Nursing system and monitoring method thereof

Abstract

The invention discloses a nursing system and a monitoring method thereof, and the method comprises the following steps: collecting the physiological data of a patient through an intelligent sensor, forming a dynamic health data flow, carrying out the analysis in combination with historical health data, extracting key health features based on a time sequence attention mechanism, and carrying out the monitoring of the key health features. A machine learning model is adopted to predict the health state of a patient, a health mode between the patient and a similar patient is calculated to generate a personalized nursing scheme, and combined optimization is performed on health state prediction and a nursing recommendation scheme in combination with a time sequence collaborative multi-task learning framework, so that dynamic adjustment of the nursing scheme is realized; the system also includes an adaptive care intervention module that optimizes a care intervention strategy according to the latest health data of the patient and continuously iteratively optimizes the care scheme based on the care execution feedback. According to the invention, a complete nursing closed loop from data acquisition, analysis, prediction and recommendation to optimization and intervention is constructed, and accurate monitoring and personalized nursing management of the health state of the patient are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of nursing monitoring, and in particular to a nursing system and a monitoring method of the nursing system. Background Art

[0002] With the development of intelligent medical technology, the role of nursing systems in medical services is becoming increasingly important. However, traditional nursing systems still have many shortcomings in the face of increasingly complex nursing needs and dynamic changes in patients' health conditions, and it is difficult to meet personalized, intelligent, and efficient nursing needs. The core goal of the nursing system is to provide real-time, accurate health status predictions and nursing plan recommendations based on patients' physiological data and historical nursing records. However, the existing nursing system has obvious defects in the following aspects: 1. Low nursing efficiency: Traditional nursing systems rely on manual recording and analysis of patient data. Nursing staff need to manually track patient health status and adjust nursing plans, resulting in cumbersome and inefficient nursing processes that cannot meet high-frequency health monitoring needs.

[0003] 2. It is difficult to monitor nursing quality in real time: Existing nursing systems usually rely on regular health checks or subjective nursing assessments, lacking automatic monitoring of patients' real-time health status and data-driven optimization of nursing plans, resulting in delayed nursing interventions and inability to adjust nursing measures in time to adapt to dynamic changes in patients' health status.

[0004] 3. Lack of personalized health management: Traditional care plans mostly adopt standardized care processes, which fail to fully consider individual differences. It is difficult to formulate accurate care plans based on the patient's historical health data, similar patient care experience and individual health characteristics, resulting in limited care effects.

[0005] 4. Low data utilization and insufficient intelligence in nursing decision-making: The existing nursing system does not fully utilize the patient's historical health data and real-time physiological data, and lacks efficient data analysis methods, making it difficult to dynamically optimize nursing plans, which affects the scientific nature and accuracy of nursing plans.

[0006] 5. Nursing intervention strategies lack adaptability: Traditional nursing systems mainly rely on static nursing plans, which make it difficult to dynamically adjust nursing intervention measures based on real-time changes in the patient's health status. This results in the nursing plan's lack of flexibility in responding to sudden health events or changes in patient status.

[0007] Therefore, how to provide a nursing system and a monitoring method for the nursing system is an urgent problem to be solved by those skilled in the art. Summary of the invention

[0008] One object of the present invention is to propose a nursing system and a monitoring method for the nursing system. The present invention utilizes a temporal attention mechanism, a collaborative filtering algorithm and a temporal collaborative multi-task learning framework, and describes in detail a closed-loop optimization process from physiological data collection, health status prediction, personalized nursing recommendation to adaptive nursing intervention. It has the advantages of strong real-time performance, precise personalized nursing, and high adaptive adjustment capability of nursing intervention.

[0009] A nursing system and a monitoring method of the nursing system according to an embodiment of the present invention include the following steps: S1, physiological data acquisition module, collects multi-dimensional physiological data of patients in real time through intelligent sensors, forming a continuously updated dynamic health data stream; S2, time series data analysis and feature extraction module, applies the time series attention mechanism to analyze the dynamic health data stream and automatically extracts the physiological characteristics and historical health data of key time nodes; S3, health status prediction module, predicts the patient's health status based on the extracted physiological characteristics of key time nodes combined with machine learning algorithms; S4, personalized nursing recommendation module, through collaborative filtering algorithm, based on the patient's health status prediction and historical health data, analyzes the health pattern between the patient and similar patients, and generates nursing recommendation plans; S5, Nursing plan optimization and adjustment module, builds a time-series collaborative multi-task learning framework, jointly optimizes the patient's health status prediction and nursing recommendation plan, determines the patient's nursing needs, adjusts the nursing recommendation plan in real time according to the patient's health status changes and nursing needs, and generates historical nursing records; S6, the adaptive nursing intervention and feedback module, automatically generates nursing intervention strategies and optimizes nursing recommendation plans based on dynamic health data streams, historical nursing records, and adjusted nursing recommendation plans.

