A management method based on intelligent physical examination queuing call system

The method optimizes patient queuing and resource scheduling in examination centers by analyzing health and complexity data, predicting waiting times, and performing real-time voice broadcasts, addressing inefficiencies in existing systems.

CN118736721BActive Publication Date: 2024-12-06WUXI DIEMEI SOFTWARE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410824367.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-25
Publication Date
2024-12-06
Estimated Expiration
2044-06-25

AI Technical Summary

Technical Problem

Existing physical examination queue management systems fail to consider patient health status and examination item complexity, leading to inefficiencies in scheduling and inaccurate waiting time predictions, resulting in low operating efficiency.

Method used

A management method that integrates data processing and analysis to generate personalized patient holographic files, optimize queuing sequences based on health and complexity impact data, predict waiting times, and perform resource scheduling with real-time voice broadcasts and anomaly detection.

Benefits of technology

Improves queuing efficiency by optimizing patient order, reducing waiting times, and ensuring accurate resource allocation, enhancing patient satisfaction and system operation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118736721B_ABST
    Figure CN118736721B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of intelligent management of physical examinations, and in particular to a management method based on an intelligent physical examination queuing call system. The method comprises the following steps: obtaining patient physical examination appointment data; screening the key data stream of the patient physical examination appointment data to obtain the patient physical examination appointment key data; performing multimodal feature fusion on the patient physical examination appointment key data to generate a standard patient physical examination appointment fusion vector; performing personalized data construction based on the standard patient physical examination appointment fusion vector to generate patient holographic archive data; performing initial queuing sequence construction on the patient holographic archive data to obtain an initial patient queuing sequence. The present invention comprehensively improves the operating efficiency of queuing call management by improving data processing, queuing optimization, waiting time prediction, resource scheduling, voice calling, anomaly detection and multi-terminal interaction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent physical examination management, and in particular to a management method based on an intelligent physical examination queuing calling system. Background Art

[0002] The development of network technology and mobile Internet has gradually led to the development of physical examination queue management systems in the direction of intelligence and networking. The intelligent queuing call system has begun to integrate more functional modules, such as appointment management, SMS reminders, automatic queuing, etc., which has greatly improved the patient's physical examination experience and the management efficiency of the hospital. At the same time, with the rise of Internet of Things (IoT) technology, intelligent physical examination equipment can be interconnected with the queuing system, making the physical examination process smoother and more efficient. In recent years, the rapid development of artificial intelligence (AI) and big data technology has brought new changes to the intelligent physical examination queue call system. Through AI technology, patients' health data can be analyzed, physical examination processes can be optimized, and personalized examination items can be recommended to further improve the scientificity and accuracy of physical examinations. Big data technology can process and analyze massive physical examination data, provide decision support for hospital managers, and improve service quality. However, the existing system usually adopts a simple first-come, first-served principle, fails to consider factors such as patient health status and the complexity of physical examination items, and has deficiencies in the scheduling of physical examination center project resources, and fails to fully consider real-time queuing conditions and waiting time predictions, resulting in low operating efficiency of queuing call management. Summary of the invention

[0003] Based on this, it is necessary to provide a management method based on an intelligent physical examination queuing call system to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a management method based on an intelligent physical examination queuing call system is provided, the method comprising the following steps:

[0005] Step S1: Acquire patient physical examination appointment data; filter the key data stream of the patient physical examination appointment data to obtain the key data of the patient physical examination appointment; perform multimodal feature fusion on the key data of the patient physical examination appointment to generate a standard patient physical examination appointment fusion vector; perform personalized data construction based on the standard patient physical examination appointment fusion vector to generate patient holographic file data;

[0006] Step S2: construct an initial queuing sequence for the patient holographic archive data to obtain an initial patient queuing sequence; perform a health queuing impact analysis on the initial patient queuing sequence according to the patient physical examination appointment key data to generate first patient queuing impact data; perform an appointment item complexity impact analysis on the initial patient queuing sequence according to the patient physical examination appointment key data to generate second patient queuing impact data; perform real-time queuing order optimization on the initial patient queuing sequence according to the first patient queuing impact data and the second patient queuing impact data to generate a real-time queuing optimization sequence;

[0007] Step S3: merging the first patient queue impact data and the second patient queue impact data to obtain comprehensive patient queue impact data; predicting the patient queue waiting time based on the comprehensive patient queue impact data to generate patient queue waiting time prediction data;

[0008] Step S4: Acquire the project resource data of the physical examination center; perform multi-dimensional resource scheduling on the project resource data of the physical examination center to generate the project resource scheduling data of the physical examination center; perform user call voice broadcast according to the real-time queuing optimization sequence and the patient queuing waiting time prediction data to obtain the user voice broadcast data; associate the user physical examination project with the project resource scheduling data of the physical examination center according to the user voice call data to generate the user voice broadcast project association data; perform anomaly detection and early warning on the user voice broadcast project association data to generate the user anomaly detection and early warning data;

[0009] Step S5: Perform real-time data synchronization on the user voice broadcast item association data and the user abnormality detection and warning data to generate physical examination queue call synchronization data; perform multi-terminal fusion interface interaction on the physical examination queue call synchronization data to generate a user interaction log to execute the intelligent physical examination queue call system management operation.

[0010] The present invention collects the appointment information of all patients. Extracts important information from the appointment data, such as appointment time, patient health status, appointment items, etc. Fusion of different types of data (such as text, numbers, etc.) generates a standardized patient physical examination appointment fusion vector. According to the standardized vector, the holographic archive data of each patient is constructed to fully reflect the patient's physical examination information and health status. According to the patient's holographic archive data, the physical examination order of all patients is preliminarily arranged. The influence of each patient's health status on the queue order is analyzed to generate the first patient queue influence data. The influence of the complexity of each patient's appointment item on the queue order is analyzed to generate the second patient queue influence data. Combined with the health degree and project complexity influence data, the initial queue sequence is optimized to generate a real-time queue optimization sequence. Combined with the health degree and project complexity influence data, comprehensive influence data is obtained. According to the comprehensive influence data, the queue waiting time of each patient is predicted to generate corresponding prediction data. Collect resource data of the physical examination center, such as equipment availability, medical staff arrangement, etc. Scheduling is performed according to the resource data to ensure the optimal allocation of resources and generate scheduling data. Combined with the real-time queue optimization sequence and waiting time prediction data, the patient is notified through the voice broadcast system. The voice call data is associated with the physical examination items to ensure that the patient undergoes the correct project examination at the right time. The call data is monitored, abnormal situations are detected and early warnings are issued to ensure the smooth operation of the system. The voice broadcast and abnormal warning data are synchronized to ensure that the information is updated in real time. A user interaction interface is provided through a variety of devices (such as mobile phones, computers, etc.), and user operation logs are recorded. According to the user interaction log, system management and optimization are performed to ensure that the intelligent physical examination queuing call system operates efficiently, and efficient patient management and physical examination resource scheduling can be achieved, reducing patient waiting time, and improving the work efficiency and patient satisfaction of the physical examination center. Therefore, the present invention comprehensively improves the operating efficiency of queuing call management by improving data processing, queuing optimization, waiting time prediction, resource scheduling, voice calls, anomaly detection and multi-terminal interaction.

[0011] Preferably, step S1 comprises the following steps:

[0012] Step S11: using edge computing nodes to obtain patient physical examination appointment data;

[0013] Step S12: screening the key data stream of the patient's physical examination appointment data to obtain the patient's physical examination appointment key data, wherein the key data stream screening includes identity information screening, health status screening, appointment time screening and real-time location screening;

[0014] Step S13: preprocessing the key data of the patient's physical examination appointment to obtain standard key data of the patient's physical examination appointment, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization;

[0015] Step S14: extracting high-dimensional features from key data of standard patient physical examination appointments to obtain high-dimensional feature vectors of standard patient physical examination appointments; performing multimodal feature fusion on the high-dimensional feature vectors of standard patient physical examination appointments to generate standard patient physical examination appointment fusion vectors;

[0016] Step S15: construct personalized data based on the standard patient physical examination appointment fusion vector to generate patient holographic file data.

