Psychological assessment and nursing system for elderly patients

Abstract

The invention discloses a psychological assessment and nursing system for elderly patients, which belongs to the technical field of psychological assessment and nursing and comprises a data acquisition module, a data processing module, a model construction module, a test optimization module, an assessment prediction module and a nursing management and control module. The problems that the mental health condition of the elderly patient cannot be effectively assessed in the prior art, the elderly patient cannot be subjected to personalized nursing in time according to the mental assessment result, the mental health problem of the elderly patient cannot be effectively solved, and the life quality of the elderly patient is reduced are solved. According to the invention, based on the psychological health assessment prediction result, personalized nursing management and control are carried out on the elderly patient, the psychological health condition of the elderly patient can be effectively assessed, and personalized nursing can be carried out on the elderly patient in time according to the psychological assessment result, so that the psychological health problem of the elderly patient can be effectively solved; the living quality of the elderly patients can be improved.

Description

Technical Field

[0001] The invention relates to the technical field of psychological assessment and nursing, and in particular to a psychological assessment and nursing system for elderly patients. Background Art

[0002] Psychological assessment is a general term for comprehensive, systematic and in-depth analysis of individual or group psychological phenomena using interviews, observations and tests under the joint guidance of biological, psychological, social and medical models. With the changes in the domestic age structure and the increasing number of elderly people, the mental health of elderly patients has attracted much attention.

[0003] The Chinese patent with publication number CN209281899U discloses an elderly care assessment system, including a cloud database and a smart bracelet for detecting the movement frequency and work and rest pattern of the elderly. The smart bracelet includes a shell, a wristband and a circuit board arranged in the shell. The wristband and the shell are connected to form a ring. The circuit board is provided with a processor, a sensor module and a wireless communication module. The processor is connected to the sensor module and the wireless communication module respectively. The movement frequency and work and rest pattern information of the elderly are collected by the smart bracelet and sent to the cloud database. Relevant personnel can view and understand the health assessment data of the elderly by logging into the cloud database, and timely understand the health status of the elderly, thereby improving the quality of elderly care and can be widely used in the field of elderly care. However, the patent has the following defects:

[0004] The existing system cannot effectively evaluate the mental health of elderly patients, and cannot provide timely personalized care for elderly patients based on the results of psychological assessment, so that the mental health problems of elderly patients cannot be effectively solved, which reduces the quality of life of elderly patients. Summary of the invention

[0005] The purpose of the present invention is to provide a psychological assessment and care system for elderly patients, which can effectively assess the mental health of elderly patients and provide timely personalized care for elderly patients based on the results of the psychological assessment, so that the mental health problems of elderly patients can be effectively solved, the quality of life of elderly patients can be improved, and the problems raised in the above-mentioned background technology can be solved.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A psychological assessment and care system for elderly patients, comprising:

[0008] The data collection module is used to collect mental health questionnaire information, interview information and record information of elderly patients, and determine the real-time mental health data based on elderly patients;

[0009] A data processing module is used to process the real-time data of mental health of elderly patients and determine the characteristic data of mental health of elderly patients;

[0010] A model building module is used to build a psychological assessment model based on elderly patients according to their psychological assessment and nursing needs;

[0011] A test optimization module is used to test and optimize the psychological assessment model based on elderly patients and determine the best psychological assessment model after optimization and adjustment;

[0012] An evaluation and prediction module is used to evaluate and predict the mental health of elderly patients and determine the prediction results based on the mental health evaluation of elderly patients;

[0013] The nursing management and control module is used to formulate personalized nursing management and control plans based on elderly patients and to carry out personalized nursing management and control for elderly patients.

[0014] Preferably, the data acquisition module includes:

[0015] A questionnaire survey unit is used to conduct a questionnaire survey on the mental health of elderly patients and determine the mental health questionnaire information of elderly patients;

[0016] The communication and interview unit is used to conduct communication and interviews on the mental health of elderly patients and determine the mental health interview information of elderly patients;

[0017] An observation and recording unit is used to observe and record the mental health conditions of elderly patients and determine the mental health record information of elderly patients;

[0018] Among them, based on the mental health questionnaire information, interview information and record information of elderly patients, real-time data on the mental health of elderly patients are determined.

[0019] Preferably, the data processing module includes:

[0020] A data retrieval unit, used for retrieving real-time data on mental health of elderly patients;

[0021] Obtain real-time data on mental health of elderly patients;

[0022] Based on the sequential retrieval method, the real-time data of mental health of elderly patients are retrieved;

[0023] Check the consistency of real-time data on mental health based on older patients;

[0024] Check whether the real-time mental health data meets the requirements based on the reasonable value range and mutual relationship of each variable in the real-time mental health data;

[0025] Remove inconsistent data in real-time mental health data that is beyond the normal range, logically unreasonable, or contradictory;

[0026] Process invalid and missing values ​​based on real-time data of mental health of elderly patients;

[0027] Remove invalid and missing data from real-time mental health data that are of no value to psychological assessment and care;

[0028] Identify real-time mental health data that is valuable for psychological assessment and care;

[0029] A data sorting unit, used for sorting the retrieved real-time mental health data;

[0030] Obtain real-time mental health data that is valuable for psychological assessment and care after retrieval;

[0031] Based on the internal ranking method, the real-time mental health data that is valuable for psychological assessment and care after retrieval is ranked;

[0032] Identify and prioritize real-time mental health data;

[0033] A feature extraction unit, used for extracting features from the sorted real-time mental health data;

[0034] Obtaining real-time mental health data that is sorted and ranked;

[0035] Extract features from real-time mental health data with ranking order;

[0036] Determine the data based on the mental health characteristics of elderly patients.

