Management system for shortening hospital examination waiting time of patient

Abstract

The invention discloses a management system for shortening hospital examination waiting time of a patient. The management system comprises a data acquisition module, a data preprocessing module, an examination time prediction module, a hyper-parameter optimization module and an examination time management module. The invention relates to the technical field of hospital process management information, in particular to a management system for shortening hospital examination waiting time of patients, and provides a multidirectional dynamic examination time reservation strategy which supports the patients to dynamically adjust reservation examination arrangement in real time by integrating real-time examination waiting time data of a plurality of hospitals, so that the hospital examination waiting time can be shortened. The inspection waiting time is shortened; a waiting time self-adaptive activation function and a checking waiting time length correlation degree adjustment mechanism are innovatively designed, and the problems of insufficient prediction result precision and dynamic updating capability are solved; the population, a nonlinear dynamic modulation strategy and a weight global regulation strategy are initialized by using interval disturbance chaotic mapping, the global search capability is enhanced, and an optimal parameter combination is obtained.

Description

Technical Field

[0001] The present invention relates to the field of hospital process management information technology, and in particular to a management system for shortening the waiting time for hospital examinations of patients. Background Art

[0002] With the increase in medical needs and the limited medical resources, the waiting time for patients to undergo examinations in hospitals has become a common problem that needs to be solved. In this context, an intelligent patient examination waiting time management system has emerged. Through artificial intelligence, real-time data monitoring and optimized scheduling, it helps hospitals improve the examination process, shorten the patient waiting time, and optimize the use of medical resources. However, the traditional examination time management system only provides queuing information for a single hospital or department, and cannot integrate real-time data from multiple hospitals, resulting in patients having difficulty in flexibly choosing the examination location and time, and having to wait for a long time for the examination. The existing activation function in the patient examination waiting time prediction model has limitations and lacks dynamic update capabilities, resulting in technical problems such as inaccurate prediction results and patients being unable to adjust their examination arrangements in a timely manner. The traditional prediction model has improper parameter settings and the parameter optimization algorithm has weak global search capabilities, resulting in inaccurate final prediction results. 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 a management system for shortening the waiting time for patients to undergo hospital examinations. The traditional examination time management system only provides the queuing information of a single hospital or department and cannot integrate the real-time data of multiple hospitals, which makes it difficult for patients to flexibly choose the examination location and time, and the examination requires a long waiting time. This solution innovatively proposes a multi-faceted dynamic examination time reservation strategy. By integrating the real-time examination waiting time data of multiple hospitals, the strategy gives patients the right to choose, so that they can flexibly choose hospitals and departments with shorter waiting times, and supports patients to adjust their appointment arrangements in a timely manner based on the latest prediction results, thereby significantly shortening the examination waiting time and solving the problem of patients having to wait for a long time for examinations. In view of the limitations of the activation function in the existing prediction model for patient examination waiting time and the lack of dynamic update capability, which leads to the prediction In order to solve the technical problems of inaccurate test results and patients being unable to adjust their examination arrangements in time, this solution innovatively designs a waiting time adaptive activation function and an examination waiting time correlation adjustment mechanism to improve the processing capability of complex time series data and the dynamic response capability of the model, thereby significantly improving the robustness and accuracy of the model, and effectively solving the problems of insufficient prediction result accuracy and dynamic update capability, so that patients can adjust their examination arrangements in time, thereby optimizing their medical experience; in order to solve the technical problems of inaccurate final prediction results caused by improper parameter settings and weak global search capabilities of parameter optimization algorithms in traditional prediction models, this solution uses interval perturbation chaotic mapping to initialize the population, nonlinear dynamic modulation strategy and weight global control strategy to enhance the global search capability and adaptive balance parameter capability, thereby obtaining the optimal parameter value and solving the problem of inaccurate output results of the final prediction model.

[0004] The technical solution adopted by the present invention is as follows: A management system for shortening the waiting time for hospital examinations of patients provided by the present invention comprises a data acquisition module, a data preprocessing module, an examination time prediction module, a hyperparameter optimization module and an examination time management module;

[0005] The data collection module collects patient information data, hospital information data, historical examination management data and real-time examination management data from the hospital's existing electronic medical record system and hospital information system to obtain original patient examination management data;

[0006] The data preprocessing module performs data cleaning, standardization, feature selection and data time series processing on the original patient examination management data to obtain preliminary patient examination management data;

[0007] The examination time prediction module establishes a patient examination waiting time prediction model to make a real-time prediction of the patient's examination waiting time, and obtains the prediction results of the patient's current examination waiting time in multiple nearby hospitals;

[0008] The hyperparameter optimization module obtains the optimal parameter combination of the patient examination waiting time prediction model through a search algorithm;

[0009] The examination time management module specifically updates the prediction results in real time based on the patient examination waiting time prediction model, and the patient can dynamically select the examination hospital and department with shorter examination waiting time in real time.

