An intelligent monitoring system for postoperative rehabilitation effect of urology surgery

Abstract

The present invention discloses an intelligent urology postoperative rehabilitation effect monitoring system, including a data acquisition module, a data preprocessing module, a urology postoperative rehabilitation effect monitoring model building module and a urology postoperative rehabilitation effect monitoring module. The present invention belongs to the field of effect evaluation technology, and specifically refers to an intelligent urology postoperative rehabilitation effect monitoring system. This scheme is based on an adaptive weighting mechanism, dynamically adjusts the weight of the influence of data points on rehabilitation evaluation, ensures that rehabilitation data at different stages are given reasonable attention, designs independent sub-data sets and sub-tasks for each stage, and improves the accuracy of rehabilitation effect prediction; by defining an adaptive kernel function, the system's adaptability to rehabilitation monitoring data is enhanced, and by gradually selecting key data points for updating, the processing speed of rehabilitation monitoring data is accelerated, and rapid convergence is achieved based on a gradual activation mechanism and path optimization, thereby improving the prediction efficiency of rehabilitation monitoring data.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information processing, and in particular to an intelligent urology surgery postoperative rehabilitation effect monitoring system. Background Art

[0002] The urology postoperative rehabilitation effect monitoring system is an intelligent platform that aims to monitor the patient's rehabilitation progress in real time and accurately evaluate it by collecting, processing and analyzing the multidimensional data generated during the postoperative rehabilitation process of urology patients. However, the general urology postoperative rehabilitation effect monitoring system has the problem of capturing the changes in different rehabilitation stages, resulting in a slow response to the patient's actual rehabilitation status; the general urology postoperative rehabilitation effect monitoring system is prone to introduce irrelevant monitoring data, increase noise, thereby reducing the prediction accuracy of rehabilitation effects, and low efficiency when processing large-scale rehabilitation monitoring data sets. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an intelligent urology postoperative rehabilitation effect monitoring system. In view of the problem that the general urology postoperative rehabilitation effect monitoring system has the problem of capturing the changes in different rehabilitation stages, resulting in a slow response to the patient's actual rehabilitation status, this scheme is based on an adaptive weighting mechanism to dynamically adjust the influence weight of data points on rehabilitation evaluation, to ensure that the rehabilitation data of different stages are given reasonable attention, and to design independent sub-data sets and sub-tasks for each stage, so as to flexibly capture the characteristics of each stage and improve the accuracy of rehabilitation effect prediction; in view of the problem that the general urology postoperative rehabilitation effect monitoring system has the problem of easily introducing irrelevant monitoring data, increasing noise, thereby reducing the prediction accuracy of rehabilitation effect, and low efficiency when processing large-scale rehabilitation monitoring data sets, this scheme defines an adaptive kernel function to enhance the system's adaptability to rehabilitation monitoring data, and gradually selects key data points for updating to speed up the processing speed of rehabilitation monitoring data, and achieves rapid convergence based on a gradual activation mechanism and path optimization, thereby improving the prediction efficiency of rehabilitation monitoring data.

[0004] The technical solution adopted by the present invention is as follows: the present invention provides an intelligent urology surgery postoperative rehabilitation effect monitoring system, including a data acquisition module, a data preprocessing module, a urology surgery postoperative rehabilitation effect monitoring model establishment module and a urology surgery postoperative rehabilitation effect monitoring module;

[0005] The data collection module collects historical urology postoperative rehabilitation data;

[0006] The data preprocessing module performs data cleaning, data conversion and standardization on the collected data;

[0007] The module for establishing a postoperative rehabilitation effect monitoring model for urology surgery is based on an adaptive weighting mechanism, dynamically adjusts the weight of the impact of data points on rehabilitation evaluation, gradually selects key data points for updating by defining an adaptive kernel function, and establishes a postoperative rehabilitation effect monitoring model for urology surgery based on a gradual activation mechanism and path optimization;

[0008] The urology surgery postoperative rehabilitation effect monitoring module realizes urology surgery postoperative rehabilitation effect monitoring based on the established urology surgery postoperative rehabilitation effect monitoring model.

