Medical resource scheduling optimization method based on digital twinning

Abstract

The invention discloses a medical resource scheduling optimization method based on digital twinning, and relates to the technical field of resource scheduling, and the method comprises the steps: carrying out the modeling of a target medical institution based on a digital twinning platform, and obtaining a target medical resource model; obtaining a historical medical resource demand and a historical medical state of the target medical institution, constructing a medical resource demand prediction model, and obtaining a medical resource demand prediction result; generating a plurality of alternative medical resource scheduling schemes, and obtaining an optimal medical resource scheduling scheme; and performing real-time scheduling on medical resources of the target medical institution based on the optimal medical resource scheduling scheme. The technical problems of unreasonable medical resource scheduling, low resource utilization rate and low medical service quality in the prior art are solved, and the technical effects of optimizing the medical resource scheduling scheme, improving the medical resource utilization efficiency and improving the medical service quality are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of resource scheduling, and in particular to a medical resource scheduling optimization method based on digital twins. Background Art

[0002] There are many defects in traditional medical resource management. On the one hand, medical equipment management lacks real-time monitoring, equipment and medical staff resource management are isolated from each other, and medical staff scheduling is based on experience, resulting in irrational use of equipment resources and uneven workload of personnel. On the other hand, resource demand forecasting does not make sufficient use of historical data, scheduling plans lack comprehensive consideration and quantitative evaluation, and there is no effective real-time monitoring mechanism during execution. All these lead to low efficiency in resource allocation and affected service quality.

[0003] The existing technology has technical problems such as unreasonable scheduling of medical resources, low resource utilization and low quality of medical services. Summary of the invention

[0004] The present application provides a medical resource scheduling optimization method based on digital twins, which is used to solve the technical problems of unreasonable medical resource scheduling, low resource utilization and medical service quality in the prior art.

[0005] In view of the above problems, the present application provides a dynamic scheduling method for an intelligent charging and swapping network, the method comprising: modeling the target medical institution based on a digital twin platform to obtain a target medical resource model; obtaining the historical medical resource demand and historical medical status of the target medical institution, and constructing a medical resource demand prediction model; combining the target medical resource model with real-time medical resource data, inputting the medical resource demand prediction model, and obtaining a medical resource demand prediction result; based on the medical resource demand prediction result, generating multiple alternative medical resource scheduling plans; analyzing multiple alternative medical resource scheduling plans to obtain the optimal medical resource scheduling plan; and scheduling the medical resources of the target medical institution in real time based on the optimal medical resource scheduling plan.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] Based on the digital twin platform, the target medical institution is modeled to obtain the target medical resource model; the historical medical resource demand and historical medical status of the target medical institution are obtained to build a medical resource demand prediction model; the target medical resource model is combined with real-time medical resource data, and the medical resource demand prediction model is input to obtain the medical resource demand prediction results; based on the medical resource demand prediction results, multiple alternative medical resource scheduling plans are generated; multiple alternative medical resource scheduling plans are analyzed to obtain the optimal medical resource scheduling plan; based on the optimal medical resource scheduling plan, the medical resources of the target medical institution are scheduled in real time. The technical effect of optimizing the medical resource scheduling plan, improving the utilization efficiency of medical resources, and improving the quality of medical services is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A flowchart of a medical resource scheduling optimization method based on digital twins provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of a process for constructing a medical resource demand prediction model in a medical resource scheduling optimization method based on digital twins provided in an embodiment of the present application. DETAILED DESCRIPTION

[0011] This application provides a medical resource scheduling optimization method based on digital twins to solve the technical problems of unreasonable medical resource scheduling, low resource utilization and medical service quality in the prior art.

[0012] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0013] Examples, such as Figure 1 As shown, the present application provides a medical resource scheduling optimization method based on digital twins, the method comprising:

[0014] Step S100: Model the target medical institution based on the digital twin platform to obtain a target medical resource model.