[0010] Furthermore, the data acquisition module specifically obtains original patient examination management data by collecting from the hospital's existing electronic medical record system and hospital information system; the original patient examination management data includes patient information data, hospital information data, historical examination management data and real-time examination management data; the patient information data includes name, age, patient medical history, diagnosis information, required examination items and severity of the disease; the hospital information data includes hospital name, hospital address, information on each examination department of the hospital and examination equipment information; the historical examination management data includes examination history records, historical examination waiting time and historical hospital patient flow; the real-time examination management data includes current examination equipment usage and current examination queue information.

[0011] Furthermore, the data preprocessing module specifically performs data cleaning, standardization, feature selection and data time series processing on the original patient examination management data to obtain preliminary patient examination management data; the data cleaning is to process missing values, abnormal values ​​and duplicate values; the standardization is to standardize the data based on the maximum and minimum normalization method; the feature selection is to use the correlation analysis method to calculate the correlation between each feature and the patient waiting time, and screen out the most valuable features for predicting the patient waiting time; the data time series processing includes analyzing the long-term trends and periodic changes of historical examination management data, as well as real-time examination management data monitoring of the current status and dynamic update of features to optimize the prediction of patient waiting time.

[0012] Furthermore, the examination time prediction module specifically establishes a patient examination waiting time prediction model to make a real-time prediction of the patient's examination waiting time, and obtains the prediction results of the current patient's examination waiting time in multiple nearby hospitals; it includes the following steps:

[0013] A prediction model for patient examination waiting time is established. Specifically, the prediction model is constructed by designing a waiting time adaptive activation function and checking the waiting time correlation adjustment mechanism, including the following steps:

[0014] Input data processing, the formula used is as follows:

[0015] ;

[0016] In the formula, Represents the output value after input data processing, Represents the weight matrix corresponding to the input data processing, Represents the bias parameter for input data processing, It indicates input data. represents the sigmoid function, Indicates the hidden state at the last moment;

[0017] Historical information forgotten adjustment, the formula used is as follows:

[0018] ;

[0019] In the formula, Represents the output after historical information forgetting adjustment, Represents the weight matrix corresponding to the forgetting adjustment of historical information, The bias parameter representing the adjustment of forgetting historical information;

[0020] Output characteristic calculation, the formula used is as follows:

[0021] ;

[0022] In the formula, represents the result of the output characteristic calculation, represents the weight matrix corresponding to the output feature calculation, Represents the bias term parameters for output characteristic calculation;

[0023] The status update candidate value calculation uses the following formula:

[0024] ;

[0025] In the formula, Indicates the new state update candidate value, represents the weight matrix corresponding to the calculation of the state update candidate value, Represents the bias parameter for calculating the candidate value of the state update, It is the hyperbolic tangent function;

[0026] The current status is obtained using the following formula:

[0027] ;

[0028] In the formula, c t Indicates the current state, c t-1 Indicates the state at the previous moment. Represents element-wise multiplication;

[0029] Get the current hidden state. The formula used is as follows:

[0030] ;

[0031] In the formula, h t Indicates the hidden state at the current moment;

[0032] Design the waiting time adaptive activation function, the formula used is as follows:

[0033] ;

[0034] In the formula, represents the waiting time adaptive activation function, x represents the input variable of the waiting time adaptive activation function, represents the center point of the activation function, Represents the scaling factor, which is used to adjust the scaling degree of the activation function output. represents the parameter that controls the shape of the curve, which is used to change the shape and properties of the activation function. p represents the dynamic adjustment parameter, which is used to control the nonlinear response of the activation function. represents the exponential function, represents the gamma function;

[0035] A mechanism for adjusting the relevance of the inspection waiting time is introduced, which includes the following steps:

[0036] The calculation of the inspection waiting time correlation weight is as follows:

[0037] ;

[0038] In the formula, Indicates the hidden state for all inputs at the current moment The importance rating of represents the similarity measurement function between two hidden states and the waiting time of patient examination, T represents the total number of time steps of the input sequence, represents the hidden state at other time steps j;

[0039] The hidden state based on the associated attention is integrated using the following formula:

[0040] ;

[0041] In the formula, represents the weighted sum value, Represents the relevance weight of time step t to the hidden state of other time steps j;

[0042] The final output result is obtained using the following formula:

[0043] ;

[0044] In the formula, represents the output value of the prediction model, represents the weight matrix corresponding to the output, Represents the bias parameter of the output layer;

[0045] Training a patient examination waiting time prediction model, specifically using the historical examination management data in the preliminary patient examination management data as input data to train the patient examination waiting time prediction model to obtain a trained patient examination waiting time prediction model;

[0046] The patient examination waiting time prediction is specifically to use the patient information data, hospital information data and real-time examination management data in the preliminary patient examination management data as input data of the trained patient examination waiting time prediction model to obtain the prediction results of the current patient's waiting time for examination in multiple nearby hospitals.

