AI-based postoperative rehabilitation nursing system and method for old people

Abstract

The invention discloses an AI-based postoperative rehabilitation nursing system and method for old people, relates to the technical field of medical treatment, and aims to calculate a rehabilitation coefficient of a current nursing period based on a feature set, accurately evaluate rehabilitation states of a patient in different nursing periods and intelligently judge whether current nursing intervention needs to be adjusted or not. By dynamically optimizing the intervention strategy, the problem of excessive or insufficient intervention in traditional nursing is avoided. And the intervention optimization instruction is received and executed, and the intensity adjustment coefficient of the nursing intervention in the next time period is automatically generated, so that the intelligent adjustment of the nursing intensity is realized, the nursing scheme is more personalized, and the intervention blindness is reduced. In the optimized nursing intervention process, physiological and metabolic parameters of the patient are continuously monitored, an optimized feature set is generated, the nursing intensity is further adjusted, a closed-loop nursing process is formed, and the closed-loop dynamic optimization mechanism improves the nursing response speed and adjustment precision and greatly shortens the rehabilitation cycle of the patient.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and specifically to an AI-based postoperative rehabilitation nursing system and method for the elderly. Background Art

[0002] With the rapid development of artificial intelligence (AI) technology, traditional medical care is gradually transforming towards digitalization, automation and intelligence. In the existing postoperative rehabilitation care for the elderly, nursing work usually relies on traditional manual observation and experience judgment. This model has obvious shortcomings, such as: nursing intervention methods are mostly experience-driven, lacking real-time monitoring and data support for the patient's personalized status; nursing intensity adjustment is relatively lagging, which may lead to excessive or insufficient intervention; the evaluation of rehabilitation effects often relies on stage-by-stage evaluation rather than real-time dynamic evaluation, and cannot quickly respond to changes in the patient's postoperative status. In addition, the elderly after surgery are often accompanied by chronic diseases, coexistence of multiple diseases and other complex conditions. The traditional nursing model is difficult to dynamically optimize the nursing plan according to the patient's status, which affects the rehabilitation efficiency and the patient's quality of life. These shortcomings restrict the development of precise, personalized and efficient rehabilitation nursing.

[0003] The above shortcomings are mainly caused by insufficient information collection, limited data processing capabilities and technical bottlenecks in personalized nursing decisions in postoperative care. On the one hand, traditional nursing relies on fixed nursing methods (such as fixed nursing intervention frequency). On the other hand, the existing nursing programs lack efficient data analysis and intelligent decision support systems, and it is difficult for nursing programs to respond to patients' complex rehabilitation status in real time. In addition, the elderly patient population after surgery often has the characteristics of slow metabolism and decreased tissue regeneration ability. If the nursing intensity is too high, it may lead to accumulated fatigue or increased postoperative burden in patients; if the nursing intensity is too low, it may delay the rehabilitation process. These problems will lead to prolonged rehabilitation period, waste of medical resources, and even increased risk of postoperative complications, which will seriously affect the patient's postoperative quality of life and rehabilitation efficiency. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an AI-based postoperative rehabilitation nursing system and method for the elderly, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an AI-based postoperative rehabilitation nursing method for the elderly, comprising the following steps: S1: Monitor the postoperative status of the elderly in advance through medical instruments to obtain relevant physiological parameters and metabolic parameters, and transmit them to the central database via wireless; S2: preprocessing the relevant physiological parameters and relevant metabolic parameters in the central database to generate a feature set, and standardizing the feature set using a dimensionless processing technique; S3: Based on the feature set, analyze the recovery status of the elderly after surgery in different nursing periods to calculate the rehabilitation coefficient Hfxs of the current nursing period. Based on the rehabilitation coefficient Hfxs of the current nursing period, analyze whether the nursing intervention degree of the elderly after surgery needs to be adjusted. If adjustment is required, trigger the intervention optimization instruction; S4: Based on AI technology, after receiving the intervention optimization instruction, the intensity of nursing intervention in the next period is automatically optimized, and the intervention adjustment coefficient Gtxs is obtained to optimize the nursing intervention operation. In the optimized nursing intervention process, the relevant physiological parameters and related metabolic parameters of the elderly after surgery are monitored again to generate an optimized feature set, and based on the optimized feature set, the intensity of nursing intervention is adjusted individually until the elderly recover after surgery.

[0006] Preferably, the specific steps of S1 include: S11: Use medical instruments to collect the postoperative physiological state and metabolic status of the elderly to obtain relevant physiological parameters and relevant metabolic parameters, wherein the relevant physiological parameters include but are not limited to the tissue regeneration index at each monitoring , heart rate variability factor and blood oxygen saturation The relevant metabolic parameters include but are not limited to the metabolic index at each monitoring and lactate concentration , medical instruments include respiratory metabolic analyzers, blood biochemistry analyzers, urine analyzers, microdialyzers, finger-clip pulse oximeters, and heart rate variability monitors; S12: The collected relevant physiological parameters and relevant metabolic parameters are transmitted to the central database through wireless communication technology. After receiving the relevant physiological parameters and relevant metabolic parameters, the central database stores the relevant physiological parameters and relevant metabolic parameters in the corresponding database table in sequence according to the data type.