[0015] Specifically, firstly, the powerful functions of the digital twin platform are used to conduct a comprehensive and in-depth modeling of the target medical institution. The digital twin platform can integrate various data of medical institutions, including building layout, medical equipment information, medical staff configuration, patient flow and other information. For medical equipment, its model, performance parameters, usage records and maintenance history are recorded in detail. Through these data, an accurate medical equipment model is constructed in the digital twin platform, which can simulate the operating status, work efficiency and possible failure of the equipment. At the same time, for medical staff, their professional skills, scheduling, and number of personnel are considered to build a medical staff model to reflect their role and behavior in actual work. In addition, the building layout of the medical institution will be considered, including the distribution of wards, the location of departments, and the setting of channels, and this information will be integrated into the model to ensure that the model can accurately reflect the actual physical environment of the medical institution. Through the integration and modeling of this information, the target medical resource model is finally obtained. This model is a digital mapping of the target medical institution, which can reflect the current status of the medical institution in real time and provide a basis for the subsequent optimization of medical resource scheduling.

[0016] Step S200: Obtain the historical medical resource demand and historical medical status of the target medical institution, and build a medical resource demand prediction model.

[0017] Specifically, we collect rich historical data of the target medical institutions to gain an in-depth understanding of the evolution of their medical resource needs and changes in their medical status, and obtain the specific demand data for various medical resources such as beds, equipment, and medical staff in different time periods in the past. These data reflect the time distribution and quantity changes of medical resource needs. At the same time, we collect relevant information about the historical medical status, including the number of patients' visits, treatment cycles, and discharge rates. This information helps us grasp the characteristics of the patients' conditions and treatment demand patterns. The collected historical medical resource demand and historical medical status data are carefully standardized. This process aims to eliminate inconsistencies and outliers in the data and ensure the quality and reliability of the data. Through standardization, we can convert these data into a unified format for subsequent analysis and modeling. Based on the standardized data, we deeply analyze the use trend of medical resources, and by mining the potential patterns and associations in the data, we find the relationship between medical resource demand and various factors, such as seasonal changes, disease epidemic trends, and changes in population structure, which affect the demand for medical resources. We use advanced machine learning algorithms to train the data. Machine learning algorithms can automatically learn complex patterns and laws in data, thereby building a model that can accurately predict the demand for medical resources. This model can predict the demand for medical resources in the future based on the current medical status and various related factors, and provide a scientific basis for the rational allocation of medical resources. Through the above steps, the construction of a medical resource demand prediction model has laid a solid foundation for the optimal scheduling of medical resources.

[0018] Step S300: combining the target medical resource model with real-time medical resource data, inputting the medical resource demand prediction model, and obtaining a medical resource demand prediction result.

[0019] Specifically, the target medical resource model is first closely combined with the medical resource data collected in real time. The real-time medical resource data includes the real-time status of various medical resources in the current medical institutions, such as the occupancy of beds, the operating parameters of equipment, the on-the-job status of medical staff, etc. These data can accurately reflect the actual configuration and use of current medical resources. Then, the integrated information is input into the medical resource demand prediction model, which is built based on the historical medical resource demand and historical medical status data previously obtained, and has strong prediction capabilities. After the relevant information is input, the model will quickly analyze and calculate. It will fully consider the structure, resource allocation and operation rules of the medical institutions contained in the target medical resource model, and combine the current actual situation reflected by the real-time medical resource data. Through the comprehensive analysis of this information, the model can predict the demand for medical resources in the future. For example, it can predict the number of beds required for a specific type of bed, the expected frequency of use of a certain type of equipment, and the approximate number of medical staff required in a specific time period. Ultimately, the medical resource demand forecast results obtained will provide important decision-making basis for the scheduling and optimization of medical resources, which will help medical institutions prepare for resource allocation in advance, ensure that patients' needs can be met in a timely manner, and improve the quality and efficiency of medical services.

[0020] Step S400: Generate multiple alternative medical resource scheduling solutions based on the medical resource demand prediction results.

[0021] Specifically, make full use of the information provided by the forecast results of medical resource demand, which show in detail the demand for medical resources in the future, including the specific demand quantity and time distribution for beds, equipment, medical staff, etc. Based on these forecast results, start to formulate multiple alternative medical resource scheduling plans. First, consider the existing resource allocation of medical institutions, including the number of available beds, the type and number of equipment, the professional skills and scheduling of medical staff, etc. Then, combine the demand for different resources in the forecast results to formulate a series of different scheduling strategies. For example, for bed scheduling, formulate plans to increase or decrease the number of beds in certain wards, or adjust the allocation of beds to better meet the needs of patients. For equipment scheduling, consider the deployment of equipment, the adjustment of maintenance plans, or the possibility of purchasing new equipment. In terms of medical staff scheduling, consider adjusting the scheduling plan, arranging training to improve the skill level of medical staff, or recruiting new personnel. In addition, different demand scenarios and emergencies will be considered, and corresponding emergency plans and backup plans will be formulated. These alternative plans will take into account various possibilities to ensure that medical resources can be effectively deployed in different situations. In this way, multiple alternative medical resource scheduling plans are generated, providing rich options for subsequent plan selection and optimization.

