Medical equipment resource intelligent load sharing method and system
Optimizing the allocation of medical equipment resources through machine learning prediction models has solved the problems of unreasonable load sharing and inaccurate waiting time estimates in the existing technology, and achieved efficient utilization of equipment resources and improved patient service experience.
Patent Information
- Application Number
- CN202410905699.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-08
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure CN118919037A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and system for intelligent load sharing of medical equipment resources. Background Art
[0002] Medical equipment resources are key medical equipment resources in hospitals, such as magnetic resonance imaging equipment and other testing instruments. Modern large hospitals are generally equipped with multiple related equipment. How to improve the efficiency of the use of these equipment resources can, on the one hand, improve patients' waiting time and improve the quality of medical services; on the other hand, it can enhance the economic value of the equipment throughout its life cycle, reduce the operating cost of the equipment throughout its life cycle, and maximize the value of the equipment.
[0003] The existing technology arranges the equipment resources for providing services to patients based on the shortest queue. That is, if there are multiple identical devices providing services at the same time, the queue with the least number of people in the queue is selected according to the number of people in the queue at each device, and the new patient is arranged in this queue to wait. The existing solution has the following disadvantages:
[0004] (1) Existing patients are assigned equipment based on the shortest queue number, but the actual time required to serve each patient is related to many factors, such as the examination items and parts, the proficiency of technicians, the patient's compliance, the current equipment examination status, etc. These factors will make it impossible to achieve reasonable load sharing among all medical equipment resources and cannot maximize the use of existing medical equipment resources. In addition, it will often lead to patient service queues;
[0005] (2) The existing scheme does not provide patients with an estimated waiting time, although they know the number of people waiting in line ahead of them. This makes it difficult for patients to arrange their own examination items reasonably. Summary of the invention
[0006] In order to overcome the above technical defects, the first aspect of the present invention provides a method for intelligent load sharing of medical equipment resources, which comprises:
[0007] Step S1: Obtain the basic data of the current patient Check project data Collect data of technicians on duty for each device And current device status data Constructing input parameters for machine learning prediction models The input parameters are then fed into a machine learning prediction model for predicting patient exam times and wait times:
[0008]
[0009] Where L means there are L devices or L waiting queues;
[0010] Step S2: Obtaining input parameters After that, the machine learning prediction model performs the following data processing in sequence:
[0011] First, calculate the patient's predicted examination time:
[0012]
[0013] in, Indicates the predicted examination time of the i-th patient in the patient queue with the current number of equipment resource l;
[0014] Then, calculate the patient's predicted waiting time: in The calculation method is:
[0015]
[0016] Among them, the current number is the waiting time required for the i-th patient in the patient queue of the equipment resource l That is, the sum of the patient examination times predicted for all the patients in the previous queue;
[0017] Finally, the predicted waiting time for patients in each device waiting queue was compared Select the waiting queue with the shortest waiting time and arrange the new patient in this queue. The calculation process is as follows:
[0018]
[0019] Among them, min means taking the minimum value of the above predicted waiting time.
[0020] Furthermore, in step S1, the method for constructing a machine learning prediction model for predicting patient examination time and waiting time includes:
[0021] Step S1.1: Collect basic patient data A, examination item data B, technician operator data C, current equipment status data D and actual time data T required for patient examination of several patients;
[0022] Step S1.2: The above five types of data for each patient are organized into a data set:
[0023] N={{P,T}
[0024] Where, P = {A, C, D, B};
[0025] Construct the datasets of all patients into a training dataset:
[0026] N={N1,N2,...,N n}
[0027] Among them, N n is the dataset N of the nth patient;
[0028] Step S1.3: Based on the training data set and using a clustering algorithm, a machine learning prediction model for predicting patient examination time and waiting time is trained and constructed.
[0029] Furthermore, the medical equipment resource intelligent load sharing method further includes step S3: updating the input parameters of the current patient in real time When the input parameter When a change occurs, steps S1 and S2 are repeated.