[0007] Preferably, the specific steps of S2 include: S21: extract relevant physiological parameters and relevant metabolic parameters from the central database through the API interface, and use the message queue to asynchronously process the relevant physiological parameters and relevant metabolic parameters, and then perform data preprocessing on the relevant physiological parameters and relevant metabolic parameters, identify and remove noise and repeated values, and use linear interpolation to fill in missing values; S22: Extracting features from the relevant physiological parameters and relevant metabolic parameters after data preprocessing, so as to extract the tissue regeneration index at each monitoring time from the relevant physiological parameters after data preprocessing , heart rate variability factor and blood oxygen saturation , extract the metabolic index at each monitoring time from the relevant metabolic parameters after data preprocessing and lactate concentration , and construct a feature set, use dimensionless processing technology to standardize the feature set, and input the standardized feature set into S3.

[0008] Preferably, the specific steps of S3 include: S31: According to the feature set, the recovery status of the elderly after surgery in different nursing periods is analyzed, and the recovery coefficient Hfxs of the current nursing period is calculated by associating the metabolic index Dxzs with the tissue regeneration index Zszs, which is specifically obtained according to the following formula: ; Where n represents the number of monitoring times in the current nursing period, i=1, 2, 3, ..., n, represents the metabolic index monitored for the i-th time during the current nursing period, Indicates the average metabolic index during the current nursing period. represents the tissue regeneration index monitored for the i-th time during the current nursing period, Indicates the average tissue regeneration index during the current care period, and are weight values, among which, and The specific value is set by the user according to the situation.

[0009] Preferably, the specific step S3 also includes: S32: Based on the rehabilitation coefficient Hfxs of the current nursing period, the nursing intervention degree of the elderly after surgery in the corresponding nursing period is analyzed to obtain the intervention intensity Gqd in the current nursing period, which is obtained specifically in the following manner: ; In the formula, Represents the recovery coefficient versus time point The partial derivative of Indicates the nursing period The rehabilitation coefficient is calculated by integrating the positive change part. Indicates taking The non-negative part, and are weight values, represents the fatigue coefficient, represents any time point in the period from t0 to T, t0 represents the first time point in the corresponding nursing period, and T represents the last time point in the corresponding nursing period; wherein, and The specific value is set by the user according to the situation.

[0010] Among them, the fatigue coefficient Obtained by the following formula: ; In the formula, represents the heart rate variability factor, represents the lactate concentration, Indicates blood oxygen saturation, , and are weight values, among which, , and The specific value is set by the user according to the situation.

[0011] Preferably, the specific step S3 also includes: S33: Based on the medical instrument, collect and calculate the rehabilitation coefficient Hfxs in the next nursing period and record it as the post-rehabilitation coefficient , combined with the rehabilitation coefficient Hfxs of the current nursing period and the intervention intensity Gqd in the current nursing period, the intervention effect coefficient Gxxs is calculated and obtained according to the following formula: ; In the formula, Rehabilitation coefficient The difference between the recovery coefficient Hfxs of the current nursing period.

[0012] Preferably, the specific step S3 also includes: S34: Preset a threshold value and compare it with the intervention effect coefficient Gxxs to analyze whether the current nursing intervention level of the elderly after surgery needs to be adjusted. The specific contents are as follows: If the intervention effect coefficient Gxxs exceeds the threshold, it is determined that the nursing intervention level of the elderly person after surgery does not need to be adjusted temporarily, and at this time, no intervention optimization instruction will be triggered externally; If the intervention effect coefficient Gxxs does not exceed the threshold, it is determined that the current nursing intervention level of the elderly person after surgery needs to be adjusted, and an intervention optimization instruction will be triggered outwardly.

[0013] Preferably, the specific steps of S4 include: S41: After receiving the intervention optimization instruction issued by S34, the intensity of the nursing intervention in the next period is automatically optimized to obtain the intervention adjustment coefficient Gtxs, which is obtained by the following formula: ; In the formula, Indicates based on The positive or negative value of determines the direction of increase or decrease of intervention intensity; represents a symbolic function; represents the initial learning rate; Indicates the intervention intensity during the current nursing period, Rehabilitation coefficient The difference between the recovery coefficient Hfxs of the current nursing period.

[0014] Preferably, the specific step S4 also includes: S42: Based on the intervention adjustment coefficient Gtxs, the nursing intervention for the current postoperative elderly is optimized, and in the process of the optimized nursing intervention, the relevant physiological parameters and relevant metabolic parameters of the postoperative elderly are monitored again to generate an optimized feature set, wherein the optimized feature set includes the relevant physiological parameters and relevant metabolic parameters of the nursing intervention after optimization, and the optimized feature set is regressed to S2, and steps S2, S3 and S4 are repeated to determine again whether the nursing intervention degree of the current postoperative elderly needs to be adjusted. If adjustment is required, the intensity of the nursing intervention in the future time period is automatically optimized again, wherein the content of automatically optimizing the intensity of the nursing intervention in the future time period is as follows: Control and adjust the initial learning rate , and each adjustment will increase by 0.01.

[0015] AI-based postoperative rehabilitation care system for the elderly, including data monitoring module, data processing module, personalized rehabilitation care module and dynamic optimization module; The data monitoring module is used to monitor the postoperative status of the elderly in advance through medical instruments to obtain relevant physiological parameters and relevant metabolic parameters, and transmit them to the central database via wireless; The data processing module is used to perform data preprocessing on the relevant physiological parameters and relevant metabolic parameters in the central database to generate a feature set, and standardize the feature set using dimensionless processing technology; The personalized rehabilitation nursing module is used to analyze the recovery status of the elderly after surgery in different nursing periods based on the feature set, so as to calculate the rehabilitation coefficient Hfxs of the current nursing period, and analyze whether the nursing intervention degree of the elderly after surgery needs to be adjusted based on the rehabilitation coefficient Hfxs of the current nursing period. If adjustment is required, the intervention optimization instruction is triggered; The dynamic optimization module is used to automatically optimize the intensity of nursing intervention in the next time period based on AI technology after receiving the intervention optimization instruction, obtain the intervention adjustment coefficient Gtxs to optimize the nursing intervention operation, and monitor the relevant physiological parameters and relevant metabolic parameters of the elderly after surgery again during the optimized nursing intervention process to generate an optimized feature set, and based on the optimized feature set, make personalized adjustments to the nursing intervention intensity until the elderly recover after surgery.