[0017] The present invention can reduce the delay of data transmission and processing and improve the efficiency of data acquisition by using edge computing nodes to obtain patient physical examination appointment data. By screening the key data stream of patient physical examination appointment data, important information related to the physical examination can be extracted from a large amount of data, reducing the amount of data for subsequent processing and improving the efficiency of data processing. Data preprocessing includes data cleaning, data missing value filling and data standardization, which can eliminate noise and outliers in the data, fill in missing data, and make the data for subsequent processing more accurate and reliable. High-dimensional feature extraction and multimodal feature fusion are performed on the key data of standard patient physical examination appointments, which can combine features from different sources and types to extract more comprehensive and rich feature information, which is helpful for subsequent data analysis and model establishment. Based on the standard patient physical examination appointment fusion vector, personalized data is constructed to generate patient holographic archive data. This can generate targeted holographic archive data according to the individual characteristics and needs of patients, providing support for personalized care.

[0018] Preferably, step S2 comprises the following steps:

[0019] Step S21: clustering the patient holographic file data to generate patient clustering grouping data; constructing an initial queuing sequence according to the patient clustering grouping data to obtain an initial patient queuing sequence;

[0020] Step S22: Perform health assessment according to the key data of the patient's physical examination appointment to obtain the patient's physical examination appointment health assessment data; perform the first patient queue impact analysis on the initial patient queue sequence through the patient's appointment health assessment data to generate the first patient queue impact data;

[0021] Step S23: performing an appointment item complexity assessment based on the patient physical examination appointment key data to generate appointment item complexity assessment data; performing a second patient impact analysis on the initial patient queue sequence based on the appointment item complexity assessment data to generate second patient queue impact data;

[0022] Step S24: Optimize the initial patient queue sequence in real time according to the first patient queue impact data and the second patient queue impact data to generate a real-time queue optimization sequence.

[0023] The present invention can classify patients according to certain similarities by clustering and grouping patient holographic archive data, so as to better manage and organize patient queues. Generating an initial patient queue sequence can provide a basic sorting for subsequent queue impact analysis and optimization. By performing a health assessment on the key data of the patient's physical examination appointment, the patient's health status can be understood. By using the patient's appointment health assessment data to perform the first patient queue impact analysis, the degree of influence of the patient on the overall queue can be determined, providing guidance for subsequent queue optimization. According to the key data of the patient's physical examination appointment, the complexity of the appointment items can be evaluated by performing an appointment item complexity assessment. By performing a second patient queue impact analysis on the initial patient queue sequence, the degree of influence of different appointment items on the overall queue can be determined, providing a basis for subsequent queue optimization. Based on the first patient queue impact data and the second patient queue impact data, the initial patient queue sequence is optimized in real time. This can adjust the patient's queue order according to the patient's health and the complexity of the appointment items, making the overall queue more reasonable and efficient.

[0024] Preferably, step S22 includes the following steps:

[0025] Step S221: collecting the patient's historical physical examination data for the patient's physical examination appointment key data to obtain the patient's historical physical examination data;

[0026] Step S222: extracting abnormal indicators from the patient's historical physical examination data to obtain abnormal indicator data of the patient's historical physical examination;

[0027] Step S223: using the entropy weight method to assign abnormal index weights to the abnormal index data of the patient's historical physical examination, and obtaining the abnormal index weights of the patient's historical physical examination; using the abnormal index weights of the patient's historical physical examination to evaluate the patient's health, and obtaining the patient's physical examination appointment health evaluation data;

[0028] Step S224: Perform a first patient queue impact analysis on the initial patient queue sequence using the patient appointment health assessment data to generate first patient queue impact data.

[0029] The present invention can obtain the patient's past physical examination records by collecting the patient's historical physical examination data for the patient's physical examination appointment key data. These historical physical examination data can provide more comprehensive health information and help to comprehensively evaluate the patient's health status. Abnormal indicators are extracted from the patient's historical physical examination data. By identifying and extracting abnormal indicators in historical physical examinations, health problems or disease risks of patients can be found. The abnormal indicator data of the patient's historical physical examination is weighted by the entropy weight method to obtain the abnormal indicator weight of the patient's historical physical examination. Then, the patient's health is evaluated by the abnormal indicator weight of the patient's historical physical examination to obtain the patient's physical examination appointment health evaluation data. In this way, a more accurate and reliable basis can be provided for the patient's health evaluation according to the importance of the abnormal indicators of the historical physical examination. Using the patient appointment health evaluation data, the first patient queuing impact analysis is performed on the initial patient queuing sequence in step S224. By analyzing the patient's health evaluation data and determining the degree of influence of the patient on the overall queuing queue, it can help optimize the queuing order to meet the patient's health needs and priorities.

[0030] Preferably, step S23 includes the following steps:

[0031] Step S231: Acquire current time data; collect patient appointment time for key data of patient physical examination appointment to obtain patient physical examination appointment time data;

[0032] Step S232: Calculate the appointment time difference of the patient's physical examination appointment time data based on the current time data to obtain the patient's appointment time difference data; sort the first time urgency based on the patient's appointment time difference data to obtain the first time urgency data;

[0033] Step S233: screening the physical examination items of the key data of the patient's physical examination appointment according to the patient's physical examination appointment time data to obtain the patient's physical examination item data; analyzing the average duration of the physical examination items on the patient's physical examination item data to generate the average duration data of the patient's physical examination items;

[0034] Step S234: Use the average duration data of the patient physical examination items to perform a second time urgency sort to obtain the second time urgency data; perform an appointment item complexity assessment using the first time urgency data and the second time urgency data to generate appointment item complexity assessment data; perform a second patient impact analysis on the initial patient queuing sequence based on the appointment item complexity assessment data to generate second patient queuing impact data.

[0035] The present invention acquires the current time data and collects the patient's appointment time for the patient's physical examination appointment key data. In this way, the patient's physical examination appointment time data can be obtained for subsequent time difference calculation and urgency sorting. The appointment time difference calculation is performed on the patient's physical examination appointment time data based on the current time data to obtain the patient's appointment time difference data. Then, the first time urgency sorting is performed according to the patient's appointment time difference data to obtain the first time urgency data. This can adjust the queue order according to the urgency of the patient's appointment time and give priority to urgent appointments. The patient's physical examination appointment key data is screened for physical examination items according to the patient's physical examination appointment time data to obtain the patient's physical examination item data. Then, the average duration of the physical examination items is analyzed for the patient's physical examination item data to generate the average duration data of the patient's physical examination items. This can help evaluate the duration of different physical examination items and provide a basis for subsequent time urgency sorting and appointment item complexity evaluation. The second time urgency sorting is performed using the patient's physical examination item average duration data to obtain the second time urgency data. Then, the appointment item complexity evaluation is performed using the first time urgency data and the second time urgency data to generate the appointment item complexity evaluation data. Based on the complexity assessment data of the appointment items, the second patient impact analysis is performed on the initial patient queue sequence to generate the second patient queue impact data. This helps to further optimize the queue sequence according to the duration and urgency of the physical examination items, and improve the efficiency of the appointment system and patient satisfaction.

[0036] Preferably, step S3 comprises the following steps:

[0037] Step S31: merging the first patient queue influence data and the second patient queue influence data to obtain comprehensive patient queue influence data;

[0038] Step S32: dividing the data set of the comprehensive impact data of patient queues to generate a model training set and a model test set; using a long short-term memory neural network algorithm to train the model training set to generate a patient physical examination waiting time training model;

[0039] Step S33: Iterate the model test of the patient physical examination waiting time training model through the model test set, so as to generate a patient physical examination waiting time prediction model; import the real-time queuing optimization sequence into the patient physical examination waiting time prediction model to predict the patient queuing waiting time, and generate patient queuing waiting time prediction data.

[0040] The present invention obtains comprehensive patient queuing influence data by merging the first patient queuing influence data and the second patient queuing influence data. By synthesizing the influence of different factors on patient queuing, the patient queuing situation can be evaluated more comprehensively. The comprehensive patient queuing influence data is divided into data sets to generate a model training set and a model test set. Then, the model training set is trained using a long short-term memory neural network algorithm to generate a patient physical examination waiting time training model. By using this neural network algorithm, long-term dependencies in time series data can be captured and the prediction ability of patient physical examination waiting time can be improved. The patient physical examination waiting time training model is iterated by model testing through the model test set, thereby generating a patient physical examination waiting time prediction model. Then, the real-time queuing optimization sequence is imported into the patient physical examination waiting time prediction model, and the patient queuing waiting time prediction is performed to generate the patient queuing waiting time prediction data. In this way, the patient's waiting time can be predicted using the trained model, which helps to make adjustments and arrangements in advance, optimize the queuing order, and reduce the patient's waiting time.