[0022] Step S500: Analyze multiple candidate medical resource scheduling plans to obtain the optimal medical resource scheduling plan.

[0023] Specifically, the generated multiple alternative medical resource scheduling schemes are analyzed in depth and detail. First, a comprehensive evaluation index system is established, which covers multiple key factors, such as the utilization rate of medical resources, the waiting time of patients, the quality and efficiency of medical services, and cost-effectiveness. These indicators will help to objectively evaluate the pros and cons of each alternative. Then, for each alternative, its performance on each evaluation indicator is analyzed in detail. For example, for resource utilization, it is evaluated whether the scheme can make full use of existing medical resources and avoid idleness and waste of resources; for patient waiting time, it is considered whether the scheme can effectively reduce the waiting time of patients in registration, medical treatment, examination and other links, and improve patient satisfaction; for the quality and efficiency of medical services, it is concerned whether the scheme can ensure the accuracy and timeliness of medical services, and whether it can reasonably arrange the work of medical staff and improve work efficiency. In the analysis process, various practical factors and constraints will also be considered, such as the existing facilities and equipment conditions of medical institutions, the number and skill level of medical staff, and the requirements of laws and regulations. At the same time, the feasibility and operability of different schemes will also be considered to ensure that the selected scheme can be smoothly implemented in practice. Through comprehensive and in-depth analysis and comparison of multiple alternatives, the best medical resource scheduling solution is selected. This solution will maximize resource utilization efficiency, reduce patient waiting time, improve medical service quality, and take into account cost-effectiveness on the basis of meeting medical resource needs, providing strong support for the efficient operation of medical institutions.

[0024] Step S600: Performing real-time scheduling of medical resources of the target medical institution based on the optimal medical resource scheduling plan.

[0025] Specifically, according to the selected optimal medical resource scheduling scheme, the medical resources of the target medical institution are accurately and timely scheduled. First, the optimal scheme is converted into specific scheduling instructions, which will clearly specify the allocation method and time arrangement of various medical resources. Subsequently, these scheduling instructions are quickly conveyed to relevant departments and personnel through the information management system within the medical institution. For example, the ward manager is notified to adjust the allocation of beds, the equipment management department is informed to reasonably allocate the use of equipment, and the work shifts and responsibilities of medical staff are arranged. During the scheduling process, the actual operation of medical resources is monitored in real time to ensure that the scheduling instructions are accurately executed. Through the connection with IoT devices and sensors, the status information of medical resources can be obtained in real time, such as the occupancy of beds, the operating parameters of equipment, the work progress of medical staff, etc. If the actual situation is found to be different from the scheduling plan, it is analyzed and adjusted immediately. For example, when the number of patients in a department suddenly increases, resulting in a shortage of beds, the idle beds of other departments are promptly allocated or temporary beds are added; if a certain equipment fails, repairs are quickly arranged or spare equipment is called to ensure the continuity of medical services. At the same time, pay close attention to the needs and feedback of patients and dynamically optimize the scheduling plan according to the actual situation. For example, according to the changes in the patient's condition, timely adjust the configuration of medical staff or arrange further examinations and treatments. Through real-time scheduling and dynamic adjustments, ensure that medical resources are optimally configured, improve the operating efficiency and service quality of medical institutions, and provide patients with more timely and effective medical services.

[0026] In a possible implementation, step S100 further includes:

[0027] Step S110: Modeling the medical equipment system based on the digital twin platform to obtain a medical equipment model, wherein the medical institution includes a medical equipment system and a medical staff system;

[0028] Step S120: Modeling the medical staff system based on the digital twin platform to obtain a medical staff model;

[0029] Step S130: The medical equipment model and the medical staff model are integrated to generate the medical resource model.