[0010] Optionally, the S2 specifically includes: S21, data preprocessing module, standardizes and aligns the dynamic health data stream, uses outlier detection method to remove abnormal data, and constructs the time series feature matrix : ; in, Represents physiological characteristics and is used to identify time steps Physiological measurements of Represents the total number of physiological characteristics, Represents the time step The Observed values ​​of physiological characteristics; S22, time series feature extraction module, based on the time series feature matrix , applying the temporal attention mechanism to calculate the weight matrix of multi-dimensional physiological data at different time steps , and use weighted summation to generate time steps The time series feature vector at ; S23, key time step identification module, based on time step The time series feature vector at , the dynamic time warping method is used to calculate the feature change amplitude between time steps and determine the key time step : ; in, For the A key time step, is the sliding window size, automatically identifying the key change moments of health status based on the feature change trend. is the time step The time series feature vector at ; S24, historical health data matching module, based on key time steps , from the time series feature matrix Extract historical health data of the corresponding time window , calculate the matching degree between the characteristic components of the key time step and the historical health data : ; in, Reflects the key time step Health status and historical health data The matching degree between The key time step The characteristic component of is the corresponding feature component of historical health data, Represents physiological characteristics, is the total number of physiological characteristics; S25, time series feature optimization module, through the matching degree between the health status of key time steps and historical health data , for the key time step Dynamic correction of the time series feature vector at: ; in, is the optimized time series feature vector, The key time step The extracted time series feature vector, For historical health data, is the feature fusion adjustment factor, with a value range of .

[0011] Optionally, the S22 specifically includes: S221, temporal attention initialization module, based on the time series feature matrix , initialize the initial weight matrix of the temporal attention mechanism , calculate the forward calculation weight matrix And the backward calculation weight matrix And jointly generate the initial weight matrix: ; in, Represents the time step The initial weight matrix, is the normalization function, and They are the forward calculation weight matrix and the backward calculation weight matrix, is the current time step The time series feature matrix, is the previous time step The time series feature matrix of S222, time step attention distribution calculation module, based on the initial weight matrix , using the normalization mechanism to calculate the multi-dimensional physiological data at the current time step The attention distribution weight : ; in, Indicates physiological characteristics At time step The attention distribution weight, is the time step Physiological characteristics The initial weight matrix, is the total number of physiological characteristics, is the exponential operation function; S223, time series feature calculation module, based on attention distribution weight , for the current time step The physiological characteristics are weighted to generate a time series feature vector : ; in, Represents the time step The time series feature vector of is the time step Physiological characteristics The observed value of is the time step The attention distribution weights of physiological features.

[0012] Optionally, the S4 specifically includes: S41, patient health feature construction module, based on the patient's health status prediction and historical health data, extracts multi-dimensional physiological parameters, medical history records and nursing feedback information, and constructs the patient's health feature vector ; S42, similar patient matching module, based on patient health feature vector , calculate the similarity of health characteristics with similar patients, and use Mahalanobis distance to calculate the similarity of health characteristics between different patients: ; in, Indicates patient Similar patients The similarity of health characteristics between and Respectively, patients and similar patients The patient health feature vector, is the inverse matrix of the covariance matrix of the health characteristics; S43, similar group construction module, based on the similarity of health characteristics between patients and similar patients , filter similarity to meet the set threshold Similar patient collections ; S44, nursing plan scoring calculation module, based on similar patient sets and historical health data, and apply collaborative filtering algorithms to calculate candidate care plans Recommended rating : ; in, Indicates for patients Candidate Nursing Programs Recommended rating, For similar patients Nursing Program Candidates Historical ratings; S45, personalized nursing plan generation module, based on the recommendation score of candidate nursing plans , sort all candidate nursing plans, select the candidate nursing plans with the highest scores, and form the final nursing recommendation plan .

[0013] Optionally, the S42 specifically includes: S421, health feature normalization module, for the patient's health feature vector Normalizing the multi-dimensional physiological parameters in the patient data to generate normalized characteristic values ​​on the patient's health characteristic components; S422, a health feature correlation calculation module, which calculates the covariance matrix of the health feature components based on the normalized eigenvalues ​​of the health feature components of the patient , to measure the correlation between various health characteristic variables: ; in, Health characteristic component Health characteristics The covariance between Health characteristic component The mean of Health characteristic component The mean of is the total number of patient data, For patients In the health characteristics The normalized eigenvalue on , For patients In the health characteristics The normalized eigenvalues ​​on ; S423, individual health feature similarity calculation module, based on the normalized eigenvalues ​​of the patient's health feature components and the covariance matrix of the health features, using the Mahalanobis distance to calculate the patient's Similar patients The similarity of health characteristics between them.

