Ward call management method, system, equipment and medium

Abstract

The invention relates to a ward call management method, system and device and a medium, and belongs to the technical field of medical informatization management, and the management method comprises the steps: receiving call demand information inputted by a patient through a sickbed extension set; collecting current vital sign data of the patient in real time; performing abnormal state evaluation on the current vital sign data according to the health record data; according to the abnormal evaluation result, configuring and adjusting call demand information; matching a corresponding medical care resource list according to the call demand information; medical care terminal equipment closest to the sickbed extension set in the medical care resource list is determined; generating a task instruction according to the call demand information and sending the task instruction to the medical care terminal equipment; receiving a task confirmation signal of the medical care terminal equipment, and updating a current task corresponding to the task instruction to a current task list of the medical care terminal equipment; and updating the task progress state of the current task in real time and storing the task progress state to a task execution log. According to the invention, the timeliness and accuracy of medical services can be improved.

Description

Technical Field

[0001] The present application relates to the field of medical information management technology, and in particular to a ward call management method, system, device and medium. Background Art

[0002] The ward call system is an indispensable part of modern hospital ward management. Its main function is to establish a communication bridge between patients and medical staff, so that patients can timely convey their needs and obtain medical services. Generally speaking, the ward call system includes calling devices on the patient side (such as buttons, voice interaction terminals, etc.), receiving devices on the medical side (such as display screens at nurse stations, mobile terminals, etc.), and background management systems. This system aims to improve the efficiency of ward services, ensure the safety of patients, and improve the overall management level of the hospital.

[0003] Most existing ward call systems transmit needs through patients manually triggering signal devices, such as pressing a bedside call button or voice input through an extension. After receiving the demand signal, the system transmits it to the nurse station or the terminal device of the medical staff, and the medical staff takes corresponding response actions based on the received information. However, due to the lack of detailed classification and hierarchical management of patient needs in the system, when multiple patients call at the same time, the system usually responds in a simple sequence, ignoring the differences in urgency between different needs. This processing method may result in emergency medical needs not being responded to in a timely manner. In addition, the scheduling of medical staff usually relies on manual allocation or a fixed rotation mode. This resource allocation method may further extend the response time when hospital resources are tight or during peak periods, thereby affecting the treatment effect of high-risk patients. Summary of the invention

[0004] In order to improve the timeliness and accuracy of medical services, the present application provides a ward call management method, system, device and medium.

[0005] In the first aspect, the present application provides a ward call management method, which adopts the following technical solution: A ward call management method, the method comprising: Receiving call demand information input by the patient through the bed extension; wherein the call demand information includes the call demand type and demand priority; Collecting the patient's current vital sign data in real time and performing preprocessing; Based on the patient health record database, retrieve the health record data of the patient; Performing an abnormal state assessment on the pre-processed current vital sign data of the patient according to the health record data to obtain an abnormality assessment result; wherein the abnormality assessment result includes an abnormality type and an abnormality severity; Adjust the call demand type and demand priority of the call demand information according to the abnormal evaluation result; Based on the medical resource database, matching the corresponding medical resource list according to the call demand type in the call demand information; Determine, according to the location information of the bed extension, the medical terminal device in the medical resource list that is closest to the bed extension; Generate a task instruction and a task priority according to the call demand information, and send the task instruction to the medical terminal device; Receive a task confirmation signal from the medical terminal device, and update the current task corresponding to the task instruction to a current task list of the medical terminal device according to the task priority; According to the task progress information fed back by the medical terminal device, the task progress status of the current task is updated in real time and stored in the task execution log.

[0006] By adopting the above technical solutions, the patient's real-time vital signs data and health record information are combined for abnormal assessment, and the type and priority of call demand are dynamically adjusted according to the abnormal assessment results to ensure that the patient's needs can be responded to accurately and quickly. Through the intelligent matching of medical resources and task scheduling optimization, the efficiency of hospital resource utilization is improved and the medical response time is significantly reduced. At the same time, the real-time tracking of task progress and log storage provide reliable data support for the continuous optimization of the system, meeting the needs of modern medical services for accuracy, efficiency and intelligent management.

[0007] Optionally, the step of performing abnormal state assessment on the pre-processed current vital sign data of the patient according to the health record data to obtain an abnormal assessment result includes: Based on the health record data, construct and train a corresponding abnormality analysis model; Inputting the pre-processed current vital sign data of the patient into the abnormality analysis model to obtain the abnormality type and abnormality severity; A corresponding abnormality assessment result is generated according to the abnormality type and the abnormality severity.

[0008] By adopting the above technical solutions, the patient's complex vital signs data can be converted into intuitive abnormality assessment results using a personalized abnormality analysis model, thereby providing comprehensive and intelligent technical support for patient health status assessment and medical response.

[0009] Optionally, the method further includes a training step of the abnormality analysis model, wherein the training step includes: Acquire a sample data set and perform data preprocessing; wherein the sample data set includes a plurality of normal or abnormal vital signs data and pre-labeled abnormal labels in the health record data; Perform feature extraction on the preprocessed sample data set to obtain sample feature data; Divide the sample data set after feature extraction into training set, validation set and test set; Inputting the training set into a pre-built multi-layer perceptron model for training, optimizing the model parameters and calculating the loss function of the multi-layer perceptron model until the loss function meets the preset conditions, thereby obtaining the trained anomaly analysis model; Validating the anomaly analysis model based on the validation set, evaluating the performance of the anomaly analysis model and adjusting the hyperparameters of the model; The predictive ability of the adjusted anomaly analysis model is tested based on the test set.