[0030] Specifically, the powerful functions of the digital twin platform are used to comprehensively model the medical equipment system. First, various information about medical equipment is collected in detail, including the type, model, specifications, performance parameters, usage records, maintenance records, etc. of the equipment. This information will be input into the digital twin platform, and the platform will build a digital model of the medical equipment based on this data. This model can accurately simulate the operating status, working principle, and possible failure conditions of the medical equipment. By analyzing the equipment model, we can better understand the performance and usage of the equipment, providing an important basis for the optimal scheduling of medical resources.

[0031] The medical staff system is also modeled based on the digital twin platform. We collect relevant information about medical staff, such as name, major, skill level, work experience, and shift schedule. The digital twin platform will build a model of medical staff based on this information. The model can reflect the medical staff's work ability, scope of responsibilities, and role in the medical process. By analyzing the medical staff model, we can better arrange the work of medical staff and improve the quality and efficiency of medical services.

[0032] The medical equipment model and the medical staff model are integrated to generate a complete medical resource model. This model comprehensively considers the relationship between medical equipment and medical staff, and can accurately reflect the actual operation of medical institutions. Through the integrated model, medical resources can be better planned and dispatched, the optimal allocation of medical resources can be achieved, and the overall operational efficiency of medical institutions can be improved. For example, according to the needs of patients and the use of medical equipment, the work of medical staff can be reasonably arranged to ensure that patients can receive timely and effective treatment. At the same time, the model can predict the failure of medical equipment, prepare for maintenance and replacement in advance, and reduce the impact of equipment failure on medical services.

[0033] In a possible implementation, step S110 further includes:

[0034] Step S111: Collect basic information of the medical device system according to the Internet of Things monitoring platform to obtain a medical device information set.

[0035] Step S112: performing data cleaning on the medical equipment information set to obtain a medical equipment basic data set.

[0036] Step S113: constructing the medical device model based on the digital twin platform and the medical device basic data set.

[0037] Specifically, in this step, the IoT monitoring platform plays a key role. It collects various basic information in real time by connecting to the medical equipment system. This information includes but is not limited to the model, specifications, production date, installation location, operating parameters, maintenance records, etc. of the medical equipment. The IoT monitoring platform uses sensors, smart terminals and other devices to comprehensively monitor each medical device to ensure accurate and timely data. For example, for an X-ray machine, the IoT monitoring platform will collect information such as its model, number of exposures, and radiation dose; for an electrocardiograph, it will collect information such as its measurement data and device status. By collecting this information, a rich set of medical equipment information is formed, which covers the relevant basic information of all medical equipment in medical institutions. The collection of this information is continuous, and the IoT monitoring platform will update the data in real time to reflect the latest status of the medical equipment system. Such real-time monitoring and data collection provide a solid foundation for subsequent data analysis and model building, enabling us to more accurately understand the operation of medical equipment and provide strong support for the optimal scheduling of medical resources.

[0038] After obtaining the medical equipment information set, it is necessary to clean the data to ensure the quality and reliability of the data. Data cleaning is an important step, which involves operations such as removing noise, correcting errors, and filling missing values. First, check each record in the data set to find abnormal data. These abnormal data include duplicate records, incorrect data formats, or unreasonable values. For duplicate records, delete them to ensure the uniqueness of the data. For incorrect data formats, we will correct them to meet unified standards. Next, deal with missing values. If some data fields are missing, try to fill these missing values ​​with other related data or information. For example, if the maintenance record of a device has some missing information for a period of time, refer to the historical maintenance records of the device or the maintenance of similar devices to make reasonable inferences and fill them. In addition, check the consistency of the data to ensure that the data is logically consistent. For example, the model and specifications of the equipment should match each other, and the operating parameters should be within a reasonable range. Through the above data cleaning process, impurities in the data are removed and the accuracy and completeness of the data are improved. Finally, the obtained basic data set of medical equipment will provide a reliable foundation for subsequent model construction and analysis.