[0047] Furthermore, the hyperparameter optimization module specifically obtains the optimal parameter combination of the patient examination waiting time prediction model through a search algorithm; comprising the following steps:

[0048] Initialization parameters, specifically by constructing the initial parameters of the algorithm; the initial parameters of the algorithm include the population size N, the population dimension D and the maximum number of iterations ;

[0049] Initializing the population, specifically, initializing the population by generating chaotic sequence values ​​through interval perturbation chaotic mapping, including the following steps:

[0050] Generate N chaotic sequence values ​​and initialize the random value z0; the formula used is as follows:

[0051] ;

[0052] In the formula, represents the i-th chaotic sequence value of the d-th dimension, represents the i+1th chaotic sequence value in the dth dimension, Indicates the control parameters in the range of (0.3, 0.5), Represents the disturbance parameter, with a value range of (0,0.5);

[0053] The chaotic sequence value conversion search individual is expressed as follows:

[0054] ;

[0055] In the formula, represents the initialization position of the dth dimension of the i-th individual, lb d andub d Respectively represent the search lower and upper limits of dimension d;

[0056] Population division, specifically calculating the fitness value f of individuals in the population i ; The performance of the patient examination waiting time prediction model established based on the individual position is used as the individual fitness value; the searched individuals in the initial population are sorted from best to worst according to the fitness value, and the individual fa with the best fitness and its position X are defined a , the individual fb with the second best fitness and its position X b , the third best individual fc and its position X c , classify fa, fb and fc as hunting individuals;

[0057] Calculate the convergence factor. Specifically, the convergence factor is obtained through a nonlinear dynamic modulation strategy. The formula used is as follows:

[0058] ;

[0059] In the formula, represents the convergence factor, which is used to control the exploration and development capabilities of the search individual, t represents the number of iterations, represents the randomness parameter in the range [0,1];

[0060] To track prey, the formula used is as follows:

[0061] ;

[0062] ;

[0063] ;

[0064] In the formula, represents the position of the candidate search individual after moving to fa, represents the position of the candidate search individual after moving to fb, represents the position of the candidate search individual after moving to fc, represents the position of the candidate search individual in the dth dimension of the tth generation population, and represents the randomness parameter in the range [0,1];

[0065] Update the individual positions of the candidate search; specifically, update the individual positions through the weighted global control strategy, and the formula used is as follows:

[0066] ;

[0067] ;

[0068] In the formula, represents the position of the candidate search individual in the dth dimension of the t+1th generation population, represents a random number with mean 0 and variance 1, Indicates that it is used to control Weight coefficient, Indicates that it is used to control Weight coefficient, Indicates that it is used to control Weight coefficient;

[0069] During the hunting phase, the formula used is as follows:

[0070] ;

[0071] In the formula, Represents hunting parameters, if , it starts to attack the prey, otherwise the individual stays away from the prey;

[0072] Search determination, specifically, by constructing a search termination condition, searching and determining the optimal individual position, and obtaining the optimal individual position data setting;

[0073] The search termination conditions include threshold termination and iteration termination;

[0074] The threshold termination is specifically to set the fitness threshold, when the individual fitness value f i When it is above the fitness threshold, the hyperparameter search is completed;

[0075] The iteration termination specifically refers to terminating the iteration and obtaining the optimal individual position when the maximum number of iterations is reached;

[0076] The optimal individual position includes parameters of a patient examination waiting time prediction model.

[0077] Furthermore, the examination time management module specifically updates the prediction results in real time based on the patient examination waiting time prediction model, and the patient can dynamically select the examination hospital and department with shorter examination waiting time in real time; comprising the following steps:

[0078] Multi-dimensional examination time reservation, specifically based on the output results of the patient examination waiting time prediction model, patients can view the examination waiting time prediction of nearby hospital departments, including the estimated waiting time in the current and future periods, and guide patients to choose examination hospitals and departments with shorter examination waiting times;

[0079] Flexible adjustment of examination arrangements: Specifically, the system updates the patient examination waiting time prediction results in real time every time the data is updated, allowing patients to flexibly adjust the examination time and hospital according to the latest information, minimizing the waiting time outside the hospital and department.

[0080] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0081] (1) The traditional examination time management system only provides the queuing information of a single hospital or department and cannot integrate the real-time data of multiple hospitals, which makes it difficult for patients to flexibly choose the examination location and time, and the examination requires a long waiting time. This solution innovatively proposes a multi-faceted dynamic examination time appointment strategy. By integrating the real-time examination waiting time data of multiple hospitals, it gives patients the right to choose, so that they can flexibly choose hospitals and departments with shorter waiting times. Based on the latest prediction results, it supports patients to adjust their appointment arrangements in a timely manner, thereby significantly shortening the examination waiting time and solving the problem of patients having to wait for a long time for examination.