[0037] Preferably, the model building module includes:

[0038] a data collection unit to collect mental health history data from older patients;

[0039] According to the psychological assessment and nursing needs of elderly patients, a large amount of mental health history data of elderly patients is collected;

[0040] A data partitioning unit, used for partitioning the mental health history data of elderly patients;

[0041] Obtain mental health history data from older patients;

[0042] Compartmentalize mental health history data of older patients;

[0043] Determine the training set and test set;

[0044] Model building module, used to build psychological assessment models;

[0045] According to the psychological assessment and nursing needs of elderly patients, select a model framework suitable for psychological assessment of elderly patients;

[0046] Based on the training set, the selected model architecture suitable for psychological assessment of elderly patients is trained;

[0047] Construct a psychological assessment model based on elderly patients.

[0048] Preferably, the data partitioning unit further includes:

[0049] A ratio extraction module is used to extract the division ratio of the training set and the test set from the database;

[0050] A partitioning execution module, used to partition the mental health history data according to the partitioning ratio to obtain a training set and a test set;

[0051] A sample quantity retrieval module is used to extract a model architecture suitable for psychological assessment of elderly patients, and retrieve a minimum number of training samples corresponding to the model architecture suitable for psychological assessment of elderly patients;

[0052] A comparison module, used for comparing the minimum number of training samples with the sample data of the training set;

[0053] A reference sample data acquisition module, used for obtaining the data volume difference between the minimum training sample volume and the sample data of the training set when the minimum training sample volume is greater than the sample data of the training set, and randomly selecting sample data corresponding to the data volume difference from the test set as the reference sample data;

[0054] The compensation data coefficient acquisition module is used to obtain the compensation data coefficients corresponding to the various data values ​​of the benchmark sample data by combining the various data values ​​contained in the benchmark sample data with the various data values ​​contained in the sample data in the training data; wherein the compensation data coefficients are obtained by the following formula:

[0055]

[0056] Where x represents the compensation data coefficient corresponding to each data value; n represents the number of sample data in the training data; X i represents the specific value corresponding to each data item contained in the i-th sample data in the training data; X i-1 represents the specific value corresponding to each data item contained in the i-1th sample data in the training data; X p Indicates the average data value corresponding to each data item of the training data; X z Represents the median value of each item of training data;

[0057] The reference sample data adjustment module is used to adjust the data values ​​of each of the reference sample data using the compensation data coefficient to obtain the adjusted reference sample data, wherein the adjusted reference sample data is obtained by the following formula:

[0058]

[0059] Among them, X t represents the adjusted benchmark sample data; X represents the data value corresponding to each data value; x represents the compensation data coefficient corresponding to each data value; X z Represents the median value of each item of training data;

[0060] A data supplementation module, used to use the adjusted benchmark sample data as supplementary data for the sample data of the training set;

[0061] The test data supplementation module is used to obtain the sample data supplementation amount corresponding to the test set according to the number of sample data of the supplementary data and the division ratio of the training set and the test set.

[0062] Preferably, the test data supplement module includes:

[0063] A data quantity acquisition module, used to acquire the data quantity of the sample data corresponding to the test set according to the number of sample data of the supplementary data and the division ratio of the training set and the test set;

[0064] A data value extraction module, used to extract data values ​​of various items of data corresponding to the training data;

[0065] A supplementary sample acquisition module, used to randomly retrieve sample data having the same number of data as the sample data corresponding to the test set from the training data as supplementary samples of the test set;

[0066] The test set compensation adjustment coefficient acquisition module is used to obtain the compensation adjustment coefficient of each data value in the supplementary sample corresponding to the test set by using the data value of each data corresponding to the training data; wherein the compensation adjustment coefficient is obtained by the following formula:

[0067]

[0068] Among them, y represents the compensation adjustment coefficient; m represents the number of sample data after the current training set completes data supplement; X j represents the data value corresponding to each item in the j-th sample data after sample supplementation; X hp represents the average data value corresponding to each item of the training data after sample supplementation; X hzrepresents the median value of each item of training data after sample supplementation; h represents the compensation coefficient, and the compensation coefficient is obtained by the following formula:

[0069]

[0070] Among them, m represents the number of sample data after the current training set completes data supplementation; X j represents the data value corresponding to each item in the j-th sample data after sample supplementation; X j-1 represents the data value corresponding to each item in the j-1th sample data after sample supplementation; n represents the number of sample data in the training data; X i represents the specific value corresponding to each data item contained in the i-th sample data in the training data; X i-1 Indicates the specific value corresponding to each data item contained in the i-1th sample data in the training data;

[0071] The test set adjustment module is used to adjust the values ​​of each data item in the supplementary sample corresponding to the test set by using the compensation adjustment coefficient of each data item, wherein the value of each data item of the supplementary sample after adjustment is obtained by the following formula:

[0072]

[0073] Among them, Y t Indicates the value of each data of the adjusted supplementary sample; X h Indicates the value of each data of the supplementary sample before adjustment; X hz Represents the median value of each item of training data after sample supplementation.

