Intelligent nursing system for postoperative rehabilitation of old people based on Internet of Things

Abstract

The invention discloses an intelligent nursing system for postoperative rehabilitation of old people based on Internet of Things, and relates to the technical field of medical rehabilitation, and the system comprises a data collection module which collects physiological data and motion data in real time; the state evaluation module calculates and generates a rehabilitation progress rate and a physiological fatigue degree; the coupling effect analysis module is used for generating a coupling tension index; and the intervention decision and dynamic adjustment module is used for generating a final intervention intensity instruction and sending the instruction to a rehabilitation equipment actuator. By introducing the coupling tension index, the conflict between the rehabilitation demand and fatigue suppression is accurately quantified, the dynamic balance between the rehabilitation demand and the physiological fatigue is realized, the rehabilitation safety and efficiency are improved, meanwhile, the individuation and self-adaptive ability of the system are enhanced, and the implementation of the scheme is ensured.

Description

Technical Field

[0001] The present invention relates to the field of medical rehabilitation technology, and in particular to an intelligent nursing system for postoperative rehabilitation of the elderly based on the Internet of Things. Background Art

[0002] Postoperative rehabilitation for elderly patients is a complex and dynamic process, the core goal of which is to restore physiological function as quickly as possible while ensuring patient safety. Existing rehabilitation systems, particularly those based on the Internet of Things (IoT), utilize closed-loop control to monitor patient status in real time and adaptively adjust the intensity of rehabilitation training. They also monitor indicators such as the patient's level of physical fatigue. When fatigue exceeds a safe threshold, intervention is forcibly reduced or suspended.

[0003] Existing technologies face severe challenges when dealing with a special and critical clinical scenario. When a patient's rehabilitation progress stagnates or falls short of expectations, the system's decision-making logic will tend to enhance intervention. However, if the patient happens to be in a state of high physiological fatigue due to high-intensity training or postoperative stress response, the safety monitoring logic will tend to inhibit intervention. This contradictory instruction stems from the negative feedback inhibition effect in the model. Existing technologies usually use simple priority strategies or linear weighting methods to deal with it, but this will lead to a significant decrease in rehabilitation efficiency and even cause the system to fail in a contradictory state, unable to give the optimal intervention instruction. The essence of this contradictory state is a nonlinear coupling effect. How to quantify the tension of this coupling effect and perform nonlinear and smooth decision modulation based on it is a technical problem that needs to be solved urgently in the current field. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent nursing system for postoperative rehabilitation of the elderly based on the Internet of Things, which solves the problems existing in the background technology.

[0005] In order to solve the above technical problems, the present invention provides an intelligent nursing system for elderly people's postoperative rehabilitation based on the Internet of Things, comprising: a data acquisition module for collecting the patient's physiological data and motion data in real time through wearable sensors; a state assessment module, configured to receive the physiological data and the motion data, and process the data to calculate and generate a rehabilitation progress rate representing rehabilitation progress and a physiological fatigue degree representing physiological risk; Coupling effect analysis module for: generating a standardized rehabilitation demand signal based on the rehabilitation progress rate and a preset target rehabilitation progress rate; generating a standardized fatigue suppression signal according to the physiological fatigue degree and a preset physiological fatigue safety threshold; and combining the rehabilitation demand signal with the fatigue inhibition signal to generate a coupling tension index that quantifies the degree of conflict between the two; Intervention decision-making and dynamic adjustment module, used to: determining a basic intervention adjustment amount based on the rehabilitation demand signal and the fatigue suppression signal; generating a nonlinear modulation factor for suppressing the basic intervention adjustment amount according to the coupling tension index; Calculating the basic intervention adjustment amount and the nonlinear modulation factor to generate an actual intervention adjustment amount; The actual intervention adjustment amount is combined with the current intervention intensity recorded by the system to generate a final intervention intensity instruction, and the instruction is sent to the rehabilitation equipment actuator.

[0006] Preferably, when generating the rehabilitation demand signal, the coupling effect analysis module is specifically used to: S11, calculating the difference between the target rehabilitation progress rate and the rehabilitation progress rate to obtain a progress gap; S12, dividing the progress gap by a preset demand signal sensitivity adjustment factor to obtain a normalized input value; S13 , applying a sigmoid function operation to the normalized input value to generate the rehabilitation demand signal.