[0041] Preferably, step S4 comprises the following steps:

[0042] Step S41: Acquire physical examination center project resource data;

[0043] Step S42: Perform resource utilization analysis on the physical examination center project resource data to generate physical examination center project resource utilization data; perform multi-dimensional resource scheduling based on the physical examination center project resource utilization data to generate physical examination center project resource scheduling data;

[0044] Step S43: Perform user call voice broadcast according to the real-time queue optimization sequence and the patient queue waiting time prediction data to obtain user voice broadcast data;

[0045] Step S44: Associating the user's physical examination items with the physical examination center's project resource scheduling data according to the user's voice call data, and generating user's voice broadcast item association data; performing anomaly detection and warning on the user's voice broadcast item association data, and generating user anomaly detection and warning data.

[0046] The present invention obtains the project resource data of the physical examination center. These data may include information such as the number of resources and available time of different physical examination items, which are used for subsequent resource utilization analysis and scheduling. The resource utilization analysis is performed on the project resource data of the physical examination center to generate the project resource utilization data of the physical examination center. According to the resource utilization data, multi-dimensional resource scheduling is performed to generate the project resource scheduling data of the physical examination center. This can help evaluate the utilization of the project resources of the physical examination center, and reasonably allocate and schedule resources according to demand to improve the efficiency of resource utilization. According to the real-time queuing optimization sequence and the patient queuing waiting time prediction data, the user call voice broadcast is performed. This can be used to convey the call information of their physical examination items to the patient and remind them to go to the corresponding inspection area. According to the user call data, the physical examination center project resource scheduling data is associated with the user physical examination items, and the user voice broadcast item association data is generated. This helps to ensure the matching of the patient and the physical examination items and provide accurate voice broadcast information. Abnormal detection and early warning are performed on the user voice broadcast item association data to generate user abnormal detection and early warning data. This can help detect whether there is an abnormal situation in the association between the patient and the physical examination item, such as wrong association, repeated association, etc. By timely discovering and warning of abnormal situations, appropriate corrective measures can be taken to improve the accuracy and effectiveness of physical examination services.

[0047] Preferably, step S42 includes the following steps:

[0048] Step S421: Perform real-time resource monitoring feature analysis on the project resource data of the physical examination center to generate project resource feature data, wherein the project resource feature data includes equipment operation status data, doctor working hours data and room occupancy data;

[0049] Step S422: Calculate the project resource utilization rate according to the equipment operation status data, the doctor's working hours data and the room occupancy data to obtain the project resource utilization rate data of the physical examination center;

[0050] Step S423: comparing the physical examination center project resource utilization data with a preset standard project resource utilization threshold, and when the physical examination center project resource utilization data is greater than or equal to the preset standard project resource utilization threshold, generating a high-utilization project resource;

[0051] Step S424: When the physical examination center project resource utilization data is less than the preset standard project resource utilization threshold, low-utilization project resources are generated; priority resource allocation is performed based on high-utilization project resources and low-utilization project resources to generate physical examination center project resource scheduling data.

[0052] The present invention generates project resource feature data by performing real-time resource monitoring feature analysis on project resource data of a physical examination center. These feature data may include equipment operation status data, doctor working time data, room occupancy data, etc. By analyzing these features, the current status and utilization of various resources can be understood. According to the equipment operation status data, doctor working time data, and room occupancy data, project resource utilization rate calculation is performed to obtain project resource utilization rate data of a physical examination center. By calculating the utilization rate of resources, the utilization efficiency and sufficiency of resources can be evaluated. The project resource utilization rate data of a physical examination center is compared with a preset standard project resource utilization rate threshold. When the project resource utilization rate data of a physical examination center is greater than or equal to the preset standard project resource utilization rate threshold, it can be judged as a high-utilization project resource. When the project resource utilization rate data of a physical examination center is less than the preset standard project resource utilization rate threshold, it can be judged as a low-utilization project resource. Based on the high-utilization project resources and the low-utilization project resources, priority resource allocation is performed to generate project resource scheduling data of a physical examination center. By reasonably allocating resources, the utilization efficiency of low-utilization projects can be improved, while ensuring that high-utilization projects receive appropriate resource support.

[0053] Preferably, step S44 includes the following steps:

[0054] Step S441: extracting voice structured data from the user voice call data to obtain user voice call text data;

[0055] Step S442: Associating the user voice call text data with the physical examination center project resource scheduling data to generate user physical examination project association data;

[0056] Step S443: voice broadcasting the user's physical examination item-related data through natural language generation technology to generate user voice broadcast item-related data;

[0057] Step S444: Identify abnormal user responses to the user voice broadcast item-related data, generate abnormal user response data, and issue voice warning reminders based on the abnormal user response data.

[0058] The present invention obtains user voice call text data by extracting voice structured data from user voice call data. This step converts voice data into processable text data, which is convenient for subsequent processing and analysis. The user voice call text data and the project resource scheduling data of the physical examination center are related to each other to generate user physical examination project related data. This can help associate the user's voice call with the corresponding physical examination project to ensure that the correct project information is acquired and processed. The user physical examination project related data is voice broadcasted through natural language generation technology to generate user voice broadcast project related data. This can convert the user's physical examination project information into voice broadcast, which is used to convey to the user the inspection area or other relevant information that he should go to. The user voice broadcast project related data is identified for user abnormal response to generate user abnormal response data. Based on the user abnormal response data, a voice early warning reminder is performed. This can help identify the user's abnormal response to the voice broadcast, such as misunderstanding, no response, etc., so as to take timely measures to intervene and remind.

[0059] Preferably, step S5 comprises the following steps:

[0060] Step S51: performing closed-loop feedback control on the user voice broadcast item associated data to generate intelligent physical examination queuing call feedback control data;

[0061] Step S52: synchronize the user abnormality detection and warning data with the intelligent physical examination queue call feedback control data in real time to generate physical examination queue call synchronization data; perform multi-terminal fusion interface interaction on the physical examination queue call synchronization data to generate a user interaction log to execute the intelligent physical examination queue call system management operation.

[0062] The present invention generates intelligent physical examination queue call feedback control data by performing closed-loop feedback control on the user voice broadcast project association data. This means that the system can intelligently regulate the queue call according to the user's feedback and needs to improve the efficiency of the physical examination queue and user satisfaction. The user's abnormal detection and warning data and the intelligent physical examination queue call feedback control data are synchronized in real time to generate physical examination queue call synchronization data. This means that the system can synchronize the abnormal detection and warning data with the queue call control data to ensure the accuracy and real-time nature of the queue call. The physical examination queue call synchronization data is interactively interacted with the multi-terminal fusion interface to generate a user interaction log to execute the intelligent physical examination queue call system management operation. This means that the system can interact with the user through a variety of interactive interfaces and record the user's interaction log for system management and optimization.

[0063] The beneficial effect of the present invention is that by screening and fusing multimodal features of patient physical examination appointment data, key data can be extracted and a standard patient physical examination appointment fusion vector can be generated. This can reduce data redundancy and provide higher quality data for subsequent data processing and analysis. Based on the standard patient physical examination appointment fusion vector, the system can construct personalized data and generate patient holographic archive data. This helps medical institutions understand the health status and needs of patients and prepare for providing personalized medical services. By performing health queuing impact analysis and appointment project complexity impact analysis on key data of patient physical examination appointments, the system can generate patient queuing impact data. Using these data, the initial patient queuing sequence can be optimized in real time to minimize patient waiting time and improve service efficiency. By analyzing the comprehensive impact data of patient queuing, the system can predict the waiting time of patients. This is beneficial to both patients and medical institutions. Patients can understand their waiting time in advance, and medical institutions can better perform resource scheduling and time arrangements. By acquiring the project resource data of the physical examination center and performing multidimensional resource scheduling, the system can generate project resource scheduling data for the physical examination center. Combined with the real-time queue optimization sequence and patient queue waiting time prediction data, the system can associate user voice calls with projects, and provide accurate user voice broadcasts and call sequences. At the same time, the system can also perform anomaly detection and early warning to promptly discover and solve potential problems. Through real-time synchronization of user voice broadcast project association data and user anomaly detection and early warning data, the system can generate physical examination queue call synchronization data. This helps to maintain the real-time and accuracy of the system. At the same time, through multi-terminal fusion interface interaction, the system can provide user interaction logs to facilitate system management and optimization. Therefore, the present invention comprehensively improves the operating efficiency of queue call management by improving data processing, queue optimization, waiting time prediction, resource scheduling, voice calls, anomaly detection and multi-terminal interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A schematic diagram of the steps of a management method based on an intelligent physical examination queuing call system;

