postoperative rehabilitation process of children.

Description

Technical Field

[0001] The present invention relates to the technical field of postoperative management, and in particular to an intelligent postoperative rehabilitation management system for critically ill children. Background Art

[0002] With the development of health information technology and artificial intelligence, intelligent postoperative rehabilitation management methods based on new technologies have become a key tool for optimizing postoperative rehabilitation effects and rationally utilizing medical resources, bringing important innovations and progress to improving the quality of treatment and the quality of life of patients. By introducing personalized rehabilitation plans and dynamic adjustment mechanisms, personalized rehabilitation plans can be formulated according to the specific cognitive state and rehabilitation needs of each critically ill child. By using artificial intelligence algorithms and data analysis technologies, changes in key indicators in the rehabilitation process can be monitored in real time, and rehabilitation plans can be adjusted in time to ensure the effectiveness and safety of the rehabilitation process. It also combines technical innovations of remote monitoring and real-time feedback, and carries biosensors and remote monitoring devices (such as wearable devices or brain-computer interface devices) to collect and transmit patients' physiological parameter data in real time. These data can help medical staff monitor the patient's rehabilitation status in real time, detect abnormal conditions in time and take corresponding measures, thereby reducing the occurrence of complications and improving rehabilitation effects. However, traditional postoperative rehabilitation management methods often rely on the experience of medical staff and the subjective feedback of patients, making it difficult to effectively monitor and adjust the rehabilitation process, especially for critically ill children, who require more meticulous and professional management and attention. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide an intelligent postoperative rehabilitation management system for critically ill children to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above purpose, an intelligent postoperative rehabilitation management system for critically ill children is provided, wherein the brain wave signals of the critically ill children during postoperative rehabilitation are the brain wave signals fed back by performing rehabilitation perception tasks on the critically ill children after surgery through preset rehabilitation perception signals, and the system comprises the following modules:

[0005] The postoperative rehabilitation EEG signal monitoring module is used to collect the EEG signals of critically ill children during the postoperative rehabilitation period in real time through the EEG signal monitoring equipment and upload them to the data processing unit for signal preprocessing to obtain the enhanced EEG signal data of the postoperative rehabilitation of critically ill children; based on the EEG signal monitoring equipment, the abnormal EEG distribution of the equipment is calibrated and processed on the enhanced EEG signal data of the postoperative rehabilitation of critically ill children to generate a calibrated spectrum of the EEG signal distribution during the postoperative rehabilitation period;

[0006] The postoperative rehabilitation consciousness and cognitive state analysis module is used to quantify the consciousness and cognitive score of the EEG signal distribution calibration spectrum during the postoperative rehabilitation period, so as to obtain the EEG consciousness and cognitive score during the postoperative rehabilitation period at each time point; based on the EEG consciousness and cognitive score during the postoperative rehabilitation period at each time point, the corresponding children's postoperative rehabilitation consciousness and cognitive period in the EEG signal distribution calibration spectrum during the postoperative rehabilitation period is divided into consciousness and cognitive states, so as to obtain the children's consciousness and cognitive functional state during the postoperative rehabilitation period, wherein the children's consciousness and cognitive functional state during the postoperative rehabilitation period includes consciousness and cognitive unawakenable state, consciousness and cognitive sedation state and consciousness and cognitive agitation state;

[0007] The intelligent strategy analysis module for rehabilitation of consciousness and cognitive status is used to set rehabilitation goals for the consciousness and cognitive function states of children in different rehabilitation periods after surgery, so as to obtain rehabilitation goals for children with different consciousness and cognitive function states after surgery; based on the rehabilitation goals for children with different consciousness and cognitive function states after surgery, intelligent strategy analysis is performed on the rehabilitation activity projects for the corresponding consciousness and cognitive function states of children in the rehabilitation period after surgery, so as to generate intelligent strategy plans for rehabilitation activity projects for children with different consciousness and cognitive states after surgery;

[0008] The children's postoperative rehabilitation intelligent management module is used to perform postoperative rehabilitation intelligent management on the children's consciousness and cognitive function status during the corresponding postoperative rehabilitation period according to the intelligent strategy plan of the rehabilitation activity project of the children's different consciousness and cognitive status after surgery, and obtain the intelligent management results of postoperative rehabilitation for critically ill children.

[0009] Furthermore, the postoperative rehabilitation EEG signal monitoring module includes the following functions:

[0010] The EEG signal monitoring equipment is used to collect the EEG signals of critically ill children during their postoperative rehabilitation in real time, and the original EEG signal data of critically ill children during their postoperative rehabilitation are obtained;

[0011] By uploading the original EEG signal data of critically ill children during postoperative rehabilitation to the data processing unit in the order of time collected in real time, the real-time EEG signal data of critically ill children during postoperative rehabilitation are obtained;

[0012] The data processing unit is used to perform signal noise reduction processing on the real-time EEG signal data of critically ill children during postoperative rehabilitation, and the noise reduction data of EEG signals during postoperative rehabilitation of critically ill children are obtained;

[0013] The EEG signal noise reduction data of critically ill children during postoperative rehabilitation was processed to obtain the EEG signal enhancement data of critically ill children during postoperative rehabilitation.

[0014] Based on the EEG signal monitoring equipment, the abnormal EEG distribution of the equipment was calibrated and processed for the EEG signal enhancement data of critically ill children after surgery, and a calibrated EEG signal distribution spectrum during postoperative rehabilitation was generated.

[0015] Furthermore, the abnormal EEG distribution calibration of the EEG signal enhancement data of critically ill children after surgery based on the EEG signal monitoring device includes:

[0016] The EEG signal distribution was mapped on the EEG signal enhancement data of critically ill children after surgery to generate the initial distribution spectrum of EEG signals during children's postoperative rehabilitation.

[0017] The signal fluctuation frequency and amplitude of the initial distribution spectrum of the EEG signals during the children's postoperative rehabilitation period were statistically analyzed to obtain the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude during the postoperative rehabilitation period;

[0018] According to the EEG signal fluctuation frequency and EEG signal fluctuation amplitude during the postoperative rehabilitation period, the abnormal distribution period of the equipment is analyzed to obtain the abnormal distribution period of the postoperative EEG signal monitoring equipment;

[0019] Based on the abnormal distribution period of the postoperative EEG signal monitoring equipment, the fault probability analysis of the EEG signal monitoring equipment during the abnormal period is performed to obtain the fault probability value of the monitoring equipment at each time point in the abnormal distribution period;

[0020] Based on the abnormal distribution period of the postoperative EEG signal monitoring equipment, the arithmetic mean calculation of the monitoring equipment failure probability value at each time point within the abnormal distribution period is performed to obtain the average value of the monitoring equipment failure probability within the abnormal distribution period; according to the average value of the monitoring equipment failure probability within the abnormal distribution period, the initial distribution spectrum of the EEG signals of children during the postoperative rehabilitation period corresponding to the abnormal distribution period of the postoperative EEG signal monitoring equipment is calibrated and processed by EEG distribution calibration to generate the EEG signal distribution calibration spectrum during the postoperative rehabilitation period.

[0021] Furthermore, the device abnormal distribution period analysis based on the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude during the postoperative rehabilitation period includes:

[0022] Performing time-series synchronization processing on the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude during the postoperative rehabilitation period, and obtaining the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude in the same time sequence dimension;

[0023] Plotting a signal fluctuation hyperbola for the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude in the same time sequence dimension to generate an EEG signal fluctuation frequency-amplitude change hyperbola;

[0024] Performing signal fluctuation inflection point statistical analysis on the EEG signal fluctuation frequency-amplitude change hyperbola to obtain an inflection point set of the EEG signal fluctuation frequency change curve and an inflection point set of the EEG signal fluctuation amplitude change curve; dividing the EEG signal fluctuation frequency-amplitude change hyperbola into curve distribution time periods based on the order of appearance between the inflection points of each pair of curves in the EEG signal fluctuation frequency change curve inflection point set and the EEG signal fluctuation amplitude change curve inflection point set to obtain distribution time periods of each EEG signal fluctuation change curve;

[0025] Based on each EEG signal fluctuation change curve distribution period, the corresponding EEG signal fluctuation frequency-amplitude change hyperbola is subjected to curve change pattern recognition analysis to obtain the EEG signal fluctuation curve change pattern within each fluctuation distribution period; the EEG signal fluctuation curve change pattern within each fluctuation distribution period is subjected to abnormal change period detection to obtain the fluctuation distribution period corresponding to the abnormal change pattern of the EEG signal fluctuation;

[0026] The fluctuation distribution period corresponding to the abnormal change pattern of the EEG signal fluctuation is screened and processed as the cause of equipment abnormality to obtain the abnormal distribution period of the postoperative EEG signal monitoring equipment.

[0027] Further, the abnormal time period point fault probability analysis of the EEG signal monitoring device based on the abnormal distribution time period of the postoperative EEG signal monitoring device includes:

[0028] The abnormal distribution period of the postoperative EEG signal monitoring device is divided into abnormal time sequence points, and the abnormal time sequence points of each EEG signal monitoring device in the abnormal distribution period are obtained;

[0029] Based on each abnormal timing point of the EEG signal monitoring device within the abnormal distribution period, the working state of the EEG signal monitoring device is monitored and analyzed to obtain the working state parameter data of the EEG signal monitoring device at each abnormal timing point of the device;

[0030] The failure probability calculation formula of the monitoring equipment is used to quantify the failure probability of the EEG signal monitoring equipment at each abnormal timing point of the equipment, so as to obtain the failure probability value of the monitoring equipment at each timing point within the abnormal distribution period.

[0031] Furthermore, the calculation formula for the probability of failure of the monitoring equipment is as follows:

[0032] ;

[0033] In the formula, is the abnormal time sequence point within the abnormal distribution period The failure probability value of the monitoring equipment at is the initial abnormal time sequence point of the abnormal distribution period, is the termination abnormal timing point of the abnormal distribution period, is the measurement variable parameter of the abnormal time series point, is the number of device working status parameters in the working status parameter data of the EEG signal monitoring device. It is the item index parameter of the equipment working status parameter. For the The fault impact attenuation coefficient of the working status parameters of each device, For the The fault impact adjustment factor of each device working status parameter, For the The fault impact normalization factor of each device working status parameter, For the The fault impact index of the working status parameters of each device, It is the correction factor of the failure probability value of the monitoring equipment.

[0034] Furthermore, the electroencephalogram distribution calibration process is performed on the initial distribution spectrum of the electroencephalogram signal during the postoperative rehabilitation period of the child corresponding to the abnormal distribution period of the postoperative electroencephalogram signal monitoring device according to the average value of the monitoring device failure probability in the abnormal distribution period, including:

[0035] Based on the abnormal distribution period of the postoperative EEG signal monitoring device, the initial distribution spectrum of the EEG signal during the children's postoperative rehabilitation period is divided into abnormal period spectrum, and the postoperative EEG signal abnormal period distribution sub-graph and the postoperative EEG signal normal period distribution sub-graph are obtained;

[0036] Based on the average value of the monitoring equipment failure probability within the abnormal distribution period, the signal distribution impact correlation analysis is performed on the corresponding EEG signal abnormal period distribution subgraph during postoperative rehabilitation to obtain the impact correlation relationship between the monitoring equipment failure probability and the EEG signal abnormal distribution;

[0037] According to the influence correlation between the failure probability of monitoring equipment and the abnormal distribution of EEG signals, the distribution sub-graph of abnormal EEG signal periods during postoperative rehabilitation is subjected to equipment failure impact calibration analysis, and the distribution line of equipment failure impact calibration during abnormal EEG signal periods is obtained;

[0038] Based on the EEG signal abnormal period equipment fault impact calibration distribution line, the EEG signal distribution curve corresponding to the EEG signal abnormal period distribution sub-graph during the postoperative rehabilitation period is calibrated and processed to generate the EEG signal abnormal period calibration distribution sub-graph;

[0039] The calibration distribution sub-graph of EEG signal abnormal period and the distribution sub-graph of EEG signal normal period after surgery are merged to generate the calibration spectrum of EEG signal distribution during postoperative rehabilitation.