[0074] Preferably, the test optimization module includes:

[0075] Performance testing unit for performance testing of psychological assessment models based on geriatric patients;

[0076] Obtain a psychological assessment model based on older patients;

[0077] Based on the test set, the performance of the psychological assessment model based on elderly patients was tested;

[0078] Determine performance test results based on psychological assessment models;

[0079] An optimization and adjustment unit, used for optimizing and adjusting the psychological assessment model based on elderly patients;

[0080] Obtain performance test results based on psychological assessment models;

[0081] Conduct in-depth exploration and relevant analysis of performance test results based on psychological assessment models;

[0082] Determine the optimal adjustment plan based on the psychological assessment model;

[0083] Optimize and adjust the psychological assessment model based on the optimization adjustment plan;

[0084] Determine the best psychological assessment model after optimization and adjustment.

[0085] Preferably, the evaluation and prediction module includes:

[0086] A data extraction unit, used for extracting psychological health characteristic data based on elderly patients;

[0087] According to the psychological assessment and nursing needs of elderly patients, the psychological health characteristic data of elderly patients are extracted;

[0088] An assessment and prediction unit, used to assess and predict the mental health of elderly patients;

[0089] Obtain the best psychological assessment model after optimization and adjustment;

[0090] Evaluate and predict the mental health characteristic data of elderly patients based on the best psychological assessment model after optimization and adjustment;

[0091] Identify outcomes based on mental health assessments in older patients;

[0092] Among them, the predicted results based on the mental health assessment of elderly patients include: normal mental health assessment of elderly patients and abnormal mental health assessment of elderly patients.

[0093] Preferably, the nursing management and control module includes:

[0094] Strategy development unit, used to develop personalized nursing management and control plans for elderly patients;

[0095] Obtain predictions based on mental health assessments of elderly patients;

[0096] Conduct in-depth exploration and relevant analysis on the prediction results of mental health assessment based on elderly patients;

[0097] Determine personalized nursing management plans for elderly patients;

[0098] Nursing control unit, used to provide personalized nursing control for elderly patients;

[0099] Obtain personalized nursing management plans for elderly patients;

[0100] Provide personalized nursing management and control for elderly patients based on personalized nursing management and control plans.

[0101] Preferably, personalized nursing management is provided for elderly patients, including:

[0102] Taking into account the personal characteristics, family environment and social relations of elderly patients, we develop personalized nursing and management plans for the mental health of elderly patients, monitor and track the mental health and needs of elderly patients in real time, and regularly update the personalized nursing and management plans based on the monitoring and tracking results to ensure their timeliness and effectiveness.

[0103] Compared with the prior art, the present invention has the following beneficial effects:

[0104] The present invention determines real-time data on mental health of elderly patients by collecting mental health questionnaire information, interview information and record information of elderly patients, processes the real-time data on mental health, determines mental health characteristic data, constructs a psychological assessment model based on elderly patients according to their psychological assessment and nursing needs, tests and optimizes the psychological assessment model, determines the best psychological assessment model after optimization and adjustment, evaluates and predicts the mental health of elderly patients based on the best psychological assessment model, determines the prediction results of the mental health assessment, formulates personalized nursing management and control plans based on elderly patients based on the prediction results of the mental health assessment, performs personalized nursing management and control on elderly patients, can effectively evaluate the mental health of elderly patients, and can perform timely personalized nursing for elderly patients according to the results of the psychological assessment, so that the mental health problems of elderly patients can be effectively solved, and the quality of life of elderly patients can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0105] Figure 1 It is a framework diagram of the psychological assessment and nursing system for elderly patients of the present invention. DETAILED DESCRIPTION

[0106] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0107] In order to solve the existing problem that the mental health of elderly patients cannot be effectively evaluated and timely personalized care cannot be provided to elderly patients based on the results of psychological evaluation, so that the mental health problems of elderly patients cannot be effectively solved and the quality of life of elderly patients is reduced, please refer to Figure 1 , this embodiment provides the following technical solutions:

[0108] A psychological assessment and nursing system for elderly patients comprises: a data acquisition module, a data processing module, a model building module, a test optimization module, an assessment prediction module and a nursing management and control module.

