Postoperative Recovery Management System for Gastrointestinal Patients Based on Big Data

Abstract

The present invention discloses a postoperative recovery management system for gastrointestinal patients based on big data, including a data acquisition module, a module for establishing a postoperative recovery guidance model, a module for establishing a patient status monitoring model, a monitoring optimization module, and a comprehensive management module. The present invention relates to the technical field of postoperative recovery management, specifically referring to a postoperative recovery management system for gastrointestinal patients based on big data. In this solution, by designing a local density function, a clustering center update formula, a data point allocation rule, and an objective function, the convergence of the model and the stability of the clustering results are improved; by designing an energy function and an adaptive weight adjustment mechanism, the activation ability of hidden units is enhanced, and the adaptability of the model and the accuracy of monitoring are improved; by designing adaptive parameters, co-evolutionary search, and elite retention, initial parameter points are generated by combining randomness and goal orientation, improving the stability, adaptability, convergence speed, and quality of the parameter search.

Description

Technical Field

[0001] The present invention relates to the technical field of postoperative recovery management, and specifically refers to a postoperative recovery management system for gastrointestinal patients based on big data. Background Art

[0002] The postoperative recovery management system for gastrointestinal patients based on big data is an innovative medical technology that constructs a postoperative recovery guidance model and a patient status monitoring model through big data technology and artificial intelligence algorithms to achieve intelligent management of the postoperative recovery process of gastrointestinal surgery patients, real-time monitoring of patients' physiological indicators and recovery progress, and the system can timely detect abnormal situations and provide early warnings.

[0003] Problems existing in traditional clustering methods in the postoperative recovery guidance model include uneven distribution of feature weights, easy omission of local data, and inaccurate update of clustering centers; problems existing in traditional patient status monitoring models include a single model architecture, weak activation ability of hidden units, insufficient feature extraction ability, and low monitoring accuracy; problems existing in traditional parameter search methods in the monitoring optimization module include low search efficiency, poor stability, and low quality of search results. Summary of the Invention

[0004] In view of the above situation, to overcome the defects of the prior art, the present invention provides a postoperative recovery management system for gastrointestinal patients based on big data. Aiming at the problems of uneven distribution of feature weights, easy omission of local data, and inaccurate update of clustering centers existing in traditional clustering methods in the postoperative recovery guidance model, this solution improves the model's ability to capture local features and the balance ability of global and local features, and improves the convergence of the model and the stability of clustering results by defining a feature discrimination factor and feature weights, designing a local density function, designing a clustering center update formula, defining a composite assignment distance function, designing a data point assignment rule, and a target function; aiming at the problems of a single model architecture, weak activation ability of hidden units, insufficient feature extraction ability, and low monitoring accuracy existing in traditional patient status monitoring models, this solution enhances the activation ability of hidden units, enhances the model's feature extraction ability for data, and improves the adaptability of the model to the postoperative recovery status of patients and the accuracy of real-time monitoring by designing a model architecture, multi-layer nonlinear transformation, designing an energy function, and designing an adaptive weight adjustment mechanism; aiming at the problems of low search efficiency, poor stability, and low quality of search results existing in traditional parameter search methods in the monitoring optimization module, this solution improves the starting point quality and convergence speed of parameter search, retains the optimal parameter positions in each search, improves the stability and quality of search results, and improves the flexibility and adaptability of parameter search by generating parameter search points, designing adaptive parameters, co-evolutionary search, elite retention, and setting search rules, and combining randomness and goal orientation to generate initial parameter points.

[0005] The technical solution adopted by the present invention is as follows: The gastrointestinal patient postoperative recovery management system based on big data provided by the present invention includes a data acquisition module, a postoperative recovery guidance model establishment module, a patient status monitoring model establishment module, a monitoring optimization module, and a comprehensive management module;

[0006] The data acquisition module collects the age, gender, medical history, surgical information, postoperative physiological data, complication data, and postoperative recovery data of gastrointestinal patients after surgery;

[0007] The postoperative recovery guidance model establishment module establishes a postoperative recovery guidance model by defining feature discrimination factors, defining feature weights, designing a local density function, designing a clustering center update formula, defining a composite assignment distance function, designing a data point assignment rule, designing an objective function, and clustering;

[0008] The patient status monitoring model establishment module establishes a patient status monitoring model by setting model labels, designing a model architecture, performing multi-layer non-linear transformation, designing an energy function, and designing an adaptive weight adjustment mechanism;

[0009] The monitoring optimization module performs monitoring optimization through initial setting, generating parameter search points, designing adaptive parameters, co-evolutionary search, elite retention, and setting search rules;

[0010] The comprehensive management module uses the postoperative recovery guidance model and the patient status monitoring model to manage the postoperative recovery of users.