[0014] Optionally, the S5 specifically includes: S51, Nursing demand modeling module, based on the patient's health status prediction and nursing recommendation plan, extracts the patient's health change trend and historical nursing records, and constructs a nursing demand vector ; S52, time series collaborative learning module, builds a time series collaborative multi-task learning framework, and jointly optimizes patient health status prediction and nursing recommendation plans: ; in, is the total loss function, Predicting loss for health status, Recommend loss for nursing, and is the task weight factor; S53, personalized care optimization module, based on the total loss function Optimize the nursing demand vector to generate the optimized nursing demand vector , Updated nursing recommendations : ; in, For updated care recommendations, Indicates the matching degree between the nursing demand vector and the candidate nursing solutions; S54, historical nursing record update module, based on updated nursing recommendation plan , update patient historical care records.

[0015] Optionally, a monitoring method of a nursing system comprises the following steps: S71. Collect multi-dimensional physiological data of patients in real time through intelligent sensors to form a dynamic health data stream; S72. Based on the dynamic health data stream, the temporal attention mechanism is used to extract the physiological features at the key time steps and construct the time series feature matrix; S73. Based on the time series feature matrix and key time steps, a machine learning model is used to predict the patient's future health status and output the patient's health risk assessment results; S74. Based on the patient's health status prediction results and historical nursing records, the Mahalanobis distance is used to calculate the similarity of health characteristics between the patient and a set of similar patients, and the collaborative filtering algorithm is used to calculate the nursing plan score to generate a nursing recommendation plan; S75. Based on the nursing recommendation plan, a time-series collaborative multi-task learning framework is constructed to jointly optimize the patient health status prediction and nursing recommendation plan, and dynamically adjust the nursing recommendation plan; S76, based on the dynamically adjusted nursing recommendation plan and the dynamic health data stream, calculating the nursing intervention state vector, and using the optimization function to calculate the optimal nursing intervention decision vector; S77. Based on the execution feedback of the nursing intervention decision vector, update the patient's historical nursing records, and synchronously adjust the nursing intervention state vector and nursing recommendation plan.

[0016] The beneficial effects of the present invention are: (1) This invention combines the temporal attention mechanism, collaborative filtering algorithm and temporal collaborative multi-task learning framework to achieve accurate prediction of the patient's health status and personalized nursing recommendations by the nursing system, so that the system can dynamically adapt to the patient's health changes and optimize the nursing plan. Based on the dynamic health data stream collected by smart sensors, the system can automatically identify key health characteristics and combine similar patient health pattern analysis to generate the optimal nursing plan, ensuring the accuracy and adaptability of nursing intervention.

[0017] (2) The present invention uses a time-series collaborative optimization mechanism to jointly optimize health status prediction and nursing recommendation plan generation, thereby achieving dynamic adjustment and personalized matching of nursing plans. Based on nursing intervention state modeling, the system can calculate the optimal decision vector of the nursing intervention strategy based on the patient's historical nursing records, current health characteristics, and recommended nursing plans, and dynamically adjust the nursing recommendation plans, so that the nursing plans can be continuously optimized and adapted to the patient's health changes.

[0018] (3) The present invention builds a closed-loop nursing monitoring process, covering data collection, feature extraction, health prediction, nursing recommendation, nursing optimization, nursing intervention and feedback update, so that the nursing system has adaptive learning capabilities. After nursing execution, the system can iteratively optimize the nursing recommendation plan based on the nursing intervention feedback information, and update the nursing intervention status, reduce dependence on manual intervention, improve the accuracy and dynamic adaptability of nursing intervention, and thus effectively improve the quality and efficiency of nursing services. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is an overall architecture diagram of a nursing system proposed by the present invention; Figure 2 The present invention is a flow chart of a monitoring method for a nursing system. DETAILED DESCRIPTION

[0020] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0021] refer to Figure 1-2 , a nursing system and a monitoring method of the nursing system.

[0022] Specifically, a nursing system comprises the following steps: S1, physiological data acquisition module, collects multi-dimensional physiological data of patients in real time through intelligent sensors, forming a continuously updated dynamic health data stream; This implementation uses smart sensors to collect multi-dimensional physiological data of patients in real time, forming a continuously updated dynamic health data stream, providing high-precision and timely data support for subsequent health status prediction and personalized nursing recommendations. This method can effectively reduce the lag and error of manual data recording, improve the real-time monitoring capability of the nursing system, and ensure the accuracy and continuity of nursing intervention.