[0082] (2) In response to the limitations of the activation function in the existing patient examination waiting time prediction model and the lack of dynamic updating capability, which leads to technical problems such as inaccurate prediction results and patients’ inability to adjust their examination arrangements in a timely manner, this solution innovatively designs a waiting time adaptive activation function and an examination waiting time correlation adjustment mechanism to improve the processing capability of complex time series data and the dynamic response capability of the model, thereby significantly improving the robustness and accuracy of the model, effectively solving the problems of insufficient prediction result accuracy and dynamic updating capability, and enabling patients to adjust their examination arrangements in a timely manner, thereby optimizing their medical experience.

[0083] (3) In order to solve the technical problems of improper parameter settings in traditional prediction models and weak global search capabilities of parameter optimization algorithms, which lead to inaccurate final prediction results, this scheme uses interval perturbation chaotic mapping to initialize the population, nonlinear dynamic modulation strategy and weight global control strategy to enhance the global search capability and adaptive balance parameter capability, thereby obtaining the optimal parameter value and solving the problem of inaccurate output results of the final prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 A schematic diagram of a module of a management system for shortening the waiting time for hospital examinations of patients provided by the present invention;

[0085] Figure 2 It is a flowchart of the inspection time prediction module;

[0086] Figure 3 A schematic diagram of the process of establishing a patient examination waiting time prediction model in the examination time prediction module;

[0087] Figure 4 This is a flowchart of the hyperparameter optimization module;

[0088] Figure 5 A flowchart for checking the time management module;

[0089] 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

[0090] 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.

[0091] In the description of the present invention, it is necessary to understand 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 referred system or element must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0092] Example 1, see Figure 1 , a management system for shortening the waiting time for hospital examination of patients provided by the present invention comprises a data acquisition module, a data preprocessing module, an examination time prediction module, a hyperparameter optimization module and an examination time management module;

[0093] The data acquisition module collects patient information data, hospital information data, historical examination management data and real-time examination management data from the hospital's existing electronic medical record system and hospital information system to obtain original patient examination management data; and sends the data to the data preprocessing module;

[0094] The data preprocessing module receives the data sent by the data acquisition module; performs data cleaning, standardization, feature selection and data time series processing on the original patient examination management data to obtain preliminary patient examination management data; and sends the data to the examination time prediction module;

[0095] The examination time prediction module receives the data sent by the data preprocessing module, establishes a patient examination waiting time prediction model, makes a real-time prediction of the patient's examination waiting time, obtains the prediction results of the current patient's examination waiting time in multiple nearby hospitals; and sends the data to the examination time management module;

[0096] The hyperparameter optimization module obtains the optimal parameter combination of the patient examination waiting time prediction model through a search algorithm; and sends the data to the examination time prediction module;

[0097] The examination time management module receives data sent by the examination time prediction module, and based on the real-time updated prediction results of the patient examination waiting time prediction model, the patient can dynamically select an examination hospital and department with a shorter examination waiting time in real time.

[0098] Example 2, see Figure 1 This embodiment is based on the above embodiment, and the data acquisition module specifically obtains the original patient examination management data by collecting from the hospital's existing electronic medical record system and hospital information system; the original patient examination management data includes patient information data, hospital information data, historical examination management data and real-time examination management data; the patient information data includes name, age, patient medical history, diagnosis information, required examination items and severity of the disease; the hospital information data includes hospital name, hospital address, information on each examination department of the hospital and examination equipment information; the historical examination management data includes examination history records, historical examination waiting time and historical hospital patient flow; the real-time examination management data includes current examination equipment usage and current examination queue information.

[0099] Example 3, see Figure 1 This embodiment is based on the above embodiment, and the data preprocessing module specifically performs data cleaning, standardization, feature selection and data time series processing on the original patient examination management data to obtain preliminary patient examination management data; the data cleaning is to process missing values, abnormal values ​​and duplicate values; the standardization is to standardize the data based on the maximum and minimum normalization method; the feature selection is to use the correlation analysis method to calculate the correlation between each feature and the patient waiting time, and screen out the most valuable features for predicting the patient waiting time; the data time series processing includes analyzing the long-term trends and periodic changes of historical examination management data, as well as real-time examination management data monitoring the current status and dynamically updating features to optimize the prediction of patient waiting time.

