Information management method and system for smart ward, medium and program product

Abstract

The invention discloses an information management method and system for a smart ward, a medium and a program product, and relates to the field of electrical digital data processing.The method comprises the steps that physiological index data and behavior characteristic data of a target patient are collected, and a characteristic data sequence is constructed; analyzing each piece of data in the feature data sequence, and determining a current characterization behavior and a behavior change sequence of the target patient; obtaining individual information of a patient, and inputting the individual information of the patient, the current characterization behavior and the behavior change sequence into a behavior evaluation model to obtain a risk characterization behavior and a behavior risk score; determining an early warning level and an early warning response time limit based on the behavior risk score; when the early warning level is higher than a preset early warning threshold value, generating a task execution list according to the early warning response time limit and the risk characterization behavior, and sending the task execution list to the medical care terminal; and updating the behavior risk score according to an early warning response result returned by the medical terminal. By implementing the application, patient state monitoring of the smart ward can be optimized, and potential safety hazards can be avoided to a greater extent.

Description

Technical Field

[0001] The present application relates to the field of electronic digital data processing, and in particular to an information management method, system, medium and program product for a smart ward. Background Art

[0002] With the rapid development of medical information technology, smart wards have become an important part of modern hospital construction. Among them, the management of non-cooperative patients is a key link in medical safety and nursing quality. Due to factors such as surgical anesthesia and disease, non-cooperative patients may experience confusion, abnormal behavior, etc., and potential risks need to be predicted and prevented in a timely manner to ensure patient safety.

[0003] In related technologies, medical institutions mainly use bedside monitoring equipment to monitor patients in real time, and set thresholds for vital signs to trigger alarms. At the same time, medical staff rely on fixed nursing inspections and video surveillance to judge the patient's condition based on experience. Some hospitals have also established a patient classification management system to increase the frequency of inspections and monitoring for high-risk patients.

[0004] However, single vital sign monitoring is difficult to reflect changes in the patient's overall condition, and fixed patrol methods and experience-based judgments lead to heavy workloads for medical staff and are prone to blind spots in monitoring. When the number of patients increases, the existing manual patrol mode is difficult to ensure timely detection and handling of emergencies, posing a safety hazard. Summary of the invention

[0005] The present application provides an information management method, system, medium and program product for a smart ward, which are used to optimize patient status monitoring in smart wards and avoid safety hazards to a greater extent.

[0006] In a first aspect, the present application provides an information management method for a smart ward, which is applied to a smart ward management system, and the method includes: real-time collection of physiological indicator data and behavioral characteristic data of a target patient to construct a characteristic data sequence; the physiological indicator data include heart rate, blood pressure, body temperature and blood oxygen saturation, and the behavioral characteristic data include frequency of body position changes, amplitude of limb movement and characteristic value of bed leaving sign; each data in the characteristic data sequence is analyzed according to the historical time series to determine the current characterization behavior and behavior change sequence of the target patient; the behavior change sequence includes one or more characterization behaviors of the target patient within a preset time period; the individual patient information of the target patient is obtained, and the individual patient information, the current characterization behavior and the behavior change sequence are input into a behavior assessment model to obtain risk characterization behavior and behavior risk score; the individual patient information includes the age, medical history, type of surgery, anesthesia method and medication status of the target patient; based on the behavioral risk score, the warning level and the warning response time limit are determined; when the warning level is higher than the preset warning threshold, a task execution list is generated according to the warning response time limit and the risk characterization behavior; the task execution list is sent to the medical terminal, and the behavioral risk score is updated according to the warning response result returned by the medical terminal.

[0007] In the above embodiment, the smart ward management system collects physiological indicators and behavioral characteristic data in real time and conducts behavioral assessments in combination with individual patient information. It can not only identify potential risk behaviors at an early stage, but also automatically generate task lists based on warning levels and continuously update risk scores, thereby achieving dynamic monitoring and early warning management of patient status and improving the level of patient safety protection.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the steps of analyzing each data in the characteristic data sequence according to historical time series to determine the current characterization behavior and behavior change sequence of the target patient specifically include: segmenting the characteristic data sequence based on a preset time window to obtain multiple data segments; extracting feature vectors of the data segments, and inputting the feature vectors into a behavior recognition model to obtain the characterization behavior type corresponding to the data segment; sorting multiple characterization behavior types in chronological order to generate a behavior change sequence; and updating the current characterization behavior of the target patient in real time based on the behavior change sequence.

[0009] In the above embodiment, the smart ward management system analyzes data in segments through preset time windows, extracts feature vectors for behavior recognition and sequence sorting, and achieves accurate quantification and dynamic tracking of patient behavior changes. It can identify abnormal behavior patterns in a timely manner, making risk warnings more timely.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the steps of determining the warning level and the warning response time limit based on the behavioral risk score specifically include: determining the initial warning level corresponding to the behavioral risk score according to multiple preset score intervals; obtaining medical and nursing configuration information including hospital department type, ward type and medical staff on duty; based on the medical and nursing configuration information, determining the warning response variables including department risk coefficient, ward congestion and medical staff workload; based on the warning response variables and the initial warning level, determining the warning level and the warning response time limit.

[0011] In the above embodiment, the smart ward management system determines the warning level based on the risk score, and at the same time, based on the medical configuration information and response variables, realizes the precision of warning classification and the rationalization of warning response, effectively balances the allocation of medical resources, and improves practicality.

[0012] In combination with some embodiments of the first aspect, in some embodiments, before the step of collecting physiological indicator data and behavioral characteristic data of the target patient in real time and constructing a characteristic data sequence, the method also includes: obtaining individual patient information of the target patient; based on the individual patient information, determining initial monitoring settings including monitoring frequency and monitoring parameters; and starting status monitoring of the target patient according to the initial monitoring settings.