[0040] Furthermore, the postoperative rehabilitation consciousness cognitive state analysis module includes the following functions:

[0041] The signal frequency band energy distribution and power density statistical analysis were performed on the EEG signal distribution calibration spectrum during the postoperative rehabilitation period to obtain the EEG signal distribution frequency band energy distribution value and the EEG signal distribution frequency band power density value during the postoperative rehabilitation period;

[0042] Performing time point segmentation processing on the energy distribution value of the EEG signal distribution frequency band during the postoperative rehabilitation period and the power density value of the EEG signal distribution frequency band during the postoperative rehabilitation period to obtain the energy distribution value of the EEG signal frequency band and the power density value of the EEG signal frequency band at each time point;

[0043] Based on the energy distribution value of the EEG signal frequency band and the power density value of the EEG signal frequency band at each time point, the EEG consciousness cognition score calculation formula is used to quantify the consciousness cognition score of the corresponding EEG signal distribution calibration spectrum during postoperative rehabilitation to obtain the EEG consciousness cognition score during postoperative rehabilitation at each time point;

[0044] Based on the EEG consciousness cognition score during postoperative rehabilitation at each time point, the corresponding rehabilitation time period in the EEG signal distribution calibration spectrum during postoperative rehabilitation is divided into cognitive equivalent time periods, and each child's postoperative rehabilitation EEG consciousness cognition equivalent time period is obtained;

[0045] The consciousness cognition scores corresponding to each child's postoperative rehabilitation EEG consciousness cognition equivalent period were used for consciousness cognition state recognition analysis to obtain the child's consciousness cognition function status during the postoperative rehabilitation period.

[0046] Furthermore, the EEG consciousness cognition score calculation formula is specifically:

[0047] ;

[0048] In the formula, For the time point EEG consciousness and cognitive scores during postoperative rehabilitation is the time range measurement parameter, is the time point measurement parameter, For the time point EEG signals Frequency band energy distribution value, For the time point EEG signals Frequency band energy distribution value, For the time point EEG signals Frequency band energy distribution value, For the time point EEG signals Band power density value, For the time point EEG signals Band power density value, For the time point EEG signals Band power density value, is the standard deviation of the EEG signal frequency of the EEG signal distribution calibration spectrum during postoperative rehabilitation, Calibration of EEG signal distribution at time points during postoperative rehabilitation The EEG signal frequency at is the contribution factor for EEG signal frequency scaling, It is the correction coefficient of EEG consciousness cognition score during postoperative rehabilitation.

[0049] Furthermore, the consciousness and cognitive state rehabilitation intelligent strategy analysis module includes the following functions:

[0050] When it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a consciousness and cognitive non-awakening state, a passive rehabilitation goal is set according to the consciousness and cognitive non-awakening state to obtain the child's postoperative non-awakening state passive rehabilitation goal;

[0051] When it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is the consciousness and cognitive sedation state, auxiliary rehabilitation goals are set according to the consciousness and cognitive sedation state to obtain the auxiliary rehabilitation goals for the child's postoperative sedation state;

[0052] When it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a state of consciousness and cognitive agitation, active rehabilitation goals are set according to the state of consciousness and cognitive agitation to obtain active rehabilitation goals for the child's postoperative agitation state;

[0053] The rehabilitation goals of children's passive rehabilitation goals for the unawakenable state after surgery, the auxiliary rehabilitation goals for children's sedation state after surgery, and the active rehabilitation goals for children's agitation state after surgery were combined to obtain rehabilitation goals for children's different states of consciousness and cognitive function after surgery.

[0054] Based on the rehabilitation goals of children with different postoperative consciousness and cognitive function states, an intelligent strategy analysis of rehabilitation activity projects is conducted on the corresponding children's consciousness and cognitive function states during the postoperative rehabilitation period to generate intelligent strategy plans for rehabilitation activity projects with different postoperative consciousness and cognitive states for children.

[0055] Beneficial effects of the present invention:

[0056] The intelligent postoperative rehabilitation management system for critically ill children proposed in the present invention is generally composed of a postoperative rehabilitation EEG signal monitoring module, a postoperative rehabilitation consciousness and cognitive state analysis module, a consciousness and cognitive state rehabilitation intelligent strategy analysis module and a children's postoperative rehabilitation intelligent management module. Compared with the prior art, the beneficial effect of the present application lies in that the EEG signal monitoring device is used to collect the EEG signals of critically ill children during postoperative rehabilitation in real time, wherein the EEG signals of critically ill children during postoperative rehabilitation are the EEG signals fed back by performing rehabilitation perception tasks on critically ill children after surgery through preset rehabilitation perception signals. The key to this step is that the preset rehabilitation perception signals are based on the children's Critical treatment conditions, including treatment plans, methods, postoperative monitoring and rehabilitation requirements, targeted selection and formulation of postoperative children's cognitive function rehabilitation training content, to achieve individualization; and targeted selection of multimedia and devices based on sound, light, electricity and other forms of carriers for presentation, purposeful rehabilitation training of postoperative children's hearing, vision, smell, touch and other cognitive functions, and also through sensors and physical devices, guide the capture of children's cognitive response and judgment to the multimedia rehabilitation content selected for playback. The EEG signals obtained can obtain detailed EEG activity information in the postoperative rehabilitation stage, thus providing a basis for subsequent data analysis and rehabilitation management plan formulation. Secondly, by uploading the original EEG signal data arranged in chronological order to the data processing unit, this step ensures the integrity and timeliness of the data, so that subsequent data processing can be based on the latest and accurate information. The data upload and processing provide real-time monitoring and analysis capabilities while ensuring data security, which helps to timely discover and respond to changes in the EEG activity of children, thereby improving the effective monitoring of EEG signals. The data processing unit is also used to perform signal noise reduction and enhancement processing on the real-time EEG signals of postoperative rehabilitation of critically ill children. This process aims to remove interference from the environment or equipment, improve the clarity and quality of the signal, and highlight useful signals and further optimize the data quality. Enhanced processing can increase the signal-to-noise ratio of the signal, making the characteristics of EEG activity more significant, which helps to analyze the EEG patterns and change trends of the children in more depth. This step ensures data accuracy while improving the availability and accuracy of EEG signal data interpretation. In addition, by calibrating the abnormal EEG distribution of the enhanced data of postoperative rehabilitation EEG signals of critically ill children based on EEG signal monitoring equipment, this process can identify and correct abnormal distribution caused by the equipment itself or environmental factors, ensuring that the spatial distribution and spectral characteristics of the EEG signal are consistent with the real physiological state, and the generated calibration spectrum can provide more accurate and reliable EEG activity data for the subsequent rehabilitation management process, thereby maximizing the management effect and prognosis evaluation of the postoperative rehabilitation process of critically ill children.Secondly, the consciousness cognition score is quantified and calculated for the EEG signal distribution calibration spectrum during the postoperative rehabilitation period. The key to this step is to obtain the corresponding consciousness cognition score through quantitative calculation, which can objectively evaluate the child's consciousness state at each time point during the postoperative rehabilitation period, and provide a scientific basis for the subsequent division of rehabilitation time periods. The consciousness cognition state recognition analysis is also performed on the corresponding rehabilitation time period in the EEG signal distribution calibration spectrum during the postoperative rehabilitation period based on the EEG consciousness cognition score during the postoperative rehabilitation period at each time point, so as to evaluate the child's consciousness and cognitive function state in each rehabilitation time period. This step can identify the different consciousness states of children in the postoperative rehabilitation stage, including the unawakenable state, the sedated state, and the agitated state, by analyzing the changes in the consciousness cognition score, thereby providing a scientific basis and support for the subsequent personalized rehabilitation plan. Then, if it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a state of consciousness and cognition that cannot be awakened, this means that the child is in a state of consciousness and cognition with relatively passive participation at this stage. Therefore, by setting passive rehabilitation goals based on the state of consciousness and cognition that cannot be awakened, corresponding passive rehabilitation goals can be effectively set to help children recover gradually. These goals include maintaining muscle and joint mobility through physical therapy and regular physical activity, promoting blood circulation and flexibility of the rehabilitation area, and reducing muscle stiffness through passive movement and massage. If it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a state of consciousness and cognition sedation, it means that the child is in a relatively relaxed and calm state during this period. In this case, setting auxiliary rehabilitation goals based on the state of consciousness and cognition sedation can help children recover more effectively. These auxiliary rehabilitation goals include using techniques such as psychotherapy, music therapy, or deep breathing to promote emotional stability and cognitive recovery, while improving muscle control and coordination through progressive physical activity and functional training. If it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a state of consciousness and cognitive agitation, it means that the child is in a more active and restless state during this period. Therefore, by setting active rehabilitation goals based on the state of consciousness and cognitive agitation, children can be helped to actively participate in the rehabilitation process. This active rehabilitation goal involves improving self-control and emotion management ability through physical training, exercise therapy and cognitive behavioral therapy, while promoting mental health and rehabilitation process through social support and emotional regulation.By combining the passive rehabilitation goals of the postoperative non-awakenable state of children, the auxiliary rehabilitation goals of the postoperative sedation state of children, and the active rehabilitation goals of the postoperative agitation state of children, the intelligent strategy analysis of the rehabilitation activity projects for the corresponding postoperative rehabilitation period of children is carried out to generate an effective intelligent strategy plan for rehabilitation activity projects. The goal of this step is to formulate a suitable rehabilitation activity plan based on the specific rehabilitation goals and individual characteristics of children, including regular evaluation and adjustment of the rehabilitation plan, intervention with advanced rehabilitation techniques and tools, and cooperation with family and community resources, so as to provide comprehensive data support and nursing plans for the subsequent postoperative rehabilitation management process of critically ill children, and to formulate more detailed and professional rehabilitation management and attention for them. Finally, by combining the previously generated intelligent strategy plan for rehabilitation activity projects for children with different postoperative consciousness and cognitive states, the corresponding postoperative rehabilitation period of children with consciousness and cognitive function states is processed for postoperative intelligent rehabilitation. This is achieved by implementing and monitoring rehabilitation activities using rehabilitation techniques and methods under different consciousness and cognitive states according to the guidance of the intelligent strategy plan to achieve the best rehabilitation management effect. Through this step, the rehabilitation plan can be dynamically adjusted to improve the rehabilitation effect of children, and continuous intelligent management and optimization process can be achieved throughout the rehabilitation process, so as to achieve more effective rehabilitation management results and improve the quality of life of children. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0058] Figure 1 This is a schematic diagram of the intelligent postoperative rehabilitation management system for critically ill children of the present invention;

[0059] Figure 2 for Figure 1 Schematic diagram of the functional flow of the postoperative rehabilitation EEG signal monitoring module;

[0060] Figure 3 for Figure 1 Schematic diagram of the functional flow of the postoperative rehabilitation consciousness cognitive state analysis module. DETAILED DESCRIPTION

[0061] The technical system of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0062] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware steps or integrated circuits, or implemented in different networks and / or processor systems and / or microcontroller systems.

[0063] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0064] To achieve this, please refer to Figures 1 to 3 The present invention provides an intelligent postoperative rehabilitation management system for critically ill children, wherein the brain wave signals of the critically ill children during postoperative rehabilitation are brain wave signals fed back by performing rehabilitation perception tasks on the critically ill children after surgery through preset rehabilitation perception signals, and the system includes the following modules:

[0065] The postoperative rehabilitation EEG signal monitoring module is used to collect the EEG signals of critically ill children during the postoperative rehabilitation period in real time through the EEG signal monitoring equipment and upload them to the data processing unit for signal preprocessing to obtain the enhanced EEG signal data of the postoperative rehabilitation of critically ill children; based on the EEG signal monitoring equipment, the abnormal EEG distribution of the equipment is calibrated and processed on the enhanced EEG signal data of the postoperative rehabilitation of critically ill children to generate a calibrated spectrum of the EEG signal distribution during the postoperative rehabilitation period;

[0066] The postoperative rehabilitation consciousness and cognitive state analysis module is used to quantify the consciousness and cognitive score of the EEG signal distribution calibration spectrum during the postoperative rehabilitation period, so as to obtain the EEG consciousness and cognitive score during the postoperative rehabilitation period at each time point; based on the EEG consciousness and cognitive score during the postoperative rehabilitation period at each time point, the corresponding children's postoperative rehabilitation consciousness and cognitive period in the EEG signal distribution calibration spectrum during the postoperative rehabilitation period is divided into consciousness and cognitive states, so as to obtain the children's consciousness and cognitive functional state during the postoperative rehabilitation period, wherein the children's consciousness and cognitive functional state during the postoperative rehabilitation period includes consciousness and cognitive unawakenable state, consciousness and cognitive sedation state and consciousness and cognitive agitation state;

[0067] The intelligent strategy analysis module for rehabilitation of consciousness and cognitive status is used to set rehabilitation goals for the consciousness and cognitive function states of children in different rehabilitation periods after surgery, so as to obtain rehabilitation goals for children with different consciousness and cognitive function states after surgery; based on the rehabilitation goals for children with different consciousness and cognitive function states after surgery, intelligent strategy analysis is performed on the rehabilitation activity projects for the corresponding consciousness and cognitive function states of children in the rehabilitation period after surgery, so as to generate intelligent strategy plans for rehabilitation activity projects for children with different consciousness and cognitive states after surgery;

[0068] The children's postoperative rehabilitation intelligent management module is used to perform postoperative rehabilitation intelligent management on the children's consciousness and cognitive function status during the corresponding postoperative rehabilitation period according to the intelligent strategy plan of the rehabilitation activity project of the children's different consciousness and cognitive status after surgery, and obtain the intelligent management results of postoperative rehabilitation for critically ill children.