[0016] The present invention provides an AI-based postoperative rehabilitation nursing system and method for the elderly, which has the following beneficial effects: Medical instruments are used to monitor multidimensional physiological and metabolic parameters of elderly people after surgery in real time, and the data is wirelessly transmitted to the central database, which helps to quickly discover changes in the patient's status and provide reliable support for subsequent nursing adjustments. The rehabilitation coefficient of the current nursing period is calculated based on the feature set, the patient's rehabilitation status in different nursing periods is accurately evaluated, and the current nursing intervention needs to be intelligently judged whether it needs to be adjusted. Through dynamic optimization of intervention strategies, the problem of excessive or insufficient intervention in traditional nursing is avoided. Through AI technology, intervention optimization instructions are received and executed, and the intensity adjustment coefficient of the nursing intervention in the next period is automatically generated, which realizes the intelligent adjustment of nursing intensity, makes the nursing plan more personalized, and can optimize intervention measures according to the patient's real-time recovery status, reducing the blindness of intervention. In the optimized nursing intervention process, the patient's physiological and metabolic parameters are continuously monitored, the optimized feature set is generated, and the nursing intensity is further adjusted, forming a closed-loop nursing process of "monitoring-evaluation-intervention optimization-re-monitoring". This closed-loop dynamic optimization mechanism improves the response speed and adjustment accuracy of nursing, and greatly shortens the patient's recovery cycle. Through the AI-based automated adjustment mechanism, the dependence of traditional nursing on manual judgment is reduced, the complexity of nursing operations is reduced, and the scientificity and execution efficiency of nursing plans are improved. At the same time, the implementation of personalized nursing intervention enables patients to recover at an appropriate intervention intensity, significantly improving the nursing experience and rehabilitation effect. The system can dynamically monitor the patient's status and accurately adjust the nursing intensity according to the rehabilitation coefficient and intervention adjustment coefficient, avoiding adverse reactions caused by excessive intervention and delayed rehabilitation caused by insufficient intervention, and significantly improving the safety of the nursing plan.

[0017] By analyzing the recovery of the elderly after surgery to obtain the rehabilitation coefficient, an accurate quantitative assessment of the patient's postoperative recovery status is achieved. The rehabilitation coefficient is calculated based on multiple monitoring data during the current nursing period, and supports real-time updates of the patient's rehabilitation status assessment. Dynamic monitoring can help caregivers promptly discover changing trends in the patient's condition (such as accelerated or slowed recovery), and quickly adjust care strategies when necessary to ensure continuous optimization of care effects. According to the characteristics of the patient's condition (such as slow recovery of metabolic function or slow tissue regeneration), dynamic adjustment of the weight value can achieve a personalized care plan that better meets the patient's actual needs.

[0018] The system reduces the burden on patients by appropriately reducing the intensity of intervention when the patient's recovery status improves; it promptly increases the intensity when the status deteriorates to help patients recover quickly and significantly optimize the patient experience. The dynamic adjustment of the fatigue coefficient combined with the calculation of intervention intensity can continuously adapt the patient's recovery status in long-term care, avoiding the accumulation of fatigue or hindered recovery of patients due to short-term excessive intervention. By accurately controlling the intensity of care, it helps patients achieve long-term rehabilitation goals and shortens the rehabilitation cycle.

[0019] The system automatically optimizes the intervention intensity, reduces the delay of nursing adjustment, and ensures that the system can quickly respond to the patient's rehabilitation needs. This efficient nursing optimization mechanism not only improves nursing efficiency, but also reduces the workload of nursing staff. Through the dynamic adjustment of the learning rate, the system can adapt to the needs of different nursing stages for the adjustment speed of intervention intensity, quickly optimize the intervention intensity in the early stage of rehabilitation, and achieve smooth adjustment in the later stage of rehabilitation. This optimization mechanism of adaptive learning rate control improves the stability and adaptability of the adjustment process, and avoids fluctuations in nursing effects that may be caused by too large or too small adjustment steps. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of the AI-based postoperative rehabilitation nursing method for the elderly of the present invention; Figure 2 This is a block diagram of the AI-based postoperative rehabilitation nursing system for the elderly. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Example 1: Please refer to Figure 1 The present invention provides an AI-based postoperative rehabilitation nursing method for the elderly, comprising the following steps: S1: Monitor the postoperative status of the elderly in advance through medical instruments to obtain relevant physiological parameters and metabolic parameters, and transmit them to the central database via wireless; S2: preprocessing the relevant physiological parameters and relevant metabolic parameters in the central database to generate a feature set, and standardizing the feature set using a dimensionless processing technique; S3: Based on the feature set, analyze the recovery status of the elderly after surgery in different nursing periods to calculate the rehabilitation coefficient Hfxs of the current nursing period. Based on the rehabilitation coefficient Hfxs of the current nursing period, analyze whether the nursing intervention degree of the elderly after surgery needs to be adjusted. If adjustment is required, trigger the intervention optimization instruction; S4: Based on AI technology, after receiving the intervention optimization instruction, the intensity of nursing intervention in the next period is automatically optimized, and the intervention adjustment coefficient Gtxs is obtained to optimize the nursing intervention operation. In the optimized nursing intervention process, the relevant physiological parameters and related metabolic parameters of the elderly after surgery are monitored again to generate an optimized feature set, and based on the optimized feature set, the intensity of nursing intervention is adjusted individually until the elderly recover after surgery.