[0013] In the above embodiment, the smart ward management system formulates initial monitoring settings by obtaining individual patient information, thereby realizing personalized configuration of monitoring parameters, making the monitoring plan more scientific and reasonable, and improving monitoring efficiency and accuracy.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of starting status monitoring of the target patient according to the initial monitoring settings, the method also includes: when the warning level is higher than the preset warning threshold, sending a warning prompt message to the user terminal of the target patient; adjusting the initial monitoring settings to backup monitoring settings, and performing status monitoring of the target patient according to the backup monitoring settings.

[0015] In the above embodiment, the smart ward management system automatically adjusts to the backup monitoring setting when the early warning is triggered, and sends a prompt to the patient terminal, thereby realizing dynamic adjustment of the monitoring intensity and timely reminder of the patient, and enhancing the timeliness and effectiveness of monitoring.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of sending the task execution list to the medical terminal and updating the behavioral risk score based on the early warning response results returned by the medical terminal, the method also includes: updating the current characterization behavior and behavior change sequence of the target patient, and generating a nursing record based on the behavior change sequence and the early warning response results; based on the nursing records, performing statistical analysis on the early warning response of the medical terminal to obtain nursing quality indicators including response timeliness rate, treatment accuracy rate and patient prognosis score; generating a nursing evaluation report based on the nursing quality indicators and preset nursing standards.

[0017] In the above embodiment, the smart ward management system generates nursing records and performs statistical analysis to obtain nursing quality indicators and generate evaluation reports, thereby achieving full-process tracking and quality evaluation of nursing work.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of generating a nursing assessment report based on nursing quality indicators and preset nursing standards, the method also includes: extracting corresponding nursing improvement suggestions from a preset nursing expert knowledge base based on the nursing assessment report; generating a nursing quality improvement plan based on the nursing improvement suggestions and individual patient information of the target patients; the nursing quality improvement plan includes nursing process optimization suggestions, medical staff training plans and medical equipment configuration suggestions; based on the nursing quality improvement plan, constructing a nursing quality tracking task including assessment indicators, improvement goals and time nodes.

[0019] In the above embodiment, the smart ward management system extracts nursing improvement suggestions and generates quality improvement plans, constructs quality tracking tasks, and achieves continuous optimization and standardized management of nursing quality.

[0020] In a second aspect, an embodiment of the present application provides a smart ward management system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the smart ward management system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions. When the above-mentioned computer program product is run on a smart ward management system, the above-mentioned smart ward management system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions. When the instructions are executed on a smart ward management system, the smart ward management system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0023] It can be understood that the smart ward management system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the adoption of multi-dimensional data collection and intelligent analysis mechanism, the patient's physiological indicators and behavioral characteristics data are collected in real time, and comprehensive evaluation is performed in combination with the patient's individual information. Therefore, potential risks can be discovered in a timely manner and task lists can be automatically generated, which effectively solves the problems of incomplete single monitoring indicators and low efficiency of manual inspections in existing technologies, thereby realizing the intelligent monitoring of patient status and the precision of early warning management, and improving the level of patient safety protection.

[0025] 2. Due to the adoption of an intelligent configuration mechanism for monitoring parameters based on individual patient information, a personalized monitoring plan is formulated based on the patient's specific situation, so differentiated monitoring can be carried out according to the characteristics of different patients, effectively solving the problem of unified and lack of targeted monitoring plans in existing technologies, thereby achieving accurate setting of monitoring parameters and efficient use of monitoring resources, and improving the effectiveness of patient monitoring.

[0026] 3. Due to the use of automatic generation and quality assessment system of nursing records, systematic statistical analysis of early warning response situations and generation of standardized assessment reports, the quality of nursing work can be fully grasped, effectively solving the problems of strong subjectivity and lack of quantitative standards in nursing quality assessment in existing technologies, thereby achieving accurate assessment and continuous improvement of nursing quality, providing reliable guarantee for improving the level of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a flowchart of the information management method of the smart ward in the embodiment of the present application; Figure 2 This is another flowchart of the information management method of the smart ward in the embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of the smart ward management system in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] It should be noted that in this application, all devices involving monitoring image recognition functions (image recognition devices) are equipped with eye-catching monitoring reminder signs in the corresponding areas for video monitoring and image acquisition. The monitoring data is strictly confidential and has been authorized by the monitored person.

[0031] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below.

[0032] In the neurosurgery ward of a certain hospital, Mr. Zhang, a postoperative patient, became confused due to the effects of anesthetic drugs. Xiao Li, a night nurse, discovered through routine inspections that the patient was agitated, but she could not continue monitoring him because she had to take care of multiple patients at the same time. When she made her next rounds, she found that Mr. Zhang had fallen, causing the surgical incision to split. This situation occasionally occurs in hospitals, especially at night when there is a shortage of staff. It is difficult to detect changes in the patient's condition in time by relying solely on manual inspections, which poses a major safety hazard.

[0033] In related technologies, basic monitoring and early warning of patient status can be achieved by using bedside monitoring equipment to monitor vital signs in real time, manual inspections at fixed time intervals, and simple video monitoring. The following introduces the scenario of using the information management method of the smart ward in related technologies.

[0034] A hospital uses traditional bedside monitoring equipment to monitor postoperative patients, sets alarm thresholds for vital signs such as heart rate and blood pressure, and installs a video surveillance system. Nurse Wang is responsible for monitoring an elderly patient with a high risk of postoperative delirium. However, when the patient's heart rate and blood pressure are within the normal range, the video surveillance shows that the patient has restless body movements, but the system cannot determine the risk level of this behavior. By the time the vital signs exceed the threshold and trigger the alarm, the patient has become restless, and because the monitoring screen cannot accurately identify the patient's specific current behavior, the timing of treatment is delayed.