[0069] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of an intelligent postoperative rehabilitation management system for critically ill children according to the present invention. In this example, the intelligent postoperative rehabilitation management system for critically ill children includes the following modules:

[0070] S1: Postoperative rehabilitation EEG signal monitoring module, used to collect EEG signals of critically ill children during postoperative rehabilitation in real time through EEG signal monitoring equipment and upload them to the data processing unit for signal preprocessing to obtain enhanced EEG signal data of critically ill children after postoperative rehabilitation; based on the EEG signal monitoring equipment, the enhanced EEG signal data of critically ill children after postoperative rehabilitation is calibrated for abnormal EEG distribution of the equipment to generate a calibrated spectrum of EEG signal distribution during postoperative rehabilitation;

[0071] In an embodiment of the present invention, the brain wave signals of critically ill children during postoperative rehabilitation are collected in real time by using corresponding EEG signal monitoring equipment, so as to pre-set rehabilitation perception signals according to the critical treatment conditions of children, including treatment plans, methods, postoperative monitoring and rehabilitation requirements, etc., and use multimedia and devices based on sound, light, electricity and other forms as carriers, such as virtual reality, music playback, natural environment sounds and smells familiar to children, etc. to design rehabilitation perception signals for each critically ill child patient after surgery, and select and formulate rehabilitation training content for the postoperative children's hearing, vision, smell, touch and other cognitive functions, and guide and capture the children's targeted cognitive reactions and responses to the multimedia rehabilitation content selected for playback through corresponding EEG signal monitoring equipment, i.e. sensors and physical devices. The acquired EEG signals are judged, and the original EEG signals obtained by real-time monitoring are uploaded to the data processing unit in the order of the time of real-time acquisition. The EEG signals are decomposed into different frequency components using corresponding noise reduction algorithms, including wavelet transform and independent component analysis (ICA), and the noise is selectively removed to ensure the best noise suppression effect, thereby helping to extract clear and reliable EEG signals for subsequent processing. The EEG signal noise reduction data obtained after the signal noise reduction processing is enhanced by using the corresponding signal enhancement processing method to further improve its quality and usability, so as to enhance the weak features or subtle changes of the EEG signals and make them more obvious and easy to identify, thereby obtaining enhanced EEG signal data for postoperative rehabilitation of critically ill children. Then, by using data visualization tools or special equipment, the signal distribution map of the EEG signal enhancement data of postoperative rehabilitation of critically ill children obtained after signal enhancement is drawn to display the spatial distribution of the EEG signal in a graphical form, and by using mathematical statistical methods, the previously drawn EEG signal distribution spectrum is further statistically analyzed to statistically analyze the corresponding EEG signal fluctuation frequency and fluctuation amplitude, and screen out the abnormal fluctuation distribution period caused by the abnormal EEG signal monitoring equipment (including checking whether the equipment connection is firm, whether the electrodes are correctly placed, and whether the equipment software needs to be updated). At the same time, by combining the abnormal distribution period of the monitoring equipment obtained by the previous screening, the corresponding fault probability is statistically analyzed to calibrate the EEG signal distribution of the corresponding EEG signal distribution spectrum. This processing process aims to correct or calibrate the EEG signal distribution spectrum to reflect the actual performance of the monitoring equipment during the abnormal period, so as to better reflect the actual monitoring capability of the monitoring equipment in different time periods, and finally calibrate and generate the corresponding EEG signal distribution calibration spectrum during postoperative rehabilitation.

[0072] S2: Postoperative rehabilitation consciousness and cognitive state analysis module, used to quantify the consciousness and cognitive score of the EEG signal distribution calibration spectrum during the postoperative rehabilitation period, so as to obtain the EEG consciousness and cognitive score during the postoperative rehabilitation period at each time point; based on the EEG consciousness and cognitive score during the postoperative rehabilitation period at each time point, the corresponding children's postoperative rehabilitation consciousness and cognitive period in the EEG signal distribution calibration spectrum during the postoperative rehabilitation period is divided into consciousness and cognitive states, so as to obtain the children's consciousness and cognitive functional state during the postoperative rehabilitation period, wherein the children's consciousness and cognitive functional state during the postoperative rehabilitation period includes consciousness and cognitive unawakenable state, consciousness and cognitive sedation state and consciousness and cognitive agitation state;

[0073] In an embodiment of the present invention, a previously drawn calibration spectrum of EEG signal distribution during postoperative rehabilitation is used to perform a statistical analysis of energy distribution and power density in signal frequency bands by using previous signal processing algorithms and data analysis tools to evaluate the characteristics of the patient's postoperative EEG signal activity, including energy distribution and power density in different frequency bands, and perform detailed time-segmented analysis according to different time points (such as the 1st minute, 1st hour, 1st day, 1st week, 1st month, etc. after surgery) to record EEG activities at different time points in detail, so that the specific EEG signal frequency band energy distribution and power density values ​​at each time point can be obtained, so as to quantitatively calculate the corresponding consciousness cognition score, and objectively evaluate the child's consciousness state at each time point during postoperative rehabilitation, so as to obtain the EEG consciousness cognition score during postoperative rehabilitation at each time point. Then, by combining the EEG consciousness cognition scores during postoperative rehabilitation at each time point obtained by previous quantitative calculation, the corresponding rehabilitation time periods in the EEG signal distribution calibration spectrum during postoperative rehabilitation are merged and divided into cognitive score equal time periods, so as to identify the equal consciousness cognition scores at adjacent time points, and integrate the time periods between them to form a large cognitive equivalent time segment, and identify and classify the corresponding consciousness and cognitive function states of children in different rehabilitation periods according to the specific values ​​of their EEG consciousness cognition scores. For example, in each cognitive equivalent time period, the medical team will The EEG consciousness cognition scores of the children were analyzed and compared. If the corresponding EEG consciousness cognition score was 0-3 points, it was identified as a state of consciousness cognition that could not be awakened; if the corresponding EEG consciousness cognition score was 3-7 points, it was identified as a state of consciousness cognition sedation; and if the corresponding EEG consciousness cognition score was 7-10 points, it was identified as a state of consciousness cognition agitation. After the consciousness cognition score in each cognitive equivalent period was identified, the different consciousness cognition states of children in different cognitive equivalent periods were identified, and finally the consciousness cognition function state of children during the postoperative rehabilitation period was obtained.

[0074] S3: Intelligent strategy analysis module for rehabilitation of consciousness and cognitive state, used to set rehabilitation goals for different consciousness and cognitive function states of children after surgery, so as to obtain rehabilitation goals for different consciousness and cognitive function states of children after surgery; based on the rehabilitation goals for different consciousness and cognitive function states of children after surgery, intelligent strategy analysis of rehabilitation activity projects for corresponding consciousness and cognitive function states of children after surgery is performed, so as to generate intelligent strategy plans for rehabilitation activity projects for different consciousness and cognitive states of children after surgery;

[0075] In an embodiment of the present invention, if it is determined that the consciousness and cognitive function state of the child during the postoperative rehabilitation period is a state where consciousness and cognition cannot be awakened, it usually refers to a coma or extreme lethargy state in which the critically ill child's brain consciousness and cognitive activity appears after surgery. At this time, the child is unable to respond to external stimuli or awakening, and corresponding passive rehabilitation goals are formulated. In this case, the passive rehabilitation goals include maintaining muscle and joint mobility through physical therapy and regular physical activity, promoting blood circulation and flexibility of the rehabilitation area, and reducing muscle stiffness through passive movement and massage to avoid the occurrence of complications, thereby setting the corresponding passive rehabilitation goals of the non-awakenable state. If it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a state of consciousness and cognitive sedation, it usually means that the child is in a semi-comatose or drowsy state, and can partially respond to external stimuli, but the response is weak or slow, and the corresponding auxiliary rehabilitation goals are formulated accordingly. In this case, the auxiliary rehabilitation goals include the use of psychotherapy, music therapy or deep breathing techniques to promote emotional stability and cognitive recovery, and at the same time, progressive physical activities and functional training to improve muscle control and coordination, so as to help critically ill children enhance their ability to respond to external stimuli, thereby setting the corresponding auxiliary rehabilitation goals for sedation. If it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a state of consciousness and cognitive agitation, it usually refers to the state of restlessness, anxiety or overactivity that occurs after the child's surgery, which is caused by postoperative pain, drug side effects or emotional changes, and the corresponding active rehabilitation goals are formulated. The active rehabilitation goals improve self-control and emotional management abilities through physical training, exercise therapy and cognitive behavioral therapy, and promote mental health and rehabilitation progress through social support and emotional regulation, so as to help children actively participate in the rehabilitation process, thereby setting the corresponding active rehabilitation goals for agitation. Then, by combining the previously set passive rehabilitation goals for the unarousable state, auxiliary rehabilitation goals for the sedated state, and active rehabilitation goals for the agitated state, an intelligent strategy analysis of the rehabilitation activity projects for the corresponding children's consciousness and cognitive function status during the postoperative rehabilitation period is conducted. According to the specific situation of the children and the corresponding rehabilitation needs goals, intelligent rehabilitation plans and activity plans are formulated, and finally an intelligent strategy plan for rehabilitation activity projects for children with different consciousness and cognitive states after surgery is generated.

[0076] S4: The intelligent management module for postoperative rehabilitation of children is used to perform intelligent management of the postoperative rehabilitation of the corresponding children's cognitive function status during the postoperative rehabilitation period according to the intelligent strategy plan of the rehabilitation activity project for the different cognitive status of children after surgery, and obtain the intelligent management results of postoperative rehabilitation of critically ill children.

[0077] In an embodiment of the present invention, the corresponding postoperative rehabilitation process is intelligently managed and processed for the corresponding postoperative rehabilitation period of children's consciousness and cognitive function states (including consciousness and cognitive unawakenable states, consciousness and cognitive sedation states, and consciousness and cognitive agitation states) according to the previously generated intelligent strategy programs for rehabilitation activity projects of different postoperative consciousness and cognitive states of children, and the intelligent strategy programs formulated according to the evaluation results are used for the postoperative rehabilitation management of critically ill children in the corresponding consciousness and cognitive function states. For children who are awake but have impaired cognitive functions, virtual reality technology combined with cognitive training programs will be used to improve memory and attention. The selection and design of the strategy programs take into account the age, rehabilitation expectations, and neurophysiological characteristics of the children to achieve the best rehabilitation effect, thereby implementing the intelligent management processing process, which includes monitoring and adjusting the execution process of the rehabilitation program, for example, using intelligent monitoring technology to track the cognitive function progress and rehabilitation response of the children in real time, so as to adjust the difficulty and frequency of rehabilitation activities according to real-time data. In addition, biofeedback and machine learning algorithms will be combined to conduct personalized evaluation and prediction of the rehabilitation performance of the children, so as to optimize the implementation and effect of the rehabilitation strategy, and finally obtain the intelligent management results of postoperative rehabilitation of critically ill children.

[0078] Furthermore, the postoperative rehabilitation EEG signal monitoring module includes the following functions:

[0079] The EEG signal monitoring equipment is used to collect the EEG signals of critically ill children during their postoperative rehabilitation in real time, and the original EEG signal data of critically ill children during their postoperative rehabilitation are obtained;

[0080] By uploading the original EEG signal data of critically ill children during postoperative rehabilitation to the data processing unit in the order of time collected in real time, the real-time EEG signal data of critically ill children during postoperative rehabilitation are obtained;

[0081] The data processing unit is used to perform signal noise reduction processing on the real-time EEG signal data of critically ill children during postoperative rehabilitation, and the noise reduction data of EEG signals during postoperative rehabilitation of critically ill children are obtained;

[0082] The EEG signal noise reduction data of critically ill children during postoperative rehabilitation was processed to obtain the EEG signal enhancement data of critically ill children during postoperative rehabilitation.

[0083] Based on the EEG signal monitoring equipment, the abnormal EEG distribution of the equipment was calibrated and processed for the EEG signal enhancement data of critically ill children after surgery, and a calibrated EEG signal distribution spectrum during postoperative rehabilitation was generated.