[0023] During the operation of this system, through step S1, medical instruments are used to monitor the physiological and metabolic parameters of the elderly in real time after surgery, and the data is transmitted to the central database in combination with wireless transmission technology, providing comprehensive and accurate basic data support for subsequent nursing optimization. The data is updated in real time, which can dynamically reflect the physiological and metabolic changes of patients in the postoperative rehabilitation process, and improve the scientificity and reliability of the nursing plan. Step S2 generates a feature set through data preprocessing, and standardizes the feature set in combination with dimensionless technology, effectively eliminating the dimensional differences between different features, facilitating unified analysis and decision-making, and improving data analysis efficiency. The standardized feature set accurately reflects the changing trend of the patient's rehabilitation status, providing a data basis for rehabilitation evaluation and intervention. Step S3 analyzes the patient's rehabilitation status in different nursing periods after surgery through feature sets, calculates the rehabilitation coefficient of the nursing period, and judges in real time whether the current nursing intensity needs to be adjusted. This dynamic adjustment capability enables the nursing plan to be flexibly optimized according to the patient's actual rehabilitation situation, further avoiding excessive or insufficient intervention, and improving the patient's rehabilitation efficiency. Step S4 receives intervention optimization instructions, uses AI technology to automatically calculate the intervention adjustment coefficient, and realizes accurate optimization of nursing intensity in the next period. The optimized intervention intensity can achieve personalized care through dynamic monitoring and readjustment, effectively adapt to the rehabilitation needs of different patients, reduce the waste of nursing resources, and reduce the risk of discomfort or complications caused by excessive or insufficient intervention. In short, this method uses a closed-loop nursing process from data collection, preprocessing, rehabilitation status assessment, intelligent intervention optimization to re-monitoring and adjustment. This closed-loop system ensures the continuity and dynamic optimization of the patient's rehabilitation process, significantly improves the nursing effect, and reduces the blindness and inefficiency of traditional manual intervention.

[0024] Example 2: Please refer to Figure 1 , specifically: S1 specific steps include: S11: Use medical instruments to collect the postoperative physiological state and metabolic status of the elderly to obtain relevant physiological parameters and relevant metabolic parameters, wherein the relevant physiological parameters include but are not limited to the tissue regeneration index at each monitoring , heart rate variability factor and blood oxygen saturation The relevant metabolic parameters include but are not limited to the metabolic index at each monitoring and lactate concentration , medical instruments include respiratory metabolic analyzers, blood biochemistry analyzers, urine analyzers, microdialyzers, finger-clip pulse oximeters, and heart rate variability monitors; Obtain high-precision raw data through sensors and analytical equipment; S12: The collected relevant physiological parameters and relevant metabolic parameters are transmitted to the central database through wireless communication technology. After receiving the relevant physiological parameters and relevant metabolic parameters, the central database stores the relevant physiological parameters and relevant metabolic parameters in the corresponding database table in sequence according to the data type. The data type includes structured data and unstructured data; The specific steps of S2 include: S21: extract relevant physiological parameters and relevant metabolic parameters from the central database through the API interface, and use message queues (such as Kafka, RabbitMQ) to asynchronously process the relevant physiological parameters and relevant metabolic parameters, and then perform data preprocessing on the relevant physiological parameters and relevant metabolic parameters, identify and remove noise and duplicate values, and use linear interpolation to fill in missing values; S22: Extracting features from the relevant physiological parameters and relevant metabolic parameters after data preprocessing, so as to extract the tissue regeneration index at each monitoring time from the relevant physiological parameters after data preprocessing , heart rate variability factor and blood oxygen saturation , extract the metabolic index at each monitoring time from the relevant metabolic parameters after data preprocessing and lactate concentration , and construct a feature set, use dimensionless processing technology to standardize the feature set, and input the standardized feature set into S3.

[0025] In this embodiment, the physiological state and metabolic status of the elderly after surgery are collected in real time by combining medical instruments with sensors and analysis equipment, covering key indicators such as tissue regeneration index, heart rate variability factor, blood oxygen saturation, metabolic index and lactate concentration, ensuring the comprehensiveness and high accuracy of the monitoring data. The data types cover structured (such as numerical indicators) and unstructured (such as images, waveform signals, etc.) data, which can reflect the multi-dimensional state of the patient. The collected raw data is quickly transmitted to the central database through wireless communication technology to achieve efficient sharing and centralized storage of data. Key features (such as tissue regeneration index, heart rate variability factor, blood oxygen saturation, etc.) are extracted from the pre-processed data, and a feature set is constructed. The feature set is standardized by dimensionless technology to eliminate the dimensional differences between features, making the data more comparable and adaptable.