[0007] Preferably, the coupling effect analysis module generates the fatigue suppression signal in the following specific steps: S21, calculating the difference between the physiological fatigue degree and the physiological fatigue safety threshold to obtain a fatigue excess limit value; S22, multiplying the fatigue limit value by a preset inhibition signal activation slope factor to obtain an activation input value; S23, applying a logistic function operation to the activation input value to generate the fatigue suppression signal.

[0008] Preferably, when generating the coupling tension index, the coupling effect analysis module generates the coupling tension index by multiplying the rehabilitation demand signal, the fatigue inhibition signal and a preset coupling effect weight coefficient.

[0009] Preferably, when determining the basic intervention adjustment amount, the intervention decision and dynamic adjustment module is specifically used to: S31, calculating the difference between the rehabilitation demand signal and the fatigue suppression signal to obtain a basic adjustment drive signal; S32: Multiply the basic adjustment driving signal by a preset proportional gain constant to generate the basic intervention adjustment amount.

[0010] Preferably, when generating the final intervention intensity instruction, the intervention decision and dynamic adjustment module is specifically configured to: S41, performing a hyperbolic tangent function operation on the coupling tension index to obtain a modulation reference value; S42, subtracting the modulation reference value from the value 1 to generate the nonlinear modulation factor; S43, multiplying the basic intervention adjustment amount by the nonlinear modulation factor to generate the actual intervention adjustment amount; S44. Add the actual intervention adjustment amount to the current intervention intensity to generate the final intervention intensity instruction.

[0011] Preferably, the target rehabilitation progress rate is pre-set based on individualized information of the patient's age, surgery type, and preoperative physical condition; and the demand signal sensitivity adjustment factor is obtained through statistical learning or offline optimization of historical clinical data.

[0012] Preferably, the physiological fatigue safety threshold is based on publicly published clinical guidelines or statistical data from related studies, and is personalized according to the patient's heart disease history and age; the inhibition signal activation slope factor is configured according to the patient's risk level.

[0013] Preferably, the proportional gain constant is debugged and set based on the target response speed and stability requirements of the system and in combination with the patient's tolerance.

[0014] Compared with the prior art, the present invention has the following beneficial effects: First, the present invention introduces the coupling tension index to accurately quantify the conflict between rehabilitation needs and fatigue suppression, enabling the system to generate logically consistent intervention instructions in any state, resolving decision-making contradictions and achieving logical consistency in decision-making.

[0015] Secondly, the present invention uses the intervention decision and dynamic adjustment module and the nonlinear modulation factor generated based on the coupling tension index to smoothly and continuously suppress the basic intervention adjustment amount, thereby achieving refined dynamic balance and improving the smoothness and continuity of the intervention.

[0016] Third, when a high coupling tension index is detected, the present invention automatically enters a buffer state, which not only avoids the risk of secondary injury caused by a hasty increase in intervention intensity, but also avoids unnecessary interruption of rehabilitation, improves rehabilitation safety and efficiency, and achieves efficiency optimization under risk avoidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention, and those skilled in the art can derive other drawings based on these drawings without inventive effort. Figure 1 This is a logic block diagram of an intelligent nursing system for postoperative rehabilitation of the elderly based on the Internet of Things of the present invention;