[0100] Example 4, see Figure 1 , Figure 2 and Figure 3 This embodiment is based on the above embodiment. The examination time prediction module specifically establishes a patient examination waiting time prediction model to make a real-time prediction of the patient's examination waiting time, and obtains the prediction results of the current patient's examination waiting time in multiple nearby hospitals; it includes the following steps:

[0101] A prediction model for patient examination waiting time is established. Specifically, the prediction model is constructed by designing a waiting time adaptive activation function and checking the waiting time correlation adjustment mechanism, including the following steps:

[0102] Input data processing, the formula used is as follows:

[0103] ;

[0104] In the formula, Represents the output value after input data processing, Represents the weight matrix corresponding to the input data processing, Represents the bias parameter for input data processing, It indicates input data. represents the sigmoid function, Indicates the hidden state at the last moment;

[0105] Historical information forgotten adjustment, the formula used is as follows:

[0106] ;

[0107] In the formula, Represents the output after historical information forgetting adjustment, Represents the weight matrix corresponding to the forgetting adjustment of historical information, The bias parameter representing the adjustment of forgetting historical information;

[0108] Output characteristic calculation, the formula used is as follows:

[0109] ;

[0110] In the formula, represents the result of the output characteristic calculation, represents the weight matrix corresponding to the output feature calculation, Represents the bias term parameters for output characteristic calculation;

[0111] The status update candidate value calculation uses the following formula:

[0112] ;

[0113] In the formula, Indicates the new state update candidate value, represents the weight matrix corresponding to the calculation of the state update candidate value, Represents the bias parameter for calculating the candidate value of the state update, It is the hyperbolic tangent function;

[0114] The current status is obtained using the following formula:

[0115] ;

[0116] In the formula, c t Indicates the current state, c t-1 Indicates the state at the previous moment. represents element-wise multiplication;

[0117] Get the current hidden state. The formula used is as follows:

[0118] ;

[0119] In the formula, h t Indicates the hidden state at the current moment;

[0120] Design the waiting time adaptive activation function, the formula used is as follows:

[0121] ;

[0122] In the formula, represents the waiting time adaptive activation function, x represents the input variable of the waiting time adaptive activation function, represents the center point of the activation function, Represents the scaling factor, which is used to adjust the scaling degree of the activation function output. represents the parameter that controls the shape of the curve, which is used to change the shape and properties of the activation function. p represents the dynamic adjustment parameter, which is used to control the nonlinear response of the activation function. represents the exponential function, represents the gamma function;

[0123] A mechanism for adjusting the relevance of the inspection waiting time is introduced, which includes the following steps:

[0124] The calculation of the inspection waiting time correlation weight is as follows:

[0125] ;

[0126] In the formula, Indicates the hidden state for all inputs at the current moment The importance rating of represents the similarity measurement function between two hidden states and the waiting time of patient examination, T represents the total number of time steps of the input sequence, represents the hidden state at other time steps j;

[0127] The hidden state based on the associated attention is integrated using the following formula:

[0128] ;

[0129] In the formula, represents the weighted sum value, Represents the relevance weight of time step t to the hidden state of other time steps j;

[0130] The final output result is obtained using the following formula:

[0131] ;

[0132] In the formula, represents the output value of the prediction model, represents the weight matrix corresponding to the output, Represents the bias parameter of the output layer;

[0133] Training a patient examination waiting time prediction model, specifically using the historical examination management data in the preliminary patient examination management data as input data to train the patient examination waiting time prediction model to obtain a trained patient examination waiting time prediction model;

[0134] The patient examination waiting time prediction is specifically to use the patient information data, hospital information data and real-time examination management data in the preliminary patient examination management data as input data of the trained patient examination waiting time prediction model to obtain the prediction results of the current patient's waiting time for examination in multiple nearby hospitals.

[0135] By performing the above operations, in order to address the technical problems that the limitations of the activation function in the existing patient examination waiting time prediction model and the lack of dynamic updating capability lead to inaccurate prediction results and the inability of patients to adjust their examination arrangements in time, this solution innovatively designs a waiting time adaptive activation function and an examination waiting time correlation adjustment mechanism to improve the processing capability of complex time series data and the dynamic response capability of the model, thereby significantly improving the robustness and accuracy of the model, effectively solving the problems of insufficient prediction result accuracy and dynamic updating capability, enabling patients to adjust their examination arrangements in time, thereby optimizing their medical experience.

[0136] Example 5, see Figure 1 and Figure 4 This embodiment is based on the above embodiment, and the hyperparameter optimization module specifically obtains the optimal parameter combination of the patient examination waiting time prediction model through a search algorithm; it includes the following steps:

[0137] Initialization parameters, specifically by constructing the initial parameters of the algorithm; the initial parameters of the algorithm include the population size N, the population dimension D and the maximum number of iterations ;

[0138] Initializing the population, specifically, initializing the population by generating chaotic sequence values ​​through interval perturbation chaotic mapping, including the following steps:

[0139] Generate N chaotic sequence values ​​and initialize the random value z0; the formula used is as follows:

[0140] ;