[0023] S2, time series data analysis and feature extraction module, applies the time series attention mechanism to analyze the dynamic health data stream and automatically extracts the physiological characteristics and historical health data of key time nodes; S3, health status prediction module, predicts the patient's health status based on the extracted physiological characteristics of key time nodes combined with machine learning algorithms; This embodiment uses a machine learning algorithm that combines a long short-term memory network with a gradient boosting decision tree to predict the patient's health status. The long short-term memory network can effectively model the temporal changes in the patient's physiological parameters, capture short-term fluctuations and long-term trends, and improve the timeliness and accuracy of health status prediction. The gradient boosting decision tree uses historical health data to explore the health evolution patterns of different patient groups and optimize health risk assessment through multi-level feature extraction. Combining the temporal modeling capabilities of the long short-term memory network and the efficient feature learning capabilities of the gradient boosting decision tree, this embodiment can accurately predict the patient's future health status and provide reliable data support for personalized care plans, while ensuring the robustness and generalization capabilities of the prediction model, and improving the decision-making accuracy and adaptability of the nursing system.

[0024] S4, personalized nursing recommendation module, through collaborative filtering algorithm, based on the patient's health status prediction and historical health data, analyzes the health pattern between the patient and similar patients, and generates nursing recommendation plans; S5, Nursing plan optimization and adjustment module, builds a time-series collaborative multi-task learning framework, jointly optimizes the patient's health status prediction and nursing recommendation plan, determines the patient's nursing needs, adjusts the nursing recommendation plan in real time according to the patient's health status changes and nursing needs, and generates historical nursing records; S6, the adaptive nursing intervention and feedback module, automatically generates nursing intervention strategies and optimizes nursing recommendation plans based on dynamic health data streams, historical nursing records, and adjusted nursing recommendation plans.

[0025] This implementation method builds an adaptive nursing intervention strategy based on dynamic health data streams, historical nursing records, and optimized nursing recommendation plans, which can adjust the nursing plan in real time to adapt to changes in the patient's health status. Through the automated strategy generation and optimization mechanism, the accuracy and response efficiency of nursing decisions are improved, and the dynamic adaptation of personalized nursing interventions is achieved, ensuring the continuous optimization of nursing plans and the efficient implementation of patient health management.

[0026] In this implementation manner, S2 specifically includes: S21, data preprocessing module, standardizes and aligns the dynamic health data stream, uses outlier detection method to remove abnormal data, and constructs the time series feature matrix : ; in, Represents physiological characteristics and is used to identify time steps Physiological measurements of Represents the total number of physiological characteristics, Represents the time step The Observed values ​​of physiological characteristics; S22, time series feature extraction module, based on the time series feature matrix , applying the temporal attention mechanism to calculate the weight matrix of multi-dimensional physiological data at different time steps , and use weighted summation to generate time steps The time series feature vector at ; S23, key time step identification module, based on time step The time series feature vector at , the dynamic time warping method is used to calculate the feature change amplitude between time steps and determine the key time step : ; in, For the A key time step, is the sliding window size, automatically identifying the key change moments of health status based on the feature change trend. is the time step The time series feature vector at ; S24, historical health data matching module, based on key time steps , from the time series feature matrix Extract historical health data of the corresponding time window , calculate the matching degree between the characteristic components of the key time step and the historical health data : ; in, Reflects the key time step Health status and historical health data The matching degree between The key time step The characteristic component of is the corresponding feature component of historical health data, Represents physiological characteristics, is the total number of physiological characteristics; S25, time series feature optimization module, through the matching degree between the health status of key time steps and historical health data , for the key time step Dynamic correction of the time series feature vector at: ; in, is the optimized time series feature vector, The key time step The extracted time series feature vector, For historical health data, is the feature fusion adjustment factor, with a value range of .

[0027] The present invention realizes accurate analysis of dynamic health data streams through data preprocessing, time series feature extraction and key time step identification. The historical health data matching module is combined to calculate the similarity of health features at key time steps, and the key features are dynamically corrected in the time series feature optimization module to ensure the accuracy of physiological data and the stability of time series features. This method improves the accuracy of health status prediction and enables personalized adjustment and optimization of nursing plans based on high-quality health feature data.

[0028] In this implementation manner, the S22 specifically includes: S221, temporal attention initialization module, based on the time series feature matrix , initialize the initial weight matrix of the temporal attention mechanism , calculate the forward calculation weight matrix And the backward calculation weight matrix And jointly generate the initial weight matrix: ; in, Represents the time step The initial weight matrix, is the normalization function, and They are the forward calculation weight matrix and the backward calculation weight matrix, is the current time step The time series feature matrix, is the previous time step The time series feature matrix of S222, time step attention distribution calculation module, based on the initial weight matrix , using the normalization mechanism to calculate the multi-dimensional physiological data at the current time step The attention distribution weight : ; in, Indicates physiological characteristics At time step The attention distribution weight, is the time step Physiological characteristics The initial weight matrix, is the total number of physiological characteristics, is the exponential operation function; S223, time series feature calculation module, based on attention distribution weight , for the current time step The physiological characteristics are weighted to generate a time series feature vector : ; in, Represents the time step The time series feature vector of is the time step Physiological characteristics The observed value of is the time step The attention distribution weights of physiological features.