[0065] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0066] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0067] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0068] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0069] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0070] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0071] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0072] To achieve this, please refer to Figures 1 to 4 , a management method based on an intelligent physical examination queuing call system, the method comprising the following steps:

[0073] Step S1: Acquire patient physical examination appointment data; filter the key data stream of the patient physical examination appointment data to obtain the key data of the patient physical examination appointment; perform multimodal feature fusion on the key data of the patient physical examination appointment to generate a standard patient physical examination appointment fusion vector; perform personalized data construction based on the standard patient physical examination appointment fusion vector to generate patient holographic file data;

[0074] Step S2: construct an initial queuing sequence for the patient holographic archive data to obtain an initial patient queuing sequence; perform a health queuing impact analysis on the initial patient queuing sequence according to the patient physical examination appointment key data to generate first patient queuing impact data; perform an appointment item complexity impact analysis on the initial patient queuing sequence according to the patient physical examination appointment key data to generate second patient queuing impact data; perform real-time queuing order optimization on the initial patient queuing sequence according to the first patient queuing impact data and the second patient queuing impact data to generate a real-time queuing optimization sequence;

[0075] Step S3: merging the first patient queue impact data and the second patient queue impact data to obtain comprehensive patient queue impact data; predicting the patient queue waiting time based on the comprehensive patient queue impact data to generate patient queue waiting time prediction data;

[0076] Step S4: Acquire the project resource data of the physical examination center; perform multi-dimensional resource scheduling on the project resource data of the physical examination center to generate the project resource scheduling data of the physical examination center; perform user call voice broadcast according to the real-time queuing optimization sequence and the patient queuing waiting time prediction data to obtain the user voice broadcast data; associate the user physical examination project with the project resource scheduling data of the physical examination center according to the user voice call data to generate the user voice broadcast project association data; perform anomaly detection and early warning on the user voice broadcast project association data to generate the user anomaly detection and early warning data;

[0077] Step S5: Perform real-time data synchronization on the user voice broadcast item association data and the user abnormality detection and warning data to generate physical examination queue call synchronization data; perform multi-terminal fusion interface interaction on the physical examination queue call synchronization data to generate a user interaction log to execute the intelligent physical examination queue call system management operation.

[0078] The present invention collects the appointment information of all patients. Extracts important information from the appointment data, such as appointment time, patient health status, appointment items, etc. Fusion of different types of data (such as text, numbers, etc.) generates a standardized patient physical examination appointment fusion vector. According to the standardized vector, the holographic archive data of each patient is constructed to fully reflect the patient's physical examination information and health status. According to the patient's holographic archive data, the physical examination order of all patients is preliminarily arranged. The influence of each patient's health status on the queue order is analyzed to generate the first patient queue influence data. The influence of the complexity of each patient's appointment item on the queue order is analyzed to generate the second patient queue influence data. Combined with the health degree and project complexity influence data, the initial queue sequence is optimized to generate a real-time queue optimization sequence. Combined with the health degree and project complexity influence data, comprehensive influence data is obtained. According to the comprehensive influence data, the queue waiting time of each patient is predicted to generate corresponding prediction data. Collect resource data of the physical examination center, such as equipment availability, medical staff arrangement, etc. Scheduling is performed according to the resource data to ensure the optimal allocation of resources and generate scheduling data. Combined with the real-time queue optimization sequence and waiting time prediction data, the patient is notified through the voice broadcast system. The voice call data is associated with the physical examination items to ensure that the patient undergoes the correct project examination at the right time. The call data is monitored, abnormal situations are detected and early warnings are issued to ensure the smooth operation of the system. The voice broadcast and abnormal warning data are synchronized to ensure that the information is updated in real time. A user interaction interface is provided through a variety of devices (such as mobile phones, computers, etc.), and user operation logs are recorded. According to the user interaction log, system management and optimization are performed to ensure that the intelligent physical examination queuing call system operates efficiently, and efficient patient management and physical examination resource scheduling can be achieved, reducing patient waiting time, and improving the work efficiency and patient satisfaction of the physical examination center. Therefore, the present invention comprehensively improves the operating efficiency of queuing call management by improving data processing, queuing optimization, waiting time prediction, resource scheduling, voice calls, anomaly detection and multi-terminal interaction.

[0079] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a management method based on an intelligent physical examination queuing and calling system of the present invention. In this example, the management method based on an intelligent physical examination queuing and calling system includes the following steps:

[0080] Step S1: Acquire patient physical examination appointment data; filter the key data stream of the patient physical examination appointment data to obtain the key data of the patient physical examination appointment; perform multimodal feature fusion on the key data of the patient physical examination appointment to generate a standard patient physical examination appointment fusion vector; perform personalized data construction based on the standard patient physical examination appointment fusion vector to generate patient holographic file data;

[0081] In an embodiment of the present invention, the physical examination appointment data of the patient is obtained through the hospital information system (HIS), including but not limited to the patient's basic information (such as name, gender, age, ID number, etc.), appointment items, appointment time, appointment doctor, etc. The collected physical examination appointment data is preprocessed to filter out key data streams. Key data includes: basic information of the patient: name, gender, age, ID number, etc. Appointment information: physical examination items, physical examination time, physical examination location, appointment doctor, etc. Historical physical examination data: past physical examination records, examination results, etc. Medical history: past medical history, allergy history, family medical history, etc. Different types of key data are feature extracted and fused to generate a standardized patient physical examination appointment fusion vector. Structured data (such as age, gender, physical examination items) are numerically encoded or uniquely encoded. Natural language processing (NLP) is performed on unstructured data (such as past medical history, doctor's notes) to extract key features. The extracted features are fused using machine learning or deep learning algorithms (such as multi-layer perceptron, convolutional neural network, recurrent neural network, etc.) to generate a unified feature vector. Use the generated standardized patient physical examination appointment fusion vector to build personalized patient holographic archive data. Integrate the patient's basic information, physical examination appointment information, historical physical examination data and medical history to generate a comprehensive patient archive. According to the patient's feature vector, predict health risks and provide personalized health advice and physical examination item recommendations. Organize personalized data into a standard format, generate electronic archives, and store them in the hospital information system for easy query and management. Use database or cloud storage to securely store and back up the generated patient holographic archive data.

[0082] Step S2: construct an initial queuing sequence for the patient holographic archive data to obtain an initial patient queuing sequence; perform a health queuing impact analysis on the initial patient queuing sequence according to the patient physical examination appointment key data to generate first patient queuing impact data; perform an appointment item complexity impact analysis on the initial patient queuing sequence according to the patient physical examination appointment key data to generate second patient queuing impact data; perform real-time queuing order optimization on the initial patient queuing sequence according to the first patient queuing impact data and the second patient queuing impact data to generate a real-time queuing optimization sequence;

[0083] In an embodiment of the present invention, all patients are preliminarily queued based on the appointment time and appointment items of the patients to generate an initial queue sequence. This step is mainly arranged according to the order of appointment time. The holographic archive data of each patient is analyzed to evaluate the health of the patient. The health assessment includes: the severity of the past medical history; the urgency of the current physical examination appointment items; the age, gender and other factors affecting the health of the patient; using a predefined algorithm or machine learning model, the health score of each patient is scored to generate the first patient queue impact data. According to the patient's physical examination appointment items, the complexity of each patient's physical examination items is evaluated. The complexity assessment includes: the time required for the physical examination items; the professionalism and equipment requirements of the physical examination items; the difficulty of the physical examination items and the patient's cooperation. Using a predefined algorithm or machine learning model, the complexity score of each patient's physical examination items is scored to generate the second patient queue impact data. According to the health score and the complexity score, the urgency of each patient and the complexity of the appointment items are comprehensively considered to optimize the initial queue sequence. A multi-objective optimization algorithm or a priority queue algorithm can be used to sort patients according to health and complexity weights. During the optimization process, real-time dynamic changes are taken into account, such as new patients joining, appointment cancellations, etc., and real-time adjustments are made. Finally, an optimized real-time queue sequence is generated to better manage the order of patient physical examinations, improve physical examination efficiency and patient satisfaction.