[0039] Make full use of the powerful modeling capabilities of the digital twin platform and the basic data set of medical equipment after cleaning. First, import the various parameters and information in the basic data set of medical equipment into the digital twin platform, and reproduce the physical structure information of the equipment, such as size and shape, digitally in the platform to build the basic appearance architecture of the equipment. Then, the operating parameters of the equipment, such as power, operating frequency, accuracy and other related data, are simulated in the digital twin platform through algorithms and simulation engines. These operating parameters are converted into mathematical models and logical rules, so that the model can accurately reflect the performance of the equipment under different working conditions. If the data set contains information such as the failure mode and maintenance record of the equipment, the digital twin platform will integrate this information. The constructed model can simulate the possible failure conditions of the equipment and the corresponding maintenance requirements based on this information. At the same time, the digital twin platform will also establish the relationship between the equipment and the external environment in the model based on the interaction data between the equipment and other medical equipment or medical systems. In this way, the medical equipment model can not only reflect its own status, but also reflect its position and role in the entire medical system. Through the above meticulous operations, the medical equipment model constructed based on the digital twin platform and the basic data set of medical equipment can simulate the operation, failure, maintenance and other aspects of the actual medical equipment with a highly realistic manner, providing precise digital support for subsequent medical resource scheduling and optimization and other tasks.

[0040] In one possible implementation, Figure 2 As shown, step S200 also includes:

[0041] Step S210: Obtain the historical medical resource demand of the target medical institution, where the historical medical resource demand includes the demand for beds, equipment, and medical staff in different time periods.

[0042] Step S220: Acquire the historical medical status, which includes the number of patient visits, treatment cycles, and discharge rate.

[0043] Step S230: Standardize the historical medical resource demands and historical medical status to generate a medical resource usage trend.

[0044] Step S240: Based on the medical resource usage trend, a machine learning algorithm is used for training to construct a medical resource demand prediction model.

[0045] Specifically, the historical medical resource demand information of the target medical institution is collected, the time dimension is divided, and the demand data for beds, equipment and medical staff in the medical institution in different time periods are carefully sorted out. By consulting the archives of the medical institution, the data logs in the management system and other channels, the number of occupied beds, the frequency of use of various medical equipment, the attendance and deployment of medical staff in different departments and other information in each specific time period in the past, such as daily, weekly, monthly or even quarterly, are summarized to form a comprehensive and detailed historical medical resource demand data set.

[0046] Next, obtain data related to historical medical status. Among them, the number of patient visits is an important indicator, which reflects the busyness of medical institutions at different times and the potential demand pressure on medical resources. Treatment cycle data can help us understand the average treatment time for different diseases, which is crucial for the reasonable arrangement of beds and working hours of medical staff. The discharge rate reflects medical efficiency and resource turnover from another perspective. Extract these key data from the hospital's registration system, medical record database and related statistical reports, integrate information such as the number of patient visits, treatment cycles and discharge rates, and construct a data set of historical medical status.

[0047] After obtaining the data on historical medical resource demand and historical medical status, they need to be standardized. Since these data come from different systems, the format, unit and magnitude of the data may be different. Through a unified data processing method, the data is normalized or standardized so that all data are under the same metric. For example, data such as bed demand, equipment usage, and medical staff demand are converted into relative proportions or standard scores. For data such as the number of patient visits, treatment cycles, and discharge rates, corresponding standardization operations are also performed. After the processed data, trend analysis is performed through data analysis algorithms and statistical tools to draw a chart or curve of the trend of medical resource usage, which clearly shows how the use of medical resources changes over time, patient flow, and medical efficiency.

[0048] After preprocessing, the trend data of medical resource usage is used as the input of the neural network. The neural network consists of an input layer, a hidden layer, and an output layer. The neurons in the input layer receive data related to the trend of medical resource usage, such as the incidence of different types of diseases, seasonal factors, population mobility data, and other information in the past period of time. During the training process, these input data are subjected to complex operations through the hidden layer. Each neuron in the hidden layer is connected to the neurons in the previous layer through weights. After the data is weighted and summed, it is transformed nonlinearly through the activation function. For example, commonly used activation functions such as the ReLU function can increase the nonlinear expression ability of the model. The neural network adjusts the weights through the back propagation algorithm. In the forward propagation, the input data is calculated by the network to obtain the output, which is compared with the actual medical resource demand data (such as the actual demand for beds, equipment, and medical staff) to calculate the error. This error is transmitted from the output layer to the hidden layer and the input layer in sequence through back propagation. During the transmission process, the gradient of each weight is calculated according to the error, and then the weight is updated according to a certain learning rate, so that the output of the network gradually approaches the actual medical resource demand. As the training continues, the neural network continuously adjusts the weights to minimize the error. In each round of training, the network is learning the complex relationship between the trend of medical resource usage and demand. After training, the model is evaluated using test data. The test data is input into the trained neural network to obtain the predicted value of medical resource demand, which is then compared with the actual demand value. The performance of the model is evaluated by calculating indicators such as mean square error and accuracy. If the model performance is not good enough, adjust the structure of the network, such as increasing the number of hidden layers or the number of neurons, or adjust parameters such as the learning rate, and retrain until a satisfactory medical resource demand prediction model is obtained.