[0026] Example 3: Please refer to Figure 1 , specifically: S3 specific steps include: S31: According to the feature set, the recovery status of the elderly after surgery in different nursing periods is analyzed, and the recovery coefficient Hfxs of the current nursing period is calculated by associating the metabolic index Dxzs with the tissue regeneration index Zszs, which is specifically obtained according to the following formula: ; Where n represents the number of monitoring times in the current nursing period, i=1, 2, 3, ..., n, represents the metabolic index monitored for the i-th time during the current nursing period, Indicates the average metabolic index during the current nursing period. represents the tissue regeneration index monitored for the i-th time during the current nursing period, Indicates the average tissue regeneration index during the current care period, and are weight values, among which, and The specific value is set by the user according to the situation, ranging from: 0< ≤1,0< ≤1.

[0027] The above metabolic index Obtained by the following formula: in, represents the cell metabolic rate, represents the concentration of metabolic waste, represents a correction constant, which is a small positive number to avoid zero denominator; among them, the cell metabolism rate Obtained by monitoring the concentration of metabolic waste products through a breathalyzer Obtained through blood biochemical analyzer, urine analyzer and microdialysis machine monitoring; Tissue regeneration index Obtained by the following formula: ;in, represents tissue regeneration rate, and t represents time.

[0028] In this embodiment, the recovery level of the elderly after surgery in a specific nursing period is accurately reflected through dynamic monitoring and calculation of the metabolic index and tissue regeneration index. The calculation formula of the rehabilitation coefficient combines the specific index value of each monitoring and its average level in the nursing period, which can more comprehensively evaluate the fluctuations and trends in the patient's rehabilitation process. This quantitative method provides a quantitative basis for the traditional nursing model that relies on subjective judgment, and significantly improves the accuracy of rehabilitation status assessment. The real-time recovery status of the patient can be quantitatively expressed through the changing trend of the rehabilitation coefficient, which helps nursing staff to quickly grasp the patient's rehabilitation progress and avoid delaying the timing of nursing adjustment. Through the calculation results of the rehabilitation coefficient, it is possible to scientifically judge whether the patient's rehabilitation level in the current nursing period has reached the expected level. The system uses the results to further analyze the necessity of nursing intervention. If it is found that the rehabilitation coefficient deviates from the target value, the intervention optimization instruction can be triggered in time to avoid insufficient or excessive intervention problems and improve the quality and efficiency of nursing. Compared with the traditional method of relying on manual evaluation of rehabilitation status, this method realizes fast and accurate state quantification through two core indicators of metabolism and regeneration, reduces the complexity of manual analysis as much as possible, and improves the rationality of nursing. The automated rehabilitation coefficient calculation can complete the analysis and generate results in a short time, saving a lot of time for nursing staff and improving the operating efficiency of the nursing system.

[0029] Example 4: Please refer to Figure 1 , specifically: S3 specific steps also include: S32: Based on the rehabilitation coefficient Hfxs of the current nursing period, the nursing intervention degree of the elderly after surgery in the corresponding nursing period is analyzed to obtain the intervention intensity Gqd in the current nursing period, which is obtained specifically in the following manner: ; In the formula, Represents the recovery coefficient versus time point The partial derivative of is used to describe the rate of change of the rehabilitation coefficient over time, where >0, indicating that the recovery status is improving and the patient's health level is rising; <0, the recovery status deteriorates and the patient's health level decreases; =0, the recovery status remains stable with no significant changes; Indicates the nursing period The rehabilitation coefficient is calculated by integrating the positive change part. Indicates taking The non-negative part, and are weight values, represents the fatigue coefficient, represents any time point in the period from t0 to T, t0 represents the first time point in the corresponding nursing period, and T represents the last time point in the corresponding nursing period; wherein, and The specific value is set by the user according to the situation, the range is: 0< ≤1,0< ≤1.

[0030] Among them, the fatigue coefficient Obtained by the following formula: ; In the formula, represents the heart rate variability factor, represents the lactate concentration, Indicates blood oxygen saturation, , and are all weight values. When the heart rate variation factor When descending, fatigue coefficient Increase, when heart rate variability factor When it rises, it means that the body is in a good recovery state, and the fatigue coefficient Reduce lactate concentration Reflects the body's anaerobic metabolism level. During exercise or high-intensity intervention, lactic acid accumulation increases, indicating increased fatigue. Blood oxygen saturation It indicates the oxygen transport capacity in the blood and is an important indicator for evaluating the patient's oxygen demand and fatigue. The higher the blood oxygen, the more adequate the body's oxygen supply and the lower the fatigue level. , and The specific value is set by the user according to the situation, the range is: 0< ≤1,0< ≤1,0< ≤1.

[0031] The lactate concentration It can be monitored and obtained through a blood biochemical analyzer, a handheld lactate analyzer or a microdialyzer; Blood oxygen saturation It can be monitored by a finger-clip pulse oximeter; Heart rate variability factor It reflects the heart rate variability, which can be obtained through electrocardiogram or heart rate variability monitor; In this embodiment, the intervention intensity Gqd is calculated according to the real-time changes in the rehabilitation status, and the adjustment range is controlled in combination with the fatigue coefficient to ensure that the nursing intervention is effective and does not increase the burden on the patient. The fatigue coefficient dynamically evaluates the patient's fatigue state by comprehensively considering multidimensional physiological indicators such as heart rate variability, lactate concentration, and blood oxygen saturation. This fatigue monitoring based on physiological indicators further improves the safety and scientificity of nursing intervention and avoids the shortcomings of subjective fatigue judgment in traditional nursing. During a nursing period, the system forms a closed-loop process through dynamic calculation of the rehabilitation coefficient and intervention intensity: real-time monitoring of rehabilitation status → dynamic adjustment of intervention intensity → re-evaluation of nursing effect. This closed-loop optimization mechanism not only ensures the continuous improvement of the patient's rehabilitation status, but also effectively avoids the problem of insufficient or excessive intervention, and accelerates the postoperative rehabilitation process.