[0109] It should be noted that through the interactive communication between the data acquisition module, the data processing module, the model building module, the test optimization module, the evaluation and prediction module and the nursing management and control module, the mental health of elderly patients can be effectively evaluated, and timely personalized care can be provided to elderly patients based on the results of the psychological evaluation, so that the mental health problems of elderly patients can be effectively solved and the quality of life of elderly patients can be improved.

[0110] Among them, the data collection module is used to collect mental health questionnaire information, interview information and record information of elderly patients, and determine the real-time mental health data based on elderly patients;

[0111] In this embodiment, the data acquisition module includes:

[0112] A questionnaire survey unit is used to conduct a questionnaire survey on the mental health of elderly patients and determine the mental health questionnaire information of elderly patients;

[0113] The communication and interview unit is used to conduct communication and interviews on the mental health of elderly patients and determine the mental health interview information of elderly patients;

[0114] An observation and recording unit is used to observe and record the mental health conditions of elderly patients and determine the mental health record information of elderly patients;

[0115] Among them, based on the mental health questionnaire information, interview information and record information of elderly patients, real-time data on the mental health of elderly patients are determined.

[0116] The data processing module is used to process the real-time data of mental health of elderly patients and determine the characteristic data of mental health of elderly patients;

[0117] In this embodiment, the data processing module includes:

[0118] A data retrieval unit, used for retrieving real-time data on mental health of elderly patients;

[0119] Obtain real-time data on mental health of elderly patients;

[0120] Based on the sequential retrieval method, the real-time data of mental health of elderly patients are retrieved;

[0121] Check the consistency of real-time data on mental health based on older patients;

[0122] Check whether the real-time mental health data meets the requirements based on the reasonable value range and mutual relationship of each variable in the real-time mental health data;

[0123] Remove inconsistent data in real-time mental health data that is beyond the normal range, logically unreasonable, or contradictory;

[0124] Process invalid and missing values ​​based on real-time data of mental health of elderly patients;

[0125] Remove invalid and missing data from real-time mental health data that are of no value to psychological assessment and care;

[0126] Identify real-time mental health data that is valuable for psychological assessment and care;

[0127] A data sorting unit, used for sorting the retrieved real-time mental health data;

[0128] Obtain real-time mental health data that is valuable for psychological assessment and care after retrieval;

[0129] Based on the internal ranking method, the real-time mental health data that is valuable for psychological assessment and care after retrieval is ranked;

[0130] Identify and prioritize real-time mental health data;

[0131] A feature extraction unit, used for extracting features from the sorted real-time mental health data;

[0132] Obtaining real-time mental health data that is sorted and ranked;

[0133] Extract features from real-time mental health data with ranking order;

[0134] Determine the data based on the mental health characteristics of elderly patients.

[0135] Among them, the model building module is used to build a psychological assessment model based on elderly patients according to their psychological assessment and nursing needs;

[0136] In this embodiment, the model building module includes:

[0137] a data collection unit to collect mental health history data from older patients;

[0138] According to the psychological assessment and nursing needs of elderly patients, a large amount of mental health history data of elderly patients is collected;

[0139] A data partitioning unit, used for partitioning the mental health history data of elderly patients;

[0140] Obtain mental health history data from older patients;

[0141] Compartmentalize mental health history data of older patients;

[0142] Determine the training set and test set;

[0143] Model building module, used to build psychological assessment models;

[0144] According to the psychological assessment and nursing needs of elderly patients, select a model framework suitable for psychological assessment of elderly patients;

[0145] Based on the training set, the selected model architecture suitable for psychological assessment of elderly patients is trained;

[0146] Construct a psychological assessment model based on elderly patients.

[0147] Among them, the test optimization module is used to test and optimize the psychological assessment model based on elderly patients and determine the best psychological assessment model after optimization and adjustment;

[0148] Specifically, the data partitioning unit further includes:

[0149] A ratio extraction module is used to extract the division ratio of the training set and the test set from the database;

[0150] A partitioning execution module, used to partition the mental health history data according to the partitioning ratio to obtain a training set and a test set;

[0151] A sample quantity retrieval module is used to extract a model architecture suitable for psychological assessment of elderly patients, and retrieve a minimum number of training samples corresponding to the model architecture suitable for psychological assessment of elderly patients;

[0152] A comparison module, used for comparing the minimum number of training samples with the sample data of the training set;

[0153] A reference sample data acquisition module, used for obtaining the data volume difference between the minimum training sample volume and the sample data of the training set when the minimum training sample volume is greater than the sample data of the training set, and randomly selecting sample data corresponding to the data volume difference from the test set as the reference sample data;

[0154] The compensation data coefficient acquisition module is used to obtain the compensation data coefficients corresponding to the various data values ​​of the benchmark sample data by combining the various data values ​​contained in the benchmark sample data with the various data values ​​contained in the sample data in the training data; wherein the compensation data coefficients are obtained by the following formula:

[0155]

[0156] Where x represents the compensation data coefficient corresponding to each data value; n represents the number of sample data in the training data; X i represents the specific value corresponding to each data item contained in the i-th sample data in the training data; X i-1 represents the specific value corresponding to each data item contained in the i-1th sample data in the training data; X p Indicates the average data value corresponding to each data item of the training data; X z Represents the median value of each item of training data;