[0011] Further, the data acquisition module collects the age, gender, medical history, surgical information, postoperative physiological data, complication data, and postoperative recovery data of gastrointestinal patients after surgery; the medical history includes past medical history, allergy history, and family medical history; the surgical information includes surgical type, surgery time, surgery duration, and drugs used during the operation; the postoperative physiological data includes heart rate, blood pressure, body temperature, respiratory rate, and blood biochemical examination indicators; the complication data is the type of complications that occur after surgery, complication prevention suggestions, and complication nursing suggestions; the postoperative recovery data includes three recovery states: good, normal, and abnormal.

[0012] Further, the postoperative recovery guidance model establishment module specifically includes the following content:

[0013] Define the feature discrimination factor, which is expressed as follows:

[0014] ;

[0015] where k represents the index of clustering, j represents the index of the feature dimension of the data, represents the feature discrimination factor of the j-th feature of the k-th cluster, represents the k-th cluster center, represents the number of data points in the k-th cluster, and i represents the index of the data point used for model training, represents the i-th data point, represents the membership symbol, represents that the i-th data point belongs to the k-th cluster, represents the j-th feature of the i-th data point, represents the mean of the j-th feature in the k-th cluster, represents all clusters except the k-th cluster, represents the mean of the j-th feature in all clusters except the k-th cluster;

[0016] Define the feature weight, which is expressed as follows:

[0017] ;

[0018] where, represents the feature weight of the j-th feature in the k-th cluster, represents the index of the feature dimension of the data, and D represents the total number of feature dimensions of the data, represents the -th feature of the k-th cluster's feature discrimination factor, represents the exponential function with the natural constant as the base;

[0019] Design the local density function, which is expressed as follows:

[0020] ;

[0021] where, represents the local density function, represents the local density value of the i-th data point, and l represents the index of the data point, represents the l-th data point, represents the set of the five data points closest to the data point i, represents the density adjustment coefficient, represents taking the modulus length;

[0022] Design the cluster center update formula, which is expressed as follows:

[0023] ;

[0024] where, represents the j-th feature of the cluster center of the k-th cluster after update;

[0025] Define the composite assignment distance function, which is expressed as follows:

[0026] ;

[0027] Among them, represents the composite assignment distance function, represents the composite assignment distance between the i-th data point and the k-th cluster center, represents the assignment weight;

[0028] Design the data point assignment rule, calculate the composite assignment distance between the data point and each cluster center, select the cluster center with the minimum composite assignment distance from the data point, and assign the data point to the cluster to which this cluster center belongs;

[0029] Design the objective function, which is expressed as follows:

[0030] ;

[0031] Among them, represents the objective function value, represents the number of cluster centers, and represents the coordination coefficient;

[0032] For clustering, set the objective function threshold. First, randomly select data points from all model training data points as the initial cluster centers, then assign each data point to a cluster according to the data point assignment rule, and then use the cluster center update formula to update the cluster centers, repeating the data point assignment and cluster center update; after each data point assignment is completed, calculate the objective function value. When the objective function value is less than the objective function threshold, the clustering converges.

[0033] Furthermore, the module for establishing the patient status monitoring model specifically includes the following content:

[0034] Set the model label, and set the postoperative recovery data as the label data of the model;

[0035] Design the model architecture. The model is stacked by restricted Boltzmann machines. Each layer is connected through an adaptive weight adjustment mechanism. The hidden units are activated through multi-layer non-linear transformations, and finally optimized through the energy function;

[0036] The multi-layer non-linear transformation is expressed as follows:

[0037] ;

[0038] Among them, u represents the layer index of the model, p and q respectively represent the indexes of the hidden unit and the visible unit, represents the activation value of the p-th hidden unit in the u-th layer of the model, represents the multi-layer non-linear transformation function, Denote the weight between the p-th hidden unit and the q-th visible unit in the u-th layer of the model, Denote the activation value of the q-th visible unit in the (u - 1)-th layer of the model, Denote the bias of the p-th hidden unit in the u-th layer of the model, Denote the input value of the multi-layer non-linear transformation function, Denote the hyperbolic tangent function, and Denote the transformation coefficient;