[0009] Furthermore, in the data collection module, the historical urology postoperative rehabilitation data includes postoperative pain scores, inflammation indicators, infection indicators, body temperature, urine monitoring indicators, heart rate, postoperative time and functional indicators of the urinary system.

[0010] Furthermore, in the data preprocessing module, the data cleaning is to process missing values ​​and duplicate values; the data conversion is to convert the data into a vector form; and the standardization is to standardize the data based on the maximum and minimum normalization method.

[0011] Furthermore, the urology surgery postoperative rehabilitation effect monitoring model establishment module specifically includes the following contents:

[0012] Model architecture design unit; the established urology surgery postoperative rehabilitation effect monitoring model uses SVM as the basic structure; the dual problem of constructing adaptive SVM is expressed as: ; ; Divide the rehabilitation process into phased recovery, create a sub-dataset for each phase, and annotate the data. The annotation type is the rehabilitation assessment level; use the rehabilitation assessment level as the data label; each phase is a task, and for each task t, define the optimization objective function of task t , expressed as: ; The joint optimization problem is expressed as: ; Where α is the Lagrange multiplier vector; K is the kernel matrix; N is the total number of data points; is the weight of the i-th data point; β is the adjustment parameter; h i is the time after surgery; is the Lagrange multiplier; is the Lagrange multiplier vector of task t; is the kernel matrix of task t; is the regularization parameter; is the L1 norm; T1 is the total task data; T is the transposition operation;

[0013] Simplified optimization scheme design unit; specifically: the objective function gradient is expressed as: ; Define the adaptive kernel function, expressed as: ; ; Calculate partial derivatives ; In each iteration, two key rehabilitation data points are selected, specifically, the rehabilitation data point with the smallest partial derivative is used as the lifting node; the rehabilitation data point with the largest partial derivative is used as the withdrawal node; the update direction is determined by the difference between the lifting node and the withdrawal node, expressed as: ; The adaptive step size of the data point is expressed as: ; Update the solution according to the step size, expressed as: ;in, is the gradient; is the optimization objective function; K(·) is the kernel matrix element; x i 、x j and x b are the i-th, j-th and b-th data points respectively; is the Euclidean distance; and are the adaptive scales of the ith and jth data points, respectively; k1 is the number of neighbors; NN(·) is the set of neighbors of a data point; is the smoothing parameter; d is the update direction; It is the data center point; is the adaptive step size of the ith data point; and are the Lagrange multiplier vectors corresponding to the promotion node and the withdrawal node respectively;

[0014] Activate the units step by step; this includes:

[0015] Initialize the active data set and the data set to be activated; in the initial iteration, the patient's rehabilitation data is divided into: the active data set, initially, the active data set contains only one patient data, indicating the currently activated key data point; the data set to be activated, the data set to be activated contains other patient data and is not activated temporarily;

[0016] Stepwise activation update; at each iteration, according to the objective function gradient Dynamically adjust the active data set and the data set to be activated; specifically: select the idle data point with the smallest negative gradient and add it to the active data set; use the data point in the active data set as a path point, denoted as p i , the path optimization objective is to minimize the gradient difference of the data points on the path, expressed as: ; Add the key data points selected according to the path optimization to the active data set; Update the coefficients of the data in the active data set, expressed as: ; Keep the coefficient of the data set to be activated to zero; where p is the set of active data set data points selected on the path; is the gradient of the objective function at the path point; and are the Lagrange multiplier vectors of the data points at the k+1th iteration and the kth iteration respectively; γ is the adaptive step size of the data points; Batch(·) is the set of key data points selected based on the path; and are the Lagrange multiplier values ​​of the i-th data point as the promotion node and the withdrawal node respectively;

[0017] Convergence judgment unit; a convergence threshold and a maximum number of iterations are set in advance; when the gradient difference between the promotion node and the withdrawal node is lower than the convergence threshold or no new data in the to-be-activated data set is added to the active data set, convergence is completed; a urology postoperative rehabilitation effect monitoring model is established; if the maximum number of iterations is reached but convergence is not completed, the initial step size, regularization parameters and kernel function parameters are adjusted and iterated again.