[0157] The reference sample data adjustment module is used to adjust the data values ​​of each of the reference sample data using the compensation data coefficient to obtain the adjusted reference sample data, wherein the adjusted reference sample data is obtained by the following formula:

[0158]

[0159] Among them, X t represents the adjusted benchmark sample data; X represents the data value corresponding to each data value; x represents the compensation data coefficient corresponding to each data value; X z Represents the median value of each item of training data;

[0160] A data supplementation module, used to use the adjusted benchmark sample data as supplementary data for the sample data of the training set;

[0161] The test data supplementation module is used to obtain the sample data supplementation amount corresponding to the test set according to the number of sample data of the supplementary data and the division ratio of the training set and the test set.

[0162] The technical effect of the above technical solution is: through the proportion extraction module and the division execution module, the training set and the test set are extracted from the database and divided strictly according to the preset ratio, which helps to ensure that the data distribution in the model training process is consistent with the data distribution in the actual application scenario, thereby improving the generalization ability of the model. The sample quantity retrieval module and the comparison module ensure that the sample quantity of the training set meets the minimum requirements of the model architecture suitable for psychological assessment of elderly patients. This is very important because insufficient training samples may cause the model to overfit or underfit, affecting the accuracy and reliability of the model.

[0163] When the number of samples in the training set is insufficient, the benchmark sample data acquisition module, the compensation data coefficient acquisition module, the benchmark sample data adjustment module and the data supplementation module intelligently randomly select sample data from the test set and adjust it to meet the characteristics of the training data, so as to add it to the training set as supplementary data. This method can effectively increase the diversity and quantity of training samples without increasing the cost of additional data collection, which helps to improve the training effect of the model. The test data supplementation module reduces the number of samples from the test set accordingly according to the number of samples added to the training set and the original division ratio to maintain the validity and independence of the test set. This ensures that the test set can truly reflect the performance of the model on unknown data, which helps to more accurately evaluate the performance of the model.

[0164] The entire process reduces human intervention and errors through automated and intelligent data processing, and improves the efficiency and accuracy of data processing. At the same time, by ensuring the scientific division of training and test sets and the adequacy and diversity of training data, a better data foundation is provided for model training, which helps to improve the training efficiency and accuracy of the model.

[0165] In summary, this technical solution effectively solves the problems of insufficient data and unreasonable division that may be encountered in the training process of the psychological assessment model for elderly patients through a series of modular data processing processes, and improves the training effect and performance of the model.

[0166] Specifically, the test data supplement module includes:

[0167] A data quantity acquisition module, used to acquire the data quantity of the sample data corresponding to the test set according to the number of sample data of the supplementary data and the division ratio of the training set and the test set;

[0168] A data value extraction module, used to extract data values ​​of various items of data corresponding to the training data;

[0169] A supplementary sample acquisition module, used to randomly retrieve sample data having the same number of data as the sample data corresponding to the test set from the training data as supplementary samples of the test set;

[0170] The test set compensation adjustment coefficient acquisition module is used to obtain the compensation adjustment coefficient of each data value in the supplementary sample corresponding to the test set by using the data value of each data corresponding to the training data; wherein the compensation adjustment coefficient is obtained by the following formula:

[0171]

[0172] Among them, y represents the compensation adjustment coefficient; m represents the number of sample data after the current training set completes data supplement; X jrepresents the data value corresponding to each item in the j-th sample data after sample supplementation; X hp represents the average data value corresponding to each item of the training data after sample supplementation; X hz represents the median value of each item of training data after sample supplementation; h represents the compensation coefficient, and the compensation coefficient is obtained by the following formula:

[0173]

[0174] Among them, m represents the number of sample data after the current training set completes data supplementation; X j represents the data value corresponding to each item in the j-th sample data after sample supplementation; X j-1 represents the data value corresponding to each item in the j-1th sample data after sample supplementation; n represents the number of sample data in the training data; X i represents the specific value corresponding to each data item contained in the i-th sample data in the training data; X i-1 Indicates the specific value corresponding to each data item contained in the i-1th sample data in the training data;

[0175] The test set adjustment module is used to adjust the values ​​of each data item in the supplementary sample corresponding to the test set by using the compensation adjustment coefficient of each data item, wherein the value of each data item of the supplementary sample after adjustment is obtained by the following formula:

[0176]

[0177] Among them, Y t Indicates the value of each data of the adjusted supplementary sample; X h Indicates the value of each data of the supplementary sample before adjustment; X hz Represents the median value of each item of training data after sample supplementation.

[0178] The technical effect of the above technical solution is: through the data quantity acquisition module, according to the original division ratio of the training set and the test set, and the number of samples added to the training set, the number of samples that should be reduced in the test set is accurately calculated, thereby ensuring that the data division still maintains the original proportion balance after adding the training set samples. The data value extraction module and the supplementary sample acquisition module randomly retrieve sample data from the training set that is the same as the number of samples reduced in the test set as supplementary samples for the test set. This random sampling method helps to maintain the diversity and representativeness of the test set samples, so that it better reflects the characteristics of the overall data set.