[0029] This embodiment uses a temporal attention mechanism to dynamically calculate the weights of the patient's physiological characteristics at different time steps, ensuring that key health information is enhanced in the nursing system. The joint application of forward and backward calculation weight matrices enables the model to combine historical and current health data to optimize the accuracy of temporal feature extraction. Through attention distribution calculation and weighted feature fusion, the present invention can accurately capture the changing trend of the patient's health status, improve the nursing system's prediction accuracy of health status, and provide more reliable data support for personalized nursing plans.

[0030] In this implementation manner, S4 specifically includes: S41, patient health feature construction module, based on the patient's health status prediction and historical health data, extracts multi-dimensional physiological parameters, medical history records and nursing feedback information, and constructs the patient's health feature vector ; S42, similar patient matching module, based on patient health feature vector , calculate the similarity of health characteristics with similar patients, and use Mahalanobis distance to calculate the similarity of health characteristics between different patients: ; in, Indicates patient Similar patients The similarity of health characteristics between and Respectively, patients and similar patients The patient health feature vector, is the inverse matrix of the covariance matrix of the health characteristics; S43, similar group construction module, based on the similarity of health characteristics between patients and similar patients , filter similarity to meet the set threshold Similar patient collections ; S44, nursing plan scoring calculation module, based on similar patient sets and historical health data, and apply collaborative filtering algorithms to calculate candidate care plans Recommended rating : ; in, Indicates for patients Candidate Nursing Programs Recommended rating, For similar patients Nursing Program Candidates Historical ratings; S45, personalized nursing plan generation module, based on the recommendation score of candidate nursing plans , sort all candidate nursing plans, select the candidate nursing plans with the highest scores, and form the final nursing recommendation plan .

[0031] The present invention combines Mahalanobis distance similarity calculation and collaborative filtering algorithm to accurately match similar patient groups and optimize nursing plan recommendations based on historical nursing data of similar patients. This method can not only dynamically adapt to the health status of individual patients, but also optimize nursing decisions through historical data learning, improve the personalized matching degree and recommendation accuracy of nursing plans, improve the scientificity and effectiveness of nursing interventions, and achieve reasonable allocation and intelligent optimization of nursing resources.

[0032] In this implementation manner, the S42 specifically includes: S421, health feature normalization module, for the patient's health feature vector Normalizing the multi-dimensional physiological parameters in the patient data to generate normalized characteristic values ​​on the patient's health characteristic components; S422, a health feature correlation calculation module, which calculates the covariance matrix of the health feature components based on the normalized eigenvalues ​​of the health feature components of the patient , to measure the correlation between various health characteristic variables: ; in, Health characteristic component Health characteristics The covariance between Health characteristic component The mean of Health characteristic component The mean of is the total number of patient data, For patients In the health characteristics The normalized eigenvalue on , For patients In the health characteristics The normalized eigenvalues ​​on ; S423, individual health feature similarity calculation module, based on the normalized eigenvalues ​​of the patient's health feature components and the covariance matrix of the health features, using the Mahalanobis distance to calculate the patient's Similar patients The similarity of health characteristics between them.

[0033] The present invention normalizes the patient's health feature vector and calculates the covariance matrix of the health feature to ensure that data of different feature dimensions have a unified scale when calculating similarity. The Mahalanobis distance is used to measure the similarity of the patient's health status, so that the system can accurately match patients with similar health features, improve the accuracy and effectiveness of personalized nursing recommendations, thereby optimizing the matching of nursing plans and improving the adaptability of nursing interventions.

[0034] In this implementation manner, S5 specifically includes: S51, Nursing demand modeling module, based on the patient's health status prediction and nursing recommendation plan, extracts the patient's health change trend and historical nursing records, and constructs a nursing demand vector ; S52, time series collaborative learning module, builds a time series collaborative multi-task learning framework, and jointly optimizes patient health status prediction and nursing recommendation plans: ; in, is the total loss function, Predicting loss for health status, Recommend loss for nursing, and is the task weight factor; S53, personalized care optimization module, based on the total loss function Optimize the nursing demand vector to generate the optimized nursing demand vector , Updated nursing recommendations : ; in, For updated care recommendations, Indicates the matching degree between the nursing demand vector and the candidate nursing solutions; S54, historical nursing record update module, based on updated nursing recommendation plan , update patient historical care records.