[0010] By adopting the above technical solutions, an efficient and accurate abnormal status assessment of the patient's current vital signs data is achieved. The model is continuously optimized through feature extraction, training, verification and testing, and can accurately predict the type and severity of abnormalities, greatly improving the intelligence level and response efficiency of the ward call system in vital sign abnormality detection. In addition, the nonlinear analysis capability based on the MLP model further enhances the system's adaptability to complex vital sign patterns, making medical resource scheduling and patient management more efficient and reliable.

[0011] Optionally, based on a medical resource database, the step of matching a corresponding medical resource list according to the call requirement type in the call requirement information includes: Based on the medical resource database, screening the medical personnel data whose current load status is lower than a preset load threshold, and obtaining a list of candidate medical personnel; Determine a corresponding skill requirement type according to the call requirement type in the call requirement information; Obtaining the skill label of each candidate medical staff in the candidate medical staff list; Based on the skill requirement type, the skill label of each candidate medical staff is matched to obtain the skill matching degree of each candidate medical staff; Perform weighted fusion based on the current load status and skill matching degree to calculate a comprehensive score for each candidate medical staff; The candidate medical personnel in the candidate medical personnel list whose comprehensive scores are greater than a preset score threshold are screened to obtain a medical resource list.

[0012] By adopting the above technical solutions, suitable resources can be intelligently screened from the huge medical resource database, and finally an accurate list of medical resources can be generated, which significantly improves the efficiency and scientificity of medical resource allocation and meets the needs of modern hospitals for intelligent task allocation.

[0013] Optionally, after the step of updating the task progress status of the current task in real time and storing it in the task execution log, the method further includes: Obtaining the execution time of the current task according to the task execution log; Determine whether the execution time of the current task exceeds a preset time threshold; If it does not exceed the limit, the current progress of the task will be maintained; If it exceeds, judging whether the current task has been completed according to the task progress status; If yes, the task progress status of the current task is updated to completed, and a timeout task record is generated and stored in the abnormal task log; If not, the task progress status of the current task is updated to a task to be remedied, and a remediation feedback signal is sent to the medical care management terminal according to the task to be remedied.

[0014] By adopting the above technical solution, the duration is extracted from the task execution log, combined with the preset duration threshold and task progress status, the task execution status is dynamically monitored, and the task is accurately judged whether it has timed out and whether it has been completed. For completed timed tasks, the timeout reason is recorded and an exception log is generated; for unfinished timed tasks, a remedial feedback signal is triggered to ensure that the task can reallocate resources and be processed in a timely manner.

[0015] Optionally, the management method further includes: Extracting abnormal task data according to the abnormal task log; Performing standardization processing on the extracted abnormal task data; Based on the clustering algorithm, cluster analysis is performed on the abnormal task data after standardization to obtain the clustering results; Identifying system bottleneck problems based on the clustering results; generating an optimization strategy according to the system bottleneck problem; The generated optimization strategy is applied to system configuration parameters; wherein the system configuration parameters include a preset task duration threshold and medical resource allocation rules.

[0016] By adopting the above technical solutions, a data-driven optimization closed loop is formed based on data extraction, cluster analysis and system bottleneck identification of abnormal task logs. By dynamically adjusting system configuration parameters, the frequency of abnormal tasks is reduced, the efficiency of task processing and resource utilization are improved, and the stability and intelligence level of the medical management system are comprehensively improved.

[0017] In the second aspect, the present application provides a ward call management system, which adopts the following technical solution: A ward call management system, the management system comprising: A call demand receiving module, used to receive call demand information input by the patient through the bed extension; wherein the call demand information includes the call demand type and demand priority; A data acquisition and processing module, used for real-time acquisition of the patient's current vital sign data and preprocessing; The file data retrieval module is used to retrieve the health file data of the patient based on the patient health file database; An abnormal state evaluation module is used to evaluate the abnormal state of the pre-processed current vital sign data of the patient according to the health record data to obtain an abnormal state evaluation result; wherein the abnormal state evaluation result includes the abnormal type and the abnormal severity; A configuration adjustment module, configured to configure and adjust the call demand type and demand priority of the call demand information according to the abnormal evaluation result; A medical resource matching module, used to match a corresponding medical resource list according to the call demand type in the call demand information based on a medical resource database; A medical terminal determination module, used to determine the medical terminal device closest to the bed extension in the medical resource list according to the location information of the bed extension; A task instruction allocation module, used to generate a task instruction and a task priority according to the call demand information, and send the task instruction to the medical terminal device; A task update module, used for receiving a task confirmation signal from the medical terminal device, and updating the current task corresponding to the task instruction to the current task list of the medical terminal device according to the task priority; According to the task progress information fed back by the medical terminal device, the task progress status of the current task is updated in real time and stored in the task execution log.

[0018] Optionally, the management system further includes: An execution time acquisition module, used to acquire the execution time of the current task according to the task execution log; The first judgment module is used to judge whether the execution time of the current task exceeds a preset time threshold; if not, output a first judgment result; if exceeded, output a second judgment result; A task status maintaining module, used for continuing to maintain the current progress status of the task in response to the first judgment result; a second judgment module, configured to judge whether the current task has been completed according to the task progress status in response to the second judgment result; if so, output a third judgment result; if not, output a fourth judgment result; A task progress status updating module, configured to update the task progress status of the current task to completion in response to the third judgment result; A timeout task record generating module, used for generating a timeout task record in response to the third judgment result and storing the record in an abnormal task log; A task progress status updating module, configured to update the task progress status of the current task to a task to be remedied in response to the fourth judgment result; A remedial feedback module is used to respond to the fourth judgment result and send a remedial feedback signal to the medical management terminal according to the task to be remedied.