[0039] Design the energy function, which is expressed as follows:

[0040] ;

[0041] where, Denote the activation value of the q-th visible unit, Denote the activation value of the p-th hidden unit, Denote the energy function value between the q-th visible unit and the p-th hidden unit, Denote the weight between the p-th hidden unit and the q-th visible unit;

[0042] Design the adaptive weight adjustment mechanism, which is expressed as follows:

[0043] ;

[0044] where, t represents the index of the time point, Denote the value of the weight between the p-th hidden unit and the q-th visible unit in the u-th layer of the model at time t, Denote the value of the weight between the p-th hidden unit and the q-th visible unit in the u-th layer of the model at time t - 1, Denote the adjustment rate, Denote the adjustment amount of the weight between the p-th hidden unit and the q-th visible unit in the u-th layer of the model at time t, and Denote the balance coefficient, E represents the energy function, S represents the activation state of the hidden layer, Denote the partial derivative of the energy function with respect to the weight Take the partial derivative, Denote the partial derivative of the activation state of the hidden layer with respect to the weight Take the partial derivative.

[0045] Furthermore, the monitoring and optimization module specifically includes the following content:

[0046] Initial setting, set the parameters to be searched, including the number of layers of the model and the number of hidden units in each layer, set the accuracy of the model as the parameter performance value, set the maximum number of parameter searches and the parameter performance qualified value;

[0047] The generated parameter search points are represented as follows:

[0048] ;

[0049] Among them, represents the position of the initial parameter search point generated, PB represents the maximum value of the search range, and LB represents the minimum value of the search range. represents a position randomly selected within the search range. represents a number with a value range between 0 and 1.

[0050] The design of adaptive parameters is represented as follows:

[0051] ;

[0052] Among them, represents the number of parameter searches. and represent the adaptive parameters at the th parameter search. and represent the adaptive parameters at the th parameter search. represents the maximum number of parameter searches. represents the maximum parameter performance value among all the searched parameter positions. represents the minimum parameter performance value among all the searched parameter positions. represents the average parameter performance value of all the searched parameter positions.

[0053] Co-evolutionary search is represented as follows:

[0054] ;

[0055] Among them, represents the parameter position obtained from the th co-evolutionary search of the parameter search point. represents the parameter position obtained from the th co-evolutionary search of the parameter search point. represents the average value of the parameter positions obtained from the th co-evolutionary search of all parameter search points. represents the optimal parameter position obtained from the th co-evolutionary search of the parameter search point.

[0056] Elite retention: After each co-evolutionary search, first update the position of the worst parameter to the optimal parameter position obtained from the previous parameter search, and then calculate the average position of the searched parameter points.

[0057] ;

[0058] wherein, represents the position of the worst parameter obtained by the th co-evolutionary search for the parameter search points, represents the average value of the parameter positions obtained by the th co-evolutionary search for all parameter search points, H represents the total number of parameter search points, represents the sum of the parameter positions obtained by the th co-evolutionary search for all parameter search points except the parameter search points where the worst parameter positions are found;

[0059] Set the search rules. First, generate the initial parameter search points, perform co-evolutionary search using the parameter search points, and perform an elitist retention operation after each search. When the parameter performance value of the searched parameter points is greater than the parameter performance qualification value, the search ends, and the parameter with the largest parameter performance value among all the searched parameter positions is output. When the number of searches is greater than the maximum number of searches, restart the search; otherwise, increment the number of searches by one and perform the next search.

[0060] Furthermore, the comprehensive management module collects the user's age, gender, medical history, surgical information, and postoperative physiological data, inputs the data into the postoperative recovery guidance model, obtains the data belonging to the same cluster as the user's data, and provides the user with complication prevention suggestions and complication nursing suggestions for the data in the same cluster; then inputs the user's data into the patient status monitoring model, and the model outputs the user's postoperative recovery data. When the status of the postoperative recovery data is abnormal, a warning signal is issued.

[0061] The beneficial effects achieved by the present invention using the above solution are as follows:

[0062] (1) Aiming at the problems of uneven feature weight distribution, easy neglect of local data, and inaccurate clustering center update in the traditional clustering method in the postoperative recovery guidance model, this solution improves the model's ability to capture local features and the balance ability of global and local features, and improves the convergence of the model and the stability of the clustering results by defining the feature discrimination factor and feature weight, designing the local density function, designing the clustering center update formula, defining the composite assignment distance function, designing the data point assignment rule and the objective function.