[0018] Furthermore, the urology postoperative rehabilitation effect monitoring module is based on the established urology postoperative rehabilitation effect monitoring model, which collects the patient's postoperative pain score, inflammation index, infection index, body temperature, urine monitoring index, heart rate, postoperative time and functional indexes of the urinary system in real time; after preprocessing, it is input into the urology postoperative rehabilitation effect monitoring model, and the rehabilitation assessment level output by the model is used as the monitoring result.

[0019] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0020] (1) In view of the problem that the general urology surgery postoperative rehabilitation effect monitoring system has the problem of capturing changes in different rehabilitation stages, resulting in a slow response to the patient's actual rehabilitation status, this scheme is based on an adaptive weighting mechanism to dynamically adjust the weight of the impact of data points on rehabilitation evaluation to ensure that rehabilitation data at different stages are given reasonable attention. Independent sub-datasets and sub-tasks are designed for each stage to flexibly capture the characteristics of each stage and improve the accuracy of rehabilitation effect prediction.

[0021] (2) In view of the problem that the general urology postoperative rehabilitation effect monitoring system is prone to introduce irrelevant monitoring data, increase noise, and thus reduce the prediction accuracy of rehabilitation effect, and is inefficient when processing large-scale rehabilitation monitoring data sets, this scheme defines an adaptive kernel function to enhance the system's adaptability to rehabilitation monitoring data, and speeds up the processing of rehabilitation monitoring data by gradually selecting key data points for updating. Based on the step-by-step activation mechanism and path optimization, it achieves rapid convergence, thereby improving the prediction efficiency of rehabilitation monitoring data. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of the process of an intelligent urology surgery postoperative rehabilitation effect monitoring system provided by the present invention;

[0023] Figure 2 Schematic diagram of the process of establishing modules for the postoperative rehabilitation effect monitoring model in urology surgery.

[0024] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0027] Example 1, see Figure 1 The present invention provides an intelligent urology surgery postoperative rehabilitation effect monitoring system, including a data acquisition module, a data preprocessing module, a urology surgery postoperative rehabilitation effect monitoring model establishment module and a urology surgery postoperative rehabilitation effect monitoring module;

[0028] The data acquisition module collects historical urology surgery postoperative rehabilitation data; and sends the data to the data preprocessing module;

[0029] The data preprocessing module receives the data sent by the data acquisition module; performs data cleaning, data conversion and standardization on the collected data; and sends the data to the urology surgery postoperative rehabilitation effect monitoring model establishment module;

[0030] The urology surgery postoperative rehabilitation effect monitoring model establishment module receives the data sent by the data preprocessing module; based on the adaptive weighting mechanism, dynamically adjusts the influence weight of the data point on the rehabilitation evaluation, gradually selects key data points for updating by defining an adaptive kernel function, and establishes the urology surgery postoperative rehabilitation effect monitoring model based on the gradual activation mechanism and path optimization; and sends the data to the urology surgery postoperative rehabilitation effect monitoring module;

[0031] The urology surgery postoperative rehabilitation effect monitoring module receives data sent by the urology surgery postoperative rehabilitation effect monitoring model establishment module; and implements urology surgery postoperative rehabilitation effect monitoring based on the established urology surgery postoperative rehabilitation effect monitoring model.

[0032] Example 2, see Figure 1 This embodiment is based on the above embodiment. In the data acquisition module, the historical urological postoperative rehabilitation data include postoperative pain score, inflammation index, infection index, body temperature, urine monitoring index, heart rate, postoperative time and functional indexes of the urinary system; inflammation indexes include white blood cell count, C-reactive protein, erythrocyte sedimentation rate, and cytokine level; infection indexes include procalcitonin, neutrophil ratio and serum immunoglobulin; urine monitoring indexes include urine protein, urine sugar, red blood cells, white blood cells, urine specific gravity and urine pH; functional indexes of the urinary system include glomerular filtration rate, urine flow rate, residual urine volume, bladder compliance and number of nocturia.