[0084] Step S3: merging the first patient queue impact data and the second patient queue impact data to obtain comprehensive patient queue impact data; predicting the patient queue waiting time based on the comprehensive patient queue impact data to generate patient queue waiting time prediction data;

[0085] In an embodiment of the present invention, the first patient queue influence data (health queue influence data) and the second patient queue influence data (appointment item complexity influence data) are merged. Use an appropriate data structure (such as a data frame or table) to associate the two types of influence data to ensure that each patient can be associated with its health queue influence data and appointment item complexity influence data. In the merging process, different merging strategies can be selected, such as weighted average or priority sorting according to the order of precedence, to determine the comprehensive queue influence data of each patient. According to the pre-set weights (such as the importance of health and complexity), the two types of influence data are weighted averaged to obtain comprehensive influence data. According to the priority order of health and complexity influence data, select data with greater or more urgent influence for queuing priority consideration. Use the comprehensive influence data of patient queues to predict the patient's queue waiting time. Use a machine learning model (such as a regression model, a decision tree model, a neural network, etc.) or a statistical method (such as time series analysis, queue theory, etc.) to predict the queue waiting time. Select appropriate features, such as patient characteristics (health, age, etc.), physical examination item characteristics (complexity, duration, etc.), current queue situation (queue length, waiting time, etc.) as input. Based on historical data or simulated data, the prediction model is trained, and the model is evaluated and tuned to improve the prediction accuracy. Based on the trained prediction model, the waiting time of each patient is predicted to generate patient waiting time prediction data. In actual operation, data is continuously collected and updated to adjust and optimize the prediction model in real time to ensure the accuracy and timeliness of the prediction results.

[0086] Step S4: Acquire the project resource data of the physical examination center; perform multi-dimensional resource scheduling on the project resource data of the physical examination center to generate the project resource scheduling data of the physical examination center; perform user call voice broadcast according to the real-time queuing optimization sequence and the patient queuing waiting time prediction data to obtain the user voice broadcast data; associate the user physical examination project with the project resource scheduling data of the physical examination center according to the user voice call data to generate the user voice broadcast project association data; perform anomaly detection and early warning on the user voice broadcast project association data to generate the user anomaly detection and early warning data;

[0087] In an embodiment of the present invention, project resource data is obtained from the information system or database of the physical examination center. These data include: the distribution of equipment resources and human resources for various physical examination items; information such as the duration and complexity of each physical examination item; and a timetable or scheduling information of resource availability. The obtained physical examination center project resource data is scheduled using a resource scheduling algorithm (such as dynamic programming, a greedy algorithm, or a constraint-based scheduling algorithm). Consider the matching between the resource requirements and available resources for each physical examination item. Consider the real-time patient queuing situation and waiting time prediction to optimize the allocation and scheduling of resources. According to the real-time queuing optimization sequence and the patient queuing waiting time prediction data, the order of patients who need to undergo physical examinations is generated. The content of the voice broadcast is designed, including information such as the patient's name, physical examination items, and location, so as to notify the patient to undergo a physical examination. Ensure that the content of the voice broadcast is clear, accurate, and easy to understand. Associate the user's voice call data with the physical examination center project resource scheduling data to determine the specific physical examination items that each patient needs to undergo and the corresponding resource allocation. According to the patient information provided in the voice call data, the corresponding physical examination items and resource scheduling data are matched. Monitor and analyze the data associated with user voice broadcast items to detect abnormal situations, such as resource allocation errors, patients not arriving on time, etc. Use statistical methods or machine learning models to detect anomalies in the data and identify problematic situations. Generate early warning information based on the anomaly detection results so that medical staff can take timely action to avoid service interruptions or delays.

[0088] Step S5: Perform real-time data synchronization on the user voice broadcast item association data and the user abnormality detection and warning data to generate physical examination queue call synchronization data; perform multi-terminal fusion interface interaction on the physical examination queue call synchronization data to generate a user interaction log to execute the intelligent physical examination queue call system management operation.

[0089] In an embodiment of the present invention, by designing and implementing a data synchronization mechanism, it is ensured that the user voice broadcast project association data and abnormal detection warning data can be updated and synchronized in real time. According to business needs and data update speed, set an appropriate synchronization frequency to ensure the real-time and accuracy of the data. Develop a multi-terminal integrated user interface to integrate the physical examination queue call synchronization data to support the interactive operations of medical staff and managers. Design a user-friendly interface, including but not limited to desktop applications, web interfaces or mobile applications, to ensure the ease of use and functional integrity of the interface. Record the user's interactive behaviors and operations in the system and generate a user interaction log. Including detailed information such as user login information, operation time, operation content, operation results, etc. Execute management tasks of the intelligent physical examination queue call system based on user interaction logs and real-time data.

[0090] Preferably, step S1 comprises the following steps:

[0091] Step S11: using edge computing nodes to obtain patient physical examination appointment data;

[0092] Step S12: screening the key data stream of the patient's physical examination appointment data to obtain the patient's physical examination appointment key data, wherein the key data stream screening includes identity information screening, health status screening, appointment time screening and real-time location screening;

[0093] Step S13: preprocessing the key data of the patient's physical examination appointment to obtain standard key data of the patient's physical examination appointment, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization;

[0094] Step S14: extracting high-dimensional features from key data of standard patient physical examination appointments to obtain high-dimensional feature vectors of standard patient physical examination appointments; performing multimodal feature fusion on the high-dimensional feature vectors of standard patient physical examination appointments to generate standard patient physical examination appointment fusion vectors;

[0095] Step S15: construct personalized data based on the standard patient physical examination appointment fusion vector to generate patient holographic file data.

[0096] In an embodiment of the present invention, the patient's physical examination appointment data is obtained from multiple data sources (such as hospital information systems, appointment platforms, etc.) through edge computing nodes. Ensure data transmission security and real-time performance to ensure data accuracy and timeliness. Extract and verify the patient's identity information to ensure the uniqueness and accuracy of the data. Identify and extract data related to health status, such as medical history, allergies, etc. Filter and organize data according to appointment time to support subsequent time-related analysis and scheduling. Obtain and analyze the patient's real-time location data (if applicable) for personalized services and resource scheduling. Detect and repair errors or outliers in the data to ensure data quality. Use appropriate methods to fill missing data, such as mean value filling, interpolation, etc. Convert data into a unified standard format or unit for subsequent processing and analysis. Use feature extraction techniques (such as principal component analysis, feature selection algorithms, etc.) to extract representative high-dimensional features from standard patient physical examination appointment key data. Fusion of feature information from different modalities (such as physical indicators, health records, behavioral data, etc.) into a comprehensive feature vector. Use appropriate fusion methods (such as weighted average, feature cascade, etc.) to ensure that the fused feature vector can fully reflect the patient's physical examination appointment and health status. Based on the standard patient physical examination appointment fusion vector generated in the previous steps, combined with personalized needs and characteristics, build the patient's holographic archive data. Including but not limited to health assessment, risk analysis, physical examination recommendations and other information. Ensure the integrity and practicality of the holographic archive data to support subsequent personalized services and decisions.

[0097] As an example of the present invention, refer to Figure 2As shown, in this example, step S2 includes:

[0098] Step S21: clustering the patient holographic file data to generate patient clustering grouping data; constructing an initial queuing sequence according to the patient clustering grouping data to obtain an initial patient queuing sequence;

[0099] Step S22: Perform health assessment according to the key data of the patient's physical examination appointment to obtain the patient's physical examination appointment health assessment data; perform the first patient queue impact analysis on the initial patient queue sequence through the patient's appointment health assessment data to generate the first patient queue impact data;

[0100] Step S23: performing an appointment item complexity assessment based on the patient physical examination appointment key data to generate appointment item complexity assessment data; performing a second patient impact analysis on the initial patient queue sequence based on the appointment item complexity assessment data to generate second patient queue impact data;

[0101] Step S24: Optimize the initial patient queue sequence in real time according to the first patient queue impact data and the second patient queue impact data to generate a real-time queue optimization sequence.