[0019] In a third aspect, the present application provides a computer device, which adopts the following technical solution: A computer device comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the methods in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is the first flow chart of a ward call management method according to one embodiment of the present application.

[0022] Figure 2 This is a second flow chart of a ward call management method according to one embodiment of the present application.

[0023] Figure 3 This is the third flow chart of a ward call management method according to one embodiment of the present application.

[0024] Figure 4 This is the fourth flow chart of a ward call management method according to one embodiment of the present application.

[0025] Figure 5 This is the fifth flow chart of a ward call management method according to one embodiment of the present application.

[0026] Figure 6 This is the sixth flow chart of a ward call management method according to one embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-6 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0028] An embodiment of the present application discloses a ward call management method.

[0029] Reference Figure 1 , a ward call management method, the method comprising: Step S101, receiving call demand information input by the patient through the bed extension; wherein the call demand information includes the call demand type and demand priority; Specifically, the bed extension is the first point of contact for patients to interact with the system. It supports multiple input methods (such as touch buttons and voice commands). Each input from the patient will trigger the extension to convert the demand information into a standardized data packet. The bed extension must have the ability to structure the input data, classify it according to the preset demand type (such as "living needs", "ordinary medical needs", "emergency medical needs"), and attach the input timestamp to the data packet. The data packet is then transmitted to the task allocation module of the central management system through the IoT communication module (such as WiFi or a dedicated medical network).

[0030] Step S102, collecting the patient's current vital sign data in real time and performing preprocessing; Among them, the bed extension collects vital signs data through sensor modules (such as heart rate sensors, blood oximeters, and blood pressure monitors), and the data is streamed to the central management system at a high frequency.

[0031] Specifically, data preprocessing steps include: removing outliers, eliminating instantaneous erroneous data (such as extreme fluctuations caused by interference) by analyzing the continuity and trend of data points; time series processing to ensure that data is stored in order according to the collection time point; Step S103, based on the patient health record database, retrieve the patient's health record data; Among them, the system uses the patient's unique identifier (such as bed extension number) to search the corresponding patient's long-term health data in the health record database, including the patient's medical history, chronic disease records, normal vital signs range, allergy history and other information, providing a benchmark for subsequent abnormal status analysis.

[0032] Step S104, performing abnormal state assessment on the pre-processed current vital sign data of the patient according to the health record data to obtain an abnormality assessment result; wherein the abnormality assessment result includes the abnormality type and the abnormality severity; Specifically, the system compares the preprocessed real-time vital sign data with the normal range in the health record, and uses the rule engine to identify the type and severity of the abnormality to generate an abnormal status assessment report.

[0033] Exemplarily, based on the current vital signs data, determine whether the heart rate, blood pressure, and blood oxygen exceed the normal range in the health record data, and mark the abnormality type (such as "abnormal heart rate", "abnormal blood pressure", "abnormal blood oxygen"), and then quantify the severity of the abnormality (mild, moderate, severe) according to the degree of deviation (such as the extent to which the heart rate is higher than the normal upper limit).

[0034] Step S105, configuring and adjusting the call demand type and demand priority of the call demand information according to the abnormality assessment result; Specifically, the call demand type and task priority are dynamically adjusted according to the abnormality type and severity. For example, assuming that the initial call demand type of the call demand information is "life demand" and the initial demand priority is "normal priority"; if the abnormality assessment result is no abnormality or slight abnormality, the initial call demand type and initial demand priority are maintained; if the abnormality assessment result is moderate abnormality, the call demand type is adjusted to "normal medical demand" and the task priority is increased to "higher priority"; if the abnormality assessment result is severe abnormality, the call demand type is adjusted to "urgent medical demand" and the task priority is adjusted to "highest priority".

[0035] Step S106, based on the medical resource database, matching the corresponding medical resource list according to the call demand type in the call demand information; Specifically, the system queries the medical resource database and screens medical staff that match the demand type. The screening conditions include skill matching and load status to ensure that the skills of the assigned medical staff meet the call demand type, and give priority to medical staff with a load threshold below the preset value to obtain a sorted list of medical resources.

[0036] Step S107, according to the location information of the bed extension, determine the medical terminal device closest to the bed extension in the medical resource list; Among them, the location information of the bed extension is a fixed attribute. The system can determine the bed location by bed ID or geographic coordinates (such as floor, room number). By extracting the current terminal device location of each medical staff from the medical resource list, calculating the distance with the bed extension location, and selecting the nearest medical terminal as the task allocation target, the response time is further reduced.

[0037] For example, the location information of the bed extension can be associated with the hospital map system to form a standardized coordinate system (such as room number, ward floor number, etc.), and then the shortest path algorithm (such as Dijkstra or A* algorithm) is used to calculate the path length between each medical terminal and the bed, and generate a ranked list of the distance between medical staff and the bed; when there are multiple medical staff with the same distance, the optimal medical resource can be selected based on skill matching or load status.

[0038] Step S108, generating a task instruction and a task priority according to the call demand information, and sending the task instruction to the medical terminal device; Among them, the system integrates call demand information (call demand type and demand priority), abnormal assessment results, bed location and other contents into task instructions, and determines the corresponding task priority according to the demand priority; wireless communication modules (such as WiFi, LoRa or dedicated networks within the hospital) can be used to push task instructions to the target medical terminal equipment. After the medical terminal receives the task, it will feedback a confirmation signal to ensure the successful distribution of the task.

[0039] Specifically, the generated task instruction may include patient ID, call requirement type, abnormality type, abnormality severity, bed location and task priority.