[0049] In a possible implementation, step S300 further includes:

[0050] Step S310: input the real-time medical resource data into the target medical resource model to generate the current medical resource status.

[0051] Step S320: Based on the current medical resource status, a medical resource demand prediction model is input to perform resource demand prediction to obtain the medical resource demand prediction result.

[0052] Specifically, real-time medical resource data is obtained, which covers all aspects of information in the current medical institutions, such as the current occupancy of beds, including the number of patients already admitted, the number of vacant beds, and the use status of beds in different wards; real-time operation data of medical equipment, such as whether the equipment is in working condition, the remaining use time of the equipment or the use time; the current working status information of medical staff, such as which medical staff are on duty, which are performing surgery or making rounds. Input these rich and real-time medical resource data into the constructed target medical resource model. The target medical resource model is based on the previous modeling work and contains information such as the overall structure of the medical institution and the configuration of medical equipment and medical staff. When the real-time data is input, the model will integrate and analyze these data according to its internal algorithms and logic. Through simulation and calculation, a detailed and accurate current medical resource status is generated. This status clearly presents the resource utilization of the medical institution at the current moment, such as whether the beds in each department are tight, which key medical equipment is under-loaded, or whether there are areas where medical staff are understaffed.

[0053] After obtaining the current medical resource status, it is used as input information and input into the medical resource demand prediction model. The medical resource demand prediction model is built and trained based on historical medical resource demand and medical status data. It has the ability to analyze the current situation and predict future demand. After receiving the data of the current medical resource status, the prediction model will predict the resource demand according to the patterns and rules stored in it. It will comprehensively consider factors such as the current shortage of beds, the saturation of medical equipment, and the work pressure of medical staff, and combine the changing trend of medical resource demand under similar circumstances in historical data to perform complex calculations and reasoning. For example, if the current medical resource status shows that the bed utilization rate of a department has reached 80%, and the admission rate of patients in the department has been on the rise recently, and the working hours of medical staff are also increasing, the model will predict the number of beds required by the department and the number of medical staff that may need to be deployed in the future based on the historical changes in similar bed utilization rates and patient admission rates. Through such a process, we finally obtained the forecast results of medical resource demand. These results provided key decision-making basis for subsequent medical resource scheduling, enabling medical institutions to prepare for resource allocation in advance to better meet the medical needs of patients.

[0054] In a possible implementation, step S400 further includes:

[0055] Step S410: Determine the demand change trend of different medical resources according to the medical resource demand prediction result.

[0056] Step S420: Based on the demand change trends of the different medical resources and in combination with different demand scenarios, generate the multiple alternative medical resource scheduling solutions.

[0057] Specifically, the focus is on the in-depth analysis of the forecast results of medical resource demand. After obtaining the forecast results of medical resource demand, we start to carefully sort out the information contained therein. For bed resources, we analyze the changes in bed demand over time in the forecast results. It is found that with the change of seasons, the high incidence of certain diseases leads to an increase in hospitalized patients, and the demand for beds shows a clear upward trend; or in some special periods, such as after holidays, the demand for beds will have a short peak. For medical equipment, the demand changes of different equipment are analyzed according to the forecast results. In terms of medical staff, it can be seen from the forecast results that when the hospital carries out new complex surgical projects, the demand for medical staff with relevant professional skills will increase; in the period of time with large patient flow, the demand for nursing staff will also have a corresponding increase trend. Through the careful interpretation of these medical resource demand forecast results, the demand change trends of different medical resources are clarified. These trend information is an important basis for generating alternative medical resource scheduling plans, allowing us to plan in advance and ensure that medical institutions can reasonably allocate resources and meet the needs of medical services when facing different situations.