[0035] This implementation method achieves accurate modeling and optimization of nursing needs by constructing a time-series collaborative multi-task learning framework to jointly optimize the prediction of patient health status and nursing recommendation plans. The nursing recommendation plan is dynamically adjusted based on the optimized nursing demand vector, and historical nursing records are iteratively updated in combination with nursing execution feedback to ensure that the nursing plan can continuously adapt to changes in the patient's health status and improve the accuracy and intelligence of nursing intervention.

[0036] This embodiment provides a monitoring method for a nursing system, the method comprising the following steps: S71. Collect multi-dimensional physiological data of patients in real time through intelligent sensors to form a dynamic health data stream; S72. Based on the dynamic health data stream, the temporal attention mechanism is used to extract the physiological features at the key time steps and construct the time series feature matrix; S73. Based on the time series feature matrix and key time steps, a machine learning model is used to predict the patient's future health status and output the patient's health risk assessment results; S74. Based on the patient's health status prediction results and historical nursing records, the Mahalanobis distance is used to calculate the similarity of health characteristics between the patient and a set of similar patients, and the collaborative filtering algorithm is used to calculate the nursing plan score to generate a nursing recommendation plan; S75. Based on the nursing recommendation plan, a time-series collaborative multi-task learning framework is constructed to jointly optimize the patient health status prediction and nursing recommendation plan, and dynamically adjust the nursing recommendation plan; S76, based on the dynamically adjusted nursing recommendation plan and the dynamic health data stream, calculating the nursing intervention state vector, and using the optimization function to calculate the optimal nursing intervention decision vector; S77. Based on the execution feedback of the nursing intervention decision vector, update the patient's historical nursing records, and synchronously adjust the nursing intervention state vector and nursing recommendation plan.

[0037] Embodiment 1: In order to verify the feasibility of the present invention, the present invention is applied to the intelligent nursing system of a large general hospital. The hospital receives a large number of inpatients and outpatients every day, with a huge nursing workload, and the health conditions of patients are complex and changeable. Nursing staff need to monitor the physiological status of patients in real time and adjust the nursing plan in time. The existing nursing methods mainly rely on manual records and experience judgments, which are difficult to achieve precision and personalization. In order to improve nursing efficiency and optimize nursing plans, the hospital decided to introduce the intelligent nursing system of the present invention, using technologies such as physiological data collection, health status prediction, personalized nursing recommendations, nursing optimization and intervention strategies, to achieve full-process intelligent nursing monitoring.

[0038] The hospital has installed smart sensors in each ward to collect multi-dimensional physiological data of patients, including heart rate, blood pressure, blood oxygen saturation, body temperature and blood sugar level, and transmit these data to the nursing database in real time. The nursing system automatically extracts the physiological characteristics of key time steps, and combines the patient's historical health data to build a time series feature matrix, and uses the time series attention mechanism to analyze the data and screen out the key factors that affect the patient's health status. Based on data collection, the system uses a machine learning model to predict the patient's health risks, and calculates the health pattern of the patient and similar patients through a collaborative filtering algorithm, thereby generating personalized nursing recommendations for each patient.

[0039] In order to ensure the dynamic adaptability of the nursing plan, the system jointly optimizes health status prediction and nursing plan generation based on a time-series collaborative multi-task learning framework, and adjusts the plan in combination with nursing execution feedback. For example, the nursing plan for a diabetic inpatient recommends monitoring blood sugar levels every 6 hours in the initial recommendation, but the system found that the patient's blood sugar fluctuated greatly after the nursing implementation, so it dynamically adjusted the plan, increased the monitoring frequency, and recommended a more accurate diet management plan. In addition, the system can also automatically generate nursing intervention strategies and optimize the implementation process of the nursing plan. For example, when the patient's blood sugar level rises abnormally, the system immediately reminds the nursing staff to adjust the insulin dosage and recommends personalized dietary intervention measures based on the patient's historical nursing records.

[0040] In order to verify the effectiveness of the nursing system of the present invention, the hospital selected 500 inpatients for comparative experiments, of which 250 patients used traditional nursing methods and 250 patients used the intelligent nursing system of the present invention. The experimental period was three months, and the performance of the two nursing methods in terms of nursing efficiency, nursing quality, health risk control, etc. was compared. The experimental data are shown in the following table: Table 1 Comparison of the effects of traditional nursing methods and intelligent nursing systems

[0041] It can be seen from the experimental results that the intelligent nursing system of the present invention has greatly improved the nursing efficiency, and the number of patients cared for by each nurse per day has increased by 50%. At the same time, since the nursing plan is optimized based on data-driven, the matching degree of the nursing plan has increased from 78.5% to 92.3%, and patients can get a nursing plan that is more in line with their health status. In addition, since the intelligent system can timely identify the health risks of patients and dynamically adjust the nursing plan, the nursing intervention response time has been shortened from 45 minutes to 15 minutes, and the incidence of health emergencies has decreased by 61%. In terms of nursing satisfaction, the satisfaction of patients using the intelligent nursing system has increased by 10.8%, indicating that the system can better meet the nursing needs of patients.