[0032] Example 5: Please refer to Figure 1 , specifically: S3 specific steps also include: S33: Based on the medical instrument, collect and calculate the rehabilitation coefficient Hfxs in the next nursing period and record it as the post-rehabilitation coefficient , combined with the rehabilitation coefficient Hfxs of the current nursing period and the intervention intensity Gqd in the current nursing period, the intervention effect coefficient Gxxs is calculated and obtained according to the following formula: ; In the formula, Rehabilitation coefficient The difference between the recovery coefficient Hfxs of the current nursing period.

[0033] The specific steps of S3 also include: S34: Preset a threshold value and compare it with the intervention effect coefficient Gxxs to analyze whether the current nursing intervention level of the elderly after surgery needs to be adjusted. The specific contents are as follows: If the intervention effect coefficient Gxxs exceeds the threshold, it is determined that the nursing intervention level of the elderly person after surgery does not need to be adjusted temporarily, and at this time, no intervention optimization instruction will be triggered externally; If the intervention effect coefficient Gxxs does not exceed the threshold, it is determined that the current nursing intervention level of the elderly person after surgery needs to be adjusted, and an intervention optimization instruction will be triggered outwardly.

[0034] In this embodiment, the actual effect of nursing intervention is accurately evaluated by dynamically associating the rehabilitation status of the current nursing period with the rehabilitation status of the next period. The difference between the post-rehabilitation coefficient and the current rehabilitation coefficient reflects the actual trend of changes in the patient's rehabilitation progress; combined with the intervention intensity of the current nursing period, the system can quantify the effectiveness of intervention measures and provide a scientific basis for nursing decisions. The comparison mechanism of the intervention effect coefficient and the preset threshold realizes the dynamic optimization of the nursing intervention intensity. This dynamic optimization mechanism improves the response speed of nursing adjustment and ensures the real-time matching of nursing plans with patient status. Through the analysis of, the system further avoids the problem of over-nursing caused by blindly increasing the intervention intensity: the closed-loop process can quickly respond to the changing trend of the patient's status and ensure that the quality of nursing is continuously improved throughout the rehabilitation cycle. The system automatically determines the necessity of intervention optimization, reduces unnecessary nursing adjustments, enables patients to receive more accurate and stable nursing interventions during the rehabilitation process, and reduces the discomfort caused by excessive adjustments or inefficient nursing. By dynamically optimizing the nursing intensity, the patient's rehabilitation efficiency is significantly improved, the postoperative rehabilitation cycle is shortened, and the overall rehabilitation experience of the patient is ultimately improved.

[0035] Example 6: Please refer to Figure 1 , specifically: S4 specific steps include: S41: After receiving the intervention optimization instruction issued by S34, the intensity of the nursing intervention in the next period is automatically optimized to obtain the intervention adjustment coefficient Gtxs, which is obtained by the following formula: ; In the formula, Indicates based on The positive or negative value of determines the direction of increase or decrease of intervention intensity: ≥0, the result is negative, and the intervention intensity is reduced; when <0, the result is positive, which increases the intensity of intervention; represents a symbolic function; Represents the initial learning rate, the initial step size of the system; Indicates the intervention intensity during the current nursing period, Rehabilitation coefficient The difference between the recovery coefficient Hfxs of the current nursing period.

[0036] The specific steps of S4 also include: S42: Based on the intervention adjustment coefficient Gtxs, the nursing intervention for the current postoperative elderly is optimized, and in the process of the optimized nursing intervention, the relevant physiological parameters and relevant metabolic parameters of the postoperative elderly are monitored again to generate an optimized feature set, wherein the optimized feature set includes the relevant physiological parameters and relevant metabolic parameters of the nursing intervention after optimization, and the optimized feature set is regressed to S2, and steps S2, S3 and S4 are repeated to determine again whether the nursing intervention degree of the current postoperative elderly needs to be adjusted. If adjustment is required, the intensity of the nursing intervention in the future time period is automatically optimized again, wherein the content of automatically optimizing the intensity of the nursing intervention in the future time period is as follows: Control and adjust the initial learning rate , and each adjustment will increase by 0.01.

[0037] The initial learning rate It is a proportional factor used to control the adjustment step size, and its main function is to affect the change range of the optimization parameters.

[0038] In this embodiment, the dynamic calculation of the intervention adjustment coefficient is fully combined with the trend of the change of the rehabilitation coefficient. When the difference between the post-rehabilitation coefficient and the current rehabilitation coefficient is positive (improvement of rehabilitation status), the system reduces the intervention intensity to avoid excessive intervention causing patient fatigue or other negative effects. When it is negative (deterioration of rehabilitation status), the system increases the intervention intensity and intervenes in time to accelerate the patient's rehabilitation. This optimization strategy based on sign function and dynamic step size adjustment realizes the scientific and real-time dynamic adjustment of nursing intensity. The system dynamically adjusts the initial learning rate (step size proportional factor) to avoid the problem of too fast or too slow adjustment that may be caused by a fixed step size: each time the nursing intensity in the future period is optimized, the initial learning rate increases by 0.01, and the adjustment efficiency is gradually improved. Through dynamic learning rate optimization, the system maintains a small step size in the early stage of rehabilitation for detailed adjustment, and gradually increases the learning rate in the later stage to speed up the optimization process. The gradual optimization of the learning rate significantly improves the flexibility of nursing adjustment and ensures that the intervention intensity is always highly adapted to the patient's recovery needs. The system monitors the patient's physiological and metabolic parameters in real time through optimized nursing intervention intensity, generates an optimized feature set and regresses to the S2 step, forming a complete closed-loop optimization process. This closed-loop mechanism ensures that the intervention intensity within each nursing cycle is adjusted based on the latest patient recovery status, continuously improving the nursing effect while avoiding the risk of blind adjustment.