[0035] By adopting the information management method of the smart ward in the embodiment of the present application, comprehensive monitoring of the patient's status and early warning of risks can be achieved through multi-source data collection and behavior warning mechanism, so that potential risks can be discovered in time. The following introduces the scenario in which the information management method of the smart ward in the present application is used.

[0036] After the hospital introduced the smart ward management system, the system collected the physiological indicators and behavioral data of Mr. Li in real time through multi-source sensors. When the system detected a slight fluctuation in the patient's heart rate and the posture sensor showed that the patient's activities increased frequently, data fusion analysis was immediately performed. Combined with the patient's personal information of high risk of postoperative delirium, the system issued an early warning. After receiving the warning, the nurse quickly arrived at the ward and found that the patient did have early symptoms of agitation. He immediately took corresponding measures and successfully prevented possible accidents.

[0037] It can be seen that the use of the smart ward information management method in the embodiment of the present application can not only realize patient safety monitoring, but also effectively solve the problems of low efficiency of manual inspections, incomplete monitoring of single indicators, and insufficient and accurate early warning, thereby realizing intelligent and precise patient safety management.

[0038] For ease of understanding, the following describes the process of the method provided by this implementation in combination with the above scenario. Figure 1 , which is a flow chart of the information management method of the smart ward in an embodiment of the present application.

[0039] S101. Collect physiological index data and behavioral characteristic data of target patients in real time and construct characteristic data sequences.

[0040] Among them, the target patient refers to the inpatient currently under monitoring. Physiological indicator data refers to the data reflecting the patient's vital signs collected by medical equipment, including heart rate, blood pressure, body temperature and blood oxygen saturation. Behavioral characteristic data is used to represent the patient's action state information, including the frequency of body position changes, the amplitude of limb movement and the characteristic value of bed leaving sign. The characteristic data sequence represents a multi-dimensional data set arranged in an array in chronological order.

[0041] The smart ward management system starts the data collection process when the patient is admitted to the hospital and begins monitoring. Specifically, the system collects physiological indicator data through bedside monitors, collects behavioral feature data through motion capture cameras, body motion sensors or pressure sensors, and integrates the collected data into feature data sequences according to unified time tags and data formats to achieve real-time monitoring of the patient's status.

[0042] It should be noted that for the collection process of behavioral characteristic data, the smart ward management system can use multi-source sensors to work together to monitor the patient's status in real time. The mattress pressure sensor array continuously collects pressure distribution data through a high-precision pressure detection unit, and cooperates with the depth camera installed on the bedside to capture spatial motion. The two types of data are fused in time series to form an accurate portrait of the patient's position and activity. The system analyzes these raw data in real time, extracts characteristic parameters such as the frequency of position changes and the amplitude of activity, and combines historical behavior patterns to establish a prediction model for the intention to leave the bed, thereby achieving all-round monitoring of patient behavior.

[0043] S102: Analyze each data in the characteristic data sequence according to the historical time series to determine the current characteristic behavior and behavior change sequence of the target patient.

[0044] Among them, the historical time series refers to the time sequence of data collection. The data segment refers to the continuous data set divided by time window. The current representation behavior is used to represent the real-time behavior state of the target patient. The behavior change sequence represents the evolution process of the patient's behavior over a period of time.

[0045] The smart ward management system immediately conducts data analysis after completing data collection. Specifically, the system first segments the feature data sequence according to the preset time window, extracts the feature vector of each data segment, and identifies the corresponding behavior type through the behavior recognition model. Then, the identified behavior types are arranged in chronological order to generate a behavior change sequence, and the patient's current representation behavior is updated in real time to achieve dynamic tracking of the patient's behavior.

[0046] In terms of behavior recognition, the smart ward management system has established a hierarchical behavior classification system. First, the patient's behavior is divided into four main categories: static behavior, routine activities, abnormal behavior, and dangerous behavior. Each category is further subdivided into multiple specific behavior types. By setting different feature thresholds and timing patterns, the system can accurately identify various behaviors from quiet rest to intense activities. In particular, for the identification of abnormal behaviors, the system will improve the recognition accuracy through multi-dimensional feature analysis based on the duration of the behavior, change trends, and environmental factors.

[0047] In some embodiments, data analysis and behavior recognition can be achieved in a variety of ways: optionally, using a sliding time window to segment data; using wavelet transform to extract time and frequency domain features; identifying behavior types through deep learning models; and building a time series behavior map. Optionally, data segmentation based on statistical features; extracting time and frequency domain features; using traditional machine learning methods such as decision trees to identify behaviors; and building a behavior state transition matrix. It is understandable that other data processing and behavior recognition methods can also be used to achieve behavior analysis, which is not limited here.

[0048] S103. Obtain individual patient information of the target patient, input the individual patient information, current representative behavior, and behavior change sequence into a behavior assessment model, and obtain risk representative behavior and behavior risk score.

[0049] Among them, individual patient information represents a set of key factors that affect patient behavior risk, including the target patient's age, medical history, surgery type, anesthesia method, and medication status. The behavior assessment model refers to a machine learning model used to assess patient behavior risk. Risk characterization behavior is used to represent dangerous behaviors that may lead to adverse events. The behavior risk score represents the quantitative risk assessment result of the patient's current state.