[0018] Figure 2 This is a diagram of the specific steps of the coupling effect analysis module in Example 2. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0020] Example 1: See also Figure 1 The present invention provides an intelligent nursing system for elderly people's postoperative rehabilitation based on the Internet of Things, comprising: a data acquisition module for collecting physiological data and motion data of patients in real time through wearable sensors; a state assessment module for receiving the physiological data and the motion data and processing the data to calculate and generate a rehabilitation progress rate representing rehabilitation progress and a physiological fatigue degree representing physiological risk; a coupling effect analysis module for generating a standardized rehabilitation demand signal based on the rehabilitation progress rate and a preset target rehabilitation progress rate; a standardized fatigue inhibition signal based on the physiological fatigue degree and a preset physiological fatigue safety threshold; and combining the rehabilitation demand signal with the fatigue inhibition signal to generate a coupling tension index that quantifies the degree of conflict between the two; an intervention decision and dynamic adjustment module for determining a basic intervention adjustment amount based on the rehabilitation demand signal and the fatigue inhibition signal; generating a nonlinear modulation factor for inhibiting the basic intervention adjustment amount based on the coupling tension index; calculating the basic intervention adjustment amount and the nonlinear modulation factor to generate an actual intervention adjustment amount; and combining the actual intervention adjustment amount with the current intervention intensity recorded by the system to generate a final intervention intensity instruction, which is then sent to a rehabilitation device actuator; This embodiment provides an IoT-based intelligent nursing system for elderly patients undergoing postoperative rehabilitation. Its design aims to precisely address the technical challenges of inefficient or dysfunctional decision-making caused by the inability to effectively address conflicting demands for rehabilitation and physiological fatigue in existing rehabilitation technologies. Through the close coordination and logical progression of its internal functional modules, it achieves refined, adaptive, and dynamic adjustment of rehabilitation intervention intensity. The system's operation begins with the data acquisition module, which uses wearable sensors deployed on the patient's body, such as heart rate monitors, electromyography sensors, and inertial measurement units, to continuously and in real time collect the patient's physiological and motion data. The status assessment module is responsible for receiving these raw data streams and processing them using built-in algorithms to calculate two core status parameters: the rehabilitation rate, which represents the progress of rehabilitation, and the physiological fatigue level, which represents physiological risk. The coupling effect analysis module, the core of this system's technological innovation, receives the rehabilitation progress rate and physiological fatigue output by the state assessment module. Based on these two real-time parameters and the system's preset target rehabilitation progress rate and physiological fatigue safety threshold, this module generates a standardized rehabilitation demand signal and fatigue suppression signal, respectively. Crucially, this module further mathematically combines these two signals to generate a coupling tension index that accurately quantifies the degree of conflict between the two instructions. As the core of decision-making and execution, the intervention decision and dynamic adjustment module makes the final decision based on the signals generated by the aforementioned modules; it determines a basic intervention adjustment amount according to the difference between the rehabilitation demand signal and the fatigue inhibition signal; crucially, it uses the coupling tension index to generate a nonlinear modulation factor, which can smoothly and effectively suppress the basic adjustment amount when the signal contradiction is sharp; the actual intervention adjustment amount is generated by calculating the basic intervention adjustment amount with the nonlinear modulation factor; this actual intervention adjustment amount is accumulated with the current intervention intensity recorded by the system to generate the final intervention intensity instruction; the instruction is sent to the rehabilitation equipment actuator, such as a continuous passive motion machine or a functional electrical stimulation device, thereby constructing a complete closed-loop adaptive control process; in this way, the system converts fuzzy clinical decision contradictions into precise mathematical models, thereby achieving a dynamic and precise balance between ensuring patient safety and maximizing rehabilitation efficiency.

[0021] Example 2: refer to Figure 2 As shown, when generating the rehabilitation demand signal, the coupling effect analysis module is specifically configured to: S11, calculate the difference between the target rehabilitation progress rate and the rehabilitation progress rate to obtain a progress gap; S12, divide the progress gap by a preset demand signal sensitivity adjustment factor to obtain a normalized input value; S13, apply an S-type function operation to the normalized input value to generate the rehabilitation demand signal; The target rehabilitation progress rate is pre-set based on individualized information about the patient's age, surgery type, and preoperative physical condition; the demand signal sensitivity adjustment factor is obtained through statistical learning or offline optimization of historical clinical data; The coupling effect analysis module in this embodiment performs a series of precise calculation steps in the process of generating the rehabilitation demand signal. Its core purpose is to convert the specific rehabilitation progress gap into a standardized signal representing the intensity of the motivation for "enhanced intervention" through nonlinear mapping. By executing steps S11 to S13, this module accurately and nonlinearly quantifies the clinical concept of "rehabilitation stagnation", providing the first key input variable for subsequent coupling analysis. The generation of the rehabilitation demand signal follows the following formula:

[0022]