[0058] Work should be carried out according to the already determined changing trends in demand for different medical resources. For bed resources, if the trend shows that the demand for beds will continue to increase in the future, consider multiple scenarios. For example, in daily demand scenarios, formulate plans to quickly organize and put into use some spare wards, or adjust the bed layout of the ward to increase the number of beds; in emergency demand scenarios such as public health emergencies, in addition to the above measures, you can also consider temporary construction of simple wards and other solutions. For medical equipment resources, when it is found that the demand for a certain type of equipment is on the rise, in regular demand scenarios, formulate plans to maintain existing equipment in advance and optimize equipment use scheduling to improve the efficiency of equipment use; in high-demand scenarios, such as large-scale disease screening periods, consider emergency procurement of new equipment or renting equipment from other medical institutions. As for medical staff resources, if the demand trend is increasing, in daily work scenarios, the medical staff's shifts can be adjusted, overtime can be increased, or medical staff from other departments can be temporarily deployed for support; in special medical peak scenarios, such as periods of concentrated major surgeries, in addition to internal deployment, temporary medical staff can be hired from outside or in cooperation with relevant medical schools to introduce interns to participate in auxiliary work. By combining the demand trend of different medical resources with different demand scenarios, various possible situations are fully considered, thereby generating multiple flexible, diverse, and targeted alternative medical resource scheduling plans.

[0059] In a possible implementation, step S500 further includes:

[0060] Step S510: Use a weighted algorithm to quantify the multiple candidate medical resource scheduling solutions to obtain the optimal medical resource scheduling solution.

[0061] Specifically, first, it is necessary to determine the key indicators used to evaluate each plan and their respective weights. These key indicators include resource utilization, the degree of reduction in patient waiting time, cost control, and the impact on the quality of medical services. For example, the weight of resource utilization can be set to 0.3. If a plan performs well in resource utilization, it can get a higher score on this indicator; the weight of the degree of reduction in patient waiting time is set to 0.35, because it is directly related to patient satisfaction. For each alternative medical resource scheduling plan, it is evaluated and scored according to these indicators. Taking resource utilization as an example, if a plan can make full use of idle beds and equipment resources and achieve a high level of utilization, then it can get a higher score on the indicator of resource utilization, assuming that it can be given 85 points; while if another plan performs generally in this regard, it will only get 60 points. Then, the score of each plan on each indicator is multiplied by the corresponding weight and accumulated. For example, if a plan scores 85 points in resource utilization, multiplied by a weight of 0.3, it will get 25.5 points; if it scores 75 points in reducing patient waiting time, multiplied by a weight of 0.35, it will get 26.25 points. And so on. The weighted results of all indicator scores are added together to get the total quantitative score of the plan. After performing such weighted quantitative calculations on all alternative plans, the total scores of each plan are compared. The plan with the highest total score is the optimal medical resource scheduling plan we have obtained. It takes into account various factors and achieves a relative balance between different indicators. It can meet the needs of medical resource scheduling to the greatest extent and achieve the optimal allocation of medical resources.

[0062] In a possible implementation, step S600 further includes:

[0063] Step S600: Establish a real-time monitoring mechanism to regularly evaluate and provide feedback on the execution effect of the optimal medical resource scheduling plan, and optimize the optimal medical resource scheduling plan based on the evaluation results.

[0064] Specifically, determine the key indicators for real-time monitoring, which are related to various aspects of medical resource scheduling. For example, for bed resources, monitor the occupancy rate and turnover rate of beds; for medical equipment, pay attention to the utilization rate and failure rate of equipment; for medical staff, observe the workload and work efficiency of staff. By setting up data collection points in the information system of medical institutions, data of these indicators can be collected in real time. Regularly evaluate the implementation effect of the optimal medical resource scheduling plan. For example, a centralized evaluation is conducted once a week or a month. During the evaluation process, the actual data collected is compared with the target data expected by the optimal scheduling plan. If the optimal plan expects to increase the bed turnover rate of a department to 3 times a week, but the actual monitoring finds that it is only 2 times a week, this indicates that the implementation effect deviates from the expectation. Feedback is given based on the evaluation results, and the problems and deviations found in the evaluation are promptly fed back to the relevant departments and personnel. For example, if it is found that the workload of medical staff is too high, resulting in a decline in service quality, this information will be fed back to the human resources department and managers of relevant departments. The optimal medical resource scheduling plan is optimized based on the feedback evaluation results. If it is found that the equipment utilization rate is low due to unreasonable equipment allocation, the equipment scheduling plan is readjusted to allocate some equipment from idle departments to departments with greater demand; if the scheduling of medical staff affects work efficiency, the scheduling plan is optimized, such as increasing the number of medical staff during peak hours, or adjusting the working hours and distribution of working hours of medical staff. Through this continuous evaluation, feedback and optimization process, it is ensured that the optimal medical resource scheduling plan can dynamically adapt to the actual operation of medical institutions and continuously improve the utilization efficiency of medical resources and the quality of medical services.