[0050] The smart ward management system performs risk assessment after obtaining patient behavior data. Specifically, the system obtains individual information such as the patient's age, medical history, type of surgery, anesthesia method, and medication from the electronic medical record, and inputs this information into the pre-trained behavior assessment model together with the current representation behavior and behavior change sequence. The model will output specific risk representation behavior types and corresponding risk scores to achieve intelligent assessment of patient behavior risks. The risk assessment link here can adopt a dynamic weighted scoring mechanism. The system first calculates the basic risk score based on the patient's individual information, including the influence of factors such as age, disease severity, and type of surgery. Then the current behavior risk weight is combined with the behavior sequence analysis results, and the time factor (such as night risk weighting) is added to regulate the risk level. The final risk score is obtained by weighted fusion of multiple dimensions and normalized to ensure the consistency and comparability of the score.

[0051] It should be noted that, specifically for the behavioral assessment model, during the model training phase, the smart ward management system will collect a large amount of historical patient data as training samples, including patients' physiological indicator data (heart rate, blood pressure, body temperature, blood oxygen saturation), behavioral characteristic data (frequency of body position changes, limb movement amplitude, bed leaving sign characteristic value), patient individual information (age, medical history, type of surgery, anesthesia method, medication status) and actual adverse event records of these patients (such as falls, accidental bed leaving, etc.). During the training process, the model uses machine learning algorithms, especially time series data analysis methods, to learn the association pattern between these input features and the risk of adverse events, with the optimization goal of minimizing prediction errors, and at the same time ensure the generalization ability of the model through cross-validation.

[0052] The behavior assessment model adopts a deep learning architecture, including a feature extraction layer, a time series processing layer, and a risk assessment layer. The feature extraction layer normalizes and fuses the input multimodal data, the time series processing layer uses recurrent neural network structures such as LSTM or GRU to capture the time evolution characteristics of the patient's status, and the risk assessment layer maps the extracted features to specific risk characterization behavior categories and corresponding risk scores.

[0053] By inputting the target patient's physiological indicator data, behavioral characteristic data, individual patient information, and the current representative behavior and behavior change sequence obtained through time series analysis in real time, the behavioral assessment model can process these data and output two key results: one is the identified specific risk representative behavior (such as the risk of falling, risk of leaving bed, etc.), and the other is the corresponding behavioral risk score (usually a quantitative score of 0-100). These output results directly support the subsequent warning level determination and warning response process. The model can also conduct online learning and optimization based on the warning response results of medical staff to continuously improve the prediction accuracy.

[0054] S104. Determine the warning level and warning response time limit based on the behavioral risk score.

[0055] The warning level indicates the classification result of the risk level. The warning response time limit refers to the maximum time required for medical staff to respond and handle the situation.

[0056] The smart ward management system determines the specific early warning plan after obtaining the risk score. Specifically, the system first determines the initial warning level according to the preset score range, and then combines the hospital department type, ward type, and medical staff on duty and other medical configuration information to calculate the department risk coefficient, ward congestion, and medical staff workload and other early warning response variables, and finally determines the actual early warning level and the corresponding response time limit. In the process of determining the early warning level, the system constructs an adaptive grading standard. By analyzing historical early warning data, a corresponding relationship between risk score and early warning level is established. At the same time, based on the real-time status of medical resources, when an early warning occurs, the system will dynamically adjust the response time limit according to factors such as the current department characteristics, staffing and workload to ensure the scientificity and executability of the early warning. For high-risk early warnings, the system will also start a multi-level linkage mechanism to ensure a rapid response.

[0057] In some embodiments, the warning level can be determined in a variety of ways: optionally, a multi-level warning threshold system is established; the weight of environmental factors is calculated; the warning level is dynamically adjusted; and the response time limit configuration is optimized. Optionally, fuzzy set theory is used to divide the levels; a medical resource load model is established; warning parameters are updated in real time; and the response time limit is adaptively adjusted. It is understandable that other grading methods and time limit determination methods can also be used to implement warning management, which are not limited here.

[0058] S105. When the warning level is higher than the preset warning threshold, a task execution list is generated according to the warning response time limit and risk characterization behavior.

[0059] The preset warning threshold represents the risk scoring criteria for triggering the warning. The task execution list refers to a list of specific intervention measures formulated for risky behaviors.

[0060] The smart ward management system generates specific execution tasks after the warning is triggered. Specifically, the system automatically generates a task execution list containing specific intervention measures, execution steps and task priorities based on the warning level, warning response time limit and identified risk characterization behavior, providing standardized handling guidance for medical staff.

[0061] In some embodiments, task list generation can be achieved in a variety of ways: optionally, matching intervention measures based on a knowledge base; generating standard operating procedures; determining task priorities; and developing alternative plans. Optionally, developing tasks in conjunction with clinical pathways; assigning execution roles and permissions; setting task completion standards; and establishing task dependencies. It is understandable that other task planning and generation methods can also be used to achieve task list management, which is not limited here.

[0062] S106. Send the task execution list to the medical terminal, and update the behavior risk score according to the early warning response result returned by the medical terminal.

[0063] The medical terminal refers to the mobile device or workstation used by medical staff. The early warning response result refers to the specific record of the medical staff's execution of the task.

[0064] The smart ward management system distributes and tracks tasks after generating a task list. Specifically, the system pushes the task execution list to the terminal devices of relevant medical staff. After completing the corresponding tasks, the medical staff will feedback the handling situation through the terminal. The system updates the patient's behavioral risk score based on the feedback results, realizing closed-loop management of early warning response.

[0065] In some embodiments, task distribution and score update can be implemented in a variety of ways: optionally, establish a multi-level task push mechanism; record the task execution process; evaluate the response effect; dynamically update the risk score. Optionally, use a workflow engine to manage tasks; synchronize execution status in real time; analyze response data; optimize the risk assessment model. It is understandable that other task management and score update methods can also be used to implement early warning response management, which is not limited here.