[0033] Example 3, see Figure 1 This embodiment is based on the above embodiment. In the data preprocessing module, data cleaning is to process missing values ​​and duplicate values; data conversion is to convert data into vector form; and standardization is to standardize data based on the maximum and minimum normalization method.

[0034] Example 4, see Figure 1 and Figure 2 Based on the above embodiment, this embodiment includes the following contents:

[0035] Model architecture design unit;

[0036] Simplified optimization scheme design unit; specifically: the objective function gradient is expressed as: ; Define the adaptive kernel function, expressed as: ; ; Calculate partial derivatives ; In each iteration, two key rehabilitation data points are selected, specifically, the rehabilitation data point with the smallest partial derivative is used as the boost node; the rehabilitation data point with the largest partial derivative is used as the retraction node; the update direction is determined by the difference between the boost node and the retraction node, expressed as ; The adaptive step size of the data point is expressed as: ; Update the solution according to the step size, expressed as: ;in, is the gradient; is the optimization objective function; K(·) is the kernel matrix element; x i 、x j and x b are the i-th, j-th and b-th data points respectively; is the Euclidean distance; and are the adaptive scales of the ith and jth data points, respectively; k1 is the number of neighbors, ranging from [5,50]; NN(·) is the set of neighbors of a data point; is the smoothing parameter, with a value of [0.1, 10]; d is the update direction; It is the data center point; is the adaptive step size of the ith data point; and are the Lagrange multiplier vectors corresponding to the promotion node and the withdrawal node respectively;

[0037] Activate the units step by step; this includes:

[0038] Initialize the active data set and the data set to be activated; in the initial iteration, the patient's rehabilitation data is divided into: the active data set, initially, the active data set contains only one patient data, indicating the currently activated key data point; the data set to be activated, the data set to be activated contains other patient data and is not activated temporarily;

[0039] Stepwise activation update; at each iteration, according to the objective function gradient Dynamically adjust the active data set and the data set to be activated; specifically: select the idle data point with the smallest negative gradient and add it to the active data set; use the data point in the active data set as a path point, denoted as p i , the path optimization objective is to minimize the gradient difference of the data points on the path, expressed as: ; Add the key data points selected according to the path optimization to the active data set; Update the coefficients of the data in the active data set, expressed as: ; Keep the coefficient of the data set to be activated to zero; where p is the set of active data set data points selected on the path; is the gradient of the objective function at the path point; and are the Lagrange multiplier vectors of the data points at the k+1th iteration and the kth iteration respectively; γ is the adaptive step size of the data points; Batch(·) is the set of key data points selected based on the path; and are the Lagrange multiplier values ​​of the i-th data point as the promotion node and the withdrawal node respectively;

[0040] Convergence judgment unit; a convergence threshold and a maximum number of iterations are pre-set, and the convergence threshold is [10 -6 ,10 -3], the maximum number of iterations is [100,1000]; when the gradient difference between the boost node and the retraction node is lower than the convergence threshold or no new data in the to-be-activated data set is added to the active data set, the convergence is completed; the established urology postoperative rehabilitation effect monitoring model is obtained; if the maximum number of iterations is reached but convergence is not completed, the initial step size, regularization parameters and kernel function parameters are adjusted and iterated again.

[0041] By performing the above operations, the general urology postoperative rehabilitation effect monitoring system is prone to introduce irrelevant monitoring data, increase noise, and thus reduce the prediction accuracy of rehabilitation effect, and has low efficiency when processing large-scale rehabilitation monitoring data sets. This scheme defines an adaptive kernel function to enhance the system's adaptability to rehabilitation monitoring data, and speeds up the processing of rehabilitation monitoring data by gradually selecting key data points for updating. It achieves rapid convergence based on a gradual activation mechanism and path optimization, thereby improving the prediction efficiency of rehabilitation monitoring data.