[0023] Represents the rehabilitation demand signal, which is a dimensionless output value ranging from (0, 1). The closer the value is to 1, the greater the gap between the current rehabilitation progress and the target, and the stronger the need for enhanced system intervention. Represents the current rehabilitation progress rate, which is the input of this formula. Its source is calculated by the state assessment module through analysis of kinematic sensor data. Its unit is (degrees / day) or similar units. In an application scenario such as knee postoperative rehabilitation, the rehabilitation progress rate It can be calculated from the patient's daily active range of motion, for example, it can be defined as the increment of the average daily maximum AROM over the last three days. , is the maximum active joint range of motion measured on day N (i.e., that day); The target rehabilitation progress rate is the input of this formula. Its source is the system preset value, which is pre-set by medical experts based on the patient's individual information. Indicates the demand signal sensitivity adjustment factor, which is a preset adjustable parameter and its unit is the same as and The units of are the same, thus ensuring that the function input is a dimensionless value. This parameter is related to rehabilitation demand. It controls the steepness of the sigmoid curve and determines the sensitivity of the demand signal to the progress gap. The sigmoid function is a standard logistic function, and its specific form is:

[0024] This function can be used to smoothly map the rehabilitation progress gap to a standardized signal between 0 and 1; The design idea of this formula is derived from the "error drive" concept in control theory (driving system regulation by calculating the difference between the actual system output and the target output), and incorporates the S-shaped response curve that is prevalent in biological regulation systems and performs nonlinear optimization on it. In rehabilitation application scenarios, if the linear error ( ) as a driving signal. When the error is small, the system may not respond sufficiently, while when the error is large, the system may respond too aggressively, which can easily lead to system oscillation or patient discomfort. The sigmoid function is used for normalized mapping, which can generate a gentle driving signal when the gap between progress and target is small, and a strong driving signal when the gap is significant. This nonlinear processing method ensures a smooth transition of the system response and confines the signal value to the interval (0,1), facilitating subsequent standardized calculations. Its characteristics are more consistent with the inherent laws of biological regulation. In the coupling effect analysis module, this formula is used to convert the specific rehabilitation progress gap, i.e. , into a standardized signal representing the intensity of motivation to enhance intervention This approach enables precise, nonlinear quantification of the clinically ambiguous concept of "recovery stagnation," providing the first key input variable for subsequent coupled tension analysis, enabling the system to make decisions based on a quantified demand intensity. Target rehabilitation progress rate The setting of is the embodiment of individualized treatment plan, which is pre-set by rehabilitation physicians or physical therapists based on the patient's specific situation, such as age, complexity of surgery, preoperative functional status and other factors after comprehensive evaluation; demand signal sensitivity adjustment factor The value of is determined by statistical learning through analysis of historical clinical data sets or by using an offline optimization algorithm, aiming to match the average response characteristics of a specific patient group. In clinical practice, rehabilitation therapists can also make manual adjustments based on treatment strategies. For example, for young patients who expect rapid recovery, a smaller To make the system more responsive; on the contrary, for elderly patients with higher risk, a larger Make the system response smoother and more conservative, thereby ensuring the safety and personalization of treatment; sigmoid function: refers to the standard logistic function, the specific form is , which can smoothly map the rehabilitation progress gap to a standardized signal between 0 and 1; the input x in the formula corresponds to the normalized input value, that is, .

[0025] Example 3: The specific steps of the coupling effect analysis module generating the fatigue suppression signal include: S21, calculating the difference between the physiological fatigue degree and the physiological fatigue safety threshold to obtain a fatigue excess limit value; S22, multiplying the fatigue limit value by a preset inhibition signal activation slope factor to obtain an activation input value; S23, applying a logistic function operation to the activation input value to generate the fatigue suppression signal; The physiological fatigue safety threshold is based on publicly published clinical guidelines or statistical data from relevant studies and is personalized according to the patient's heart disease history and age. The inhibitory signal activation slope factor is configured based on the patient's risk level. The coupling effect analysis module in this embodiment, when generating the fatigue inhibition signal, converts the specific physiological fatigue value into a standardized signal representing the intensity of the "inhibition intervention" motivation through steps S21 to S23. The impact of physiological fatigue on rehabilitation has a significant threshold effect. When the fatigue level is low, its inhibitory effect is negligible. However, once a certain physiological critical point is exceeded, the risk rises sharply and the inhibitory effect should be rapidly enhanced. The calculation method used in this embodiment can accurately characterize the nonlinear characteristics of this "safety threshold" activation, and its performance is far superior to linear or step threshold judgment methods. Its calculation formula is as follows:

[0026] Represents the fatigue inhibition signal, which is a dimensionless output value ranging from (0, 1). The closer the value is to 1, the more severe the patient's physiological fatigue is and the stronger the need for system inhibition intervention is. Represents real-time physiological fatigue, a dimensionless comprehensive index that is the input of this formula. Its source is the state assessment module. This parameter is associated with physiological risk and is calculated through a weighted fusion algorithm by comprehensively analyzing multidimensional physiological data such as heart rate variability (HRV) and electromyography (EMG). Represents the physiological fatigue safety threshold, which is also a dimensionless index. It is the input of this formula and its source is the system preset value. It is a symbol commonly used in mathematics to represent the threshold value, which is related to the physiological fatigue level. corresponding; It represents the activation slope factor of the inhibitory signal, which is a dimensionless adjustable parameter. This parameter is related to the inhibitory signal and controls the activation slope of the inhibitory signal. Exceeding the threshold hour, How quickly the signal grows; The weighted fusion algorithm can be specifically expressed as the normalized weighted summation of multiple physiological indicators:

[0027] Indicates the A raw physiological indicator (such as the SDNN value in heart rate variability, or the mean power frequency MPF value in electromyography); Represents a function whose value is normalized by the maximum and minimum normalization method; Indicates the preset weight coefficient corresponding to the indicator, and the sum of all weight coefficients is 1 (i.e. ); n: represents the total number of original physiological indicators used to calculate physiological fatigue; These weights can be individually adjusted by the clinician based on the patient's specific circumstances and rehabilitation goals; This formula is a standard logistic function, widely used in biology and machine learning to simulate phenomena with threshold activation characteristics. The inhibitory effect of physiological fatigue on the recovery process does not increase linearly, but rather surges near a certain safety threshold. The logistic function accurately captures this characteristic: when fatigue is below the threshold, the inhibitory signal grows slowly; once it exceeds the threshold, the signal rapidly increases. This nonlinear response mechanism ensures that the system does not perform unnecessary intervention and inhibition in low-fatigue zones, while providing decisive and strong protective signals in high-fatigue zones. In the coupling effect analysis module, this formula is used to convert the specific physiological fatigue value into a standardized signal representing the intensity of the inhibitory intervention motivation. This process enables precise, nonlinear quantification of fatigue risk, providing a second key input for subsequent coupled analysis. It avoids unnecessary intervention inhibition in low-fatigue areas while providing decisive and strong protective inhibition in high-fatigue areas, significantly improving the safety of the rehabilitation process. Physiological fatigue safety threshold It is the cornerstone of the safety of this program. Its value is set based on clinical medical knowledge and individualized assessment. Its initial value is based on publicly published clinical guidelines or statistical data from related studies. During application, the doctor will personalize the value according to the patient's specific situation, such as heart disease history, age, cardiopulmonary function reserve, etc. to ensure safety. The system's "risk aversion level" is defined, and its value can be automatically configured by the expert system according to the patient's risk level, or manually set by the rehabilitation therapist; a larger Values are suitable for high-risk patients and can cause the system to react extremely quickly and strongly to suprathreshold fatigue, and vice versa.

[0028] Example 4: When generating the coupling tension index, the coupling effect analysis module specifically generates the coupling tension index by multiplying the rehabilitation demand signal, the fatigue inhibition signal, and a preset coupling effect weight coefficient; After generating the rehabilitation demand signal and fatigue suppression signal, the coupling effect analysis module in this embodiment ultimately generates a coupling tension index. The core function of this index is to quantify the degree of conflict when the two instructions "high rehabilitation demand" and "high fatigue suppression demand" coexist. A simple weighted summation would obscure this conflict, but this embodiment uses a product form to accurately capture this "and" logic. The conflict is considered acute only when both signals approach 1. The calculation formula for this index is:

[0029] It represents the coupling tension index, a dimensionless value, which is the final output of the coupling effect analysis module. It directly quantifies the conflict intensity between the two instructions of "enhance intervention" and "inhibit intervention"; Represents the rehabilitation demand signal, which is the input of this formula and comes from the calculation result of the first step above; represents the fatigue suppression signal, which is the input of this formula and comes from the calculation result of the second step above; Represents the coupling effect weight coefficient, which is a dimensionless preset adjustable parameter, usually set to 1, for standardization or scaling magnitude; This formula draws on the idea of describing coupling strength in systems engineering, that is, the coupling effect is strongest when multiple interacting factors exist simultaneously and are all significant; the core of the technical problem lies in dealing with contradictory instructions; this contradiction only occurs when "rehabilitation needs are high" ( approaches 1) and “high fatigue suppression demand” ( It is most acute when it approaches 1); the product form can accurately capture this logic. and At the same time, significant If any of the signals is very weak (close to 0), it means that there is no or only a weak instruction contradiction at this time. The value of is also correspondingly small, thus avoiding overreaction to non-contradictory states; Coupling tension index As the output of the coupling effect analysis module, it is passed to the intervention decision and dynamic adjustment module as the core basis for resolving decision contradictions; this invention proposes a computable indicator for the first time To quantify the instruction conflict in the rehabilitation process, a vague, qualitative contradiction problem is transformed into a precise, quantitative engineering parameter, providing a solid foundation for solving the problem and making subsequent intervention decisions possible with precise regulation; Coupling effect weight coefficient It is usually set to 1 as a standardized benchmark; in specific application scenarios, if the influence of the coupling effect needs to be amplified or reduced, this parameter can be adjusted, but its default value of 1 is sufficient for most cases.

[0030] Example 5: When determining the basic intervention adjustment amount, the intervention decision and dynamic adjustment module is specifically configured to: S31, calculate the difference between the rehabilitation demand signal and the fatigue suppression signal to obtain a basic adjustment drive signal; S32, multiply the basic adjustment drive signal by a preset proportional gain constant to generate the basic intervention adjustment amount; The proportional gain constant is set based on the target response speed and stability requirements of the system and combined with the patient's tolerance; The intervention decision and dynamic adjustment module in this embodiment uses a proportional controller logic to determine the basic intervention adjustment amount. It calculates the difference between the rehabilitation demand signal and the fatigue suppression signal to obtain a basic adjustment drive signal, which intuitively reflects the basic adjustment intention of the system when the coupling effect is not considered. Then, this drive signal is multiplied by a preset proportional gain constant to generate the basic intervention adjustment amount. This process forms the basis for the subsequent final intervention decision. Its calculation formula is:

[0031] It represents the basic intervention adjustment amount, which is an intermediate calculated variable. Its physical unit is consistent with the final intervention intensity unit (for example, degree / second or milliampere). Its positive value indicates a tendency to strengthen the intervention, and its negative value indicates a tendency to weaken the intervention. It represents the proportional gain constant, which is a preset adjustable parameter. Its unit is the same as the intervention intensity unit to ensure the consistency of the formula dimension. and are the dimensionless rehabilitation demand signal and fatigue inhibition signal obtained from the above calculations; This formula is based on the classic proportional control idea in feedback control theory and constructs a basic incremental regulation model; The difference directly reflects whether the current system is "demand-driven" or "inhibition-driven", and its sign and magnitude determine the direction and basic strength of regulation; this provides a basic regulation logic for the system when there is no significant conflict. This formula calculates As the basis for subsequent calculation of the actual intervention adjustment amount; it combines two standardized opposing signals into a driving signal with clear physical meaning, simplifies the decision logic, and clearly expresses the basic adjustment tendency of the system when there is no contradiction or conflict, that is, to enhance intervention (when when) or reduce intervention (when hour); Proportional gain constant Is the standard proportional controller gain, which comes from system debugging; the setting of this parameter requires a balance between the response speed and stability of the system; a larger A large value will make the system respond faster to progress deviations, but may cause overshoot and oscillation; a small value will respond smoothly but may be slow; in practical applications, The value needs to be adjusted and set in combination with the patient's specific tolerance and rehabilitation goals to achieve the best control effect.