[0102] In the embodiment of the present invention, by using the patient holographic archive data, the feature vector is prepared for cluster analysis. Select a suitable clustering algorithm, such as K-means clustering, hierarchical clustering or density clustering, and determine the number of clusters according to the actual situation. Cluster the patients to ensure that the patients in the same group have similar characteristics or needs, so as to ensure the effectiveness of subsequent queuing and resource allocation. Construct the initial patient queue sequence based on the cluster grouping data. Determine the initial position of each patient in the queue, and optimize the formation of the initial queue sequence in consideration of the patient's characteristics and clustering results. Use the patient's physical examination appointment key data, including health status, medical history, laboratory tests and other information, to assess the patient's health. Use a medical scoring system or algorithm to quantitatively assess the patient's health status and generate health assessment data. Analyze the impact of each patient on the queue order based on the health assessment data. Determine which patients need to undergo physical examinations first to improve the overall queuing efficiency and the patient's health management effect. According to the specific project information of the patient's appointment (such as examination type, equipment requirements, medical staff skill requirements, etc.), conduct a complexity assessment of the appointment project. Quantify the complexity of the appointment project based on factors such as resource consumption, time requirements and technical difficulty of the project. Analyze the impact of each patient's appointment items on the queue order based on the complexity evaluation data of the appointment items. Determine which items require more resources or time, thereby affecting the patient's queue order and waiting time. Combine the first patient's queue impact data and the second patient's queue impact data to optimize the initial patient queue sequence. Use optimization algorithms (such as greedy algorithms, genetic algorithms, or heuristic algorithms) to adjust the patient's queue order to minimize the overall waiting time and resource utilization.

[0103] Preferably, step S22 includes the following steps:

[0104] Step S221: collecting the patient's historical physical examination data for the patient's physical examination appointment key data to obtain the patient's historical physical examination data;

[0105] Step S222: extracting abnormal indicators from the patient's historical physical examination data to obtain abnormal indicator data of the patient's historical physical examination;

[0106] Step S223: using the entropy weight method to assign abnormal index weights to the abnormal index data of the patient's historical physical examination, and obtaining the abnormal index weights of the patient's historical physical examination; using the abnormal index weights of the patient's historical physical examination to evaluate the patient's health, and obtaining the patient's physical examination appointment health evaluation data;

[0107] Step S224: Perform a first patient queue impact analysis on the initial patient queue sequence using the patient appointment health assessment data to generate first patient queue impact data.

[0108] In an embodiment of the present invention, the patient's historical physical examination data is obtained from a hospital information system or other health record system. The data includes physiological indicators, medical history, diagnosis results, etc. Data mining and analysis techniques are used to extract abnormal indicators in the patient's historical physical examination data. Abnormal indicators involve physiological abnormalities, disease markers, health risks, etc. The entropy weight method is a multi-indicator weight determination method, which can determine the weight of each indicator in a comprehensive evaluation based on the information entropy of each indicator. The patient's historical physical examination abnormal indicator data is analyzed by entropy weight method, and the weight of each indicator is calculated to reflect its importance in health assessment. According to the weight of the patient's historical physical examination abnormal indicator, combined with the current physical examination appointment key data, a health assessment is performed. Health assessment data is generated by comprehensively considering the patient's physical condition, disease risk, health history and other factors. The health assessment data is used to analyze the degree of influence of each patient on the queue order. Determine which patients need to be given priority for physical examinations due to their health conditions to maximize resource utilization and patient health management effects.

[0109] Preferably, step S23 includes the following steps:

[0110] Step S231: Acquire current time data; collect patient appointment time for key data of patient physical examination appointment to obtain patient physical examination appointment time data;

[0111] Step S232: Calculate the appointment time difference of the patient's physical examination appointment time data based on the current time data to obtain the patient's appointment time difference data; sort the first time urgency based on the patient's appointment time difference data to obtain the first time urgency data;

[0112] Step S233: screening the physical examination items of the key data of the patient's physical examination appointment according to the patient's physical examination appointment time data to obtain the patient's physical examination item data; analyzing the average duration of the physical examination items on the patient's physical examination item data to generate the average duration data of the patient's physical examination items;

[0113] Step S234: Use the average duration data of the patient physical examination items to perform a second time urgency sort to obtain the second time urgency data; perform an appointment item complexity assessment using the first time urgency data and the second time urgency data to generate appointment item complexity assessment data; perform a second patient impact analysis on the initial patient queuing sequence based on the appointment item complexity assessment data to generate second patient queuing impact data.

[0114] In the embodiment of the present invention, the current time of the system is obtained for subsequent time difference calculation and urgency sorting. Appointment time information, including appointment time, appointment date, etc., is extracted from the patient's physical examination appointment data. The difference between the appointment time and the current time of each patient is calculated to determine the urgency of the appointment. According to the appointment time difference, the patients are sorted to determine which patients need to be treated first. Urgency can be defined according to the urgency of time, such as the appointment closer to the current time can be considered more urgent. According to the appointment time data, the specific physical examination items that each patient needs to undergo are determined. The screening includes ensuring that each patient obtains appropriate physical examination services based on factors such as medical advice, medical history, and appointment type. The average time consumption of each physical examination item is counted and analyzed, taking into account factors such as equipment usage time and medical staff deployment. According to the average duration of the physical examination items and the specific queuing situation, the patients are further sorted to determine the urgency of the physical examination items. The complexity of each patient's appointment items is evaluated by comprehensively considering the first time urgency and the second time urgency data. Considering the technical difficulty and resource consumption of the physical examination items, the patient queuing order is determined.

[0115] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0116] Step S31: merging the first patient queue influence data and the second patient queue influence data to obtain comprehensive patient queue influence data;

[0117] Step S32: dividing the data set of the comprehensive impact data of patient queues to generate a model training set and a model test set; using a long short-term memory neural network algorithm to train the model training set to generate a patient physical examination waiting time training model;

[0118] Step S33: Iterate the model test of the patient physical examination waiting time training model through the model test set, so as to generate a patient physical examination waiting time prediction model; import the real-time queuing optimization sequence into the patient physical examination waiting time prediction model to predict the patient queuing waiting time, and generate patient queuing waiting time prediction data.

[0119] In an embodiment of the present invention, the first patient queue impact data and the second patient queue impact data generated in step S24 are merged. The merger involves the integration of data fields, deduplication or other data cleaning operations to ensure the consistency and integrity of the data. The merged patient queue comprehensive impact data is divided into a model training set and a model test set. Usually, a cross-validation method or a method of retaining a portion of the data as a test set is used to ensure the independence and accuracy of model training and evaluation. A deep learning model suitable for time series prediction is selected, such as a long short-term memory (LSTM) neural network. LSTM is suitable for processing time series data and can capture long-term dependencies in the data. The selected LSTM model is trained using the model training set. During the training process, it is necessary to adjust the model parameters, select a suitable loss function, and perform back propagation to optimize the weights of the model. The performance of the trained LSTM model is evaluated using the model test set. The model is iteratively adjusted to optimize the generalization ability and prediction accuracy of the model. The real-time queue optimization sequence generated in step S5 is imported into the trained patient physical examination waiting time prediction model. The model is used to predict the waiting time of the patient in the current queue state.

[0120] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0121] Step S41: Acquire physical examination center project resource data;

[0122] Step S42: Perform resource utilization analysis on the physical examination center project resource data to generate physical examination center project resource utilization data; perform multi-dimensional resource scheduling based on the physical examination center project resource utilization data to generate physical examination center project resource scheduling data;

[0123] Step S43: Perform user call voice broadcast according to the real-time queue optimization sequence and the patient queue waiting time prediction data to obtain user voice broadcast data;

[0124] Step S44: Associating the user's physical examination items with the physical examination center's project resource scheduling data according to the user's voice call data, and generating user's voice broadcast item association data; performing anomaly detection and warning on the user's voice broadcast item association data, and generating user anomaly detection and warning data.