[0084] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 The functional flow chart of the postoperative rehabilitation EEG signal monitoring module is as follows. In this embodiment, the functions of the postoperative rehabilitation EEG signal monitoring module include:

[0085] S11: The EEG signal monitoring device is used to collect the EEG signal of critically ill children during the postoperative rehabilitation period in real time to obtain the original EEG signal data of critically ill children during the postoperative rehabilitation period;

[0086] In the embodiment of the present invention, the brain wave signals of critically ill children during postoperative rehabilitation are collected in real time by using corresponding EEG signal monitoring equipment, so as to pre-set rehabilitation perception signals according to the critical treatment conditions of children, including treatment plans, methods, postoperative monitoring and rehabilitation requirements, etc., and use multimedia and devices based on sound, light, electricity and other forms as carriers, such as virtual reality, music playback, natural environment sounds and smells familiar to children, etc. to design rehabilitation perception signals for each critically ill child patient after surgery, and select and formulate rehabilitation training content for the cognitive functions of hearing, vision, smell, touch and other cognitive functions of children after surgery, and use corresponding EEG signals to monitor and control the postoperative children's brain wave signals. Monitoring equipment, that is, sensors and physical devices, guides and captures children's targeted cognitive responses and judgments to the multimedia rehabilitation content selected for playback. The key to this process is to accurately and continuously capture children's EEG activities to support subsequent rehabilitation monitoring and analysis. For example, in postoperative rehabilitation management, a critically ill child needs to closely monitor his EEG activity after undergoing brain trauma surgery. The medical team will install EEG signal monitoring equipment and ensure the correct placement and connection of the equipment. Subsequently, the equipment will collect the child's EEG signals in real time during postoperative rehabilitation, and finally obtain the original EEG signal data of the critically ill child during postoperative rehabilitation.

[0087] S12: uploading the original EEG signal data of the critically ill children during the postoperative rehabilitation period to the data processing unit according to the time sequence of real-time acquisition to obtain the real-time EEG signal data of the critically ill children during the postoperative rehabilitation period;

[0088] In an embodiment of the present invention, the original EEG signals of critically ill children during postoperative rehabilitation obtained by real-time monitoring are uploaded to a data processing unit in the order of time of real-time acquisition to ensure that available and formatted data are obtained from the monitored EEG signals. For example, in postoperative rehabilitation management, the monitoring equipment will continuously record and transmit the children's brain wave signal data to the data processing unit, and the medical team will upload these data to dedicated data processing software or server through a special data transmission interface or network connection. During the uploading process, the security and integrity of the EEG signal data will be ensured to avoid any potential information loss or damage, and finally the real-time EEG signal data of critically ill children after postoperative rehabilitation will be obtained.

[0089] S13: using the data processing unit to perform signal noise reduction processing on the real-time EEG signal data of the critically ill children during postoperative rehabilitation, to obtain EEG signal noise reduction data of the critically ill children during postoperative rehabilitation;

[0090] In an embodiment of the present invention, a corresponding noise reduction algorithm is used in the data processing unit, including wavelet transform and independent component analysis (ICA). For example, through wavelet transform, the EEG signal can be decomposed into different frequency components, and then the noise is selectively removed. In this process, the noise reduction algorithm will be adjusted according to the previous data statistical characteristics and the real-time collected signal to ensure the best noise suppression effect, thereby helping to extract clear and reliable EEG signals for subsequent processing, and finally obtaining EEG signal noise reduction data during postoperative rehabilitation of critically ill children.

[0091] S14: Perform signal enhancement processing on the EEG signal noise reduction data of critically ill children during postoperative rehabilitation to obtain EEG signal enhancement data of critically ill children during postoperative rehabilitation;

[0092] In an embodiment of the present invention, the noise reduction data of EEG signals during the postoperative rehabilitation of critically ill children obtained after the signal noise reduction processing is previously obtained by using a corresponding signal enhancement processing method to perform signal enhancement processing to further improve its quality and usability. Once the noise-reduced EEG signal data is obtained, the next step will focus on signal enhancement and optimization. This step involves spectrum analysis and frequency feature extraction of EEG signals. For example, fast Fourier transform (FFT) or other frequency domain analysis techniques can be used to check the energy distribution of EEG signals in different frequency bands. It also involves the application of spatial characteristic analysis and spatial filtering technology of EEG signals. In EEG signal processing, spatial filtering can enhance the localization characteristics of signals through the spatiotemporal relationship between electrodes. For example, commonly used spatial filtering methods include co-occurrence matrix analysis and calculation of local field potentials. These methods help to reduce the impact of environmental and physiological noise and enhance the spatiotemporal resolution of EEG signals, thereby enhancing weak features or subtle changes in EEG signals, making them more obvious and easy to identify, and finally obtaining enhanced EEG signal data for postoperative rehabilitation of critically ill children.

[0093] S15: Based on the EEG signal monitoring equipment, the abnormal EEG distribution of the equipment is calibrated and processed for the EEG signal enhancement data of critically ill children after surgery, and a calibration spectrum of the EEG signal distribution during postoperative rehabilitation is generated.

[0094] In an embodiment of the present invention, a signal distribution diagram is drawn for the enhanced EEG signal data of critically ill children after postoperative rehabilitation obtained after signal enhancement by using a data visualization tool or a special device, so as to display the spatial distribution of the EEG signal in a graphical form, and a further statistical analysis is performed on the EEG signal distribution spectrum previously drawn by using a mathematical statistical method, so as to statistically analyze the corresponding EEG signal fluctuation frequency and fluctuation amplitude, and screen out the abnormal fluctuation distribution period caused by the abnormal EEG signal monitoring device (including checking whether the device connection is firm, whether the electrodes are correctly placed, and whether the device software needs to be updated). At the same time, by combining the statistical analysis of the abnormal distribution period of the monitoring device obtained by the previous screening, The corresponding failure probability is used to calibrate the corresponding EEG signal distribution spectrum. This process aims to correct or calibrate the EEG signal distribution spectrum to reflect the actual performance of the monitoring equipment during the abnormal period. For example, assuming that the failure probability of the monitoring equipment is high during a certain abnormal distribution period, indicating that the equipment fails to accurately record all the characteristics of the child's EEG signals, the EEG signal distribution spectrum of the corresponding period will be adjusted according to this failure probability, and mathematical correction or data correction technology, such as weighted processing or error correction, will be used to ensure the accuracy and consistency of the spectrum, so as to better reflect the actual monitoring capability of the monitoring equipment in different time periods, and finally the corresponding EEG signal distribution calibration spectrum during postoperative rehabilitation will be generated.

[0095] Furthermore, the abnormal EEG distribution calibration of the EEG signal enhancement data of critically ill children after surgery based on the EEG signal monitoring device includes:

[0096] The EEG signal distribution was mapped on the EEG signal enhancement data of critically ill children after surgery to generate the initial distribution spectrum of EEG signals during children's postoperative rehabilitation.

[0097] In an embodiment of the present invention, a signal distribution map is drawn for the EEG signal enhancement data of critically ill children after postoperative rehabilitation that was previously obtained after signal enhancement by using a data visualization tool or a specialized device, so as to display the spatial distribution of the EEG signal in a graphical form, draw a topological map of the EEG signal distribution, and display the electrical activity intensity and distribution pattern of the EEG signal, thereby determining the initial distribution of the child's EEG signal during postoperative rehabilitation, and finally drawing and generating an initial distribution spectrum of the EEG signal during postoperative rehabilitation of the child.

[0098] Preferably, the signal fluctuation frequency and amplitude statistical analysis is performed on the initial distribution spectrum of the EEG signal during the postoperative rehabilitation period of the child to obtain the EEG signal fluctuation frequency during the postoperative rehabilitation period and the EEG signal fluctuation amplitude during the postoperative rehabilitation period;

[0099] In an embodiment of the present invention, a mathematical statistical method is used to further statistically analyze the previously drawn initial distribution spectrum of EEG signals during children's postoperative rehabilitation, so as to statistically analyze the number of occurrences and durations of corresponding EEG signal frequency bands in different time periods, thereby statistically calculating the frequency of EEG signal fluctuations on the initial distribution spectrum of EEG signals during children's postoperative rehabilitation. At the same time, the amplitude changes of the EEG signals are also analyzed, which includes determining the peak amplitude, fluctuation amplitude and amplitude distribution pattern of the signal, thereby helping to understand the intensity and stability of children's brain activity during postoperative rehabilitation, and finally obtaining the frequency of EEG signal fluctuations during postoperative rehabilitation and the amplitude of EEG signal fluctuations during postoperative rehabilitation.

[0100] Preferably, the abnormal distribution period of the equipment is analyzed according to the fluctuation frequency of the EEG signal during the postoperative rehabilitation period and the fluctuation amplitude of the EEG signal during the postoperative rehabilitation period, so as to obtain the abnormal distribution period of the postoperative EEG signal monitoring equipment;

[0101] In an embodiment of the present invention, the abnormal time periods of the equipment are screened and processed by combining the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude during postoperative rehabilitation obtained by previous statistical calculations to screen out the abnormal fluctuation distribution time periods caused by abnormal monitoring equipment (including checking whether the equipment connection is firm, whether the electrodes are correctly placed, and whether the equipment software needs to be updated). The data recorded by the EEG signal monitoring equipment is reviewed to identify the time periods with sudden changes in fluctuation frequency or amplitude, and these time periods are marked as abnormal distribution time periods, finally obtaining the abnormal distribution time periods of the postoperative EEG signal monitoring equipment.

[0102] Preferably, based on the abnormal distribution period of the postoperative EEG signal monitoring device, an abnormal period point failure probability analysis is performed on the EEG signal monitoring device to obtain a monitoring device failure probability value at each time sequence point within the abnormal distribution period;

[0103] In an embodiment of the present invention, the failure probability of the corresponding EEG signal monitoring device at the timing point is quantitatively calculated by combining the abnormal distribution time period of the postoperative EEG signal monitoring device obtained by combining the previously screened out, so as to evaluate and calculate the failure probability value of the monitoring device at each timing point in the abnormal distribution time period. This step uses statistical methods and data analysis techniques to conduct an in-depth analysis of the monitoring device data in the abnormal distribution time period. For example, in postoperative rehabilitation management, if the monitoring device has frequent data collection errors or signal loss in certain specific time periods, this will affect the medical team's accurate monitoring of the child's EEG activity, thereby quantitatively calculating the failure probability of each monitoring timing point in the abnormal distribution time period. This probability analysis helps to identify monitoring points with higher failure risks and ensure the normal working state of the monitoring equipment in critical time periods, and finally obtain the failure probability value of the monitoring device at each timing point in the abnormal distribution time period.

[0104] Preferably, based on the abnormal distribution period of the postoperative EEG signal monitoring device, the failure probability value of the monitoring device at each time point within the abnormal distribution period is calculated by arithmetic mean during the abnormal distribution period to obtain the average failure probability value of the monitoring device within the abnormal distribution period; according to the average failure probability value of the monitoring device within the abnormal distribution period, the initial distribution spectrum of the EEG signal of the child during the postoperative rehabilitation period corresponding to the abnormal distribution period of the postoperative EEG signal monitoring device is calibrated and processed by EEG distribution calibration to generate a calibrated distribution spectrum of the EEG signal during the postoperative rehabilitation period.

[0105] In an embodiment of the present invention, an arithmetic average calculation is performed on the failure probability value of the monitoring equipment at each timing point within the abnormal distribution period by combining the previously determined duration of the abnormal distribution period of the postoperative EEG signal monitoring equipment, so as to comprehensively consider the failure probability of all monitoring points within the abnormal distribution period and perform an arithmetic average quantitative calculation, and quantify the calculation to obtain an overall failure probability average value, thereby obtaining the failure probability average value of the monitoring equipment within the abnormal distribution period. At the same time, the EEG signal distribution is calibrated by combining the average failure probability of the monitoring equipment in the abnormal distribution period obtained by previous quantitative calculation to the initial distribution spectrum of the EEG signal during the postoperative rehabilitation period of the children corresponding to the abnormal distribution period of the postoperative EEG signal monitoring equipment. This processing process aims to correct or calibrate the EEG signal distribution spectrum to reflect the actual performance of the monitoring equipment in the abnormal period. For example, assuming that in a certain abnormal distribution period, the average failure probability of the monitoring equipment is high, indicating that the equipment fails to accurately record all the characteristics of the child's EEG signal, the EEG signal distribution spectrum of the corresponding period will be adjusted according to the average failure probability, so as to adopt mathematical correction or data correction technology, such as weighted processing or error correction, to ensure the accuracy and consistency of the spectrum, so as to better reflect the actual monitoring capability of the monitoring equipment in different time periods, and finally calibrate and generate the corresponding EEG signal distribution calibration spectrum during postoperative rehabilitation.

[0106] Furthermore, the device abnormal distribution period analysis based on the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude during the postoperative rehabilitation period includes:

[0107] Performing time-series synchronization processing on the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude during the postoperative rehabilitation period, and obtaining the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude in the same time sequence dimension;

[0108] In an embodiment of the present invention, a timing synchronization method is used to perform timing synchronization processing on the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude during postoperative rehabilitation obtained from previous statistical analysis, so as to ensure the accuracy and consistency of the EEG signal fluctuation frequency (such as alpha wave, beta wave, etc.) and amplitude (signal strength) at each monitoring time point, and to ensure the precise matching and comparison of each EEG signal fluctuation feature in the same time sequence dimension, so as to reveal the changing trend and pattern of the EEG signal at different time points, and finally obtain the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude in the same time sequence dimension.