[0141] In the formula, represents the i-th chaotic sequence value of the d-th dimension, represents the i+1th chaotic sequence value in the dth dimension, Indicates the control parameters in the range of (0.3, 0.5), Represents the disturbance parameter, with a value range of (0,0.5);

[0142] The chaotic sequence value conversion search individual is expressed as follows:

[0143] ;

[0144] In the formula, represents the initialization position of the dth dimension of the i-th individual, lb d andub d Respectively represent the search lower and upper limits of dimension d;

[0145] Population division, specifically calculating the fitness value f of individuals in the population i ; The performance of the patient examination waiting time prediction model established based on the individual position is used as the individual fitness value; the searched individuals in the initial population are sorted from best to worst according to the fitness value, and the individual fa with the best fitness and its position X are defined a , the individual fb with the second best fitness and its position X b , the third best individual fc and its position X c , classify fa, fb and fc as hunting individuals;

[0146] Calculate the convergence factor. Specifically, the convergence factor is obtained through a nonlinear dynamic modulation strategy. The formula used is as follows:

[0147] ;

[0148] In the formula, represents the convergence factor, which is used to control the exploration and development capabilities of the search individual, t represents the number of iterations, represents the randomness parameter in the range [0,1];

[0149] To track prey, the formula used is as follows:

[0150] ;

[0151] ;

[0152] ;

[0153] In the formula, represents the position of the candidate search individual after moving to fa, represents the position of the candidate search individual after moving to fb, represents the position of the candidate search individual after moving to fc, represents the position of the candidate search individual in the dth dimension of the tth generation population, and represents the randomness parameter in the range [0,1];

[0154] Update the individual positions of the candidate search; specifically, update the individual positions through the weighted global control strategy, and the formula used is as follows:

[0155] ;

[0156] ;

[0157] In the formula, represents the position of the candidate search individual in the dth dimension of the t+1th generation population, represents a random number with mean 0 and variance 1, Indicates that it is used to control Weight coefficient, Indicates that it is used to control Weight coefficient, Indicates that it is used to control Weight coefficient;

[0158] During the hunting phase, the formula used is as follows:

[0159] ;

[0160] In the formula, Represents hunting parameters, if , it starts to attack the prey, otherwise the individual stays away from the prey;

[0161] Search determination, specifically, by constructing a search termination condition, searching and determining the optimal individual position, and obtaining the optimal individual position data setting;

[0162] The search termination conditions include threshold termination and iteration termination;

[0163] The threshold termination is specifically to set the fitness threshold, when the individual fitness value f i When it is above the fitness threshold, the hyperparameter search is completed;

[0164] The iteration termination specifically refers to terminating the iteration and obtaining the optimal individual position when the maximum number of iterations is reached;

[0165] The optimal individual position includes parameters of a patient examination waiting time prediction model.

[0166] By performing the above operations, in order to solve the technical problems of improper parameter settings in traditional prediction models and weak global search capabilities of parameter optimization algorithms, which lead to inaccurate final prediction results, this solution uses interval perturbation chaotic mapping to initialize the population, nonlinear dynamic modulation strategy and weight global control strategy to enhance the global search capability and adaptive balance parameter capability, thereby obtaining the optimal parameter values ​​and solving the problem of inaccurate output results of the final prediction model.

[0167] Example 6, see Figure 1 and Figure 5 This embodiment is based on the examination time management module described in the above embodiment, specifically based on the real-time update prediction results of the patient examination waiting time prediction model, and the patient can dynamically select the examination hospital and department with a shorter examination waiting time in real time; including the following steps:

[0168] Multi-dimensional examination time reservation, specifically based on the output results of the patient examination waiting time prediction model, patients can view the examination waiting time prediction of nearby hospital departments, including the estimated waiting time in the current and future periods, and guide patients to choose examination hospitals and departments with shorter examination waiting times;

[0169] Flexible adjustment of examination arrangements: Specifically, the system updates the patient examination waiting time prediction results in real time every time the data is updated, allowing patients to flexibly adjust the examination time and hospital according to the latest information, minimizing the waiting time outside the hospital and department.

[0170] By performing the above operations, the traditional examination time management system only provides the queuing information of a single hospital or department, and cannot integrate the real-time data of multiple hospitals, which makes it difficult for patients to flexibly choose the examination location and time, and the examination requires a long waiting time. This solution innovatively proposes a multi-faceted dynamic examination time appointment strategy. By integrating the real-time examination waiting time data of multiple hospitals, it gives patients the right to choose, so that they can flexibly choose hospitals and departments with shorter waiting times, and based on the latest prediction results, it supports patients to adjust their appointment arrangements in time, thereby significantly shortening the examination waiting time and solving the problem of patients having to wait for a long time for examination.

[0171] 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.

[0172] 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.