[0040] Step S109, receiving a task confirmation signal from the medical terminal device, and updating the current task corresponding to the task instruction to the current task list of the medical terminal device according to the task priority; Among them, after the medical terminal receives the task instruction, it feeds back a confirmation signal to the system to confirm that the current task has been received. The system can then dynamically update the current task list of the medical terminal device according to the task priority (such as high, medium, or low) of the current task.

[0041] In some embodiments, if the current task is the highest priority task, it can be directly placed on the top; if the current task is a lower priority task, it can be placed after the high priority task to ensure that the current task list can be processed in order of urgency.

[0042] Step S110, based on the task progress information fed back by the medical terminal device, the task progress status of the current task is updated in real time and stored in the task execution log.

[0043] Among them, the medical terminal equipment provides real-time feedback of progress information (such as "arrived at the bedside", "completed", etc.) during the task execution process. The system updates the task progress status based on the feedback, such as "processing", "completed", "abnormal", etc., and stores the key node information of the task execution (allocation time, response time, completion time, etc.) in the task log to form a task history record.

[0044] In the above implementation, abnormality assessment is performed by combining the patient's real-time vital signs data with health record information, and the type and priority of call demand are dynamically adjusted according to the abnormality assessment results to ensure that the patient's needs can be responded to accurately and quickly. Through the intelligent matching of medical resources and task scheduling optimization, the efficiency of hospital resource utilization is improved and the medical response time is significantly reduced. At the same time, real-time tracking of task progress and log storage provide reliable data support for the continuous optimization of the system, meeting the needs of modern medical services for accuracy, efficiency and intelligent management.

[0045] Reference Figure 2 As an implementation of step S104, the abnormal state evaluation of the current vital sign data of the pre-processed patient is performed according to the health record data, and the step of obtaining the abnormal evaluation result includes: Step S201, constructing and training a corresponding abnormality analysis model based on health record data; Among them, the patient's health record data includes normal or abnormal historical vital signs data (heart rate, blood pressure, blood oxygen, etc.) and patient medical history records (such as chronic diseases, high-risk medical history, etc.). By building and training anomaly analysis models, personalized anomaly detection can be achieved for the patient.

[0046] Step S202, inputting the pre-processed current vital sign data of the patient into the abnormality analysis model to obtain the abnormality type and abnormality severity; Among them, the patient's current vital signs data are standardized according to the model input format, and the trained model is used to output the probability distribution of each abnormality type and severity. Through the model prediction, it is possible to quickly determine whether there is an abnormality and its severity.

[0047] Step S203: Generate a corresponding abnormality assessment result according to the abnormality type and the abnormality severity.

[0048] Among them, the abnormal type corresponding to the highest probability is selected as the classification result according to the probability distribution output by the model. At the same time, the severity of the abnormality can be divided into "mild", "moderate" or "severe" according to the probability value and severity rules; by integrating the abnormal status of all indicators, a structured abnormality assessment report is generated.

[0049] In the above implementation, the personalized abnormality analysis model can be used to transform the patient's complex vital signs data into intuitive abnormality assessment results, thereby providing comprehensive and intelligent technical support for the patient's health status assessment and medical response.

[0050] Reference Figure 3 As an implementation of the anomaly analysis model, the training steps of the anomaly analysis model include: Step S301, obtaining a sample data set and performing data preprocessing; wherein the sample data set includes a plurality of normal or abnormal vital sign data and pre-marked abnormal labels in the health record data; Specifically, historical vital sign data is obtained from the patient's health record data, including normal and abnormal vital sign data (such as heart rate, blood pressure, blood oxygen, etc.), and pre-labeled abnormal labels (such as "normal", "abnormal heart rate", "abnormal blood pressure", "abnormal blood oxygen", etc.) are used as supervisory signals for model training. Among them, the data preprocessing steps may include data cleaning and data standardization, which can ensure the accuracy and stability of model training by providing high-quality, structured data input.

[0051] Step S302, extracting features from the preprocessed sample data set to obtain sample feature data; Among them, features related to abnormal vital signs, such as heart rate, blood oxygen, systolic blood pressure, diastolic blood pressure, and related attributes in historical health records (such as whether or not a person has a chronic disease) are selected from the original data to construct new high-dimensional feature combinations, such as: the joint distribution of heart rate and blood pressure, the cross-features of blood oxygen and historical chronic disease records, and differential features calculated based on time series changes (such as "heart rate change rate").

[0052] Step S303, dividing the sample data set after feature extraction into a training set, a validation set and a test set; The sample data is randomly divided according to common proportions (such as 80% for training set, 10% for validation set, and 10% for test set) to ensure that each part of the data contains normal and abnormal samples.

[0053] It should be noted that if the proportion of abnormal samples is much lower than that of normal samples, undersampling or oversampling techniques (such as the SMOTE algorithm) can be used to balance the data to avoid the model being overly biased towards the majority class during training.

[0054] Step S304, inputting the training set into the pre-built multi-layer perceptron model for training, optimizing the model parameters and calculating the loss function of the multi-layer perceptron model until the loss function meets the preset conditions, thereby obtaining a trained anomaly analysis model; Among them, the abnormality analysis model in the embodiment of the present application can adopt a multi-layer perceptron (MLP) model, which is a neural network model based on a multi-layer fully connected network, used to process nonlinear classification tasks, has a strong nonlinear learning ability, and can efficiently capture complex patterns in vital sign data. Specifically, the multi-layer perceptron (MLP) model includes an input layer, a hidden layer, and an output layer. The input layer is used to receive the extracted feature vector, the hidden layer is used to extract high-order features through a multi-layer fully connected network and a nonlinear activation function (such as ReLU), and the output layer is used to output the probability distribution of each abnormality type and severity.