[0063] (2)Aiming at the problems of single model architecture, weak activation ability of hidden units, insufficient feature extraction ability, and low monitoring accuracy in traditional patient status monitoring models, this solution enhances the activation ability of hidden units, enhances the model's feature extraction ability for data, and improves the adaptability of the model to the postoperative recovery status of patients and the accuracy of real-time monitoring by designing the model architecture, multi-layer non-linear transformation, designing an energy function, and designing an adaptive weight adjustment mechanism.

[0064] (3)Aiming at the problems of low search efficiency, poor stability, and low quality of search results in traditional parameter search methods in the monitoring optimization module, this solution generates parameter search points, designs adaptive parameters, co-evolutionary search, elite retention, and sets search rules, combines randomness and goal orientation to generate initial parameter points, improves the starting quality and convergence speed of parameter search, retains the optimal parameter positions in each search, improves the stability of parameter search and the quality of results, and improves the flexibility and adaptability of parameter search. Description of the Drawings

[0065] Figure 1 It is a schematic diagram of the gastrointestinal patient postoperative recovery management system based on big data provided by the present invention;

[0066] Figure 2 It is a schematic diagram of the module for establishing a postoperative recovery guidance model;

[0067] Figure 3 It is a schematic diagram of the module for establishing a patient status monitoring model;

[0068] Figure 4 It is a schematic diagram of the monitoring optimization module;

[0069] Figure 5 It is a schematic diagram of the search rules.

[0070] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. Detailed Embodiments

[0071] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a 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 those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0072] In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the 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 orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0073] Example 1, refer to Figure 1 , the postoperative recovery management system for gastrointestinal patients based on big data provided by the present invention includes a data collection module, a module for establishing a postoperative recovery guidance model, a module for establishing a patient status monitoring model, a monitoring optimization module, and a comprehensive management module;

[0074] The data collection module collects the age, gender, medical history, surgical information, postoperative physiological data, complication data, and postoperative recovery data of gastrointestinal patients after surgery; the medical history includes past medical history, allergy history, and family medical history; the surgical information includes surgical type, surgery time, surgery duration, and drugs used during the operation; the postoperative physiological data includes heart rate, blood pressure, body temperature, respiratory rate, and blood biochemical examination indicators; the complication data is the type of complications that occur after surgery, complication prevention suggestions, and complication nursing suggestions; the postoperative recovery data includes three recovery states: good, normal, and abnormal; and sends the data to the module for establishing a postoperative recovery guidance model and the module for establishing a patient status monitoring model;

[0075] The module for establishing a postoperative recovery guidance model receives the data sent by the data collection module, and establishes a postoperative recovery guidance model by defining feature discrimination factors, defining feature weights, designing a local density function, designing a clustering center update formula, defining a composite assignment distance function, designing a data point assignment rule, designing an objective function, and clustering, and sends the data to the comprehensive management module;

[0076] The module for establishing a patient status monitoring model receives the data sent by the data collection module, and establishes a patient status monitoring model by setting model tags, designing a model architecture, performing multi-layer non-linear transformation, designing an energy function, and designing an adaptive weight adjustment mechanism, and sends the data to the monitoring optimization module;

[0077] The monitoring optimization module receives the data sent by the module for establishing a patient status monitoring model, and performs monitoring optimization by initial setting, generating parameter search points, designing adaptive parameters, co-evolutionary search, elite retention, and setting search rules, and sends the data to the comprehensive management module;

[0078] The comprehensive management module receives the data sent by the postoperative recovery guidance model module and the monitoring and optimization module, and uses the postoperative recovery guidance model and the patient status monitoring model to manage the user's postoperative recovery.

[0079] Example 2, refer to Figure 1 and Figure 2 , based on the above example, the postoperative recovery guidance model module specifically includes the following content:

[0080] Define the feature discrimination factor to quantify the difference between features within and between clusters, expressed as follows:

[0081] ;

[0082] Among them, k represents the index of the cluster, j represents the index of the feature dimension of the data, represents the feature discrimination factor of the j-th feature of the k-th cluster, represents the center of the k-th cluster, represents the number of data points in the k-th cluster, i represents the index of the data point used for model training, represents the i-th data point, represents the membership symbol, represents that the i-th data point belongs to the k-th cluster, represents the j-th feature of the i-th data point, represents the mean of the j-th feature in the k-th cluster, represents all clusters except the k-th cluster, represents the mean of the j-th feature in all clusters except the k-th cluster;