[0030] Furthermore, step S1 also includes: obtaining basic data of the current batch of patients Check project data Collect data of technicians on duty for each device And current device status data Constructing input parameters for machine learning prediction models The input parameters are then fed into the trained machine learning prediction model:
[0031]
[0032] Where L means there are L devices or L waiting queues;
[0033] The step S2 also includes: obtaining the input parameters of the current batch of patients After that, the trained machine learning prediction model performs the following data processing in sequence:
[0034] First, calculate the predicted examination time for the current batch of patients
[0035]
[0036] Among them, there are K new patients in the current batch of patients, k represents the serial number of the patients in this batch, and l represents the serial number of all equipment resources;
[0037] Secondly, calculate the predicted waiting time for this batch of patients
[0038]
[0039] Then, compare the predicted waiting time of the batch of patients in each device waiting queue Select the waiting queue with the shortest waiting time and arrange the patients who spend the shortest time in this queue. The calculation process is as follows:
[0040]
[0041] Finally, the above method is repeated for the remaining patients to arrange equipment resources until the last patient in the batch.
[0042] A second aspect of the present invention provides a medical equipment resource intelligent load sharing system, which includes: a data acquisition module and a medical equipment resource intelligent load sharing module;
[0043] The data acquisition module is used to acquire the basic data of the current patient Check project data Collect data of technicians on duty for each device And current device status data Constructing input parameters for machine learning prediction models Then the input parameters are input into the intelligent load sharing module for medical device resources:
[0044]
[0045] Where L means there are L devices or L waiting queues;
[0046] The medical equipment resource intelligent load sharing module is used to obtain input parameters After that, the machine learning prediction model is used to perform the following data processing in sequence:
[0047] First, calculate the patient's predicted examination time:
[0048]
[0049] in, Indicates the predicted examination time of the i-th patient in the patient queue with the current number of equipment resource l;
[0050] Then, calculate the patient's predicted waiting time: in The calculation method is:
[0051]
[0052] Among them, the current number is the waiting time required for the i-th patient in the patient queue of the equipment resource l That is, the sum of the patient examination times predicted for all the patients in the previous queue;
[0053] Finally, the predicted waiting time for patients in each device waiting queue was compared Select the waiting queue with the shortest waiting time and arrange the new patient in this queue. The calculation process is as follows:
[0054]
[0055] Among them, min means taking the minimum value of the above predicted waiting time.
[0056] Furthermore, in the medical equipment resource intelligent load sharing module, the method for constructing the machine learning prediction model for predicting patient examination time and waiting time includes:
[0057] Step S1.1: Collect basic patient data A, examination item data B, technician operator data C, current equipment status data D and actual time data T required for patient examination of several patients;
[0058] Step S1.2: The above five types of data for each patient are organized into a data set:
[0059] N={{P,T}
[0060] Where, P = {A, C, D, B};
[0061] Construct the datasets of all patients into a training dataset:
[0062] N={N1,N2,...,N n}
[0063] Among them, N n is the dataset N of the nth patient;
[0064] Step S1.3: Based on the training data set and using a clustering algorithm, a machine learning prediction model for predicting patient examination time and waiting time is trained and constructed.
[0065] Furthermore, the medical equipment resource intelligent load sharing system further includes a real-time update module, which is used to update the input parameters of the current patient in real time. When the input parameter When a change occurs, the data acquisition module and the medical equipment resource intelligent load sharing module are called.
[0066] Furthermore, the data acquisition module is also used to: obtain the basic data of the current batch of patients Check project data Collect data of technicians on duty for each device And current device status data Constructing input parameters for machine learning prediction models The input parameters are then fed into the trained machine learning prediction model:
[0067]
[0068] Where L means there are L devices or L waiting queues;
[0069] The medical equipment resource intelligent load sharing module is also used to: obtain the input parameters of the current batch of patients After that, the trained machine learning prediction model performs the following data processing in sequence:
[0070] First, calculate the predicted examination time for the current batch of patients
[0071]
[0072] Among them, there are K new patients in the current batch of patients, k represents the serial number of the patients in this batch, and l represents the serial number of all equipment resources;
[0073] Secondly, calculate the predicted waiting time for this batch of patients
[0074]
[0075] Then, compare the predicted waiting time of the batch of patients in each device waiting queue Select the waiting queue with the shortest waiting time and arrange the patients who spend the shortest time in this queue. The calculation process is as follows:
[0076]
[0077] Finally, the above method is repeated for the remaining patients to arrange equipment resources until the last patient in the batch.