[0066] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the information management method of the smart ward in the embodiment of the present application.

[0067] S201. Obtain individual patient information of a target patient.

[0068] The smart ward management system starts the information collection process when the patient is admitted to the hospital. Specifically, the system obtains the patient's basic information through the electronic medical record system, extracts medical information such as disease diagnosis and treatment plans from the clinical information system, and collects the patient's special circumstances and risk factors in combination with the admission assessment form to achieve comprehensive collection of patient information. Basic information refers to the patient's age, gender and other demographic characteristics. Clinical information is used to represent the patient's medical history, diagnosis and treatment-related information. Risk factors refer to various factors that may affect the patient's safety, including a history of falls, cognitive function, etc. In some embodiments, the patient's individual information may also be the information in step S103 above, specifically including the target patient's age, medical history, type of surgery, anesthesia method and medication.

[0069] In some embodiments, patient information acquisition can be achieved in a variety of ways: optionally, connecting to the hospital HIS system to automatically extract basic information; calling the electronic medical record interface to obtain clinical information; entering assessment information through a mobile terminal; establishing an information integrity verification mechanism. Optionally, designing a standardized information collection form; using face recognition to automatically associate patient files; entering additional information through voice; and updating information synchronously in real time. It is understandable that other information collection and management methods can also be used to achieve patient information acquisition, which is not limited here.

[0070] S202: Determine initial monitoring settings including monitoring frequency and monitoring parameters based on individual patient information.

[0071] The monitoring frequency refers to the time interval for data collection. The monitoring parameters refer to the specific indicators that need to be monitored. The initial monitoring settings are used to represent the basic configuration plan at the beginning of the monitoring stage.

[0072] The smart ward management system formulates a monitoring plan after completing information collection. Specifically, the system automatically determines the configuration parameters such as monitoring indicator selection, sampling frequency, parameter threshold and sampling accuracy based on individual information such as the patient's age, disease severity, and surgery type, combined with clinical guidelines and expert rules, to form a personalized initial monitoring plan. The setting of monitoring frequency and monitoring parameters can be automatically planned based on historical data, or adjusted based on user settings through a dedicated visual interface on the system.

[0073] In some embodiments, the monitoring plan can be formulated in a variety of ways: optionally, establish a patient classification system; configure corresponding monitoring templates; automatically adjust parameter thresholds; optimize sampling strategies. Optionally, set up a monitoring plan in combination with a clinical pathway; apply fuzzy reasoning to determine the monitoring frequency; establish multi-level warning thresholds; configure data quality control parameters. It is understandable that other plan formulation methods can also be used to determine the monitoring settings, which are not limited here.

[0074] S203. Start status monitoring of the target patient according to the initial monitoring settings.

[0075] The smart ward management system starts the monitoring process after determining the monitoring plan. Specifically, the system automatically configures the working parameters of monitoring equipment such as motion capture cameras, bedside monitors, and body motion sensors according to the initial monitoring settings, establishes data collection channels, selects appropriate monitoring modes, and starts real-time data collection and signal quality monitoring to ensure the accuracy and continuity of monitoring data.

[0076] In some embodiments, the status monitoring can be started in a variety of ways: optionally, executing the device self-test program; establishing a data transmission connection; configuring acquisition parameters; starting real-time monitoring. Optionally, initializing the monitoring module; calibrating sensor parameters; verifying data integrity; establishing a backup mechanism. It is understandable that other monitoring startup methods can also be used to implement patient status monitoring, which is not limited here.

[0077] S204: Collect physiological index data and behavioral characteristic data of the target patient in real time and construct a characteristic data sequence.

[0078] Referring to step S101, the smart ward management system will construct a feature data sequence.

[0079] S205. Analyze each data in the characteristic data sequence according to the historical time series to determine the current characteristic behavior and behavior change sequence of the target patient.

[0080] Referring to step S102 , the smart ward management system determines the current representative behavior and the behavior change sequence.

[0081] In some embodiments, the smart ward management system segments the feature data sequence based on a preset time window to obtain multiple data segments; extracts the feature vectors of the data segments, and inputs the feature vectors into the behavior recognition model to obtain the representation behavior types corresponding to the data segments; sorts the multiple representation behavior types in chronological order to generate a behavior change sequence; and based on the behavior change sequence, updates the current representation behavior of the target patient in real time.

[0082] The preset time window represents a fixed data collection time period. The data segment refers to a continuous data set divided by a time window. The feature vector is used to represent the key feature combination of the data segment. The behavior recognition model represents an algorithm model that maps the feature vector to a behavior type. The characterization behavior type refers to the classification of the patient's specific behavior state. The behavior change sequence is used to represent the temporal change process of the patient's behavior state.

[0083] The smart ward management system starts the behavior recognition process after completing data collection. Specifically, the system first segments the continuously collected data according to the preset time window (such as 15 minutes), extracts multi-dimensional feature vectors such as time domain features and frequency domain features from each data segment, inputs the pre-trained behavior recognition model for behavior classification, obtains the main behavior types in each time window, and then arranges these behavior types in chronological order to form a behavior change sequence, which is used to update the patient's current status in real time.