[0042] During the specific implementation process, the system also optimized personalized care for certain special patient groups. For example, in the ICU ward, the nursing system automatically detected changes in the patient's condition based on the patient's real-time health monitoring data, and pushed nursing adjustment suggestions to the nursing staff. A patient who was recovering from surgery had a drop in blood pressure at night. The system combined his historical health data and the nursing records of similar patients, automatically recommended that the nursing staff adjust the intravenous infusion rate and take additional nursing measures, successfully avoiding the deterioration of the condition.

[0043] In summary, the intelligent nursing system of the present invention effectively improves nursing efficiency, nursing quality and health management level through real-time data collection, time series analysis, personalized recommendation, dynamic optimization and nursing intervention feedback. The system can dynamically adapt to the health changes of patients, provide precise and personalized nursing plans, and reduce the workload of nursing staff, providing an efficient and feasible solution for intelligent nursing management of medical institutions.

[0044] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A nursing system, characterized in that: The steps include: S1, physiological data acquisition module, collects multi-dimensional physiological data of patients in real time through intelligent sensors, forming a continuously updated dynamic health data stream; S2, time series data analysis and feature extraction module, applies the time series attention mechanism to analyze the dynamic health data stream and automatically extracts the physiological characteristics and historical health data of key time nodes; S3, health status prediction module, predicts the patient's health status based on the extracted physiological characteristics of key time nodes combined with machine learning algorithms; S4, personalized nursing recommendation module, through collaborative filtering algorithm, based on the patient's health status prediction and historical health data, analyzes the health pattern between the patient and similar patients, and generates nursing recommendation plans; S5, Nursing plan optimization and adjustment module, builds a time-series collaborative multi-task learning framework, jointly optimizes the patient's health status prediction and nursing recommendation plan, determines the patient's nursing needs, adjusts the nursing recommendation plan in real time according to the patient's health status changes and nursing needs, and generates historical nursing records; S6, the adaptive nursing intervention and feedback module, automatically generates nursing intervention strategies and optimizes nursing recommendation plans based on dynamic health data streams, historical nursing records, and adjusted nursing recommendation plans.

2. A nursing system according to claim 1, characterized in that: The S2 specifically includes: S21, data preprocessing module, standardizes and aligns the dynamic health data stream, uses outlier detection method to remove abnormal data, and constructs the time series feature matrix : ； in, Represents physiological characteristics and is used to identify time steps Physiological measurements of Represents the total number of physiological characteristics, Represents the time step The Observed values ​​of physiological characteristics; S22, time series feature extraction module, based on the time series feature matrix , applying the temporal attention mechanism to calculate the weight matrix of multi-dimensional physiological data at different time steps , and use weighted summation to generate time steps The time series feature vector at ; S23, key time step identification module, based on time step The time series feature vector at , the dynamic time warping method is used to calculate the feature change amplitude between time steps and determine the key time step : ； in, For the A key time step, is the sliding window size, automatically identifying the key change moments of health status based on the feature change trend. is the time step The time series feature vector at ; S24, historical health data matching module, based on key time steps , from the time series feature matrix Extract historical health data of the corresponding time window , calculate the matching degree between the characteristic components of the key time step and the historical health data : ； in, Reflects the key time step Health status and historical health data The matching degree between The key time step The characteristic component of is the corresponding feature component of historical health data, Represents physiological characteristics, is the total number of physiological characteristics; S25, time series feature optimization module, through the matching degree between the health status of key time steps and historical health data , for the key time step Dynamic correction of the time series feature vector at: ； in, is the optimized time series feature vector, The key time step The extracted time series feature vector, For historical health data, is the feature fusion adjustment factor, with a value range of .

3. A nursing system according to claim 2, characterized in that: The S22 specifically includes: S221, temporal attention initialization module, based on the time series feature matrix , initialize the initial weight matrix of the temporal attention mechanism , calculate the forward calculation weight matrix And the backward calculation weight matrix And jointly generate the initial weight matrix: ； in, Represents the time step The initial weight matrix, is the normalization function, and They are the forward calculation weight matrix and the backward calculation weight matrix, is the current time step The time series feature matrix, is the previous time step The time series feature matrix of S222, time step attention distribution calculation module, based on the initial weight matrix , using the normalization mechanism to calculate the multi-dimensional physiological data at the current time step The attention distribution weight : ； in, Indicates physiological characteristics At time step The attention distribution weight, is the time step Physiological characteristics The initial weight matrix, is the total number of physiological characteristics, is the exponential operation function; S223, time series feature calculation module, based on attention distribution weight , for the current time step The physiological characteristics are weighted to generate a time series feature vector : ； in, Represents the time step The time series feature vector of is the time step Physiological characteristics The observed value of is the time step The attention distribution weights of physiological features.