[0179] The test set compensation adjustment coefficient acquisition module uses the data value characteristics of the training data (such as the average data value, the median data value, and the compensation coefficient) to calculate the compensation adjustment coefficients of each data value in the supplementary sample of the test set. The application of these compensation adjustment coefficients is intended to make the data distribution of the supplementary samples of the test set closer to the overall distribution of the training set, thereby improving the validity and reliability of the test set. Through the test set adjustment module, the compensation adjustment coefficient is used to adjust the data values ​​in the supplementary samples of the test set, so that the adjusted supplementary samples are more consistent with the data characteristics of the training set. Doing so helps to improve the evaluation accuracy of the model on the test set, because the data difference between the test set and the training set is minimized, thereby reducing the evaluation bias. The entire process is implemented in a modular way, reducing the possibility of manual intervention and errors. Automated and intelligent data processing improves the efficiency and accuracy of data processing, and provides a more reliable data foundation for model training and evaluation.

[0180] In summary, this technical solution effectively solves the problem of how to maintain the effectiveness and representativeness of the test set when increasing the number of training set samples through a series of modular data processing processes, thereby improving the overall effect of model evaluation and training.

[0181] In this embodiment, the test optimization module includes:

[0182] Performance testing unit for performance testing of psychological assessment models based on geriatric patients;

[0183] Obtain a psychological assessment model based on older patients;

[0184] Based on the test set, the performance of the psychological assessment model based on elderly patients was tested;

[0185] Determine performance test results based on psychological assessment models;

[0186] An optimization and adjustment unit, used for optimizing and adjusting the psychological assessment model based on elderly patients;

[0187] Obtain performance test results based on psychological assessment models;

[0188] Conduct in-depth exploration and relevant analysis of performance test results based on psychological assessment models;

[0189] Determine the optimal adjustment plan based on the psychological assessment model;

[0190] Optimize and adjust the psychological assessment model based on the optimization adjustment plan;

[0191] Determine the best psychological assessment model after optimization and adjustment.

[0192] Among them, the evaluation and prediction module is used to evaluate and predict the mental health of elderly patients and determine the prediction results based on the mental health evaluation of elderly patients;

[0193] In this embodiment, the evaluation prediction module includes:

[0194] A data extraction unit, used for extracting psychological health characteristic data based on elderly patients;

[0195] According to the psychological assessment and nursing needs of elderly patients, the psychological health characteristic data of elderly patients are extracted;

[0196] An assessment and prediction unit, used to assess and predict the mental health of elderly patients;

[0197] Obtain the best psychological assessment model after optimization and adjustment;

[0198] Evaluate and predict the mental health characteristic data of elderly patients based on the best psychological assessment model after optimization and adjustment;

[0199] Identify outcomes based on mental health assessments in older patients;

[0200] Among them, the predicted results based on the mental health assessment of elderly patients include: normal mental health assessment of elderly patients and abnormal mental health assessment of elderly patients.

[0201] Among them, the nursing management and control module is used to formulate personalized nursing management and control plans based on elderly patients and to carry out personalized nursing management and control for elderly patients.

[0202] In this embodiment, the nursing management and control module includes:

[0203] Strategy development unit, used to develop personalized nursing management and control plans for elderly patients;

[0204] Obtain predictions based on mental health assessments of elderly patients;

[0205] Conduct in-depth exploration and relevant analysis on the prediction results of mental health assessment based on elderly patients;

[0206] Determine personalized nursing management plans for elderly patients;

[0207] Nursing control unit, used to provide personalized nursing control for elderly patients;

[0208] Obtain personalized nursing management plans for elderly patients;

[0209] Provide personalized nursing management and control for elderly patients based on personalized nursing management and control plans.

[0210] In this embodiment, personalized nursing management and control is performed on elderly patients, including:

[0211] Taking into account the personal characteristics, family environment and social relations of elderly patients, we develop personalized nursing and management plans for the mental health of elderly patients, monitor and track the mental health and needs of elderly patients in real time, and regularly update the personalized nursing and management plans based on the monitoring and tracking results to ensure their timeliness and effectiveness.

[0212] Therefore, by collecting real-time mental health data of elderly patients, processing the real-time mental health data, determining the mental health characteristic data, and constructing a psychological assessment model based on elderly patients according to their psychological assessment and nursing needs, the psychological assessment model is tested and optimized to determine the best psychological assessment model after optimization and adjustment, and the mental health of elderly patients is evaluated and predicted based on the best psychological assessment model, and the prediction results of the mental health assessment are determined. Based on the prediction results of the mental health assessment, a personalized nursing control plan based on the elderly patients is formulated, and personalized nursing control is performed on the elderly patients. The mental health of elderly patients can be effectively evaluated, and timely personalized care can be performed for elderly patients according to the results of the psychological assessment, so that the mental health problems of elderly patients can be effectively solved, and the quality of life of elderly patients can be improved.