[0084] It should be noted that the behavior recognition model uses a large amount of annotated patient behavior data as a training set during model training, including physiological indicator data (heart rate, blood pressure, body temperature, blood oxygen saturation) and behavioral feature data (frequency of body position changes, amplitude of limb movement, characteristic values ​​of bed leaving signs), etc., combined with the actual behavior types annotated by medical staff (such as quiet bed rest, restlessness, trying to leave the bed, etc.) for supervised learning, and optimizes model parameters by minimizing prediction errors. The behavior recognition model adopts a deep learning architecture, including a feature extraction layer, a time series processing layer, and a classification layer. The feature extraction layer is used to process multimodal input data, the time series processing layer uses LSTM or GRU structure to capture time series features, and the classification layer outputs the probability distribution of behavior types. By inputting multidimensional feature data in the current time window, the behavior recognition model can output the corresponding behavior type and provide the confidence of behavior recognition.

[0085] S206. Obtain individual patient information of the target patient, input the individual patient information, current representative behavior, and behavior change sequence into a behavior assessment model, and obtain risk representative behavior and behavior risk score.

[0086] Referring to step S103, the smart ward management system generates risk characterization behaviors and behavior risk scores.

[0087] S207. Determine the warning level and warning response time limit based on the behavioral risk score.

[0088] Referring to step S104, the smart ward management system will determine the warning level and warning response time limit.

[0089] In some embodiments, the smart ward management system determines the initial warning level corresponding to the behavioral risk score based on multiple preset score intervals; obtains medical configuration information including hospital department type, ward type and medical staff on duty; based on the medical configuration information, determines the warning response variables including department risk coefficient, ward congestion and medical staff workload; based on the warning response variables and the initial warning level, determines the warning level and warning response time limit.

[0090] Among them, the score range represents the score range corresponding to different warning levels. The initial warning level refers to the preliminary classification result based on the risk score. Medical and nursing configuration information is used to represent the current status of medical resources. The department risk coefficient represents the inherent risk level of different departments. Ward crowding refers to the ward utilization rate and patient density. The warning response variable represents the environmental factors that affect the adjustment of the warning level. The warning response time limit is used to represent the maximum time required for disposal.

[0091] The smart ward management system determines the warning level after obtaining the risk score. Specifically, the system first determines the initial warning level according to the preset score range (such as 0-30 points, 31-60 points, 61-90 points, etc.), and then obtains information such as the current hospital department type, ward occupancy and duty personnel configuration, calculates variables including department risk coefficient (such as the high risk coefficient of the intensive care department), ward crowding and medical staff workload, and dynamically adjusts the initial warning level based on these factors, and finally determines the actual warning level and the corresponding response time limit. The determination of the warning level can be achieved in a variety of ways: optionally, establish a multi-level warning threshold system; calculate the weights of various influencing factors; execute the warning level adjustment algorithm; generate the response time limit configuration. Optionally, use fuzzy logic to divide the level; construct a medical resource load model; dynamically update the warning parameters; optimize the response time allocation. It is understandable that other grading methods and time limit determination methods can also be used to achieve warning management, which is not limited here.

[0092] It should be noted that the specific warning level and response time limit can be determined using a behavioral warning model. The behavioral warning model is based on historical warning case data, including medical and nursing configuration information (department type, staffing), environmental factors (ward crowding, workload) and actual warning response records during model training, and the training model learns the dynamic adjustment rules of the warning level. The training standard is to optimize the accuracy and timeliness of the warning. The behavioral warning model combines a rule engine and a machine learning method, and includes a warning level determination module, an environmental factor evaluation module and a time limit calculation module. The rule engine handles deterministic logic, and the machine learning part handles dynamic adjustment. By inputting risk scores and medical and nursing configuration information, the behavioral warning model can combine the current environmental factors to output the final warning level (such as low, medium, and high risks) and specific response time limits (such as 5 minutes, 15 minutes, 30 minutes, etc.).

[0093] S208. When the warning level is higher than the preset warning threshold, a task execution list is generated according to the warning response time limit and risk characterization behavior.

[0094] Referring to step S105, the smart ward management system will generate a task execution list.

[0095] S209: Send the task execution list to the medical terminal, and update the behavior risk score according to the early warning response result returned by the medical terminal.

[0096] Referring to step S106, the smart ward management system will update the behavior risk score.

[0097] S210: When the warning level is higher than a preset warning threshold, a warning prompt message is sent to a user terminal of the target patient.

[0098] The user terminal refers to a mobile device used by the patient or family member. The early warning information refers to the risk reminders and precautions sent by the system.

[0099] The smart ward management system initiates enhanced monitoring when a high-risk state is detected. Specifically, the system sends precautionary reminders and early warning information to the patient terminal to ensure that the patient and his family understand the current situation and cooperate with the monitoring.

[0100] S211. Adjust the initial monitoring setting to the backup monitoring setting, and perform status monitoring on the target patient according to the backup monitoring setting.

[0101] Among them, the backup monitoring setting represents the enhanced monitoring plan under risk conditions.

[0102] The smart ward management system will also start adjusting the monitoring plan when a high-risk state is detected. Specifically, the system automatically increases the monitoring level according to the current warning level, increases the data collection density, adjusts the monitoring indicator weight, improves the alarm sensitivity, and implements enhanced monitoring of high-risk patients. Monitoring level refers to monitoring levels of different intensities. Data collection density is used to indicate the number of sampling times per unit time. Monitoring indicator weights indicate the importance of different indicators. Alarm sensitivity refers to the sensitivity of the system to trigger an alarm. Modifications to monitoring settings can also be pushed to the user terminal synchronously through warning prompt information.

[0103] In some embodiments, the monitoring settings can be adjusted in a variety of ways: optionally, switching to a high-frequency sampling mode; enabling additional monitoring parameters; lowering the alarm threshold; turning on continuous recording. Optionally, activating a backup sensor; increasing sampling accuracy; adjusting signal filtering parameters; configuring a real-time analysis module. It is understandable that other settings adjustment methods can also be used to optimize the monitoring solution, which is not limited here.