[0039] Example 7: Please refer to Figure 2 ,Specifically: AI-based postoperative rehabilitation nursing system for the elderly, including data monitoring module, data processing module, personalized rehabilitation nursing module and dynamic optimization module; The data monitoring module is used to monitor the postoperative status of the elderly in advance through medical instruments to obtain relevant physiological parameters and relevant metabolic parameters, and transmit them to the central database via wireless; The data processing module is used to perform data preprocessing on the relevant physiological parameters and relevant metabolic parameters in the central database to generate a feature set, and standardize the feature set using dimensionless processing technology; The personalized rehabilitation nursing module is used to analyze the recovery status of the elderly after surgery in different nursing periods based on the feature set, so as to calculate the rehabilitation coefficient Hfxs of the current nursing period, and analyze whether the nursing intervention degree of the elderly after surgery needs to be adjusted based on the rehabilitation coefficient Hfxs of the current nursing period. If adjustment is required, the intervention optimization instruction is triggered; The dynamic optimization module is used to automatically optimize the intensity of nursing intervention in the next time period based on AI technology after receiving the intervention optimization instruction, obtain the intervention adjustment coefficient Gtxs to optimize the nursing intervention operation, and monitor the relevant physiological parameters and relevant metabolic parameters of the elderly after surgery again during the optimized nursing intervention process to generate an optimized feature set, and based on the optimized feature set, make personalized adjustments to the nursing intervention intensity until the elderly recover after surgery.

[0040] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. AI-based postoperative rehabilitation nursing method for the elderly, characterized by: The following steps are involved: S1: Monitor the postoperative status of the elderly in advance through medical instruments to obtain relevant physiological parameters and metabolic parameters, and transmit them to the central database via wireless; S2: preprocessing the relevant physiological parameters and relevant metabolic parameters in the central database to generate a feature set, and standardizing the feature set using a dimensionless processing technique; S3: Based on the feature set, analyze the recovery status of the elderly after surgery in different nursing periods to calculate the rehabilitation coefficient Hfxs of the current nursing period. Based on the rehabilitation coefficient Hfxs of the current nursing period, analyze whether the nursing intervention degree of the elderly after surgery needs to be adjusted. If adjustment is required, trigger the intervention optimization instruction; S4: Based on AI technology, after receiving the intervention optimization instruction, the intensity of nursing intervention in the next period is automatically optimized, and the intervention adjustment coefficient Gtxs is obtained to optimize the nursing intervention operation. In the optimized nursing intervention process, the relevant physiological parameters and related metabolic parameters of the elderly after surgery are monitored again to generate an optimized feature set, and based on the optimized feature set, the intensity of nursing intervention is adjusted individually until the elderly recover after surgery.

2. The AI-based postoperative rehabilitation nursing method for the elderly according to claim 1 is characterized by: The specific steps of S1 include: S11: Use medical instruments to collect the postoperative physiological state and metabolic status of the elderly to obtain relevant physiological parameters and relevant metabolic parameters, where the medical instruments include respiratory metabolic analyzers, blood biochemical analyzers, urine analyzers, microdialyzers, finger-clip pulse oximeters, and heart rate variability monitors; S12: The collected relevant physiological parameters and relevant metabolic parameters are transmitted to the central database through wireless communication technology. After receiving the relevant physiological parameters and relevant metabolic parameters, the central database stores the relevant physiological parameters and relevant metabolic parameters in the corresponding database table in sequence according to the data type.

3. The AI-based postoperative rehabilitation nursing method for the elderly according to claim 2 is characterized by: The specific steps of S2 include: S21: extract relevant physiological parameters and relevant metabolic parameters from the central database through the API interface, and use the message queue to asynchronously process the relevant physiological parameters and relevant metabolic parameters, and then perform data preprocessing on the relevant physiological parameters and relevant metabolic parameters, identify and remove noise and repeated values, and use linear interpolation to fill in missing values; S22: Extracting features from the relevant physiological parameters and relevant metabolic parameters after data preprocessing, so as to extract the tissue regeneration index at each monitoring time from the relevant physiological parameters after data preprocessing , heart rate variability factor and blood oxygen saturation , extract the metabolic index at each monitoring time from the relevant metabolic parameters after data preprocessing and lactate concentration , and construct a feature set, use dimensionless processing technology to standardize the feature set, and input the standardized feature set into S3.

4. The AI-based postoperative rehabilitation nursing method for the elderly according to claim 3 is characterized by: The specific steps of S3 include: S31: According to the feature set, the recovery status of the elderly after surgery in different nursing periods is analyzed, and the recovery coefficient Hfxs of the current nursing period is calculated by associating the metabolic index Dxzs with the tissue regeneration index Zszs, which is specifically obtained according to the following formula: ； Where n represents the number of monitoring times in the current nursing period, i=1, 2, 3, ..., n, represents the metabolic index monitored for the i-th time during the current nursing period, Indicates the average metabolic index during the current nursing period. represents the tissue regeneration index monitored for the i-th time during the current nursing period, Indicates the average tissue regeneration index during the current care period, and are weight values, among which, and The specific value is set by the user according to the situation.