[0055] In one embodiment of the present application, the loss function may use a cross entropy loss function to evaluate the difference between the prediction result and the true label, and use an optimization algorithm (such as Adam) to adjust the model parameters until the loss function converges to a preset threshold.

[0056] Step S305, verifying the anomaly analysis model based on the validation set, evaluating the performance of the anomaly analysis model and adjusting the hyperparameters of the model; The validation set data is input into the trained model, and the accuracy, recall rate, F1 score and other indicators of the model on the validation set are calculated. The hyperparameters of the model (such as the number of hidden layers, the number of nodes, the learning rate, etc.) are optimized according to the validation results to balance the fitting ability and generalization ability of the model and avoid overfitting or underfitting.

[0057] Step S306: testing the prediction capability of the adjusted anomaly analysis model based on the test set.

[0058] Specifically, the test set data is input into the finally adjusted model, and key performance indicators (such as accuracy and AUC value) are calculated. By verifying the model's ability to detect anomalies of different types and severity (such as the recall rate of "abnormal heart rate" and the F1 score of "abnormal blood oxygen"), the model performance is ensured to be true and reliable, and to avoid overfitting problems caused by the adjustment of the validation set.

[0059] In the above implementation, an efficient and accurate abnormal status assessment of the patient's current vital signs data is achieved. The model is continuously optimized through feature extraction, training, verification and testing, and can accurately predict the type and severity of abnormalities, greatly improving the intelligence level and response efficiency of the ward call system in vital sign abnormality detection. In addition, the nonlinear analysis capability based on the MLP model further enhances the system's adaptability to complex vital sign patterns, making medical resource scheduling and patient management more efficient and reliable.

[0060] Reference Figure 4 As an implementation of step S106, the step of matching the corresponding medical resource list according to the call requirement type in the call requirement information includes: Step S401, based on the medical resource database, screening the medical staff data whose current load status is lower than the preset load threshold, and obtaining a list of candidate medical staff; Among them, the current data of all medical staff are retrieved from the medical resource database, and key fields such as medical staff ID, current load status, maximum task load threshold, etc. are extracted; by comparing the current load status (current number of tasks) of each medical staff with the preset load threshold (for example, the maximum number of tasks allowed to be processed simultaneously by the medical staff is 5), if the current number of tasks is less than the threshold, it is considered that the load status of the medical staff is low and can be used as a candidate resource.

[0061] Step S402, determining a corresponding skill requirement type according to the call requirement type in the call requirement information; The task type (such as "emergency medical treatment" or "general nursing care") is extracted from the call demand information, and the demand type is mapped to the required skill type through the preset skill demand mapping table. For example, emergency medical treatment can correspond to cardiovascular emergency treatment, respiratory management, etc., and general nursing can correspond to nursing monitoring, life assistance, etc.

[0062] Step S403, obtaining the skill label of each candidate medical staff in the candidate medical staff list; Among them, a list of skill labels of candidate medical staff is extracted from the medical resource database. The skill label represents the professional qualification or ability of each medical staff. By binding the skill label of each medical staff with his / her ID, structured data is formed to facilitate subsequent processing.

[0063] Step S404, matching the skill label of each candidate medical staff member based on the skill requirement type to obtain the skill matching degree of each candidate medical staff member; Among them, the skill label of each candidate medical staff is compared with the skill requirement type, and the skill matching degree is calculated as: matching degree = (number of matched skills ÷ total number of required skills) × 100%, and the skill matching degree is stored as an additional feature of each candidate medical staff.

[0064] For example, the skill requirement type is ["Cardiovascular First Aid", "Respiratory Management"]. For medical staff N001, the matching skill is ["Cardiovascular First Aid"], and the skill matching degree is 1 / 2=50%; for N003: the matching skills are ["Cardiovascular First Aid", "Respiratory Management"], and the skill matching degree is 2 / 2=100%.

[0065] Step S405, performing weighted fusion according to the current load status and skill matching degree to calculate the comprehensive score of each candidate medical staff; Specifically, the scoring weights are pre-set, and the weights of the load status and skill matching can be set according to the specific needs of hospital management. For example, the skill matching weight is 70%, and the load status weight is 30%.

[0066] The score calculation formula is: Comprehensive score = (skill matching degree × weight 1) + (load status score × weight 2), load status score = 1-(current number of tasks ÷ maximum number of tasks).

[0067] Step S406, screening candidate medical personnel in the candidate medical personnel list whose comprehensive scores are greater than a preset score threshold to obtain a medical resource list.

[0068] Specifically, according to the urgency of the task or the hospital management strategy, a minimum score requirement (such as 60 points) can be set to screen medical staff with comprehensive scores higher than the threshold to construct a final list of medical resources.

[0069] In the above implementation mode, suitable resources are intelligently screened from a huge medical resource database, and an accurate list of medical resources is finally generated, which significantly improves the efficiency and scientificity of medical resource allocation and meets the needs of modern hospitals for intelligent task allocation.

[0070] Reference Figure 5 As a further implementation method of the ward call management method, after the step of updating the task progress status of the current task in real time and storing it in the task execution log, it also includes: Step S501, obtaining the execution time of the current task according to the task execution log; Among them, query the task execution log, extract the task allocation time (task start time) and current time according to the task ID, and use the current time to subtract the allocation time to calculate the actual execution time of the task: Step S502, determine whether the execution time of the current task exceeds the preset time threshold; if not, jump to step S503; if exceeded, jump to step S504; The preset duration threshold corresponding to the current task type is obtained from the task parameter table (e.g., 30 minutes for "emergency medical task" and 40 minutes for "general nursing task"). The actual execution time is compared with the preset duration threshold. If the execution time is longer than the preset duration threshold, the current task is marked as "timeout"; if not, the task continues to maintain its normal state.