[0042] Example 5, see Figure 2 This embodiment is based on the above embodiment. In the urology surgery postoperative rehabilitation effect monitoring model establishment module, the model architecture design unit specifically includes the following contents:

[0043] The established urology surgery postoperative rehabilitation effect monitoring model uses SVM as the basic structure; the dual problem of constructing an adaptive SVM is expressed as: ; ; The rehabilitation process is divided into stages of recovery, with the short-term recovery stage defined as 0-1 week after surgery, the medium-term recovery stage as 1-4 weeks, and the long-term recovery stage as after 4 weeks. A sub-dataset is created for each stage, and data annotation is performed. The annotation type is the rehabilitation assessment level; the rehabilitation assessment levels include normal, mildly abnormal, moderately abnormal, and severely abnormal; the rehabilitation assessment level is used as the data label, and the indicators of the short-term recovery data set are postoperative pain scores, inflammation indicators, infection indicators, and body temperature; the indicators of the medium-term recovery data set are urine monitoring indicators, body temperature, and heart rate; the long-term recovery data set is the functional indicators of the urinary system; each stage is taken as a task, and for each task t, the optimization objective function of task t is defined , expressed as: ; The joint optimization problem is expressed as: ; Where α is the Lagrange multiplier vector, and the upper limit of the Lagrange multiplier vector is [0.1, 1000]; K is the kernel matrix; N is the total number of data points; is the weight of the i-th data point; β is the adjustment parameter, with a value of [0.01, 1]; h i is the time after surgery; is the Lagrange multiplier; is the Lagrange multiplier vector of task t; is the kernel matrix of task t; is the regularization parameter, and its value is [10 -5 ,10]; is the L1 norm; T1 is the total task data, which is 3 here; T is the transpose operation.

[0044] By performing the above operations, the general urology postoperative rehabilitation effect monitoring system has the problem of capturing changes in different rehabilitation stages, resulting in a slow response to the patient's actual rehabilitation status. Based on the adaptive weighting mechanism, this solution dynamically adjusts the influence weight of data points on rehabilitation evaluation to ensure that rehabilitation data at different stages are given reasonable attention. Independent sub-datasets and sub-tasks are designed for each stage to flexibly capture the characteristics of each stage and improve the accuracy of rehabilitation effect prediction.

[0045] Example 6, see Figure 1 This embodiment is based on the above embodiment. The urology surgery postoperative rehabilitation effect monitoring module is based on the established urology surgery postoperative rehabilitation effect monitoring model, and collects the patient's postoperative pain score, inflammation index, infection index, body temperature, urine monitoring index, heart rate, postoperative time and urinary system functional indexes in real time; after preprocessing, it is input into the urology surgery postoperative rehabilitation effect monitoring model, and the rehabilitation assessment level output by the model is used as the monitoring result; if the rehabilitation assessment level is moderately abnormal or severely abnormal, early warning processing is performed.