[0032] Example 6: When generating the final intervention intensity instruction, the intervention decision and dynamic adjustment module is specifically configured to: S41, perform a hyperbolic tangent function operation on the coupling tension index to obtain a modulation reference value; S42, subtract the modulation reference value from 1 to generate the nonlinear modulation factor; S43, multiply the basic intervention adjustment amount by the nonlinear modulation factor to generate the actual intervention adjustment amount; S44, add the actual intervention adjustment amount to the current intervention intensity to generate the final intervention intensity instruction; The intervention decision-making and dynamic adjustment module of this embodiment demonstrates its core nonlinear modulation mechanism when generating the final intervention intensity instruction. Rather than simply executing the basic adjustment amount, it introduces a modulation mechanism based on the coupling tension index to automatically enter a buffering or braking state when conflicts become acute. This mechanism achieves a dynamic balance between rehabilitation needs and fatigue risk through a smooth, nonlinear modulation factor. The generation of the final intervention intensity instruction is the endpoint of the entire decision-making process, and its calculation formula is:

[0033] It represents the final intervention intensity instruction, which is the final output of this formula and is sent to the rehabilitation equipment actuator. Its unit is (degrees / second) or (milliamperes), etc. Indicates the current intervention intensity, which is the input of this formula. Its source is the output value of the previous moment recorded by the system. The unit is the same as The same, the initial intervention intensity of the system, that is, the first calculation The values are manually preset by the rehabilitation therapist based on the patient's initial postoperative condition assessment and tolerance level; Represents the basic intervention adjustment amount, which is the result of the previous step and the unit is the same as same; Represents the dimensionless coupling tension index, which is the output of the coupling effect analysis module; represents the hyperbolic tangent function, which is a standard mathematical function well known to those skilled in the art. This is the nonlinear modulation factor, and its value is dimensionless; This formula is an incremental regulation model based on feedback control theory, and innovatively introduces a nonlinear modulation term based on the hyperbolic tangent function tanh() to deal with coupling tension; when the coupling tension index When it is very high, it indicates that the system is facing a serious decision contradiction. At this time, the system should not simply stop or choose one side, but should enter a buffer state, that is, inhibit any regulatory action; the modulation item This goal was achieved: when When it is close to 0 (no conflict), , the modulation term is close to 1, and the system is adjusted according to the basic logic; when When the conflict intensifies, It approaches 1 quickly, and the modulation term approaches 0 quickly, thus greatly compressing the basic adjustment amount. , making its change to the current intensity minimal; this is equivalent to the system automatically suppressing its own adjustment impulse when the contradiction is acute, maintaining stability, and waiting for the contradiction to ease; the tanh function provides a smoother braking effect than linear attenuation because of its characteristics of being approximately linear near the origin and quickly saturating away from the origin; This formula is the final decision core of the intervention decision and dynamic adjustment module; it receives all state information and coupling analysis results to calculate the most appropriate rehabilitation intensity at the next moment. This formula effectively resolves the conflicting instruction problem in background technology through a smooth, nonlinear modulation factor, achieving a dynamic balance between rehabilitation needs and fatigue risks. This mechanism ensures patient safety while avoiding the complete cessation of rehabilitation due to over-conservatism, thus maximizing the continuity and effectiveness of rehabilitation. This design enables the system to automatically enter a buffer state when faced with a risk scenario where high fatigue and rehabilitation stagnation coexist, effectively avoiding secondary injuries or excessive fatigue that may be caused by a hasty increase in intervention intensity, and significantly improving the overall safety and efficiency of rehabilitation. All adjustable parameters in this final formula ( , , , , ) have been explained in the previous steps; the parameters of the entire model have clear clinical and engineering significance, and their sources and adjustment methods are clear. This allows the rehabilitation program to be easily configured and adaptively adjusted according to individual patient differences, truly tailored to each patient and highly implementable; The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. An intelligent nursing system for elderly people's postoperative rehabilitation based on the Internet of Things, characterized by: include: A data acquisition module is used to collect the patient's physiological data and motion data in real time through wearable sensors; a state assessment module, configured to receive the physiological data and the motion data, and process the data to calculate and generate a rehabilitation progress rate representing rehabilitation progress and a physiological fatigue degree representing physiological risk; Coupling effect analysis module for: generating a standardized rehabilitation demand signal based on the rehabilitation progress rate and a preset target rehabilitation progress rate; generating a standardized fatigue suppression signal according to the physiological fatigue degree and a preset physiological fatigue safety threshold; and combining the rehabilitation demand signal with the fatigue inhibition signal to generate a coupling tension index that quantifies the degree of conflict between the two; Intervention decision-making and dynamic adjustment module, used to: determining a basic intervention adjustment amount based on the rehabilitation demand signal and the fatigue suppression signal; generating a nonlinear modulation factor for suppressing the basic intervention adjustment amount according to the coupling tension index; Calculating the basic intervention adjustment amount and the nonlinear modulation factor to generate an actual intervention adjustment amount; The actual intervention adjustment amount is combined with the current intervention intensity recorded by the system to generate a final intervention intensity instruction, and the instruction is sent to the rehabilitation equipment actuator.