[0071] Step S503, continue to maintain the current progress status of the task; Step S504, judging whether the current task has been completed according to the task progress status; if so, jumping to step S505; if not, jumping to step S506; Among them, the progress status field of the current task is retrieved from the task execution log. The task progress status usually includes: processing (the task is being executed), completed (the task has been processed), abnormal (the task is interrupted for some reason) and to be remedied (the task needs to reallocate resources).

[0072] Specifically, if the task progress status is "completed", the task is determined to be completed; otherwise, the task is determined to be incomplete.

[0073] Step S505, updating the task progress status of the current task to completion, generating a timeout task record and storing it in the abnormal task log; The task progress status is updated from "Processing" to "Completed", and the task completion time is recorded. If the task is completed in timeout, the task is marked as "Completed in timeout" and a timeout task record is generated, including the following fields: task ID, execution time, preset time threshold, timeout reason description (such as "response delay", "high workload", etc.). The timeout task record is stored in the abnormal task log for subsequent analysis and optimization.

[0074] Step S506: update the task progress status of the current task to a task to be remedied, and send a remediation feedback signal to the medical management terminal according to the task to be remedied.

[0075] Among them, the task progress status is updated from "in process" to "to be remedied", the unfinished status of the current task is recorded, and a remediation feedback signal is created, which includes the following: task ID, current task status ("to be remedied"), description of the reason for incompleteness (such as "task timeout and incomplete"), and remediation suggestions (such as "reallocate resources"). The remediation feedback signal is sent to the medical management terminal to trigger the remediation resource allocation process.

[0076] In the above implementation, the duration is extracted from the task execution log, combined with the preset duration threshold and task progress status, to dynamically monitor the task execution status and accurately determine whether the task has timed out and whether it has been completed. For completed timed out tasks, the timeout reason is recorded and an exception log is generated; for unfinished timed out tasks, a remedial feedback signal is triggered to ensure that the task can reallocate resources and be processed in a timely manner.

[0077] Reference Figure 6 , as a further implementation of the ward call management method, further comprising: Step S601, extracting abnormal task data according to the abnormal task log; Among them, abnormal task logs include timed-out unfinished tasks (task execution time exceeds the preset time threshold and is not completed), timed-out completed tasks (task execution time exceeds the preset time threshold but is completed) and interrupted tasks (tasks are not completed due to external reasons); abnormal task data includes task ID, task type, task priority, execution time, preset time threshold, timeout duration, related medical resources and abnormal reasons; Step S602, standardizing the extracted abnormal task data; Among them, the data time fields from different sources are converted into a standard format (such as ISO 8601 format) to facilitate time calculation and comparison. At the same time, classification fields such as task type and priority are encoded to simplify subsequent calculations and processing.

[0078] Step S603, performing cluster analysis on the normalized abnormal task data based on a clustering algorithm to obtain a clustering result; Among them, the task type, priority, timeout duration, and related medical resources in the standardized abnormal task data are used as clustering features. Specifically, the K-Means clustering algorithm can be used to input clustering features, set the number of clusters K (such as K=3, dividing abnormal tasks into 3 categories), and output the abnormal task pattern of each cluster cluster. According to the cluster cluster, the characteristic pattern of each type of abnormal task is analyzed, for example: the timeout duration of a certain type of task is concentrated in 10-15 minutes; a certain type of task is mainly associated with specific medical resources.

[0079] It can be understood that by automatically discovering the patterns of abnormal tasks, the problem task types and associated resources can be quickly located, providing a clear feature basis for system bottleneck identification.

[0080] Step S604, identifying system bottleneck problems based on the clustering results; Among them, system bottleneck problems include abnormally high-incidence task type bottlenecks, resource allocation bottlenecks and response delay problems.

[0081] Specifically, abnormally high-incidence task types can be identified by counting the timeout frequency of each type of task, and marking the task types with timeout rates higher than the preset threshold as system bottleneck problems; resource allocation bottlenecks can be identified by analyzing the medical resources associated with abnormal tasks and identifying resource allocation problems with high timeout rates. For example, a high timeout rate of tasks associated with a certain medical staff may be caused by excessive resource load; response delay problems can be identified by checking the response time distribution of tasks and identifying the main causes of task response delays.

[0082] Step S605, generating an optimization strategy according to the system bottleneck problem; Specifically, to address task type bottlenecks, increase the priority of tasks with high timeout rates and adjust the preset task duration threshold; to address resource allocation bottlenecks, increase redundant resource pools and dynamically allocate high-load resource tasks to idle resources; to address response delay issues, optimize task allocation rules, such as giving priority to medical resources that are closer.

[0083] Step S606, applying the generated optimization strategy to system configuration parameters; wherein the system configuration parameters include a preset task duration threshold and medical resource allocation rules.

[0084] Specifically, the following configuration parameters are dynamically updated according to the optimization strategy: task preset duration threshold and medical resource allocation rules (such as load limit, allocation priority, etc.), and the adjusted configuration parameters are written into the system configuration table to ensure that the optimization strategy takes effect immediately.

[0085] In the above implementation, a data-driven optimization closed loop is formed based on data extraction, cluster analysis and system bottleneck identification of abnormal task logs. By dynamically adjusting system configuration parameters, the frequency of abnormal tasks is reduced, the efficiency of task processing and resource utilization are improved, and the stability and intelligence level of the medical management system are comprehensively improved.