[0213] 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.

[0214] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A psychological assessment and care system for elderly patients, characterized in that: include: The data collection module is used to collect mental health questionnaire information, interview information and record information of elderly patients, and determine the real-time mental health data based on elderly patients; A data processing module is used to process the real-time data of mental health of elderly patients and determine the characteristic data of mental health of elderly patients; A model building module is used to build a psychological assessment model based on elderly patients according to their psychological assessment and nursing needs; A test optimization module is used to test and optimize the psychological assessment model based on elderly patients and determine the best psychological assessment model after optimization and adjustment; An evaluation and prediction module is used to evaluate and predict the mental health of elderly patients and determine the prediction results based on the mental health evaluation of elderly patients; The nursing management and control module is used to formulate personalized nursing management and control plans based on elderly patients and to carry out personalized nursing management and control for elderly patients.

2. A psychological assessment and care system for elderly patients according to claim 1, characterized in that: The data acquisition module comprises: A questionnaire survey unit is used to conduct a questionnaire survey on the mental health of elderly patients and determine the mental health questionnaire information of elderly patients; The communication and interview unit is used to conduct communication and interviews on the mental health of elderly patients and determine the mental health interview information of elderly patients; An observation and recording unit is used to observe and record the mental health conditions of elderly patients and determine the mental health record information of elderly patients; Among them, based on the mental health questionnaire information, interview information and record information of elderly patients, real-time data on the mental health of elderly patients are determined.

3. A psychological assessment and care system for elderly patients according to claim 2, characterized in that: The data processing module comprises: A data retrieval unit, used for retrieving real-time data on mental health of elderly patients; Obtain real-time data on mental health of elderly patients; Based on the sequential retrieval method, the real-time data of mental health of elderly patients are retrieved; Check the consistency of real-time data on mental health based on older patients; Check whether the real-time mental health data meets the requirements based on the reasonable value range and mutual relationship of each variable in the real-time mental health data; Remove inconsistent data in real-time mental health data that is beyond the normal range, logically unreasonable, or contradictory; Process invalid and missing values ​​based on real-time data of mental health of elderly patients; Remove invalid and missing data from real-time mental health data that are of no value to psychological assessment and care; Identify real-time mental health data that is valuable for psychological assessment and care; A data sorting unit, used for sorting the retrieved real-time mental health data; Obtain real-time mental health data that is valuable for psychological assessment and care after retrieval; Based on the internal ranking method, the real-time mental health data that is valuable for psychological assessment and care after retrieval is ranked; Identify and prioritize real-time mental health data; A feature extraction unit, used for extracting features from the sorted real-time mental health data; Obtaining real-time mental health data that is sorted and ranked; Extract features from real-time mental health data with ranking order; Determine the data based on the mental health characteristics of elderly patients.

4. A psychological assessment and care system for elderly patients according to claim 3, characterized in that: The model building module includes: a data collection unit to collect mental health history data from older patients; According to the psychological assessment and nursing needs of elderly patients, a large amount of mental health history data of elderly patients is collected; A data partitioning unit, used for partitioning the mental health history data of elderly patients; Obtain mental health history data from older patients; Compartmentalize mental health history data of older patients; Determine the training set and test set; Model building unit, used to build psychological assessment models; According to the psychological assessment and nursing needs of elderly patients, select a model framework suitable for psychological assessment of elderly patients; Based on the training set, the selected model architecture suitable for psychological assessment of elderly patients is trained; Construct a psychological assessment model based on elderly patients.

5. A psychological assessment and care system for elderly patients according to claim 4, characterized in that: The data partitioning unit further includes: A ratio extraction module is used to extract the division ratio of the training set and the test set from the database; A partitioning execution module, used to partition the mental health history data according to the partitioning ratio to obtain a training set and a test set; A sample quantity retrieval module is used to extract a model architecture suitable for psychological assessment of elderly patients, and retrieve a minimum number of training samples corresponding to the model architecture suitable for psychological assessment of elderly patients; A comparison module, used for comparing the minimum number of training samples with the sample data of the training set; A reference sample data acquisition module, used for obtaining the data volume difference between the minimum training sample volume and the sample data of the training set when the minimum training sample volume is greater than the sample data of the training set, and randomly selecting sample data corresponding to the data volume difference from the test set as the reference sample data; The compensation data coefficient acquisition module is used to obtain the compensation data coefficients corresponding to the various data values ​​of the benchmark sample data by combining the various data values ​​contained in the benchmark sample data with the various data values ​​contained in the sample data in the training data; wherein the compensation data coefficients are obtained by the following formula: Where x represents the compensation data coefficient corresponding to each data value; n represents the number of sample data in the training data; X i represents the specific value corresponding to each data item contained in the i-th sample data in the training data; X i-1 represents the specific value corresponding to each data item contained in the i-1th sample data in the training data; X p Indicates the average data value corresponding to each data item of the training data; X z Represents the median value of each item of training data; The reference sample data adjustment module is used to adjust the data values ​​of each of the reference sample data using the compensation data coefficient to obtain the adjusted reference sample data, wherein the adjusted reference sample data is obtained by the following formula: Among them, X t represents the adjusted benchmark sample data; X represents the data value corresponding to each data value; x represents the compensation data coefficient corresponding to each data value; X z Represents the median value of each item of training data; A data supplementation module, used to use the adjusted benchmark sample data as supplementary data for the sample data of the training set; The test data supplementation module is used to obtain the sample data supplementation amount corresponding to the test set according to the number of sample data of the supplementary data and the division ratio of the training set and the test set.