[0065] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0067] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A medical resource scheduling optimization method based on digital twins, characterized in that: The method comprises: Model the target medical institution based on the digital twin platform to obtain the target medical resource model; Obtain the historical medical resource demand and historical medical status of the target medical institution and build a medical resource demand prediction model; Combining the target medical resource model with the real-time medical resource data, inputting the medical resource demand prediction model, and obtaining a medical resource demand prediction result; Based on the medical resource demand prediction results, generate multiple alternative medical resource scheduling solutions; Analyze multiple alternative medical resource scheduling plans to obtain the optimal medical resource scheduling plan; The medical resources of the target medical institution are scheduled in real time based on the optimal medical resource scheduling plan.

2. A medical resource scheduling optimization method based on digital twins as described in claim 1, characterized in that: Model the target medical institution based on the digital twin platform to obtain the target medical resource model, including: Modeling a medical device system based on the digital twin platform to obtain a medical device model, wherein the medical institution includes a medical device system and a medical staff system; Modeling the medical staff system based on the digital twin platform to obtain a medical staff model; The medical equipment model and the medical staff model are integrated to generate the medical resource model.

3. A medical resource scheduling optimization method based on digital twins as described in claim 2, characterized in that: Modeling the medical device system based on the digital twin platform to obtain a medical device model includes: Collect basic information of the medical device system according to the Internet of Things monitoring platform to obtain a medical device information set; Performing data cleaning on the medical equipment information set to obtain a basic data set of medical equipment; Based on the digital twin platform and the medical device basic data set, the medical device model is constructed.

4. The medical resource scheduling optimization method based on digital twins according to claim 1, characterized in that: Obtain the historical medical resource demand and historical medical status of the target medical institution and build a medical resource demand prediction model, including: Obtaining the historical medical resource demand of the target medical institution, wherein the historical medical resource demand includes the demand for beds, equipment, and medical staff in different time periods; Obtaining the historical medical status, which includes the number of visits, treatment cycles, and discharge rates of the patient; Standardizing the historical medical resource demands and historical medical status to generate medical resource usage trends; Based on the medical resource usage trend, a machine learning algorithm is used for training to build a medical resource demand prediction model.

5. A medical resource scheduling optimization method based on digital twins as described in claim 4, characterized in that: Combining the target medical resource model with the real-time medical resource data, inputting the medical resource demand prediction model, and obtaining the medical resource demand prediction result, including: Inputting the real-time medical resource data into the target medical resource model to generate a current medical resource status; Based on the current medical resource status, a medical resource demand prediction model is input to perform resource demand prediction to obtain the medical resource demand prediction result.

6. A medical resource scheduling optimization method based on digital twins as described in claim 5, characterized in that: Based on the medical resource demand prediction results, multiple alternative medical resource scheduling solutions are generated, including: Determine the demand change trend of different medical resources according to the medical resource demand forecast result; Based on the changing trends in demand for the different medical resources and in combination with different demand scenarios, the multiple alternative medical resource scheduling solutions are generated.

7. A medical resource scheduling optimization method based on digital twins as claimed in claim 6, characterized in that: Analyze multiple alternative medical resource scheduling plans to obtain the optimal medical resource scheduling plan, including: A weighted algorithm is used to quantify the multiple candidate medical resource scheduling schemes to obtain the optimal medical resource scheduling scheme.

8. A medical resource scheduling optimization method based on digital twins as claimed in claim 7, characterized in that: The medical resources of the target medical institution are scheduled in real time based on the optimal medical resource scheduling scheme, including: Establish a real-time monitoring mechanism to regularly evaluate and provide feedback on the implementation effect of the optimal medical resource scheduling plan, and optimize the optimal medical resource scheduling plan based on the evaluation results.

Images