[0104] S212. Update the current representative behavior and behavior change sequence of the target patient, and generate a nursing record according to the behavior change sequence and the early warning response result.

[0105] Among them, nursing records refer to the standardized records of the nursing process. Behavior change sequence refers to the time-series record of the patient's behavior status. Early warning response results are used to indicate the treatment status of medical staff.

[0106] The smart ward management system generates nursing documents after completing the early warning response. Specifically, the system updates the patient's behavioral status information, associates the behavioral change sequence with the early warning response results, and automatically generates nursing records containing patient status, treatment measures, and effect evaluation according to standardized templates.

[0107] In some embodiments, the generation of nursing records can be achieved in a variety of ways: optionally, collecting early warning response data; integrating behavior change information; filling in record templates; verifying record integrity. Optionally, extracting key event information; building a nursing pathway map; generating standardized documents; and establishing a document index. It is understandable that other record generation methods can also be used to achieve nursing document management, which is not limited here.

[0108] S213. Based on the nursing records, statistical analysis is performed on the early warning response of the medical terminal to obtain nursing quality indicators including response timeliness rate, treatment accuracy rate and patient prognosis score.

[0109] Among them, nursing quality indicators represent quantitative parameters for measuring the quality of nursing work. Timely response rate refers to the proportion of early warning responses completed within the specified time limit. Disposition accuracy rate is used to indicate the correct implementation degree of nursing measures.

[0110] The smart ward management system conducts quality analysis after accumulating a certain amount of nursing records. Specifically, the system conducts data mining on nursing records within the preset statistical period, calculates indicators such as the warning response time of medical staff, the compliance of treatment measures, and the patient's recovery status, and evaluates the nursing quality level through multi-dimensional analysis to provide data support for nursing management decisions.

[0111] In some embodiments, nursing quality analysis can be implemented in a variety of ways: optionally, establishing a multi-dimensional evaluation system; performing data statistical analysis; generating trend charts; identifying abnormal patterns; and outputting analysis reports. Optionally, building a quality control model; calculating core quality indicators; performing comparative analysis over the same period; evaluating improvement effects; and tracking quality changes. It is understandable that other analysis methods can also be used to implement nursing quality assessment, which is not limited here.

[0112] S214. Generate a nursing assessment report based on nursing quality indicators and preset nursing standards.

[0113] Among them, the nursing evaluation report represents a comprehensive evaluation document of nursing quality. The preset nursing standard refers to the standardized nursing quality requirements. The evaluation dimension is used to represent different angles of quality evaluation. The improvement suggestion represents the optimization plan for the problem. The evaluation grade refers to the graded result of the quality evaluation.

[0114] The smart ward management system generates an evaluation report after completing the quality analysis. Specifically, the system compares the nursing quality indicators with the preset nursing standards, evaluates from the dimensions of nursing timeliness, standardization, effectiveness, etc., determines the evaluation level, and automatically generates an evaluation report containing the quality status, problem analysis and improvement suggestions based on the analysis results. In terms of nursing quality evaluation, the system has established a comprehensive quality monitoring system. By tracking the entire early warning response process, the system calculates core indicators such as nursing response timeliness, disposal accuracy, and patient prognosis improvement. These indicators not only reflect the quality of a single nursing session, but also reflect the overall changes in nursing quality through trend analysis. The system will regularly generate quality analysis reports and match improvement suggestions according to the problem type to form a closed-loop management of continuous improvement.

[0115] In some embodiments, the smart ward management system will extract corresponding nursing improvement suggestions from the preset nursing expert knowledge base based on the nursing assessment report; generate a nursing quality improvement plan based on the nursing improvement suggestions and the individual patient information of the target patients; the nursing quality improvement plan includes nursing process optimization suggestions, medical staff training plans and medical equipment configuration suggestions; based on the nursing quality improvement plan, construct a nursing quality tracking task including assessment indicators, improvement goals and time nodes.

[0116] Among them, the nursing expert knowledge base represents a standardized collection of nursing experience. Nursing improvement suggestions refer to solutions to problems. Nursing quality improvement plans are used to represent systematic improvement plans. Assessment indicators represent quantitative standards for evaluating improvement effects. Improvement goals refer to the quality level expected to be achieved. Time nodes are used to represent key time points for task execution.

[0117] Nursing quality tracking adopts a goal-oriented management approach. The smart ward management system sets clear target values ​​and time nodes for each improvement project, and monitors the implementation and effectiveness of improvement measures through real-time data collection and analysis. During the tracking process, the system will dynamically adjust the improvement strategy according to the actual progress to ensure the achievement of improvement goals. At the same time, through regular effect evaluation and feedback, the nursing process and specifications are continuously optimized. The smart ward management system starts the quality improvement process after generating an evaluation report. Specifically, based on the problems found in the evaluation report, the system matches the corresponding improvement suggestions from the nursing expert knowledge base, and formulates personalized improvement plans based on the individual characteristics of the patient, including specific measures such as optimizing the nursing process, formulating training plans, and adjusting equipment configuration. At the same time, a tracking task is established that includes assessment indicators, stage goals, and execution schedules to ensure the effective implementation of the improvement plan.

[0118] In some embodiments, the formulation of quality improvement plans can be achieved in a variety of ways: optionally, analyzing and evaluating reports to find key issues; matching solutions in the knowledge base; formulating personalized improvement plans; setting improvement effect indicators. Optionally, building a problem-solving model; generating multi-dimensional improvement suggestions; formulating an implementation schedule; and establishing a supervisory feedback mechanism. It is understandable that other plan formulation methods can also be used to achieve nursing quality improvement, which is not limited here.