[0086] This application significantly improves the shortcomings of traditional ward call systems in terms of accuracy and intelligence. Through real-time data collection and processing, the system can dynamically evaluate the patient's health status, thereby responding to personalized medical service needs. The real-time recording function of the task execution log provides transparent and traceable task execution data for hospital management, which helps to optimize management processes and improve service quality. In addition, this application also alleviates the pressure of uneven distribution of medical resources through intelligent resource scheduling, while improving patients' sense of security and enhancing the hospital's operational efficiency. This technology application plays an important role in promoting modern medical services and lays a solid foundation for the construction of intelligent medical systems.

[0087] The embodiment of the present application also discloses a ward call management system.

[0088] A ward call management system, the management system comprising: A call demand receiving module is used to receive call demand information input by the patient through the bed extension; wherein the call demand information includes the call demand type and demand priority; A data acquisition and processing module is used to collect the patient's current vital signs data in real time and perform preprocessing; The file data retrieval module is used to retrieve the patient's health file data based on the patient's health file database; The abnormal state evaluation module is used to evaluate the abnormal state of the current vital sign data of the pre-processed patient according to the health record data to obtain the abnormal state evaluation result; wherein the abnormal state evaluation result includes the abnormal type and the abnormal severity; A configuration adjustment module, used to configure and adjust the call demand type and demand priority of the call demand information according to the abnormal evaluation result; A medical resource matching module is used to match a corresponding medical resource list according to the call demand type in the call demand information based on the medical resource database; A medical terminal determination module, used to determine the medical terminal device closest to the bed extension in the medical resource list according to the location information of the bed extension; A task instruction allocation module is used to generate task instructions and task priorities according to call demand information, and send the task instructions to the medical terminal device; A task update module is used to receive a task confirmation signal from a medical terminal device, and update the current task corresponding to the task instruction to a current task list of the medical terminal device according to the task priority; According to the task progress information fed back by the medical terminal device, the task progress status of the current task is updated in real time and stored in the task execution log.

[0089] In the above implementation, the patient's vital signs data is combined with the health record data to dynamically adjust the call demand type and priority to ensure that high-risk patients can be treated first. By accurately matching medical resources, the efficiency of resource utilization is improved, and the delay problem caused by unreasonable priority allocation or insufficient resource allocation in the traditional call system is avoided. The location-based dynamic matching function further shortens the response time, ensures the timely issuance and accurate delivery of task instructions, and thus improves the response speed and processing efficiency of medical services.

[0090] As a further implementation of the management system, the management system further includes: The execution time acquisition module is used to obtain the execution time of the current task based on the task execution log; The first judgment module is used to judge whether the execution time of the current task exceeds a preset time threshold; if not, output a first judgment result; if exceeded, output a second judgment result; A task status maintaining module, used for continuing to maintain the current progress status of the task in response to the first judgment result; A second judgment module is used to judge whether the current task has been completed according to the task progress status in response to the second judgment result; if so, output a third judgment result; if not, output a fourth judgment result; A task progress status updating module, configured to update the task progress status of the current task to completion in response to the third judgment result; A timeout task record generating module, used for generating a timeout task record in response to the third judgment result and storing the record in an abnormal task log; A task progress status updating module, configured to update the task progress status of the current task to a task to be remedied in response to the fourth judgment result; The remedial feedback module is used to send a remedial feedback signal to the medical management terminal according to the task to be remedied in response to the fourth judgment result.

[0091] In the above implementation, the task execution status is dynamically monitored to accurately determine whether the task has timed out and whether it has been completed; for completed timed-out tasks, the timeout reason is recorded and an exception log is generated; for unfinished timed-out tasks, a remedial feedback signal is triggered to ensure that the task can reallocate resources and be processed in a timely manner.

[0092] A ward call management system of an embodiment of the present application can implement any of the above-mentioned ward call management methods, and the specific working process of each module in the ward call management system can refer to the corresponding process in the above-mentioned method embodiment.

[0093] In the several embodiments provided in this application, it should be understood that the provided methods and systems can be implemented in other ways. For example, the system embodiments described above are only illustrative; for example, the division of a certain module is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0094] The embodiment of the present application also discloses a computer device.

[0095] The computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a ward call management method as described above is implemented.

[0096] The embodiment of the present application also discloses a computer-readable storage medium.

[0097] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the above-mentioned ward call management methods.

[0098] Among them, computer-readable storage media can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus or device; the program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0099] It should be noted that in the above embodiments, the description of each embodiment has different emphases, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0100] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A ward call management method, characterized in that: The method comprises: Receiving call demand information input by the patient through the bed extension; wherein the call demand information includes the call demand type and demand priority; Collecting the patient's current vital sign data in real time and performing preprocessing; Based on the patient health record database, retrieve the health record data of the patient; Performing an abnormal state assessment on the pre-processed current vital sign data of the patient according to the health record data to obtain an abnormality assessment result; wherein the abnormality assessment result includes an abnormality type and an abnormality severity; Adjust the call demand type and demand priority of the call demand information according to the abnormal evaluation result; Based on the medical resource database, matching the corresponding medical resource list according to the call demand type in the call demand information; Determine, according to the location information of the bed extension, the medical terminal device in the medical resource list that is closest to the bed extension; Generate a task instruction and a task priority according to the call demand information, and send the task instruction to the medical terminal device; Receive a task confirmation signal from the medical terminal device, and update the current task corresponding to the task instruction to a current task list of the medical terminal device according to the task priority; According to the task progress information fed back by the medical terminal device, the task progress status of the current task is updated in real time and stored in the task execution log.