[0125] In an embodiment of the present invention, by obtaining the physical examination project resource data from the physical examination center management system or related database, including detailed information of resources such as equipment, personnel, and space. Analyze the utilization rate of various resources in the physical examination center, including equipment utilization rate, medical staff utilization rate, space utilization rate, etc. The frequency of use of resources, the duration of use, and other indicators can be calculated by statistical methods to evaluate the effective utilization of resources. Based on the resource utilization data, multi-dimensional resource scheduling is performed to optimize resource allocation and scheduling. Ensure the balanced use of resources in different time periods and different areas to cope with the dynamic needs of patients. According to the real-time queuing optimization sequence generated in step S5 and the patient queuing waiting time prediction data, formulate a voice broadcast strategy. The broadcast content may include information such as the patient's name, appointment items, and waiting time prediction to remind the patient to go to the corresponding physical examination items or locations. According to the user's voice call data and the actual physical examination item requirements, the patient is associated with the corresponding physical examination item resources. Ensure that each patient is properly supported by physical examination resources to avoid waste or delay of resources. Monitor and analyze the user's voice broadcast project association data to detect abnormal conditions (such as insufficient resource allocation, long patient waiting time, etc.). Design early warning mechanisms to promptly detect and resolve potential problems to improve service quality and patient satisfaction.

[0126] Preferably, step S42 includes the following steps:

[0127] Step S421: Perform real-time resource monitoring feature analysis on the project resource data of the physical examination center to generate project resource feature data, wherein the project resource feature data includes equipment operation status data, doctor working hours data and room occupancy data;

[0128] Step S422: Calculate the project resource utilization rate according to the equipment operation status data, the doctor's working hours data and the room occupancy data to obtain the project resource utilization rate data of the physical examination center;

[0129] Step S423: comparing the physical examination center project resource utilization data with a preset standard project resource utilization threshold, and when the physical examination center project resource utilization data is greater than or equal to the preset standard project resource utilization threshold, generating a high-utilization project resource;

[0130] Step S424: When the physical examination center project resource utilization data is less than the preset standard project resource utilization threshold, low-utilization project resources are generated; priority resource allocation is performed based on high-utilization project resources and low-utilization project resources to generate physical examination center project resource scheduling data.

[0131] In an embodiment of the present invention, by real-time monitoring of the project resources of the physical examination center, the operation status data of the equipment is obtained, including whether the equipment is operating normally, equipment failure, etc. The working time data of the doctor is monitored, and the working time and rest time of the doctor are recorded to understand the workload of the doctor. The occupancy data of the room is monitored, including which rooms are in use and which rooms are idle. Based on the equipment operation status data, the utilization rate of the equipment is calculated, that is, the proportion of the normal operation time of the equipment to the total time. Based on the working time data of the doctor, the utilization rate of the doctor is calculated, that is, the proportion of the working time of the doctor to the total time. Based on the room occupancy data, the utilization rate of the room is calculated, that is, the proportion of the occupied room time to the total time. The calculated physical examination center project resource utilization data is compared with the preset standard project resource utilization threshold. When the project resource utilization data is greater than or equal to the preset threshold, the project is marked as a high utilization project resource. When the project resource utilization data is less than the preset threshold, the project is marked as a low utilization project resource. Based on the high utilization project resources and the low utilization project resources, the priority allocation of resources is performed. It can be considered to give priority to the allocation of high utilization project resources to patients in need to improve the efficiency of resource utilization. Generate project resource scheduling data for the physical examination center, that is, which project resources are allocated to which patients for physical examinations.

[0132] Preferably, step S44 includes the following steps:

[0133] Step S441: extracting voice structured data from the user voice call data to obtain user voice call text data;

[0134] Step S442: Associating the user voice call text data with the physical examination center project resource scheduling data to generate user physical examination project association data;

[0135] Step S443: voice broadcasting the user's physical examination item-related data through natural language generation technology to generate user voice broadcast item-related data;

[0136] Step S444: Identify abnormal user responses to the user voice broadcast item-related data, generate abnormal user response data, and issue voice warning reminders based on the abnormal user response data.

[0137] In an embodiment of the present invention, the voice call data of the user is subjected to voice recognition to convert the voice into text data. The extracted text data is structured to extract key information, such as the patient's name, the appointment project, etc. The user's voice call text data is associated with the project resource scheduling data of the physical examination center to find the project resources related to the user's needs. The user's physical examination project association data is generated, that is, the user's voice call is associated with the available project resources to determine the physical examination projects that the user can perform. The user's physical examination project association data is converted into voice broadcast content by using natural language generation technology. The user's voice broadcast project association data is generated, that is, the physical examination projects that the user can perform are informed to the user by voice broadcast. The user's response to the voice broadcast is monitored, and the user's response is converted into text data by voice recognition technology. The user's abnormal response is identified to determine whether there is any abnormal situation of the user. The user's abnormal response data is generated, the user's abnormal situation is recorded, and a voice warning reminder is made based on the abnormal situation, and an alarm or notification is sent to the relevant personnel.

[0138] Preferably, step S5 comprises the following steps:

[0139] Step S51: performing closed-loop feedback control on the user voice broadcast item associated data to generate intelligent physical examination queuing call feedback control data;

[0140] Step S52: synchronize the user abnormality detection and warning data with the intelligent physical examination queue call feedback control data in real time to generate physical examination queue call synchronization data; perform multi-terminal fusion interface interaction on the physical examination queue call synchronization data to generate a user interaction log to execute the intelligent physical examination queue call system management operation.

[0141] In an embodiment of the present invention, by monitoring the user's response to the voice broadcast project associated data, the user's feedback information is voice recognized or converted to text. Closed-loop feedback control is performed according to the user's feedback information, such as confirming whether the user accepts the recommended physical examination items, whether the queue order needs to be adjusted, etc. Generate intelligent physical examination queue call feedback control data, that is, perform corresponding queue call control instructions according to user feedback. Real-time data synchronization is performed between user abnormal detection and early warning data and intelligent physical examination queue call feedback control data to ensure that abnormal conditions and user feedback can be reflected in the queue call system in a timely manner. Physical examination queue call synchronization data is generated from the synchronized data, including the user's physical examination queue information, abnormal conditions, feedback control instructions, etc. Multi-terminal fusion interface interaction is performed on the physical examination queue call synchronization data, that is, the data is displayed and interacted on different terminals, such as displayed on the doctor's workstation, the computer interface of the manager, etc. Generate a user interaction log to record the interaction between the user and the intelligent physical examination queue call system, including the user's operation, the system's response, etc., for system management and subsequent analysis.

[0142] The beneficial effect of the present invention is that by screening and fusing multimodal features of patient physical examination appointment data, key data can be extracted and a standard patient physical examination appointment fusion vector can be generated. This can reduce data redundancy and provide higher quality data for subsequent data processing and analysis. Based on the standard patient physical examination appointment fusion vector, the system can construct personalized data and generate patient holographic archive data. This helps medical institutions understand the health status and needs of patients and prepare for providing personalized medical services. By performing health queuing impact analysis and appointment project complexity impact analysis on key data of patient physical examination appointments, the system can generate patient queuing impact data. Using these data, the initial patient queuing sequence can be optimized in real time to minimize patient waiting time and improve service efficiency. By analyzing the comprehensive impact data of patient queuing, the system can predict the waiting time of patients. This is beneficial to both patients and medical institutions. Patients can understand their waiting time in advance, and medical institutions can better perform resource scheduling and time arrangements. By acquiring the project resource data of the physical examination center and performing multidimensional resource scheduling, the system can generate project resource scheduling data for the physical examination center. Combined with the real-time queue optimization sequence and patient queue waiting time prediction data, the system can associate user voice calls with projects, and provide accurate user voice broadcasts and call sequences. At the same time, the system can also perform anomaly detection and early warning to promptly discover and solve potential problems. Through real-time synchronization of user voice broadcast project association data and user anomaly detection and early warning data, the system can generate physical examination queue call synchronization data. This helps to maintain the real-time and accuracy of the system. At the same time, through multi-terminal fusion interface interaction, the system can provide user interaction logs to facilitate system management and optimization. Therefore, the present invention comprehensively improves the operating efficiency of queue call management by improving data processing, queue optimization, waiting time prediction, resource scheduling, voice calls, anomaly detection and multi-terminal interaction.