[0083] Define the feature weight, and dynamically allocate the importance of each feature in the cluster based on the feature discrimination factor, expressed as follows:

[0084] ;

[0085] Among them, represents the feature weight of the j-th feature of the k-th cluster, represents the index of the feature dimension of the data, D represents the total number of feature dimensions of the data, represents the -th feature of the k-th cluster represents the exponential function with the natural constant as the base;

[0086] Design the local density function to quantify the distribution density of data points in the neighborhood and capture the local structural characteristics of the data, expressed as follows:

[0087] ;

[0088] Among them, represents the local density function, represents the local density value of the i-th data point, l represents the index of the data point, represents the l-th data point, represents the set of the five data points closest to data point i, represents the density adjustment coefficient, represents taking the modulus length;

[0089] Design the clustering center update formula, and dynamically update the position of the clustering center through weighted average and local density adjustment, which is expressed as follows:

[0090] ;

[0091] Among them, represents the j-th feature of the clustering center of the k-th cluster after update;

[0092] Define the composite assignment distance function, which combines feature difference and local density to quantify the distance between the data point and the clustering center, and is expressed as follows:

[0093] ;

[0094] Among them, represents the composite assignment distance function, represents the composite assignment distance between the i-th data point and the k-th clustering center, represents the assignment weight;

[0095] Design the data point assignment rule, calculate the composite assignment distance between the data point and each clustering center, select the clustering center with the smallest composite assignment distance from the data point, and assign the data point to the cluster to which this clustering center belongs;

[0096] Design the objective function, and design the objective function by comprehensively considering the compactness within the cluster, local density, and sparsity of feature weights, which is expressed as follows:

[0097] ;

[0098] Among them, represents the objective function value, represents the number of clustering centers, and represent the coordination coefficients;

[0099] For clustering, set the objective function threshold. First, randomly select from all the model training data points Use a number of data points as the initial clustering centers, then assign each data point to a cluster according to the data point assignment rule, and then use the clustering center update formula to update the clustering centers, repeating the data point assignment and clustering center update; after each data point assignment is completed, calculate the objective function value, and when the objective function value is less than the objective function threshold, the clustering converges.

[0100] By performing the above operations, for the problems of uneven feature weight assignment, easy omission of local data, and inaccurate clustering center update existing in the traditional clustering method in the postoperative recovery guidance model, this solution improves the model's ability to capture local features and the balance ability of global and local features, as well as the convergence of the model and the stability of the clustering results by defining the feature discrimination factor and feature weights, designing the local density function, designing the clustering center update formula, defining the composite assignment distance function, designing the data point assignment rule and the objective function.

[0101] Example 3, refer to Figure 1 and Figure 3 , based on the above example, the module for establishing the patient status monitoring model specifically includes the following content:

[0102] Set the model label, and set the postoperative recovery data as the label data of the model;

[0103] Design the model architecture. The model is stacked by restricted Boltzmann machines, and each layer is connected through an adaptive weight adjustment mechanism. The hidden units are activated through multi-layer non-linear transformations, and finally optimized through the energy function;

[0104] The multi-layer non-linear transformation is expressed as follows:

[0105] ;

[0106] Among them, u represents the layer index of the model, p and q respectively represent the indices of the hidden unit and the visible unit, represents the activation value of the p-th hidden unit in the u-th layer of the model, represents the multi-layer non-linear transformation function, represents the weight between the p-th hidden unit and the q-th visible unit in the u-th layer of the model, represents the activation value of the q-th visible unit in the (u - 1)-th layer of the model, represents the bias of the p-th hidden unit in the u-th layer of the model, represents the input value of the multi-layer non-linear transformation function, represents the hyperbolic tangent function, and represent the transformation coefficients;

[0107] Design an energy function to quantify the interaction between visible units and hidden units, measure the stability of the model, and is expressed as follows:

[0108] ;

[0109] Among them, represents the activation value of the q-th visible unit, represents the activation value of the p-th hidden unit, represents the energy function value between the q-th visible unit and the p-th hidden unit, represents the weight between the p-th hidden unit and the q-th visible unit;

[0110] Design an adaptive weight adjustment mechanism, which is expressed as follows:

[0111] ;

[0112] Among them, t represents the index of the time point, represents the value of the weight between the p-th hidden unit and the q-th visible unit in the u-th layer of the model at time t, represents the value of the weight between the p-th hidden unit and the q-th visible unit in the u-th layer of the model at time t-1, represents the adjustment rate, represents the adjustment amount of the weight between the p-th hidden unit and the q-th visible unit in the u-th layer of the model at time t, and represent the balance coefficient, E represents the energy function, S represents the activation state of the hidden layer, represents the partial derivative of the energy function with respect to the weight taking the partial derivative, represents the partial derivative of the activation state of the hidden layer with respect to the weight taking the partial derivative.