[0173] 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. A management system for shortening the waiting time for patients to undergo hospital examinations, characterized in that: The system includes a data acquisition module, a data preprocessing module, an inspection time prediction module, a hyperparameter optimization module and an inspection time management module; The data collection module collects patient information data, hospital information data, historical examination management data and real-time examination management data from the hospital's existing electronic medical record system and hospital information system to obtain original patient examination management data; The data preprocessing module performs data cleaning, standardization, feature selection and data time series processing on the original patient examination management data to obtain preliminary patient examination management data; The examination time prediction module constructs a patient examination waiting time prediction model by designing a waiting time adaptive activation function and an examination waiting time correlation adjustment mechanism, and performs real-time prediction of the patient's examination waiting time to obtain the prediction results of the current patient's examination waiting time in multiple nearby hospitals; The hyperparameter optimization module improves the search algorithm by using interval perturbation chaotic mapping to initialize the population, nonlinear dynamic modulation strategy and weight global control strategy, so as to obtain the optimal parameter combination of the patient examination waiting time prediction model; The examination time management module specifically updates the prediction results in real time based on the patient examination waiting time prediction model, and the patient can dynamically select the examination hospital and department with shorter examination waiting time in real time.

2. A management system for shortening the waiting time for hospital examinations according to claim 1, characterized in that: The examination time prediction module specifically establishes a patient examination waiting time prediction model to make a real-time prediction of the patient's examination waiting time, and obtains the prediction results of the current patient's examination waiting time in multiple nearby hospitals; it includes the following steps: A prediction model for patient examination waiting time is established. Specifically, the prediction model is constructed by designing a waiting time adaptive activation function and checking the waiting time correlation adjustment mechanism, including the following steps: Input data processing, the formula used is as follows: ； In the formula, Represents the output value after input data processing, Represents the weight matrix corresponding to the input data processing, represents the bias parameter for input data processing, It indicates input data. represents the sigmoid function, Indicates the hidden state at the last moment; Historical information forgotten adjustment, the formula used is as follows: ； In the formula, Represents the output after historical information forgetting adjustment, Represents the weight matrix corresponding to the forgetting adjustment of historical information, The bias parameter representing the adjustment of forgetting historical information; Output characteristic calculation, the formula used is as follows: ； In the formula, represents the result of the output characteristic calculation, represents the weight matrix corresponding to the output feature calculation, Represents the bias term parameters for output characteristic calculation; The status update candidate value calculation uses the following formula: ； In the formula, Indicates the new state update candidate value, represents the weight matrix corresponding to the calculation of the state update candidate value, Represents the bias parameter for calculating the candidate value of the state update, It is the hyperbolic tangent function; The current status is obtained using the following formula: ； In the formula, c t Indicates the current state, c t-1 Indicates the state at the previous moment. represents element-wise multiplication; Get the current hidden state. The formula used is as follows: ； In the formula, h t Indicates the hidden state at the current moment; Design the waiting time adaptive activation function, the formula used is as follows: ； In the formula, represents the waiting time adaptive activation function, x represents the input variable of the waiting time adaptive activation function, represents the center point of the activation function, Represents the scaling factor, which is used to adjust the scaling degree of the activation function output. represents the parameter that controls the shape of the curve, which is used to change the shape and properties of the activation function. p represents the dynamic adjustment parameter, which is used to control the nonlinear response of the activation function. represents the exponential function, represents the gamma function; A mechanism for adjusting the relevance of the inspection waiting time is introduced, which includes the following steps: The calculation of the inspection waiting time correlation weight is as follows: ； In the formula, Indicates the hidden state for all inputs at the current moment The importance rating of represents the similarity measurement function between two hidden states and the waiting time of patient examination, T represents the total number of time steps of the input sequence, represents the hidden state at other time steps j; The hidden state based on the associated attention is integrated using the following formula: ； In the formula, represents the weighted sum value, Represents the relevance weight of time step t to the hidden state of other time steps j; The final output result is obtained using the following formula: ； In the formula, represents the output value of the prediction model, represents the weight matrix corresponding to the output, Represents the bias parameter of the output layer; Training a patient examination waiting time prediction model, specifically using the historical examination management data in the preliminary patient examination management data as input data to train the patient examination waiting time prediction model to obtain a trained patient examination waiting time prediction model; The patient examination waiting time prediction is specifically to use the patient information data, hospital information data and real-time examination management data in the preliminary patient examination management data as input data of the trained patient examination waiting time prediction model to obtain the prediction results of the current patient's waiting time for examination in multiple nearby hospitals.