[0109] Preferably, a signal fluctuation hyperbola is plotted for the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude in the same time sequence dimension to generate an EEG signal fluctuation frequency-amplitude change hyperbola;

[0110] In an embodiment of the present invention, a signal fluctuation hyperbola is drawn for the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude in the same time sequence dimension obtained after time series synchronization by using statistical analysis software or a dedicated data processing tool, aiming to illustrate the relationship and change trend between different fluctuation characteristics through a curve diagram, thereby drawing a hyperbola of EEG signal fluctuation frequency-amplitude change. For example, by using the frequency and amplitude obtained from EEG signal monitoring, a hyperbola graph between fluctuation frequency-amplitude change is drawn. This graph can clearly show how the dynamic characteristics of EEG signals during rehabilitation change over time, such as whether there are significant changes in frequency or fluctuations in amplitude at a specific rehabilitation stage, thereby helping to understand the changes in neural activity during the patient's rehabilitation process, and finally drawing and generating a hyperbola of EEG signal fluctuation frequency-amplitude change.

[0111] Preferably, a signal fluctuation inflection point statistical analysis is performed on the EEG signal fluctuation frequency-amplitude change hyperbola to obtain an inflection point set of the EEG signal fluctuation frequency change curve and an inflection point set of the EEG signal fluctuation amplitude change curve; based on the inflection points between each two curves in the EEG signal fluctuation frequency change curve inflection point set and the EEG signal fluctuation amplitude change curve inflection point set, the EEG signal fluctuation frequency-amplitude change hyperbola is divided into curve distribution time periods according to their appearance order to obtain distribution time periods of each EEG signal fluctuation change curve;

[0112] In an embodiment of the present invention, a data inflection point analysis method is used to perform a statistical analysis of the signal fluctuation inflection points on the previously drawn EEG signal fluctuation frequency-amplitude change hyperbola, so as to identify and determine the key change points on the fluctuation hyperbola, that is, the corresponding curve inflection points, so as to facilitate the subsequent time period division and pattern analysis, so that the inflection points on the frequency change curve and the amplitude change curve can be accurately identified, that is, the time points when important changes occur. These inflection points represent specific changes in the patient's nervous system activity, such as rapid changes in frequency fluctuations or significant increases or decreases in amplitude within a certain period of time, thereby obtaining an EEG signal fluctuation frequency change curve inflection point set and an EEG signal fluctuation amplitude change curve inflection point set. At the same time, by combining the previously obtained EEG signal fluctuation frequency change curve inflection point set and the EEG signal fluctuation amplitude change curve inflection point set, the corresponding fluctuation frequency-amplitude change hyperbola is divided into time periods according to the order of their appearance, so that the continuous EEG signal fluctuation change curve inflection points are divided into different curve distribution time periods according to the order of their appearance, and finally the distribution time periods of each EEG signal fluctuation change curve are obtained.

[0113] Preferably, based on each EEG signal fluctuation change curve distribution period, the corresponding EEG signal fluctuation frequency-amplitude change hyperbola is subjected to curve change pattern recognition analysis to obtain the EEG signal fluctuation curve change pattern within each fluctuation distribution period; the EEG signal fluctuation curve change pattern within each fluctuation distribution period is subjected to abnormal change period detection to obtain the fluctuation distribution period corresponding to the abnormal change pattern of EEG signal fluctuation;

[0114] In an embodiment of the present invention, by combining the previously divided distribution periods of each EEG signal fluctuation change curve, a change pattern method is used to identify and analyze the curve change pattern of the corresponding EEG signal fluctuation frequency-amplitude change hyperbola, aiming to explore the change pattern of EEG signal fluctuations in different time periods, such as whether there are periodic changes, trend changes or sudden changes, etc. For example, during rehabilitation, the change pattern of the fluctuation curve can be analyzed for different fluctuation distribution periods, for example, a curve change pattern in which the frequency fluctuation increases and the amplitude fluctuation decreases in a certain period, or a change pattern in which the frequency and amplitude increase synchronously in another period. These pattern analyses can help understand the complex dynamics of neural activity during rehabilitation, thereby obtaining the change pattern of the EEG signal fluctuation curve in each fluctuation distribution period. At the same time, by using an abnormal detection algorithm to detect abnormal change periods of the EEG signal fluctuation curve change pattern in each fluctuation distribution period, the abnormal change period is detected to identify and mark the period in which the abnormal change pattern appears, and finally the fluctuation distribution period corresponding to the abnormal change pattern of the EEG signal fluctuation is obtained.

[0115] Preferably, the fluctuation distribution period corresponding to the abnormal change pattern of the EEG signal fluctuation is subjected to equipment abnormality cause period screening processing to obtain the abnormal distribution period of the postoperative EEG signal monitoring equipment.

[0116] In an embodiment of the present invention, by tracing the cause of the abnormal change of the fluctuation distribution time period corresponding to the abnormal change pattern of the EEG signal fluctuation previously identified, the cause of the abnormal fluctuation is identified and analyzed as a monitoring equipment problem or other technical influencing factors. If it is found during the analysis process that abnormal change patterns appear in some abnormal fluctuation distribution time periods, such as a sudden decrease in frequency or an abnormal increase in amplitude, this indicates that there is a potential problem with the equipment, and the interference source of the abnormal change pattern is recorded and analyzed, such as electromagnetic field interference, power supply fluctuations, or monitoring equipment abnormalities, thereby screening out the fluctuation distribution time periods caused by abnormal monitoring equipment (including checking whether the equipment connection is firm, whether the electrodes are correctly placed, and whether the equipment software needs to be updated), and finally obtaining the abnormal distribution time periods of the postoperative EEG signal monitoring equipment.

[0117] Further, the abnormal time period point fault probability analysis of the EEG signal monitoring device based on the abnormal distribution time period of the postoperative EEG signal monitoring device includes:

[0118] The abnormal distribution period of the postoperative EEG signal monitoring device is divided into abnormal time sequence points, and the abnormal time sequence points of each EEG signal monitoring device in the abnormal distribution period are obtained;

[0119] In an embodiment of the present invention, the abnormal distribution time period of the postoperative EEG signal monitoring device previously determined is divided into abnormal time series points to accurately locate the abnormal events of the device occurring during the monitoring process, and further analyze the time series points corresponding to these abnormal events. For example, consider a child undergoing EEG signal monitoring after surgery to evaluate his brain activity. During the monitoring process, the monitoring device will record some abnormal distribution time periods due to possible equipment failures, such as signal loss, increased noise or electromagnetic interference, and based on these abnormal time periods, each abnormal time series point is accurately marked through time series analysis. These time series points can help track the probability of occurrence of abnormal events in the monitoring device, thereby evaluating the degree of its impact on the quality of EEG signal monitoring data, and finally mark and divide each abnormal time series point of the EEG signal monitoring device within the abnormal distribution time period.

[0120] Preferably, the working state of the EEG signal monitoring device is monitored and analyzed based on each abnormal timing point of the EEG signal monitoring device within the abnormal distribution period, and the working state parameter data of the EEG signal monitoring device at each abnormal timing point of the device is obtained;

[0121] In an embodiment of the present invention, by combining each abnormal timing point of the EEG signal monitoring device within the abnormal distribution time period obtained by the previous division, the working status of the EEG signal monitoring device at the corresponding abnormal timing point is monitored in real time, so as to have an in-depth understanding of the working status and performance of the device when each abnormal event occurs. In actual operation, the device working status parameters at each abnormal timing point are collected and recorded, such as the signal strength, spectrum distribution, electromagnetic interference level, etc. of the monitoring device. For example, continuing with the above-mentioned case of children's EEG signal monitoring, when the device records the abnormal timing point, the working status of the monitoring device at each timing point in the time period is analyzed, including whether the device is in normal working mode, whether it is affected by external interference, the quality of signal capture, etc., so as to determine the performance problems or data distortion of the monitoring device during the abnormal event, and finally obtain the working status parameter data of the EEG signal monitoring device at each abnormal timing point of the device.

[0122] Preferably, the equipment failure probability is quantitatively calculated for the EEG signal monitoring equipment working status parameter data at each abnormal timing point of the equipment using the monitoring equipment operation failure probability calculation formula to obtain the monitoring equipment failure probability value at each timing point within the abnormal distribution period.

[0123] In an embodiment of the present invention, a suitable monitoring equipment operation failure probability calculation formula is constructed by combining the initial abnormal timing point of the abnormal distribution period, the terminal abnormal timing point of the abnormal distribution period, the measurement variable parameters of the abnormal timing point, the measurement variable parameters of the equipment working status parameters, the fault impact attenuation coefficient, the fault impact adjustment factor, the fault impact normalization factor, the fault impact index and related parameters to quantitatively calculate the equipment failure probability of the EEG signal monitoring equipment working status parameter data at each equipment abnormal timing point, so as to quantitatively calculate the failure possibility of the monitoring equipment at the corresponding abnormal timing point, and finally obtain the monitoring equipment failure probability value at each timing point in the abnormal distribution period.

[0124] Furthermore, the calculation formula for the probability of failure of the monitoring equipment is as follows:

[0125] ;

[0126] In the formula, is the abnormal time sequence point within the abnormal distribution period The failure probability value of the monitoring equipment at is the initial abnormal time sequence point of the abnormal distribution period, is the termination abnormal timing point of the abnormal distribution period, is the measurement variable parameter of the abnormal time series point, is the number of device working status parameters in the working status parameter data of the EEG signal monitoring device. It is the item index parameter of the equipment working status parameter. For the The fault impact attenuation coefficient of the working status parameters of each device, For the The fault impact adjustment factor of each device working status parameter, For the The fault impact normalization factor of each device working status parameter, For the The fault impact index of the working status parameters of each device, It is the correction factor of the failure probability value of the monitoring equipment.

[0127] The present invention obtains a monitoring equipment operation failure probability calculation formula by using a specific mathematical model and after verification, which is used to quantitatively calculate the equipment failure probability of the EEG signal monitoring equipment working state parameter data at each equipment abnormal timing point. The parameters in the monitoring equipment operation failure probability calculation formula include (Fault impact attenuation coefficient), (Fault Impact Adjustment Factor), (Fault Impact Normalization Factor) and (Fault Impact Index), these parameters comprehensively consider the impact of multiple working status parameters of the monitoring equipment on the probability of failure, and can comprehensively evaluate the working status of the equipment. The formula also calculates the fault impact index of each time point in the abnormal distribution period by integration. This time series analysis not only considers the state at a single moment, but also comprehensively analyzes the state changes within the abnormal time series point interval. It is a parameter that measures the rate at which the probability of equipment failure decays over time. This model represents a model in which the probability of equipment failure decays exponentially over time. This model can more realistically reflect the changing trend of the equipment failure probability at abnormal time sequence points. As a correction coefficient for the failure probability value of the monitoring equipment, it is used to correct the calculation results to make them more consistent with the actual working status of the monitoring equipment. The introduction of the correction coefficient enhances the applicability and accuracy of the formula. At the same time, the calculation results of the formula can be used to monitor the working status of the equipment in real time, detect equipment abnormalities in a timely manner and perform maintenance, which is crucial to ensure the stable operation of the EEG signal monitoring equipment during postoperative rehabilitation, and helps to improve the quality and reliability of data acquisition. In summary, the calculation formula for the operating failure probability of the monitoring equipment is not just a simple mathematical expression, but also a powerful tool for quantifying and analyzing the failure probability of the monitoring equipment under abnormal time series points. By comprehensively considering multiple working status parameters and time change trends, the formula provides an in-depth and accurate equipment status assessment, thereby supporting clinical and scientific research personnel in effective management during postoperative rehabilitation. Therefore, this formula fully considers the abnormal distribution period at the abnormal time series point. Failure probability of monitoring equipment at , the initial abnormal time series point of the abnormal distribution period , the termination abnormal timing point of the abnormal distribution period , the measurement variable parameters of abnormal time series points , the number of device working status parameters in the EEG signal monitoring device working status parameter data , item index parameter of equipment working status parameter , No. Fault impact attenuation coefficient of equipment working status parameters , No. Fault impact adjustment factor of each equipment working status parameter , No. Fault impact normalization factor of equipment working status parameters , No. Fault impact index of equipment working status parameters , correction coefficient of the failure probability value of the monitoring equipment , according to the abnormal time sequence point within the abnormal distribution period Failure probability of monitoring equipment at The correlation between the above parameters constitutes a functional relationship This formula can realize the quantitative calculation process of the equipment failure probability of the EEG signal monitoring equipment working status parameter data at each equipment abnormal timing point. At the same time, the correction coefficient of the monitoring equipment failure probability value is The introduction of can be adjusted according to the errors that occur in the calculation process, thereby improving the accuracy and applicability of the calculation formula for the probability of failure of the monitoring equipment.