[0113] By performing the above operations, for the problems of single model architecture, weak activation ability of hidden units, insufficient feature extraction ability, and low monitoring accuracy in the traditional patient status monitoring model, this solution enhances the activation ability of hidden units, enhances the model's feature extraction ability for data, and improves the adaptability of the model to the postoperative recovery status of patients and the accuracy of real-time monitoring by designing the model architecture, multi-layer non-linear transformation, designing the energy function, and designing the adaptive weight adjustment mechanism.

[0114] Example 4, refer to Figure 1 、 Figure 4 and Figure 5 , based on the above example, the monitoring optimization module specifically includes the following contents:

[0115] Initial setting: Set the parameters for the search, including the number of layers of the model and the number of hidden units in each layer. Set the accuracy of the model as the parameter performance value, set the maximum number of parameter searches and the qualified value of parameter performance.

[0116] Generate parameter search points: Generate initial parameter search points through randomization and adjustment coefficients, which are expressed as follows:

[0117] ;

[0118] Among them, represents the position of the generated initial parameter search point, PB represents the maximum value of the search range, LB represents the minimum value of the search range, represents a randomly selected position within the search range, represents a number with a value range between 0 and 1;

[0119] Design adaptive parameters: Dynamically adjust the search step size to balance global search and local search, which is expressed as follows:

[0120] ;

[0121] Among them, represents the number of parameter searches, and represent the adaptive parameters at the th parameter search, and represent the adaptive parameters at the th parameter search, represents the maximum number of parameter searches, represents the maximum parameter performance value among all the searched parameter positions, represents the minimum parameter performance value among all the searched parameter positions, represents the average parameter performance of all the searched parameter positions;

[0122] Co-evolutionary search, which is expressed as follows:

[0123] ;

[0124] Among them, represents the parameter position obtained by the th co-evolutionary search of the parameter search point, represents the parameter position obtained by the th co-evolutionary search of the parameter search point, represents the average value of the parameter positions obtained by the th co-evolutionary search of all parameter search points, represents the The optimal parameter position is obtained through the second co-evolution search;

[0125] Elite retention: After each co-evolution search, first update the position of the worst parameter to the optimal parameter position obtained from the previous parameter search, and then calculate the average position of the parameter points searched.

[0126] ;

[0127] Among them, represents the position of the worst parameter obtained through the th co-evolution search of the parameter search points, represents the average value of the parameter positions obtained through the th co-evolution search of all parameter search points. H represents the total number of parameter search points, represents the sum of the parameter positions obtained through the th co-evolution search of all parameter search points except the parameter search points where the worst parameter position is searched;

[0128] Set the search rules: First, generate the initial parameter search points, and use the parameter search points for co-evolution search. After each search ends, perform an elite retention operation. When the parameter performance value of the searched parameter points is greater than the parameter performance qualified value, the search ends, and the parameter with the largest parameter performance value among all the searched parameter positions is output. When the number of searches is greater than the maximum number of searches, start a new search; otherwise, increment the number of searches by one and perform the next search.

[0129] By performing the above operations, aiming at the problems of low search efficiency, poor stability, and low quality of search results in the traditional parameter search method in the monitoring and optimization module, this solution generates parameter search points, designs adaptive parameters, conducts co-evolution search, performs elite retention, and sets search rules. By combining randomness and goal orientation to generate initial parameter points, it improves the starting quality and convergence speed of parameter search, retains the optimal parameter positions in each search, improves the stability of parameter search and the quality of results, and enhances the flexibility and adaptability of parameter search.

[0130] Example 5, refer to Figure 1 , based on the above example, the comprehensive management module collects the user's age, gender, medical history, surgical information, and postoperative physiological data, inputs the data into the postoperative recovery guidance model, obtains the data belonging to the same cluster as the user data, and provides the user with complication prevention suggestions and complication nursing suggestions for the data in the same cluster; then inputs the user data into the patient status monitoring model, and the model outputs the user's postoperative recovery data. When the status of the postoperative recovery data is abnormal, a warning signal is issued.

[0131] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0132] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention.