2. A ward call management method according to claim 1, characterized in that: The step of performing abnormal state evaluation on the pre-processed current vital sign data of the patient according to the health record data to obtain an abnormal evaluation result comprises: Based on the health record data, construct and train a corresponding abnormality analysis model; Inputting the pre-processed current vital sign data of the patient into the abnormality analysis model to obtain the abnormality type and abnormality severity; A corresponding abnormality assessment result is generated according to the abnormality type and the abnormality severity.

3. A ward call management method according to claim 2, characterized in that: The method further includes a training step of the abnormality analysis model, wherein the training step includes: Acquire a sample data set and perform data preprocessing; wherein the sample data set includes a plurality of normal or abnormal vital signs data and pre-labeled abnormal labels in the health record data; Perform feature extraction on the preprocessed sample data set to obtain sample feature data; Divide the sample data set after feature extraction into training set, validation set and test set; Inputting the training set into a pre-built multi-layer perceptron model for training, optimizing the model parameters and calculating the loss function of the multi-layer perceptron model until the loss function meets the preset conditions, thereby obtaining the trained anomaly analysis model; Validating the anomaly analysis model based on the validation set, evaluating the performance of the anomaly analysis model and adjusting the hyperparameters of the model; The predictive ability of the adjusted anomaly analysis model is tested based on the test set.

4. A ward call management method according to claim 1, characterized in that: Based on the medical resource database, the step of matching the corresponding medical resource list according to the call requirement type in the call requirement information includes: Based on the medical resource database, screening the medical personnel data whose current load status is lower than a preset load threshold, and obtaining a list of candidate medical personnel; Determine a corresponding skill requirement type according to the call requirement type in the call requirement information; Obtaining the skill label of each candidate medical staff in the candidate medical staff list; Based on the skill requirement type, the skill label of each candidate medical staff is matched to obtain the skill matching degree of each candidate medical staff; Perform weighted fusion based on the current load status and skill matching degree to calculate a comprehensive score for each candidate medical staff; The candidate medical personnel in the candidate medical personnel list whose comprehensive scores are greater than a preset score threshold are screened to obtain a medical resource list.

5. A ward call management method according to any one of claims 1 to 3, characterized in that: After the step of updating the task progress status of the current task in real time and storing it in the task execution log, the method further includes: Obtaining the execution time of the current task according to the task execution log; Determine whether the execution time of the current task exceeds a preset time threshold; If it does not exceed the limit, the current progress of the task will be maintained; If it exceeds, judging whether the current task has been completed according to the task progress status; If yes, the task progress status of the current task is updated to completed, and a timeout task record is generated and stored in the abnormal task log; If not, the task progress status of the current task is updated to a task to be remedied, and a remediation feedback signal is sent to the medical care management terminal according to the task to be remedied.

6. A ward call management method according to claim 5, characterized in that: The management method also includes: Extracting abnormal task data according to the abnormal task log; Performing standardization processing on the extracted abnormal task data; Based on the clustering algorithm, cluster analysis is performed on the abnormal task data after standardization to obtain the clustering results; Identifying system bottleneck problems based on the clustering results; generating an optimization strategy according to the system bottleneck problem; The generated optimization strategy is applied to system configuration parameters; wherein the system configuration parameters include a preset task duration threshold and medical resource allocation rules.

7. A ward call management system, characterized in that: The management system comprises: A call demand receiving module, used to receive call demand information input by the patient through the bed extension; wherein the call demand information includes the call demand type and demand priority; A data acquisition and processing module, used for real-time acquisition of the patient's current vital sign data and preprocessing; The file data retrieval module is used to retrieve the health file data of the patient based on the patient health file database; An abnormal state evaluation module is used to evaluate the abnormal state of the pre-processed current vital sign data of the patient according to the health record data to obtain an abnormal state evaluation result; wherein the abnormal state evaluation result includes the abnormal type and the abnormal severity; A configuration adjustment module, configured to configure and adjust the call demand type and demand priority of the call demand information according to the abnormal evaluation result; A medical resource matching module, used to match a corresponding medical resource list according to the call demand type in the call demand information based on a medical resource database; A medical terminal determination module, used to determine the medical terminal device closest to the bed extension in the medical resource list according to the location information of the bed extension; A task instruction allocation module, used to generate a task instruction and a task priority according to the call demand information, and send the task instruction to the medical terminal device; A task update module, used for receiving a task confirmation signal from the medical terminal device, and updating the current task corresponding to the task instruction to the current task list of the medical terminal device according to the task priority; According to the task progress information fed back by the medical terminal device, the task progress status of the current task is updated in real time and stored in the task execution log.

8. A ward call management system according to claim 7, characterized in that: The management system also includes: An execution time acquisition module, used to acquire the execution time of the current task according to the task execution log; The first judgment module is used to judge whether the execution time of the current task exceeds a preset time threshold; if not, output a first judgment result; if exceeded, output a second judgment result; A task status maintaining module, used for continuing to maintain the current progress status of the task in response to the first judgment result; a second judgment module, configured to judge whether the current task has been completed according to the task progress status in response to the second judgment result; if so, output a third judgment result; if not, output a fourth judgment result; A task progress status updating module, configured to update the task progress status of the current task to completion in response to the third judgment result; A timeout task record generating module, used for generating a timeout task record in response to the third judgment result and storing the record in an abnormal task log; A task progress status updating module, configured to update the task progress status of the current task to a task to be remedied in response to the fourth judgment result; A remedial feedback module is used to respond to the fourth judgment result and send a remedial feedback signal to the medical management terminal according to the task to be remedied.

9. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 6.

Images