[0143] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0144] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A management method based on intelligent physical examination queuing call system, It is characterized in that The following steps are involved: Step S1: Obtaining patient physical examination appointment data; Screen the key data stream of the patient's physical examination appointment data to obtain the key data of the patient's physical examination appointment; Perform multimodal feature fusion on key data of patient physical examination appointments to generate a standard patient physical examination appointment fusion vector; perform personalized data construction based on the standard patient physical examination appointment fusion vector to generate patient holographic file data; Step S2: construct an initial queuing sequence for the patient holographic archive data to obtain an initial patient queuing sequence; perform a health queuing impact analysis on the initial patient queuing sequence based on the patient's physical examination appointment key data to generate the first patient queuing impact data; Perform an impact analysis of the complexity of appointment items on the initial patient queue sequence based on the key data of the patient's physical examination appointment, and generate the impact data of the second patient queue; Performing real-time queue order optimization on the initial patient queue sequence according to the first patient queue impact data and the second patient queue impact data to generate a real-time queue optimization sequence; Step S2 includes the following steps: Step S21: clustering the patient holographic file data to generate patient clustering grouping data; constructing an initial queuing sequence according to the patient clustering grouping data to obtain an initial patient queuing sequence; Step S22: Perform health assessment according to the patient physical examination appointment key data to obtain the patient physical examination appointment health assessment data; perform the first patient queue impact analysis on the initial patient queue sequence through the patient appointment health assessment data to generate the first patient queue impact data; Step S22 includes the following steps: Step S221: collecting the patient's historical physical examination data for the patient's physical examination appointment key data to obtain the patient's historical physical examination data; Step S222: extracting abnormal indicators from the patient's historical physical examination data to obtain abnormal indicator data of the patient's historical physical examination; Step S223: using the entropy weight method to assign abnormal index weights to the abnormal index data of the patient's historical physical examination, and obtaining the abnormal index weights of the patient's historical physical examination; using the abnormal index weights of the patient's historical physical examination to evaluate the patient's health, and obtaining the patient's physical examination appointment health evaluation data; Step S224: performing a first patient queue impact analysis on the initial patient queue sequence using the patient appointment health assessment data to generate first patient queue impact data; Step S23: perform an appointment item complexity assessment based on the patient physical examination appointment key data to generate appointment item complexity assessment data; perform a second patient impact analysis on the initial patient queue sequence based on the appointment item complexity assessment data to generate second patient queue impact data; Step S23 includes the following steps: Step S231: Acquire current time data; collect patient appointment time for key data of patient physical examination appointment to obtain patient physical examination appointment time data; Step S232: Calculate the appointment time difference of the patient's physical examination appointment time data based on the current time data to obtain the patient's appointment time difference data; sort the first time urgency based on the patient's appointment time difference data to obtain the first time urgency data; Step S233: screening the physical examination items of the key data of the patient's physical examination appointment according to the patient's physical examination appointment time data to obtain the patient's physical examination item data; analyzing the average duration of the physical examination items on the patient's physical examination item data to generate the average duration data of the patient's physical examination items; Step S234: using the average duration data of the patient's physical examination items to perform a second time urgency sorting to obtain second time urgency data; performing an appointment item complexity assessment using the first time urgency data and the second time urgency data to generate appointment item complexity assessment data; performing a second patient impact analysis on the initial patient queue sequence according to the appointment item complexity assessment data to generate second patient queue impact data; Step S24: optimizing the initial patient queue sequence in real time according to the first patient queue influence data and the second patient queue influence data to generate a real-time queue optimization sequence; Step S3: merging the first patient queue impact data and the second patient queue impact data to obtain comprehensive patient queue impact data; predicting the patient queue waiting time based on the comprehensive patient queue impact data to generate patient queue waiting time prediction data; Step S4: Acquire the project resource data of the physical examination center; perform multi-dimensional resource scheduling on the project resource data of the physical examination center to generate the project resource scheduling data of the physical examination center; perform user call voice broadcast according to the real-time queuing optimization sequence and the patient queuing waiting time prediction data to obtain the user voice broadcast data; associate the user physical examination project with the project resource scheduling data of the physical examination center according to the user voice call data to generate the user voice broadcast project association data; perform anomaly detection and early warning on the user voice broadcast project association data to generate the user anomaly detection and early warning data; Step S5: Perform real-time data synchronization on the user voice broadcast item association data and the user abnormality detection and warning data to generate physical examination queue call synchronization data; perform multi-terminal fusion interface interaction on the physical examination queue call synchronization data to generate a user interaction log to execute the intelligent physical examination queue call system management operation.

2. According to the management method based on the intelligent physical examination queuing call system of claim 1, It is characterized in that Step S1 includes the following steps: Step S11: using edge computing nodes to obtain patient physical examination appointment data; Step S12: screening the key data stream of the patient's physical examination appointment data to obtain the patient's physical examination appointment key data, wherein the key data stream screening includes identity information screening, health status screening, appointment time screening and real-time location screening; Step S13: preprocessing the key data of the patient's physical examination appointment to obtain standard key data of the patient's physical examination appointment, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization; Step S14: extracting high-dimensional features from key data of standard patient physical examination appointments to obtain high-dimensional feature vectors of standard patient physical examination appointments; performing multimodal feature fusion on the high-dimensional feature vectors of standard patient physical examination appointments to generate standard patient physical examination appointment fusion vectors; Step S15: construct personalized data based on the standard patient physical examination appointment fusion vector to generate patient holographic file data.

3. The management method based on the intelligent physical examination queuing call system according to claim 1, It is characterized in that Step S3 includes the following steps: Step S31: merging the first patient queue influence data and the second patient queue influence data to obtain comprehensive patient queue influence data; Step S32: dividing the data set for the comprehensive impact data of patient queues to generate a model training set and a model test set; using a long short-term memory neural network algorithm to train the model training set to generate a patient physical examination waiting time training model; Step S33: Iterate the model test of the patient physical examination waiting time training model through the model test set, so as to generate a patient physical examination waiting time prediction model; import the real-time queuing optimization sequence into the patient physical examination waiting time prediction model to predict the patient queuing waiting time, and generate patient queuing waiting time prediction data.

4. The management method based on the intelligent physical examination queuing call system according to claim 1, It is characterized in that Step S4 includes the following steps: Step S41: Acquire physical examination center project resource data; Step S42: Perform resource utilization analysis on the physical examination center project resource data to generate physical examination center project resource utilization data; perform multi-dimensional resource scheduling based on the physical examination center project resource utilization data to generate physical examination center project resource scheduling data; Step S43: Perform user call voice broadcast according to the real-time queue optimization sequence and the patient queue waiting time prediction data to obtain user voice broadcast data; Step S44: Associating the user's physical examination items with the physical examination center's project resource scheduling data according to the user's voice call data, and generating user's voice broadcast item association data; performing anomaly detection and warning on the user's voice broadcast item association data, and generating user anomaly detection and warning data.

5. The management method based on the intelligent physical examination queuing calling system according to claim 4, It is characterized in that Step S42 includes the following steps: Step S421: Perform real-time resource monitoring feature analysis on the project resource data of the physical examination center to generate project resource feature data, wherein the project resource feature data includes equipment operation status data, doctor working hours data and room occupancy data; Step S422: Calculate the project resource utilization rate according to the equipment operation status data, the doctor's working hours data and the room occupancy data to obtain the project resource utilization rate data of the physical examination center; Step S423: comparing the physical examination center project resource utilization data with a preset standard project resource utilization threshold, and when the physical examination center project resource utilization data is greater than or equal to the preset standard project resource utilization threshold, generating a high-utilization project resource; Step S424: When the physical examination center project resource utilization data is less than the preset standard project resource utilization threshold, low-utilization project resources are generated; priority resource allocation is performed based on high-utilization project resources and low-utilization project resources to generate physical examination center project resource scheduling data.

6. The management method based on the intelligent physical examination queuing calling system according to claim 4, It is characterized in that Step S44 includes the following steps: Step S441: extracting voice structured data from the user voice call data to obtain user voice call text data; Step S442: Associating the user voice call text data with the physical examination center project resource scheduling data to generate user physical examination project association data; Step S443: voice broadcasting the user's physical examination item-related data through natural language generation technology to generate user voice broadcast item-related data; Step S444: Identify abnormal user responses to the user voice broadcast item-related data, generate abnormal user response data, and issue voice warning reminders based on the abnormal user response data.

7. The management method based on the intelligent physical examination queuing calling system according to claim 1, It is characterized in that Step S5 includes the following steps: Step S51: performing closed-loop feedback control on the user voice broadcast item associated data to generate intelligent physical examination queuing call feedback control data; Step S52: synchronize the user abnormality detection and warning data with the intelligent physical examination queue call feedback control data in real time to generate physical examination queue call synchronization data; perform multi-terminal fusion interface interaction on the physical examination queue call synchronization data to generate a user interaction log to execute the intelligent physical examination queue call system management operation.