[0133] The above description of the present invention and its embodiments is not restrictive. What is shown in the drawings is only one of the embodiments of the present invention, and the actual structure is not limited thereto. In general, if those of ordinary skill in the art are inspired by this and, without departing from the gist of the present invention, design similar structural modes and embodiments to this technical solution without creative efforts, they shall fall within the protection scope of the present invention.

Claims

1. A gastrointestinal patient postoperative recovery management system based on big data, characterized by: It includes data collection module, postoperative recovery guidance model establishment module, patient status monitoring model establishment module, monitoring optimization module and comprehensive management module; The data collection module collects the age, gender, medical history, surgical information, postoperative physiological data, complication data and postoperative recovery data of gastrointestinal patients undergoing surgery; The postoperative recovery guidance model establishment module establishes the postoperative recovery guidance model by defining feature distinguishing factors, defining feature weights, designing local density functions, designing cluster center update formulas, defining composite distribution distance functions, designing data point distribution rules, designing objective functions and clustering, and specifically includes the following contents: Define the feature distinguishing factor, expressed as follows: ； Among them, k represents the cluster index, j represents the feature dimension index of the data, represents the feature distinguishing factor of the jth feature of the kth cluster, represents the kth cluster center, represents the number of data points in the kth cluster, i represents the index of the data point used for model training, represents the i-th data point, Indicates that it belongs to the symbol, Indicates that the i-th data point belongs to the k-th cluster, represents the jth feature of the i-th data point, represents the mean of the jth feature in the kth cluster, represents all clusters except the kth cluster, represents the mean of the jth feature in all clusters except the kth cluster; Define feature weights as follows: ； in, represents the feature weight of the jth feature of the kth cluster, represents the feature dimension index of the data, and D represents the total number of feature dimensions of the data. represents the kth cluster The characteristic distinguishing factor of the feature, represents an exponential function with a natural constant as base; Design the local density function, expressed as follows: ； in, represents the local density function, represents the i-th data point, represents the local density value of the i-th data point, l represents the index of the data point, represents the lth data point, represents the set of five data points closest to data point i, represents the density adjustment coefficient, Indicates the modulus length; Design the cluster center update formula, which is expressed as follows: ； in, Represents the jth feature of the cluster center of the kth cluster after updating; Define the composite distribution distance function, expressed as follows: ； in, represents the composite partition distance function, represents the composite distribution distance between the i-th data point and the k-th cluster center, represents the allocation weight; Design data point allocation rules, calculate the composite allocation distance between the data point and each cluster center, select the cluster center with the smallest composite allocation distance to the data point, and allocate the data point to the cluster to which this cluster center belongs; The objective function is designed as follows: ； in, represents the objective function value, represents the number of cluster centers, and represents the coordination coefficient; Clustering, setting the objective function threshold, first randomly select from all model training data points Data points are used as the initial cluster centers, and then each data point is assigned to a cluster according to the data point assignment rule. The cluster center is then updated using the cluster center update formula, and the data point assignment and cluster center update are repeated. After each data point assignment, the objective function value is calculated. When the objective function value is less than the objective function threshold, the clustering converges. The patient status monitoring model establishment module establishes the patient status monitoring model by setting model labels, designing model architecture, multi-layer nonlinear transformation, designing energy functions and designing adaptive weight adjustment mechanisms; The monitoring optimization module performs monitoring optimization through initial setting, generating parameter search points, designing adaptive parameters, co-evolutionary search, elite retention and setting search rules; The comprehensive management module manages the user's postoperative recovery using a postoperative recovery guidance model and a patient status monitoring model.