[0128] Furthermore, the electroencephalogram distribution calibration process is performed on the initial distribution spectrum of the electroencephalogram signal during the postoperative rehabilitation period of the child corresponding to the abnormal distribution period of the postoperative electroencephalogram signal monitoring device according to the average value of the monitoring device failure probability in the abnormal distribution period, including:

[0129] Based on the abnormal distribution period of the postoperative EEG signal monitoring device, the initial distribution spectrum of the EEG signal during the children's postoperative rehabilitation period is divided into abnormal period spectrum, and the postoperative EEG signal abnormal period distribution sub-graph and the postoperative EEG signal normal period distribution sub-graph are obtained;

[0130] In an embodiment of the present invention, the corresponding initial distribution spectrum of EEG signals during the postoperative rehabilitation period of children is divided into sub-graphs of abnormal periods by combining the abnormal distribution period of the postoperative EEG signal monitoring equipment determined previously, so as to identify and analyze certain abnormal distribution periods that occur during the rehabilitation process, the abnormal causes of these periods are related to the failure of the monitoring equipment, changes in the child's state or other external interference, and the corresponding EEG signal distribution spectrum is divided into time periods based on these abnormal time periods to extract EEG signal distribution sub-graphs in abnormal time periods and EEG signal distribution sub-graphs in normal time periods from the initial EEG signal distribution spectrum, wherein the abnormal time period distribution sub-graph shows the distribution characteristics of abnormal EEG signals detected during the monitoring process, while the normal time period distribution sub-graph shows the EEG signal distribution when there is no abnormality or interference, and finally the postoperative EEG signal abnormal time period distribution sub-graph and the postoperative EEG signal normal time period distribution sub-graph are obtained.

[0131] Preferably, based on the average value of the monitoring device failure probability within the abnormal distribution period, the corresponding EEG signal abnormal period distribution subgraph during postoperative rehabilitation is subjected to signal distribution influence correlation analysis to obtain the influence correlation relationship between the monitoring device failure probability and the EEG signal abnormal distribution;

[0132] In an embodiment of the present invention, the influence correlation mining analysis of signal distribution is performed on the corresponding EEG signal abnormal period distribution subgraph during postoperative rehabilitation by combining the average value of the monitoring equipment failure probability in the abnormal distribution period obtained by previous quantitative calculation, so as to help determine the influence correlation relationship between the equipment failure probability and the abnormal distribution pattern of the EEG signal. For example, the abnormal EEG signal occurring in the high failure probability period is directly related to the equipment failure, while the abnormal situation in the low failure probability period requires further analysis of other corresponding influencing factors, and finally the influence correlation relationship between the monitoring equipment failure probability and the abnormal distribution of EEG signals is obtained.

[0133] Preferably, according to the influence correlation relationship between the monitoring equipment failure probability and the abnormal distribution of EEG signals, the distribution sub-graph of abnormal EEG signal periods during postoperative rehabilitation is subjected to equipment failure impact calibration analysis to obtain a distribution line of equipment failure impact calibration during abnormal EEG signal periods;

[0134] In an embodiment of the present invention, by combining the influence correlation relationship between the monitoring equipment failure probability and the abnormal distribution of EEG signals obtained by previous mining analysis, the corresponding signal abnormal distribution pattern in the EEG signal abnormal period distribution subgraph during postoperative rehabilitation is calibrated for the impact of the equipment failure cause, so as to deeply understand how the monitoring equipment failure affects the EEG signal abnormal distribution pattern, and perform calibration processing on the signal error caused by the equipment failure. For example, consider a child who receives EEG signal monitoring during postoperative rehabilitation to evaluate his neural activity and rehabilitation progress. During certain abnormal periods, the monitoring equipment will have different degrees of failure, such as signal loss, increased noise or electromagnetic interference. By collecting the equipment failure probability during these abnormal periods, the possible impact of the equipment failure on the EEG signal distribution can be quantified, and the corresponding possible impact can be calibrated for abnormal deviations to establish a calibration distribution line for the impact of equipment failure during the EEG signal abnormal period, so as to reveal the impact calibration relationship between equipment failure and EEG signal abnormal distribution, so as to better identify the deviation or misunderstanding of equipment failure in the monitoring process, and generate corresponding calibration distribution lines, and finally obtain the calibration distribution line for the impact of equipment failure during the EEG signal abnormal period.

[0135] Preferably, based on the EEG signal abnormal period equipment fault impact calibration distribution line, the EEG signal distribution curve corresponding to the EEG signal abnormal period distribution subgraph during the postoperative rehabilitation period is calibrated and processed to generate the EEG signal abnormal period calibration distribution subgraph;

[0136] In an embodiment of the present invention, a calibration process is performed to calibrate the corresponding EEG signal distribution curve in the distribution subgraph of the EEG signal abnormal period during postoperative rehabilitation by combining the calibration distribution line of the impact of equipment failure in the EEG signal abnormal period obtained after previous calibration, so as to correct the EEG signal analysis deviation caused by the equipment failure. In actual operation, the medical team will accurately calibrate and calibrate the EEG signal distribution data in the abnormal period according to the calibration distribution line established previously. For example, continuing with the above-mentioned example of children's EEG signal monitoring, in a specific abnormal period, equipment failure will cause deviations or errors in the recorded EEG signal data. By applying the calibration distribution line obtained from the previous analysis, the EEG signal distribution curve in these abnormal periods can be adjusted, thereby reducing data distortion or misunderstanding caused by equipment failure, and finally calibrating and generating a calibration distribution subgraph for calibrating the EEG signal abnormal period.

[0137] Preferably, the calibration distribution sub-graph of the abnormal EEG signal period and the distribution sub-graph of the normal EEG signal period after surgery are merged to generate a calibration spectrum of the EEG signal distribution during the postoperative rehabilitation period.

[0138] In an embodiment of the present invention, the calibration distribution subgraph of the EEG signal abnormal period obtained after the abnormal calibration and the normal period distribution subgraph of the postoperative EEG signal obtained by the previous division are reintegrated and merged according to the order of appearance of the time periods, and finally a calibration spectrum of the EEG signal distribution during postoperative rehabilitation is generated.

[0139] Furthermore, the postoperative rehabilitation consciousness cognitive state analysis module includes the following functions:

[0140] The signal frequency band energy distribution and power density statistical analysis were performed on the EEG signal distribution calibration spectrum during the postoperative rehabilitation period to obtain the EEG signal distribution frequency band energy distribution value and the EEG signal distribution frequency band power density value during the postoperative rehabilitation period;

[0141] Performing time point segmentation processing on the energy distribution value of the EEG signal distribution frequency band during the postoperative rehabilitation period and the power density value of the EEG signal distribution frequency band during the postoperative rehabilitation period to obtain the energy distribution value of the EEG signal frequency band and the power density value of the EEG signal frequency band at each time point;

[0142] Based on the energy distribution value of the EEG signal frequency band and the power density value of the EEG signal frequency band at each time point, the EEG consciousness cognition score calculation formula is used to quantify the consciousness cognition score of the corresponding EEG signal distribution calibration spectrum during postoperative rehabilitation to obtain the EEG consciousness cognition score during postoperative rehabilitation at each time point;

[0143] Based on the EEG consciousness cognition score during postoperative rehabilitation at each time point, the corresponding rehabilitation time period in the EEG signal distribution calibration spectrum during postoperative rehabilitation is divided into cognitive equivalent time periods, and each child's postoperative rehabilitation EEG consciousness cognition equivalent time period is obtained;

[0144] The consciousness cognition scores corresponding to each child's postoperative rehabilitation EEG consciousness cognition equivalent period were used for consciousness cognition state recognition analysis to obtain the child's consciousness cognition function status during the postoperative rehabilitation period.

[0145] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 The functional flow diagram of the postoperative rehabilitation consciousness cognitive state analysis module is as follows. In this embodiment, the functions of the postoperative rehabilitation consciousness cognitive state analysis module include:

[0146] S21: performing a statistical analysis of the signal frequency band energy distribution and power density of the EEG signal distribution calibration spectrum during the postoperative rehabilitation period, and obtaining the energy distribution value of the EEG signal distribution frequency band during the postoperative rehabilitation period and the power density value of the EEG signal distribution frequency band during the postoperative rehabilitation period;

[0147] In an embodiment of the present invention, a previously drawn calibration spectrum of EEG signal distribution during postoperative rehabilitation is used to perform a statistical analysis of energy distribution and power density in signal frequency bands by using a previously drawn signal processing algorithm and data analysis tool to evaluate the characteristics of the patient's postoperative EEG signal activity, including energy distribution and power density in different frequency bands. For example, assuming that a patient has undergone brain surgery, the medical team needs to monitor the patient's EEG signal activity during postoperative rehabilitation. By using EEG recordings, the original data of the EEG signal can be obtained and converted into statistical indicators of frequency band energy distribution and power density. In this process, advanced signal processing algorithms and data analysis tools are used to analyze the spectral characteristics of the EEG signal in order to obtain accurate energy distribution values ​​and power density values, where the frequency band energy distribution values ​​represent different frequency bands (such as Wave, Wave, The energy proportion of EEG signals (such as waves, etc.) in the EEG signals, and the power density reflects the signal strength and distribution characteristics of these frequency bands. Finally, the energy distribution values ​​of the EEG signal distribution frequency bands during postoperative rehabilitation and the power density values ​​of the EEG signal distribution frequency bands during postoperative rehabilitation are obtained.

[0148] S22: performing time point segmentation processing on the energy distribution value of the EEG signal distribution frequency band during the postoperative rehabilitation period and the power density value of the EEG signal distribution frequency band during the postoperative rehabilitation period to obtain the energy distribution value of the EEG signal frequency band and the power density value of the EEG signal frequency band at each time point;

[0149] In an embodiment of the present invention, the energy distribution value of the EEG signal distribution frequency band during postoperative rehabilitation and the power density value of the EEG signal distribution frequency band during postoperative rehabilitation obtained by previous statistical analysis are subdivided into time points. This process involves performing detailed time-segmented analysis of the obtained frequency band energy distribution and power density values ​​according to different time points (such as the 1st minute, 1st hour, 1st day, 1st week, 1st month, etc. after surgery). For example, continuing to take the above-mentioned patients after brain surgery as an example, during the postoperative rehabilitation process, the medical team will regularly monitor the time points of the EEG to record the EEG activities at different time points in detail, so as to obtain the specific EEG signal frequency band energy distribution and power density values ​​at each time point, and finally obtain the EEG signal frequency band energy distribution value and the EEG signal frequency band power density value at each time point.

[0150] S23: Based on the energy distribution value of the EEG signal frequency band and the power density value of the EEG signal frequency band at each time point, the EEG consciousness cognition score calculation formula is used to perform a quantitative calculation of the consciousness cognition score on the corresponding EEG signal distribution calibration spectrum during the postoperative rehabilitation period, so as to obtain the EEG consciousness cognition score during the postoperative rehabilitation period at each time point;

[0151] In the embodiment of the present invention, by combining the time range measurement parameter, the time point measurement parameter, and each time point in the EEG signal frequency band (such as Wave, Wave, The energy distribution value on the EEG signal frequency band (such as Wave, Wave, The power density value on the EEG signal distribution calibration spectrum during postoperative rehabilitation, the EEG signal frequency, the EEG signal frequency standard deviation, the EEG signal frequency scaling contribution factor and related parameters constitute a suitable EEG consciousness cognition score calculation formula. The consciousness cognition score of the corresponding EEG signal distribution calibration spectrum during postoperative rehabilitation is quantitatively calculated to obtain the corresponding consciousness cognition score, which can objectively evaluate the consciousness state of children at each time point during postoperative rehabilitation, and finally obtain the EEG consciousness cognition score during postoperative rehabilitation at each time point.

[0152] S24: Based on the EEG consciousness cognition score during the postoperative rehabilitation period at each time point, the corresponding rehabilitation time period in the EEG signal distribution calibration spectrum during the postoperative rehabilitation period is divided into cognitive equivalent time periods, and each child's postoperative rehabilitation EEG consciousness cognition equivalent time period is obtained;

[0153] In an embodiment of the present invention, the corresponding rehabilitation time periods in the EEG signal distribution calibration spectrum during the postoperative rehabilitation period are merged and divided into cognitive score equivalent time periods by combining the EEG consciousness cognition scores during the postoperative rehabilitation period at each time point obtained by previous quantitative calculation, so as to identify the equal consciousness cognition scores at adjacent time points, and integrate the time periods between them to form a large cognitive equivalent time segment, so that the entire rehabilitation period can be divided into multiple cognitive equivalent time periods, for example, the first week, the second week and the third week can be divided into different cognitive equivalent time periods, so as to further analyze and compare the changes in the cognitive state of the children, and finally obtain the EEG consciousness cognition equivalent time period for postoperative rehabilitation of each child.