2. The intelligent nursing system for postoperative rehabilitation of the elderly based on the Internet of Things according to claim 1 is characterized in that: When generating the rehabilitation demand signal, the coupling effect analysis module is specifically configured to: S11, calculating the difference between the target rehabilitation progress rate and the rehabilitation progress rate to obtain a progress gap; S12, dividing the progress gap by a preset demand signal sensitivity adjustment factor to obtain a normalized input value; S13 , applying a sigmoid function operation to the normalized input value to generate the rehabilitation demand signal.

3. The intelligent nursing system for postoperative rehabilitation of the elderly based on the Internet of Things according to claim 1 is characterized in that: The specific steps of the coupling effect analysis module generating the fatigue suppression signal include: S21, calculating the difference between the physiological fatigue degree and the physiological fatigue safety threshold to obtain a fatigue excess limit value; S22, multiplying the fatigue limit value by a preset inhibition signal activation slope factor to obtain an activation input value; S23, applying a logistic function operation to the activation input value to generate the fatigue suppression signal.

4. The intelligent nursing system for postoperative rehabilitation of the elderly based on the Internet of Things according to claim 3 is characterized in that: When generating the coupling tension index, the coupling effect analysis module specifically generates the coupling tension index by multiplying the rehabilitation demand signal, the fatigue inhibition signal, and a preset coupling effect weight coefficient.

5. The intelligent nursing system for postoperative rehabilitation of the elderly based on the Internet of Things according to claim 3 is characterized in that: When determining the basic intervention adjustment amount, the intervention decision and dynamic adjustment module is specifically used to: S31, calculating the difference between the rehabilitation demand signal and the fatigue suppression signal to obtain a basic adjustment drive signal; S32: Multiply the basic adjustment driving signal by a preset proportional gain constant to generate the basic intervention adjustment amount.

6. The intelligent nursing system for postoperative rehabilitation of the elderly based on the Internet of Things according to claim 5 is characterized in that: When generating the final intervention intensity instruction, the intervention decision and dynamic adjustment module is specifically configured to: S41, performing a hyperbolic tangent function operation on the coupling tension index to obtain a modulation reference value; S42, subtracting the modulation reference value from the value 1 to generate the nonlinear modulation factor; S43, multiplying the basic intervention adjustment amount by the nonlinear modulation factor to generate the actual intervention adjustment amount; S44. Add the actual intervention adjustment amount to the current intervention intensity to generate the final intervention intensity instruction.

7. The intelligent nursing system for postoperative rehabilitation of the elderly based on the Internet of Things according to claim 2 is characterized in that: The target rehabilitation progress rate is pre-set based on individualized information of the patient's age, surgery type, and preoperative physical condition; the demand signal sensitivity adjustment factor is obtained through statistical learning or offline optimization of historical clinical data.

8. The intelligent nursing system for postoperative rehabilitation of the elderly based on the Internet of Things according to claim 3 is characterized in that: The physiological fatigue safety threshold is based on publicly published clinical guidelines or statistical data from related studies, and is personalized according to the patient's heart disease history and age; the inhibition signal activation slope factor is configured based on the patient's risk level.

9. The intelligent nursing system for postoperative rehabilitation of the elderly based on the Internet of Things according to claim 5 is characterized in that: The proportional gain constant is adjusted and set based on the target response speed and stability requirements of the system and in combination with the patient's tolerance.

Images