2. The gastrointestinal patient postoperative recovery management system based on big data according to claim 1 is characterized by: The patient status monitoring model module is established, specifically including the following contents: Set the model label and set the postoperative recovery data as the label data of the model; Design the model architecture. The model is composed of a stack of restricted Boltzmann machines. Each layer is connected through an adaptive weight adjustment mechanism. The hidden units are activated through multiple layers of nonlinear transformations and finally optimized through energy functions. Multi-layer nonlinear transformation, expressed as follows: ； Among them, u represents the layer index of the model, p and q represent the indexes of hidden units and visible units respectively. represents the activation value of the pth hidden unit in the uth layer of the model, represents a multi-layer nonlinear transformation function, represents the weight between the p-th hidden unit and the q-th visible unit of the u-th layer of the model, represents the activation value of the qth visible unit in the u-1th layer of the model, represents the bias of the p-th hidden unit in the u-th layer of the model, Represents the input value of the multi-layer nonlinear transformation function, represents the hyperbolic tangent function, and represents the transformation coefficient; Design the energy function, which is expressed as follows: ； in, represents the activation value of the qth visible unit, represents the activation value of the pth hidden unit, represents the energy function value of the qth visible unit and the pth hidden unit, represents the weight between the pth hidden unit and the qth visible unit; Design an adaptive weight adjustment mechanism, which is expressed as follows: ； Among them, t represents the index of the time point, represents the value of the weight between the p-th hidden unit and the q-th visible unit of the u-th layer of the model at time t, represents the value of the weight between the p-th hidden unit and the q-th visible unit of the u-th layer of the model at time t-1, represents the regulation rate, represents the adjustment of the weight between the p-th hidden unit and the q-th visible unit of the u-th layer of the model at time t, and represents the balance coefficient, E represents the energy function, S represents the activation state of the hidden layer, Represents the energy function for weight Find the partial derivative, Represents the activation state of the hidden layer to the weight Find the partial derivative.

3. The gastrointestinal patient postoperative recovery management system based on big data according to claim 1 is characterized by: The monitoring optimization module specifically Includes the following: Initial settings: set the search parameters, including the number of layers of the model and the number of hidden units in each layer, set the accuracy of the model as the parameter performance value, set the maximum number of parameter searches and the parameter performance qualification value; Generate parameter search points, expressed as follows: ； in, Indicates the position of the generated initial parameter search point, PB indicates the maximum value of the search range, and LB indicates the minimum value of the search range. represents a randomly selected position within the search range. Represents a number ranging from 0 to 1; Design the adaptive parameters, expressed as follows: ； in, Indicates the number of parameter searches. and Indicated in Adaptive parameters during secondary parameter search, and Indicated in Adaptive parameters during secondary parameter search, Indicates the maximum number of parameter searches, represents the maximum parameter performance value among all searched parameter positions, represents the minimum parameter performance value among all searched parameter positions, represents the average parameter performance of all searched parameter positions; Coevolutionary search, expressed as follows: ； in, Indicates that the parameter search point is The parameter positions obtained by the co-evolutionary search are Indicates that the parameter search point is The parameter positions obtained by the co-evolutionary search are Indicates that all parameter search points are The average value of the parameter positions obtained by the coevolutionary search, Indicates that the parameter search point is The optimal parameter position is obtained by the second co-evolutionary search; Elite retention: After each co-evolutionary search, the worst parameter position is first updated to the optimal parameter position obtained in the previous parameter search, and then the average position of the searched parameter points is calculated; ； in, Indicates that the parameter search point is The worst parameter position is obtained by the co-evolutionary search. Indicates that all parameter search points are The average value of the parameter positions obtained by the coevolutionary search, H represents the total number of parameter search points, Indicates that all parameter search points except the parameter search point that searches for the worst parameter position are performed. The sum of the parameter positions obtained by the coevolutionary search; Set the search rules, first generate the initial parameter search points, use the parameter search points to perform co-evolutionary search, perform an elite retention operation after each search, and when the parameter performance value of the searched parameter point is greater than the parameter performance qualified value, the search ends and the parameter with the largest parameter performance value among all searched parameter positions is output; when the search times are greater than the maximum search times, search again; otherwise, the search times are increased by one and the next search is performed.

4. The gastrointestinal patient postoperative recovery management system based on big data according to claim 1 is characterized by: The data acquisition module collects the age, gender, medical history, surgical information, postoperative physiological data, complication data and postoperative recovery data of gastrointestinal patients who have undergone surgery; the medical history includes past medical history, allergy history and family medical history; the surgical information includes the type of surgery, surgery time, surgery duration and drugs used during the surgery; the postoperative physiological data includes heart rate, blood pressure, body temperature, respiratory rate and blood biochemical examination indicators; the complication data includes the type of complication that occurs after surgery, complication prevention suggestions and complication nursing suggestions; the postoperative recovery data includes three recovery states: good, normal and abnormal; The comprehensive management module collects the user's age, gender, medical history, surgical information, and postoperative physiological data, and inputs the data into a postoperative recovery guidance model to obtain data belonging to the same cluster as the user data, and provides the user with complication prevention suggestions and complication care suggestions for the data in the same cluster; the user data is then input into a patient status monitoring model, and the model outputs the user's postoperative recovery data. When the status of the postoperative recovery data is abnormal, an early warning signal is issued.

Images