[0119] In the embodiments of the present application, due to the use of intelligent monitoring methods of multi-source data collection and deep learning model analysis, combined with a multi-level early warning mechanism and dynamically optimized disposal plan management, it is possible to achieve comprehensive monitoring of patient status and early warning of risks, effectively solving the problems of low efficiency of manual inspections, incomplete monitoring of single indicators, insufficiently timely and accurate early warnings, and insufficiently personalized disposal plans in traditional monitoring methods, thereby achieving intelligent management of patient safety. Through continuous data accumulation and model optimization, the system's early warning accuracy continues to improve, the disposal effect continues to improve, the efficiency of medical care work is improved, and safety accidents are effectively avoided.

[0120] The following describes the smart ward management system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the structure of a physical device of the smart ward management system in an embodiment of the present application.

[0121] It should be noted that Figure 3The structure of the smart ward management system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0122] like Figure 3 As shown, the smart ward management system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0123] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0124] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0125] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0126] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0127] Specifically, the smart ward management system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the information management method of the smart ward provided in the above embodiment is implemented.

[0128] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the smart ward management system described in the above embodiment; or may exist independently without being assembled into the smart ward management system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the smart ward management system, the smart ward management system implements the smart ward information management method provided in the above embodiment.

[0129] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0130] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0131] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for information management of a smart ward, characterized in that: Applied to the smart ward management system, the method includes: Collect the target patient's physiological index data and behavioral characteristic data in real time to construct a characteristic data sequence; the physiological index data includes heart rate, blood pressure, body temperature and blood oxygen saturation; the behavioral characteristic data includes the frequency of body position changes, the amplitude of limb movement and the characteristic value of bed leaving sign; Analyze each data in the characteristic data sequence according to the historical time sequence to determine the current characteristic behavior and behavior change sequence of the target patient; the behavior change sequence includes one or more characteristic behaviors of the target patient within a preset time period; Obtaining individual patient information of the target patient, inputting the individual patient information, the current representative behavior, and the behavior change sequence into a behavior assessment model to obtain risk representative behavior and a behavior risk score; the individual patient information includes the target patient's age, medical history, surgery type, anesthesia method, and medication status; Determine the warning level and warning response time limit based on the behavior risk score; When the warning level is higher than a preset warning threshold, a task execution list is generated according to the warning response time limit and the risk characterization behavior; The task execution list is sent to the medical terminal, and the behavior risk score is updated according to the early warning response result returned by the medical terminal.

2. The method according to claim 1, characterized in that The step of analyzing each data in the characteristic data sequence according to the historical time sequence to determine the current characteristic behavior and behavior change sequence of the target patient specifically includes: Segmenting the characteristic data sequence based on a preset time window to obtain multiple data segments; Extracting a feature vector of the data segment, and inputting the feature vector into a behavior recognition model to obtain a characterization behavior type corresponding to the data segment; Sorting the plurality of said representative behavior types in chronological order to generate a behavior change sequence; Based on the behavior change sequence, the current representative behavior of the target patient is updated in real time.

3. The method according to claim 1, characterized in that The step of determining the warning level and warning response time limit based on the behavior risk score specifically includes: Determine the initial warning level corresponding to the behavior risk score according to the preset multiple score intervals; Obtain medical and nursing configuration information including hospital department type, ward type and medical staff on duty; Based on the medical and nursing configuration information, determining early warning response variables including department risk coefficient, ward crowding and medical staff workload; Based on the early warning response variable and the early warning initial level, the early warning level and the early warning response time limit are determined.

4. The method according to claim 1, characterized in that: Before the step of collecting the physiological index data and behavioral characteristic data of the target patient in real time and constructing a characteristic data sequence, the method further includes: Acquiring individual patient information of the target patient; Based on the individual patient information, determining initial monitoring settings including monitoring frequency and monitoring parameters; According to the initial monitoring settings, status monitoring of the target patient is started.

5. The method according to claim 4, characterized in that After the step of starting status monitoring of the target patient according to the initial monitoring setting, the method further includes: When the warning level is higher than a preset warning threshold, sending a warning prompt message to the user terminal of the target patient; The initial monitoring setting is adjusted to a backup monitoring setting, and the status of the target patient is monitored according to the backup monitoring setting.

6. The method according to claim 1, characterized in that After the step of sending the task execution list to the medical terminal and updating the behavior risk score according to the early warning response result returned by the medical terminal, the method further includes: Updating the current representative behavior and behavior change sequence of the target patient, and generating a nursing record according to the behavior change sequence and the early warning response result; Based on the nursing records, statistical analysis is performed on the early warning response of the medical terminal to obtain nursing quality indicators including response timeliness rate, treatment accuracy rate and patient prognosis score; Generate a nursing assessment report based on the nursing quality indicators and preset nursing standards.

7. The method according to claim 6, characterized in that After the step of generating a nursing assessment report according to the nursing quality indicator and the preset nursing standard, the method further comprises: According to the nursing assessment report, corresponding nursing improvement suggestions are extracted from a preset nursing expert knowledge base; Generate a nursing quality improvement plan based on the nursing improvement suggestions and the individual patient information of the target patient; the nursing quality improvement plan includes nursing process optimization suggestions, medical staff training plans and medical equipment configuration suggestions; Based on the nursing quality improvement plan, a nursing quality tracking task including assessment indicators, improvement goals and time nodes is constructed.

8. A smart ward management system, characterized in that: The smart ward management system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the smart ward management system to execute the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the smart ward management system, the smart ward management system executes the method as described in any one of claims 1-7.

10. A computer program product, characterized in that When the computer program product runs on a smart ward management system, the smart ward management system executes the method as described in any one of claims 1 to 7.

Images