5. The AI-based postoperative rehabilitation nursing method for the elderly according to claim 4 is characterized in that: The specific steps of S3 also include: S32: Based on the rehabilitation coefficient Hfxs of the current nursing period, the nursing intervention degree of the elderly after surgery in the corresponding nursing period is analyzed to obtain the intervention intensity Gqd in the current nursing period, which is obtained specifically in the following manner: ； In the formula, Represents the recovery coefficient versus time point The partial derivative of Indicates the nursing period The rehabilitation coefficient is calculated by integrating the positive change part. Indicates taking The non-negative part, and are weight values, represents the fatigue coefficient, represents any time point in the period from t0 to T, t0 represents the first time point in the corresponding nursing period, and T represents the last time point in the corresponding nursing period; wherein, and The specific value is set by the user according to the situation; Among them, the fatigue coefficient Obtained by the following formula: ； In the formula, represents the heart rate variability factor, represents the lactate concentration, Indicates blood oxygen saturation, , and are weight values, among which, , and The specific value is set by the user according to the situation.

6. The AI-based postoperative rehabilitation nursing method for the elderly according to claim 5 is characterized by: The specific steps of S3 also include: S33: Based on the medical instrument, collect and calculate the rehabilitation coefficient Hfxs in the next nursing period and record it as the post-rehabilitation coefficient , combined with the rehabilitation coefficient Hfxs of the current nursing period and the intervention intensity Gqd in the current nursing period, the intervention effect coefficient Gxxs is calculated and obtained according to the following formula: ； In the formula, Rehabilitation coefficient The difference between the recovery coefficient Hfxs of the current nursing period.

7. The AI-based postoperative rehabilitation nursing method for the elderly according to claim 6 is characterized by: The specific steps of S3 also include: S34: Preset a threshold value and compare it with the intervention effect coefficient Gxxs to analyze whether the current nursing intervention level of the elderly after surgery needs to be adjusted. The specific contents are as follows: If the intervention effect coefficient Gxxs exceeds the threshold, it is determined that the nursing intervention level of the elderly person after surgery does not need to be adjusted temporarily, and at this time, no intervention optimization instruction will be triggered externally; If the intervention effect coefficient Gxxs does not exceed the threshold, it is determined that the current nursing intervention level of the elderly person after surgery needs to be adjusted, and an intervention optimization instruction will be triggered outwardly.

8. The AI-based postoperative rehabilitation nursing method for the elderly according to claim 7 is characterized by: The specific steps of S4 include: S41: After receiving the intervention optimization instruction issued by S34, the intensity of the nursing intervention in the next period is automatically optimized to obtain the intervention adjustment coefficient Gtxs, which is obtained by the following formula: ； In the formula, Indicates based on The positive or negative value of determines the direction of increase or decrease of intervention intensity; represents a symbolic function; represents the initial learning rate; Indicates the intervention intensity during the current nursing period, Rehabilitation coefficient The difference between the recovery coefficient Hfxs of the current nursing period.

9. The AI-based postoperative rehabilitation nursing method for the elderly according to claim 8 is characterized by: The specific steps of S4 also include: S42: Based on the intervention adjustment coefficient Gtxs, the nursing intervention for the current postoperative elderly is optimized, and in the process of the optimized nursing intervention, the relevant physiological parameters and relevant metabolic parameters of the postoperative elderly are monitored again to generate an optimized feature set, wherein the optimized feature set includes the relevant physiological parameters and relevant metabolic parameters of the nursing intervention after optimization, and the optimized feature set is regressed to S2, and steps S2, S3 and S4 are repeated to determine again whether the nursing intervention degree of the current postoperative elderly needs to be adjusted. If adjustment is required, the intensity of the nursing intervention in the future time period is automatically optimized again, wherein the content of automatically optimizing the intensity of the nursing intervention in the future time period is as follows: Control and adjust the initial learning rate , and each adjustment will increase by 0.

01.

10. An AI-based postoperative rehabilitation nursing system for the elderly, used to implement the AI-based postoperative rehabilitation nursing method for the elderly as described in any one of claims 1 to 9, characterized in that: It includes data monitoring module, data processing module, personalized rehabilitation nursing module and dynamic optimization module; The data monitoring module is used to monitor the postoperative status of the elderly in advance through medical instruments to obtain relevant physiological parameters and relevant metabolic parameters, and transmit them to the central database via wireless; The data processing module is used to perform data preprocessing on the relevant physiological parameters and relevant metabolic parameters in the central database to generate a feature set, and standardize the feature set using dimensionless processing technology; The personalized rehabilitation nursing module is used to analyze the recovery status of the elderly after surgery in different nursing periods based on the feature set, so as to calculate the rehabilitation coefficient Hfxs of the current nursing period, and analyze whether the nursing intervention degree of the elderly after surgery needs to be adjusted based on the rehabilitation coefficient Hfxs of the current nursing period. If adjustment is required, the intervention optimization instruction is triggered; The dynamic optimization module is used to automatically optimize the intensity of nursing intervention in the next time period based on AI technology after receiving the intervention optimization instruction, obtain the intervention adjustment coefficient Gtxs to optimize the nursing intervention operation, and monitor the relevant physiological parameters and relevant metabolic parameters of the elderly after surgery again during the optimized nursing intervention process to generate an optimized feature set, and based on the optimized feature set, make personalized adjustments to the nursing intervention intensity until the elderly recover after surgery.

Images