6. A psychological assessment and care system for elderly patients according to claim 5, characterized in that: Test data supplement module, including: A data quantity acquisition module, used to acquire the data quantity of the sample data corresponding to the test set according to the number of sample data of the supplementary data and the division ratio of the training set and the test set; A data value extraction module, used to extract data values ​​of various items of data corresponding to the training data; A supplementary sample acquisition module, used to randomly retrieve sample data having the same number of data as the sample data corresponding to the test set from the training data as supplementary samples of the test set; The test set compensation adjustment coefficient acquisition module is used to obtain the compensation adjustment coefficient of each data value in the supplementary sample corresponding to the test set by using the data value of each data corresponding to the training data; wherein the compensation adjustment coefficient is obtained by the following formula: Among them, y represents the compensation adjustment coefficient; m represents the number of sample data after the current training set completes data supplement; X j represents the data value corresponding to each item in the j-th sample data after sample supplementation; X hp represents the average data value corresponding to each item of the training data after sample supplementation; X hz represents the median value of each item of training data after sample supplementation; h represents the compensation coefficient, and the compensation coefficient is obtained by the following formula: Among them, m represents the number of sample data after the current training set completes data supplementation; X j represents the data value corresponding to each item in the j-th sample data after sample supplementation; X j-1 represents the data value corresponding to each item in the j-1th sample data after sample supplementation; n represents the number of sample data in the training data; X i represents the specific value corresponding to each data item contained in the i-th sample data in the training data; X i-1 Indicates the specific value corresponding to each data item contained in the i-1th sample data in the training data; The test set adjustment module is used to adjust the values ​​of each data item in the supplementary sample corresponding to the test set by using the compensation adjustment coefficient of each data item, wherein the value of each data item of the supplementary sample after adjustment is obtained by the following formula: Among them, Y t Indicates the value of each data of the adjusted supplementary sample; X h Indicates the value of each data of the supplementary sample before adjustment; X hz Represents the median value of each item of training data after sample supplementation.

7. A psychological assessment and care system for elderly patients according to claim 4, characterized in that: The test optimization module includes: Performance testing unit for performance testing of psychological assessment models based on geriatric patients; Acquire a psychological assessment model based on older patients; Based on the test set, the performance of the psychological assessment model based on elderly patients was tested; Determine performance test results based on psychological assessment models; An optimization and adjustment unit, used for optimizing and adjusting the psychological assessment model based on elderly patients; Obtain performance test results based on psychological assessment models; Conduct in-depth exploration and relevant analysis of performance test results based on psychological assessment models; Determine the optimal adjustment plan based on the psychological assessment model; Optimize and adjust the psychological assessment model based on the optimization adjustment plan; Determine the best psychological assessment model after optimization and adjustment.

8. A psychological assessment and care system for elderly patients according to claim 7, characterized in that: The evaluation prediction module comprises: A data extraction unit, used for extracting psychological health characteristic data based on elderly patients; According to the psychological assessment and nursing needs of elderly patients, the psychological health characteristic data of elderly patients are extracted; An assessment and prediction unit, used to assess and predict the mental health of elderly patients; Obtain the best psychological assessment model after optimization and adjustment; Evaluate and predict the mental health characteristic data of elderly patients based on the best psychological assessment model after optimization and adjustment; Identify outcomes based on mental health assessments in older patients; Among them, the predicted results based on the mental health assessment of elderly patients include: normal mental health assessment of elderly patients and abnormal mental health assessment of elderly patients.

9. A psychological assessment and care system for elderly patients according to claim 8, characterized in that: The nursing management and control module includes: Strategy development unit, used to develop personalized nursing management and control plans for elderly patients; Obtain predictions based on mental health assessments of elderly patients; Conduct in-depth exploration and relevant analysis on the prediction results of mental health assessment based on elderly patients; Determine personalized nursing management plans for elderly patients; Nursing control unit, used to provide personalized nursing control for elderly patients; Obtain personalized nursing management plans for elderly patients; Provide personalized nursing management and control for elderly patients based on personalized nursing management and control plans.

10. A psychological assessment and care system for elderly patients according to claim 9, characterized in that: Personalized care management for elderly patients, including: Taking into account the personal characteristics, family environment and social relations of elderly patients, we develop personalized nursing and management plans for the mental health of elderly patients, monitor and track the mental health and needs of elderly patients in real time, and regularly update the personalized nursing and management plans based on the monitoring and tracking results to ensure their timeliness and effectiveness.

Images