[0154] S25: Conduct consciousness cognition state recognition analysis on the consciousness cognition scores corresponding to each child's postoperative rehabilitation EEG consciousness cognition equivalent period to obtain the child's consciousness cognition function status during the postoperative rehabilitation period.

[0155] In an embodiment of the present invention, the consciousness cognition state is identified and analyzed by combining the corresponding consciousness cognition scores in each child's postoperative rehabilitation EEG consciousness cognition equivalent period obtained by previous integration, so as to identify and classify the corresponding consciousness cognition function states of the child in different rehabilitation periods according to the specific values ​​of the EEG consciousness cognition scores. For example, in each cognitive equivalent period, the medical team will analyze and compare the EEG consciousness cognition scores of the children. If the corresponding EEG consciousness cognition score is 0-3 points, it will be identified as a consciousness cognition unawakenable state; if the corresponding EEG consciousness cognition score is 3-7 points, it will be identified as a consciousness cognition sedation state; and if the corresponding EEG consciousness cognition score is 7-10 points, it will be identified as a consciousness cognition agitation state. After the consciousness cognition score in each cognitive equivalent period is identified and determined, the different consciousness cognition states of the child in different cognitive equivalent periods are identified, and finally the consciousness cognition function state of the child in the postoperative rehabilitation period is obtained.

[0156] Furthermore, the EEG consciousness cognition score calculation formula is specifically:

[0157] ;

[0158] In the formula, For the time point EEG consciousness and cognitive scores during postoperative rehabilitation is the time range measurement parameter, is the time point measurement parameter, For the time point EEG signals Frequency band energy distribution value, For the time point EEG signals Frequency band energy distribution value, For the time point EEG signals Frequency band energy distribution value, For the time point EEG signals Band power density value, For the time point EEG signals Band power density value, For the time point EEG signals Band power density value, is the standard deviation of the EEG signal frequency of the EEG signal distribution calibration spectrum during postoperative rehabilitation, Calibration of EEG signal distribution at time points during postoperative rehabilitation The EEG signal frequency at is the contribution factor for EEG signal frequency scaling, It is the correction coefficient of EEG consciousness cognition score during postoperative rehabilitation.

[0159] The present invention obtains a EEG consciousness cognition score calculation formula by using a specific mathematical model and verifying it, which is used to quantify the consciousness cognition score of the corresponding EEG signal distribution calibration spectrum during postoperative rehabilitation. The EEG consciousness cognition score calculation formula combines different frequency bands The energy distribution value and power density value of the EEG signal reflect the activity level of the EEG signal in a specific frequency band. By integrating this information, the characteristics of the EEG signal can be more comprehensively evaluated. The formula also takes into account the time point position. The EEG signal data at the time point is also the specific moment of the time point. This subdivision of time points makes the analysis more dynamic and accurate, and can capture the changing trend of EEG signals during the rehabilitation process. The consciousness and cognitive score obtained by this formula is not only a mathematical combination of the energy and power density of the EEG signal frequency band, but more importantly, it can quantify the changes in the children's consciousness and cognitive level during rehabilitation. It is an objective evaluation indicator. The introduction of corresponding parameters enables the formula to adapt to different actual EEG signal data and can be adjusted to meet specific research. Based on the scoring results, the cognitive equivalent time periods of the rehabilitation period can be further divided. This analysis not only helps to understand the changes in consciousness and cognition during the rehabilitation process of children, but also provides a scientific basis for the formulation of personalized rehabilitation plans. In summary, this EEG consciousness and cognitive score calculation formula is not only a collection of mathematical calculations, but also a tool for in-depth analysis and quantitative evaluation of EEG signal data. It combines the dynamic processing of time points, the comprehensive analysis of frequency band energy and power density, and provides researchers and clinicians with a powerful tool for evaluating the consciousness and cognitive state of children during postoperative rehabilitation. Therefore, this formula fully takes into account the time points. EEG consciousness and cognitive scores during postoperative rehabilitation , time range metric parameter , time point measurement parameters , at the time point EEG signals Frequency band energy distribution value , at the time point EEG signals Frequency band energy distribution value , at the time point EEG signals Frequency band energy distribution value , at the time point EEG signals Band power density value , at the time point EEG signals Band power density value , at the time point EEG signals Band power density value , Standard deviation of EEG signal frequency of EEG signal distribution calibration spectrogram during postoperative rehabilitation , EEG signal distribution calibration spectrum during postoperative rehabilitation at time points EEG signal frequency , EEG signal frequency scaling contribution factor , Correction coefficient of EEG consciousness cognition score during postoperative rehabilitation , according to the time point EEG consciousness and cognitive scores during postoperative rehabilitation The correlation between the above parameters constitutes a functional relationship This formula can realize the quantitative calculation process of the consciousness cognition score of the corresponding EEG signal distribution calibration spectrum during postoperative rehabilitation. At the same time, the correction coefficient of the EEG consciousness cognition score during postoperative rehabilitation is used. The introduction of can be adjusted according to the errors that occur in the calculation process, thereby improving the accuracy and applicability of the EEG consciousness cognition score calculation formula.

[0160] Furthermore, the consciousness and cognitive state rehabilitation intelligent strategy analysis module includes the following functions:

[0161] When it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a consciousness and cognitive non-awakening state, a passive rehabilitation goal is set according to the consciousness and cognitive non-awakening state to obtain the child's postoperative non-awakening state passive rehabilitation goal;

[0162] In an embodiment of the present invention, if it is determined that the consciousness and cognitive function state of the child during the postoperative rehabilitation period is a state where consciousness and cognition cannot be awakened, it usually refers to a coma or extreme lethargy state in which the critically ill child's brain consciousness and cognitive activity appears after surgery. At this time, the child cannot respond to external stimuli or awakening. For example, assuming that a child undergoes brain surgery and develops a state where consciousness and cognition cannot be awakened, the rehabilitation team will determine the child's exact state based on the monitoring results of EEG signal activity and formulate corresponding passive rehabilitation goals. In this case, the passive rehabilitation goals include maintaining muscle and joint mobility through physical therapy and regular physical activity, promoting blood circulation and flexibility of the rehabilitation area, and reducing muscle stiffness through passive movement and massage to avoid complications. In addition, professional caregivers will also use specific mattresses and position change techniques to reduce skin damage caused by long-term bed rest and promote blood circulation, and finally set the corresponding passive rehabilitation goals for the child's postoperative state where consciousness cannot be awakened.

[0163] Preferably, when it is determined that the consciousness and cognitive function state of the child during the postoperative rehabilitation period is the consciousness and cognitive sedation state, auxiliary rehabilitation goals are set according to the consciousness and cognitive sedation state to obtain auxiliary rehabilitation goals for the child's postoperative sedation state;

[0164] In an embodiment of the present invention, if it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a state of consciousness and cognitive sedation, it usually means that the child is in a semi-comatose or drowsy state and can partially respond to external stimuli, but the response is weak or slow. For example, a child receives rehabilitation after brain trauma. In the state of consciousness and cognitive sedation, the rehabilitation team will determine the child's level of consciousness based on the monitoring results of the EEG signal consciousness and cognitive activities, and formulate corresponding auxiliary rehabilitation goals accordingly. In this case, the auxiliary rehabilitation goals include the use of psychotherapy, music therapy, or deep breathing techniques to promote emotional stability and cognitive recovery, while improving muscle control and coordination through progressive physical activities and functional training, thereby helping critically ill children enhance their ability to respond to external stimuli. This auxiliary rehabilitation goal aims to gradually activate the child's nervous system through mild cognitive and sensory stimulation, promote the recovery of their consciousness and cognitive functions, and finally set the corresponding auxiliary rehabilitation goal for the child's postoperative sedation state.

[0165] Preferably, when it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a consciousness and cognitive agitation state, active rehabilitation goals are set according to the consciousness and cognitive agitation state to obtain active rehabilitation goals for the child's postoperative agitation state;

[0166] In an embodiment of the present invention, if it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a state of consciousness and cognitive agitation, it usually refers to the state of restlessness, anxiety or overactivity that occurs after the child's surgery, which is caused by postoperative pain, drug side effects or emotional changes. For example, suppose a child undergoes heart surgery and develops a state of consciousness and cognitive agitation due to postoperative pain and emotional changes. In this case, the rehabilitation team will conduct detailed real-time monitoring of EEG consciousness and cognitive activities to determine the exact state of the child and formulate corresponding active rehabilitation goals. The active rehabilitation goals improve self-control and emotional management abilities through physical training, exercise therapy and cognitive behavioral therapy, and promote mental health and rehabilitation progress through social support and emotional regulation, so as to help children actively participate in the rehabilitation process, thereby reducing anxiety and restlessness, and finally setting the corresponding active rehabilitation goals for children's postoperative agitation state.

[0167] Preferably, the passive rehabilitation goals for children's non-awakenable state after surgery, the auxiliary rehabilitation goals for children's sedation state after surgery, and the active rehabilitation goals for children's agitation state after surgery are combined to obtain rehabilitation goals for children's different states of consciousness and cognitive function after surgery;

[0168] In an embodiment of the present invention, the passive rehabilitation goals for children's postoperative unawakenable state, the auxiliary rehabilitation goals for children's postoperative sedation state, and the active rehabilitation goals for children's postoperative agitation state, which were previously set according to different EEG consciousness and cognitive activity states, are integrated into the overall rehabilitation goals to comprehensively consider the rehabilitation needs and challenges of children in different consciousness and cognitive function states. By integrating these goals, a comprehensive framework can be provided for the rehabilitation team to effectively manage and optimize the children's rehabilitation process, ensure that personalized rehabilitation plans can comprehensively cover different rehabilitation stages and states, and ultimately obtain rehabilitation goals for children with different consciousness and cognitive function states after surgery.

[0169] Preferably, based on the rehabilitation goals of children's different consciousness and cognitive function states after surgery, an intelligent strategy analysis of rehabilitation activity projects is performed on the corresponding children's consciousness and cognitive function states during postoperative rehabilitation periods to generate intelligent strategy plans for rehabilitation activity projects for children's different consciousness and cognitive states after surgery.

[0170] In an embodiment of the present invention, by combining the previously integrated rehabilitation goals for different postoperative cognitive states of children, an intelligent strategy analysis of rehabilitation activity projects is performed on the corresponding cognitive states of children during the postoperative rehabilitation period, so as to formulate intelligent rehabilitation plans and activity plans according to the specific conditions of the children and the corresponding rehabilitation needs, so as to promote the rehabilitation process and functional recovery to the greatest extent. For example, after a child undergoes brain trauma surgery, the rehabilitation team sets corresponding rehabilitation goals according to the different cognitive states of the children (such as unawakenable, sedated or agitated states). Different intelligent strategies and rehabilitation activity projects need to be adopted for different rehabilitation goals. For example, when dealing with the cognitive unawakenable state, the intelligent strategy includes regular passive exercise, bedside physical therapy and skin care to prevent complications. For the cognitive sedation state, the intelligent strategy focuses on the intelligent application of auxiliary technologies such as psychotherapy, music therapy or deep breathing, while for the cognitive agitation state, the intelligent strategy focuses on the intelligent application of emotion management, pain relief and cognitive behavioral technologies, so as to realize the conversion of corresponding rehabilitation goals into corresponding activity project strategy plans, and finally generate intelligent strategy plans for rehabilitation activity projects for children with different cognitive states of consciousness after surgery.