4. A nursing system according to claim 1, characterized in that: The S4 specifically includes: S41, patient health feature construction module, based on the patient's health status prediction and historical health data, extracts multi-dimensional physiological parameters, medical history records and nursing feedback information, and constructs the patient's health feature vector ; S42, similar patient matching module, based on patient health feature vector , calculate the similarity of health characteristics with similar patients, and use Mahalanobis distance to calculate the similarity of health characteristics between different patients: ； in, Indicates patient Similar patients The similarity of health characteristics between and Respectively, patients and similar patients The patient health feature vector, is the inverse matrix of the covariance matrix of the health characteristics; S43, similar group construction module, based on the similarity of health characteristics between patients and similar patients , filter similarity to meet the set threshold Similar patient collections ; S44, nursing plan scoring calculation module, based on similar patient sets and historical health data, and apply collaborative filtering algorithms to calculate candidate care plans Recommended rating : ； in, Indicates for patients Candidate Nursing Programs Recommended rating, For similar patients Nursing Program Candidates Historical ratings; S45, personalized nursing plan generation module, based on the recommendation score of candidate nursing plans , sort all candidate nursing plans, select the candidate nursing plans with the highest scores, and form the final nursing recommendation plan .

5. A nursing system according to claim 4, characterized in that: The S42 specifically includes: S421, health feature normalization module, for the patient's health feature vector Normalizing the multi-dimensional physiological parameters in the patient data to generate normalized characteristic values ​​on the patient's health characteristic components; S422, a health feature correlation calculation module, which calculates the covariance matrix of the health feature components based on the normalized eigenvalues ​​of the health feature components of the patient , to measure the correlation between various health characteristic variables: ； in, Health characteristic component Health characteristics The covariance between Health characteristic component The mean of Health characteristic component The mean of is the total number of patient data, For patients In the health characteristics The normalized eigenvalue on , For patients In the health characteristics The normalized eigenvalues ​​on ; S423, individual health feature similarity calculation module, based on the normalized eigenvalues ​​of the patient's health feature components and the covariance matrix of the health features, using the Mahalanobis distance to calculate the patient's Similar patients The similarity of health characteristics between them.

6. A nursing system according to claim 5, characterized in that: The S5 specifically includes: S51, Nursing demand modeling module, based on the patient's health status prediction and nursing recommendation plan, extracts the patient's health change trend and historical nursing records, and constructs a nursing demand vector ; S52, time series collaborative learning module, builds a time series collaborative multi-task learning framework, and jointly optimizes patient health status prediction and nursing recommendation plans: ； in, is the total loss function, Predicting loss for health status, Recommend loss for nursing, and is the task weight factor; S53, personalized care optimization module, based on the total loss function Optimize the nursing demand vector to generate the optimized nursing demand vector , Updated nursing recommendations : ； in, For updated care recommendations, Indicates the matching degree between the nursing demand vector and the candidate nursing solutions; S54, historical nursing record update module, based on updated nursing recommendation plan , update patient historical care records.

7. A nursing system monitoring method, applied to a nursing system according to any one of claims 1 to 6, characterized in that: The method comprises the following steps: S71. Collect multi-dimensional physiological data of patients in real time through intelligent sensors to form a dynamic health data stream; S72. Based on the dynamic health data stream, the temporal attention mechanism is used to extract the physiological features at the key time steps and construct the time series feature matrix; S73. Based on the time series feature matrix and key time steps, a machine learning model is used to predict the patient's future health status and output the patient's health risk assessment results; S74. Based on the patient's health status prediction results and historical nursing records, the Mahalanobis distance is used to calculate the similarity of health characteristics between the patient and a set of similar patients, and the collaborative filtering algorithm is used to calculate the nursing plan score to generate a nursing recommendation plan; S75. Based on the nursing recommendation plan, a time-series collaborative multi-task learning framework is constructed to jointly optimize the patient health status prediction and nursing recommendation plan, and dynamically adjust the nursing recommendation plan; S76, based on the dynamically adjusted nursing recommendation plan and the dynamic health data stream, calculating the nursing intervention state vector, and using the optimization function to calculate the optimal nursing intervention decision vector; S77. Based on the execution feedback of the nursing intervention decision vector, update the patient's historical nursing records, and synchronously adjust the nursing intervention state vector and nursing recommendation plan.

Images