3. A management system for shortening the waiting time for hospital examinations according to claim 1, characterized in that: The hyperparameter optimization module specifically obtains the optimal parameter combination of the patient examination waiting time prediction model through a search algorithm; The following steps are involved: Initialization parameters, specifically by constructing the initial parameters of the algorithm; the initial parameters of the algorithm include the population size N, the population dimension D and the maximum number of iterations ; Initializing the population, specifically, initializing the population by generating chaotic sequence values ​​through interval perturbation chaotic mapping, including the following steps: Generate N chaotic sequence values ​​and initialize the random value z0; the formula used is as follows: ； In the formula, represents the i-th chaotic sequence value of the d-th dimension, represents the i+1th chaotic sequence value in the dth dimension, Indicates the control parameters in the range of (0.3, 0.5), Represents the disturbance parameter, with a value range of (0,0.5); The chaotic sequence value conversion search individual is expressed as follows: ； In the formula, represents the initialization position of the dth dimension of the i-th individual, lb d andub d Respectively represent the search lower and upper limits of dimension d; Population division, specifically calculating the fitness value f of individuals in the population i ; The performance of the patient examination waiting time prediction model established based on the individual position is used as the individual fitness value; the searched individuals in the initial population are sorted from best to worst according to the fitness value, and the individual fa with the best fitness and its position X are defined a , the individual fb with the second best fitness and its position X b , the third best individual fc and its position X c , classify fa, fb and fc as hunting individuals; Calculate the convergence factor. Specifically, the convergence factor is obtained through a nonlinear dynamic modulation strategy. The formula used is as follows: ； In the formula, represents the convergence factor, which is used to control the exploration and development capabilities of the search individual, t represents the number of iterations, represents the randomness parameter in the range [0,1]; To track prey, the formula used is as follows: ； ； ； In the formula, represents the position of the candidate search individual after moving to fa, represents the position of the candidate search individual after moving to fb, represents the position of the candidate search individual after moving to fc, represents the position of the candidate search individual in the dth dimension of the tth generation population, and represents the randomness parameter in the range [0,1]; Update the individual positions of the candidate search; specifically, update the individual positions through the weighted global control strategy, and the formula used is as follows: ； ； In the formula, represents the position of the candidate search individual in the dth dimension of the t+1th generation population, represents a random number with mean 0 and variance 1, Indicates that it is used to control Weight coefficient, Indicates that it is used to control Weight coefficient, Indicates that it is used to control Weight coefficient; During the hunting phase, the formula used is as follows: ； In the formula, Represents hunting parameters, if , it starts to attack the prey, otherwise the individual stays away from the prey; Search determination, specifically, by constructing a search termination condition, searching and determining the optimal individual position, and obtaining the optimal individual position data setting; The search termination conditions include threshold termination and iteration termination; The threshold termination is specifically to set the fitness threshold, when the individual fitness value f i When it is above the fitness threshold, the hyperparameter search is completed; The iteration termination specifically refers to terminating the iteration and obtaining the optimal individual position when the maximum number of iterations is reached; The optimal individual position includes parameters of a patient examination waiting time prediction model.

4. A management system for shortening the waiting time for hospital examinations according to claim 1, characterized in that: The examination time management module specifically updates the prediction results in real time based on the patient examination waiting time prediction model, so that the patient can dynamically select the examination hospital and department with shorter examination waiting time in real time; it includes the following steps: Multi-dimensional examination time reservation, specifically based on the output results of the patient examination waiting time prediction model, patients can view the examination waiting time prediction of nearby hospital departments, including the estimated waiting time in the current and future periods, and guide patients to choose examination hospitals and departments with shorter examination waiting times; Flexible adjustment of examination arrangements: Specifically, the system updates the patient examination waiting time prediction results in real time every time the data is updated, allowing patients to flexibly adjust the examination time and hospital according to the latest information, minimizing the waiting time outside the hospital and department.

5. A management system for shortening the waiting time for hospital examinations according to claim 1, characterized in that: The data acquisition module specifically acquires original patient examination management data from the hospital's existing electronic medical record system and hospital information system by collecting data; the original patient examination management data includes patient information data, hospital information data, historical examination management data and real-time examination management data; the patient information data includes name, age, patient medical history, diagnosis information, required examination items and severity of the disease; the hospital information data includes hospital name, hospital address, information on each examination department of the hospital and examination equipment information; the historical examination management data includes examination history records, historical examination waiting time and historical hospital patient flow; the real-time examination management data includes current examination equipment usage and current examination queue information.

6. A management system for shortening the waiting time for hospital examinations according to claim 1, characterized in that: The data preprocessing module specifically performs data cleaning, standardization, feature selection and data time series processing on the original patient examination management data to obtain preliminary patient examination management data; the data cleaning is to process missing values, abnormal values ​​and duplicate values; the standardization is to standardize the data based on the maximum and minimum normalization method; the feature selection is to use the correlation analysis method to calculate the correlation between each feature and the patient waiting time, and screen out the most valuable features for predicting the patient waiting time; the data time series processing includes analyzing the long-term trends and periodic changes of historical examination management data, as well as real-time examination management data monitoring of the current status and dynamic update features, to obtain key features for real-time prediction of patient waiting time.

Images