[0171] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0172] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent postoperative rehabilitation management system for critically ill children, characterized by: The brain wave signals of critically ill children during postoperative rehabilitation are brain wave signals fed back by performing rehabilitation perception tasks on critically ill children after surgery through preset rehabilitation perception signals. The intelligent postoperative rehabilitation management system for critically ill children includes the following modules: The postoperative rehabilitation EEG signal monitoring module is used to collect the EEG signals of critically ill children during postoperative rehabilitation in real time through the EEG signal monitoring equipment and upload them to the data processing unit for signal preprocessing to obtain the enhanced EEG signal data of critically ill children during postoperative rehabilitation; Based on the EEG signal monitoring equipment, the abnormal EEG distribution of the equipment is calibrated and processed for the EEG signal enhancement data of critically ill children after surgery, and the EEG signal distribution calibration spectrum during postoperative rehabilitation is generated; The postoperative rehabilitation EEG signal monitoring module includes the following functions: The EEG signal monitoring equipment is used to collect the EEG signals of critically ill children during their postoperative rehabilitation in real time, and the original EEG signal data of critically ill children during their postoperative rehabilitation are obtained; By uploading the original EEG signal data of critically ill children during postoperative rehabilitation to the data processing unit in the order of time collected in real time, the real-time EEG signal data of critically ill children during postoperative rehabilitation are obtained; The data processing unit is used to perform signal noise reduction processing on the real-time EEG signal data of critically ill children during postoperative rehabilitation, and the noise reduction data of EEG signals during postoperative rehabilitation of critically ill children are obtained; The EEG signal noise reduction data of critically ill children during postoperative rehabilitation was processed with signal enhancement to obtain the EEG signal enhancement data of critically ill children during postoperative rehabilitation. The EEG signal distribution was mapped on the EEG signal enhancement data of critically ill children after surgery to generate the initial distribution spectrum of EEG signals during children's postoperative rehabilitation. The signal fluctuation frequency and amplitude of the initial distribution spectrum of the EEG signals during the children's postoperative rehabilitation period were statistically analyzed to obtain the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude during the postoperative rehabilitation period; According to the EEG signal fluctuation frequency and EEG signal fluctuation amplitude during the postoperative rehabilitation period, the abnormal distribution period of the equipment is analyzed to obtain the abnormal distribution period of the postoperative EEG signal monitoring equipment; Based on the abnormal distribution period of the postoperative EEG signal monitoring equipment, the fault probability analysis of the EEG signal monitoring equipment during the abnormal period is performed to obtain the fault probability value of the monitoring equipment at each time point in the abnormal distribution period; Based on the abnormal distribution period of the postoperative EEG signal monitoring device, the failure probability value of the monitoring device at each time point in the abnormal distribution period is calculated by the arithmetic mean of the abnormal period to obtain the average failure probability of the monitoring device in the abnormal distribution period; According to the average value of the monitoring equipment failure probability in the abnormal distribution period, the initial distribution spectrum of the EEG signal of the child during the postoperative rehabilitation period corresponding to the abnormal distribution period of the postoperative EEG signal monitoring device is calibrated and processed to generate a calibrated spectrum of the EEG signal distribution during the postoperative rehabilitation period; The postoperative rehabilitation consciousness and cognitive state analysis module is used to quantify the consciousness and cognitive score of the EEG signal distribution calibration spectrum during the postoperative rehabilitation period to obtain the EEG consciousness and cognitive score during the postoperative rehabilitation period at each time point; Based on the EEG consciousness cognition score during postoperative rehabilitation at each time point, the corresponding children's postoperative rehabilitation consciousness cognition period in the EEG signal distribution calibration spectrum during postoperative rehabilitation was divided into consciousness cognition states to obtain the children's consciousness cognition function state during postoperative rehabilitation period, wherein the children's consciousness cognition function state during postoperative rehabilitation period includes consciousness cognition unawakenable state, consciousness cognition sedation state and consciousness cognition agitation state; The intelligent strategy analysis module for consciousness and cognitive state rehabilitation is used to set rehabilitation goals for children's consciousness and cognitive function states in different rehabilitation periods after surgery, so as to obtain rehabilitation goals for children's different consciousness and cognitive function states after surgery; Based on the rehabilitation goals of children's different postoperative cognitive function states, intelligent strategy analysis of rehabilitation activity projects is conducted on the corresponding children's postoperative cognitive function states during rehabilitation periods, so as to generate intelligent strategy plans for rehabilitation activity projects of children's different postoperative cognitive function states; The children's postoperative rehabilitation intelligent management module is used to perform postoperative rehabilitation intelligent management on the children's consciousness and cognitive function status during the corresponding postoperative rehabilitation period according to the intelligent strategy plan of the rehabilitation activity project of the children's different consciousness and cognitive status after surgery, and obtain the intelligent management results of postoperative rehabilitation for critically ill children.

2. The intelligent postoperative rehabilitation management system for critically ill children according to claim 1 is characterized in that: The device abnormal distribution period analysis based on the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude during the postoperative rehabilitation period includes: Performing time-series synchronization processing on the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude during the postoperative rehabilitation period, and obtaining the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude in the same time sequence dimension; Plotting a signal fluctuation hyperbola for the EEG signal fluctuation frequency and the EEG signal fluctuation amplitude in the same time sequence dimension to generate an EEG signal fluctuation frequency-amplitude change hyperbola; Performing signal fluctuation inflection point statistical analysis on the EEG signal fluctuation frequency-amplitude change hyperbola to obtain an inflection point set of the EEG signal fluctuation frequency change curve and an inflection point set of the EEG signal fluctuation amplitude change curve; dividing the EEG signal fluctuation frequency-amplitude change hyperbola into curve distribution time periods based on the order of appearance between the inflection points of each pair of curves in the EEG signal fluctuation frequency change curve inflection point set and the EEG signal fluctuation amplitude change curve inflection point set to obtain distribution time periods of each EEG signal fluctuation change curve; Based on each EEG signal fluctuation change curve distribution period, the corresponding EEG signal fluctuation frequency-amplitude change hyperbola is subjected to curve change pattern recognition analysis to obtain the EEG signal fluctuation curve change pattern within each fluctuation distribution period; the EEG signal fluctuation curve change pattern within each fluctuation distribution period is subjected to abnormal change period detection to obtain the fluctuation distribution period corresponding to the abnormal change pattern of the EEG signal fluctuation; The fluctuation distribution period corresponding to the abnormal change pattern of the EEG signal fluctuation is screened and processed as the cause of equipment abnormality to obtain the abnormal distribution period of the postoperative EEG signal monitoring equipment.

3. The intelligent postoperative rehabilitation management system for critically ill children according to claim 1 is characterized in that: The abnormal time period point fault probability analysis of the EEG signal monitoring device based on the abnormal distribution time period of the EEG signal monitoring device after surgery includes: The abnormal distribution period of the postoperative EEG signal monitoring device is divided into abnormal time sequence points, and the abnormal time sequence points of each EEG signal monitoring device in the abnormal distribution period are obtained; Based on each abnormal timing point of the EEG signal monitoring device within the abnormal distribution period, the working state of the EEG signal monitoring device is monitored and analyzed to obtain the working state parameter data of the EEG signal monitoring device at each abnormal timing point of the device; The failure probability calculation formula of the monitoring equipment is used to quantify the failure probability of the EEG signal monitoring equipment at each abnormal timing point of the equipment, so as to obtain the failure probability value of the monitoring equipment at each timing point within the abnormal distribution period.

4. The intelligent postoperative rehabilitation management system for critically ill children according to claim 3 is characterized in that: The specific calculation formula for the monitoring equipment operation failure probability is: ； In the formula, is the abnormal time sequence point within the abnormal distribution period The failure probability value of the monitoring equipment at is the initial abnormal time sequence point of the abnormal distribution period, is the termination abnormal timing point of the abnormal distribution period, is the measurement variable parameter of the abnormal time series point, is the number of device working status parameters in the working status parameter data of the EEG signal monitoring device. It is the item index parameter of the equipment working status parameter. For the The fault impact attenuation coefficient of the working status parameters of each device, For the The fault impact adjustment factor of each device working status parameter, For the The fault impact normalization factor of each device working status parameter, For the The fault impact index of the working status parameters of each device, It is the correction factor of the failure probability value of the monitoring equipment.

5. The intelligent postoperative rehabilitation management system for critically ill children according to claim 1 is characterized in that: The electroencephalogram distribution calibration process of the initial distribution spectrum of the electroencephalogram signal of the child during the postoperative rehabilitation period corresponding to the abnormal distribution period of the postoperative electroencephalogram signal monitoring device according to the average value of the monitoring device failure probability in the abnormal distribution period includes: Based on the abnormal distribution period of the postoperative EEG signal monitoring device, the initial distribution spectrum of the EEG signal during the children's postoperative rehabilitation period is divided into abnormal period spectrum, and the postoperative EEG signal abnormal period distribution sub-graph and the postoperative EEG signal normal period distribution sub-graph are obtained; Based on the average value of the monitoring equipment failure probability within the abnormal distribution period, the signal distribution impact correlation analysis is performed on the corresponding EEG signal abnormal period distribution subgraph during postoperative rehabilitation to obtain the impact correlation relationship between the monitoring equipment failure probability and the EEG signal abnormal distribution; According to the influence correlation between the failure probability of monitoring equipment and the abnormal distribution of EEG signals, the distribution sub-graph of abnormal EEG signal periods during postoperative rehabilitation is subjected to equipment failure impact calibration analysis, and the distribution line of equipment failure impact calibration during abnormal EEG signal periods is obtained; Based on the EEG signal abnormal period equipment fault impact calibration distribution line, the EEG signal distribution curve corresponding to the EEG signal abnormal period distribution sub-graph during the postoperative rehabilitation period is calibrated and processed to generate the EEG signal abnormal period calibration distribution sub-graph; The calibration distribution sub-graph of EEG signal abnormal period and the distribution sub-graph of EEG signal normal period after surgery are merged to generate the calibration spectrum of EEG signal distribution during postoperative rehabilitation.

6. The intelligent postoperative rehabilitation management system for critically ill children according to claim 1 is characterized in that: The postoperative rehabilitation consciousness cognitive state analysis module includes the following functions: The signal frequency band energy distribution and power density statistical analysis were performed on the EEG signal distribution calibration spectrum during the postoperative rehabilitation period to obtain the EEG signal distribution frequency band energy distribution value and the EEG signal distribution frequency band power density value during the postoperative rehabilitation period; Performing time point segmentation processing on the energy distribution value of the EEG signal distribution frequency band during the postoperative rehabilitation period and the power density value of the EEG signal distribution frequency band during the postoperative rehabilitation period to obtain the energy distribution value of the EEG signal frequency band and the power density value of the EEG signal frequency band at each time point; Based on the energy distribution value of the EEG signal frequency band and the power density value of the EEG signal frequency band at each time point, the EEG consciousness cognition score calculation formula is used to quantify the consciousness cognition score of the corresponding EEG signal distribution calibration spectrum during postoperative rehabilitation to obtain the EEG consciousness cognition score during postoperative rehabilitation at each time point; Based on the EEG consciousness cognition score during postoperative rehabilitation at each time point, the corresponding rehabilitation time period in the EEG signal distribution calibration spectrum during postoperative rehabilitation is divided into cognitive equivalent time periods, and each child's postoperative rehabilitation EEG consciousness cognition equivalent time period is obtained; The consciousness cognition scores corresponding to each child's postoperative rehabilitation EEG consciousness cognition equivalent period were used for consciousness cognition state recognition analysis to obtain the child's consciousness cognition function status during the postoperative rehabilitation period.

7. The intelligent postoperative rehabilitation management system for critically ill children according to claim 6 is characterized in that: The calculation formula of the EEG consciousness cognition score is specifically as follows: ； In the formula, For the time point EEG consciousness and cognitive scores during postoperative rehabilitation is the time range measurement parameter, is the time point measurement parameter, For the time point EEG signals Frequency band energy distribution value, For the time point EEG signals Frequency band energy distribution value, For the time point EEG signals Frequency band energy distribution value, For the time point EEG signals Band power density value, For the time point EEG signals Band power density value, For the time point EEG signals Band power density value, is the standard deviation of the EEG signal frequency of the EEG signal distribution calibration spectrum during postoperative rehabilitation, Calibration of EEG signal distribution at time points during postoperative rehabilitation The EEG signal frequency at is the contribution factor for EEG signal frequency scaling, It is the correction factor of EEG consciousness cognition score during postoperative rehabilitation.

8. The intelligent postoperative rehabilitation management system for critically ill children according to claim 1 is characterized in that: The consciousness and cognitive state rehabilitation intelligent strategy analysis module includes the following functions: When it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a consciousness and cognitive non-awakening state, a passive rehabilitation goal is set according to the consciousness and cognitive non-awakening state to obtain the child's postoperative non-awakening state passive rehabilitation goal; When it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is the consciousness and cognitive sedation state, auxiliary rehabilitation goals are set according to the consciousness and cognitive sedation state to obtain the auxiliary rehabilitation goals for the child's postoperative sedation state; When it is determined that the child's consciousness and cognitive function state during the postoperative rehabilitation period is a state of consciousness and cognitive agitation, active rehabilitation goals are set according to the state of consciousness and cognitive agitation to obtain active rehabilitation goals for the child's postoperative agitation state; The rehabilitation goals of children's passive rehabilitation goals for the unawakenable state after surgery, the auxiliary rehabilitation goals for children's sedation state after surgery, and the active rehabilitation goals for children's agitation state after surgery were combined to obtain rehabilitation goals for children's different states of consciousness and cognitive function after surgery. Based on the rehabilitation goals of children with different postoperative consciousness and cognitive function states, an intelligent strategy analysis of rehabilitation activity projects is conducted on the corresponding children's consciousness and cognitive function states during the postoperative rehabilitation period to generate intelligent strategy plans for rehabilitation activity projects with different postoperative consciousness and cognitive states for children.

Images