[0046] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0047] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0048] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. An intelligent postoperative rehabilitation effect monitoring system for urology surgery, characterized by: The system includes a data acquisition module, a data preprocessing module, a urology surgery postoperative rehabilitation effect monitoring model establishment module and a urology surgery postoperative rehabilitation effect monitoring module; The data collection module collects historical urology postoperative rehabilitation data; The data preprocessing module performs data cleaning, data conversion and standardization on the collected data; The module for establishing a postoperative rehabilitation effect monitoring model for urology surgery is based on an adaptive weighting mechanism, dynamically adjusts the weight of the impact of data points on rehabilitation evaluation, gradually selects key data points for updating by defining an adaptive kernel function, and establishes a postoperative rehabilitation effect monitoring model for urology surgery based on a gradual activation mechanism and path optimization; The urology surgery postoperative rehabilitation effect monitoring module realizes urology surgery postoperative rehabilitation effect monitoring based on the established urology surgery postoperative rehabilitation effect monitoring model; The urology surgery postoperative rehabilitation effect monitoring model establishment module includes the following contents: Model architecture design unit; specifically: the established urology surgery postoperative rehabilitation effect monitoring model uses SVM as the basic structure; the dual problem of constructing an adaptive SVM is expressed as: ; ; Divide the rehabilitation process into phased recovery, create a sub-dataset for each phase, and annotate the data. The annotation type is the rehabilitation assessment level; use the rehabilitation assessment level as the data label; each phase is a task, and for each task t, define the optimization objective function of task t , expressed as: ; The joint optimization problem is obtained, which is expressed as: ; Where α is the Lagrange multiplier vector; K is the kernel matrix; N is the total number of data points; is the weight of the i-th data point; β is the adjustment parameter; h i is the time after surgery; is the Lagrange multiplier; is the Lagrange multiplier vector of task t; is the kernel matrix of task t; is the regularization parameter; is the L1 norm; T1 is the total task data; T is the transposition operation; Simplified optimization scheme design unit; specifically: the objective function gradient is expressed as: ; Define the adaptive kernel function, expressed as: ; ; Calculate partial derivatives ; In each iteration, two key rehabilitation data points are selected, specifically, the rehabilitation data point with the smallest partial derivative is used as the boost node; the rehabilitation data point with the largest partial derivative is used as the retraction node; the update direction is determined by the difference between the boost node and the retraction node, expressed as ; The adaptive step size of the data point is expressed as: ; Update the solution according to the step size, expressed as: ;in, is the gradient; is the optimization objective function; K(·) is the kernel matrix element; x i 、x j and x b are the i-th, j-th and b-th data points respectively; is the Euclidean distance; and are the adaptive scales of the ith and jth data points, respectively; k1 is the number of neighbors; NN(·) is the set of neighbors of a data point; is the smoothing parameter; d is the update direction; It is the data center point; is the adaptive step size of the ith data point; and are the Lagrange multiplier vectors corresponding to the promotion node and the withdrawal node respectively; Activate units gradually; Convergence judgment unit; a convergence threshold and a maximum number of iterations are pre-set; when the gradient difference between the boost node and the retract node is lower than the convergence threshold or no new data in the to-be-activated data set is added to the active data set, convergence is completed; a urology postoperative rehabilitation effect monitoring model is established; if the maximum number of iterations is reached but convergence is not completed, the initial step size, regularization parameter and kernel function parameter are adjusted and iterated again; The step-by-step activation unit specifically includes: Initialize the active data set and the data set to be activated; in the initial iteration, the patient's rehabilitation data is divided into: the active data set, initially, the active data set contains only one patient data, indicating the currently activated key data point; the data set to be activated, the data set to be activated contains other patient data and is not activated temporarily; Stepwise activation update; at each iteration, according to the objective function gradient Dynamically adjust the active data set and the data set to be activated; specifically: select the idle data point with the smallest negative gradient and add it to the active data set; use the data point in the active data set as a path point, denoted as p i , the path optimization objective is to minimize the gradient difference of the data points on the path, expressed as: ; Add the key data points selected according to the path optimization to the active data set; Update the coefficients of the data in the active data set, expressed as: ; Keep the coefficient of the data set to be activated to zero; where p is the set of active data set data points selected on the path; is the gradient of the objective function at the path point; and are the Lagrange multiplier vectors of the data points at the k+1th iteration and the kth iteration respectively; γ is the adaptive step size of the data points; Batch(·) is the set of key data points selected based on the path; and are the Lagrange multiplier values ​​of the i-th data point as the promotion node and the withdrawal node respectively.

2. The intelligent urology surgery postoperative rehabilitation effect monitoring system according to claim 1 is characterized by: In the data collection module, the historical urology postoperative rehabilitation data includes postoperative pain score, inflammation index, infection index, body temperature, urine monitoring index, heart rate, postoperative time and functional indexes of the urinary system.

3. The intelligent urology surgery postoperative rehabilitation effect monitoring system according to claim 1 is characterized by: The urology postoperative rehabilitation effect monitoring module is based on the established urology postoperative rehabilitation effect monitoring model, which collects the patient's postoperative pain score, inflammation index, infection index, body temperature, urine monitoring index, heart rate, postoperative time and urinary system functional indexes in real time; after preprocessing, it is input into the urology postoperative rehabilitation effect monitoring model, and the rehabilitation assessment level output by the model is used as the monitoring result.

4. The intelligent urology surgery postoperative rehabilitation effect monitoring system according to claim 1 is characterized by: In the data preprocessing module, the data cleaning is to process missing values ​​and duplicate values; the data conversion is to convert the data into vector form; and the standardization is to standardize the data based on the maximum and minimum normalization method.

Images