[0078] Compared with the prior art, the above technical solution has the following beneficial effects:
[0079] The key technical points of the present invention include the following:
[0080] 1. The present invention comprehensively considers and collects basic data of new patients Check project data Collect data of technicians on duty for each device And current device status data Constructing the input parameters of the prediction model To structure patient examination time and waiting time prediction models;
[0081] 2. The method of allocating medical equipment resources for a single patient of the present invention is to calculate the examination time Recalculate the waiting time Select waiting time Minimal equipment provides medical care;
[0082] 3. The present invention also proposes a method for optimizing resources according to patient batches, such as selecting patients within a period of time, such as 10 minutes, and calculating according to the above method; or selecting new patients with a certain data, such as 5 new patients, to allocate overall patient medical equipment resources. This method is beneficial to taking into account both patient service experience and the overall comprehensive utilization efficiency of medical equipment resources.
[0083] The present invention optimizes the design of a solution for how to efficiently improve the use efficiency and patient service experience of limited medical equipment resources. The present invention comprehensively considers factors such as the patient's health status, the patient's examination items, the current working status of the equipment, the ability and level of the technician on duty, etc., constructs a statistical learning model, predicts the examination time and waiting time required for the patient, allocates medical equipment resources according to the prediction results, and informs the patient of the prediction results, so that the patient can arrange examination and diagnosis items independently. Compared with the existing methods, the present invention greatly improves the patient's medical service experience while improving the comprehensive use efficiency of medical equipment resources. BRIEF DESCRIPTION OF THE DRAWINGS
[0084] Figure 1 The module structure diagram of the intelligent load sharing system for medical equipment resources;
[0085] Figure 2 Flowchart of a method for implementing intelligent load sharing of medical equipment resources for a machine learning prediction model for predicting patient examination time and waiting time. DETAILED DESCRIPTION
[0086] The advantages of the present invention are further described below in conjunction with the accompanying drawings and specific embodiments. Those skilled in the art should understand that the following specific description is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.
[0087] Example 1: Constructing a prediction model
[0088] This embodiment provides a method for a machine learning prediction model for predicting patient examination time and waiting time, including steps S1.1 to S1.3:
[0089] Step S1.1: Collect basic patient data A, examination item data B, technician operator data C, current equipment status data D and actual time data T required for patient examination of several patients.
[0090] (1) Collect basic patient data A, such as patient age a, gender a2, health status a3, etc. The patient's health status data A3 can be defined independently according to the situation. At the implementation level, an operational health status definition method is as shown in Table 1:
[0091] Table 1 Comparison table of health status definitions
[0092] Health Status Value Level Definition 1 Multiple people are needed to complete the inspection 2 One person is required to complete the inspection 3 No assistance is required to complete the inspection
[0093] The basic data of the patient constitutes a data vector value describing the patient's characteristics, A = {a1, a2, a3}. It should be noted that the above definition of the patient's health status is not unique, and other health status assessment indicators can also be used for evaluation during the implementation process.
[0094] (2) Collect the inspection item data B and assign a unique identification number to each inspection item corresponding to the equipment resource. If a defined inspection item library already exists in the medical system or medical equipment, the number in the inspection item library can be directly used. If there is no corresponding inspection item, the code of the corresponding inspection item needs to be defined.
[0095] (3) Collect technician operator data C and construct a unique identification number for the operator, such as 001, 002, etc.;
[0096] (4) Collect the current equipment status data D. The definition of the current equipment status is divided into two categories. One category is the status D that corresponds to the inspection item one by one, that is, each inspection item B1 corresponds to an equipment status D1, and the equipment status D1 indicates that the equipment has made all preparations for the inspection item B1. The other category is some special statuses of the equipment, such as the startup status, fault status, etc. The current equipment status is numbered one by one. One possible coding method is to be completely consistent with the inspection item, and the redundant special statuses of the equipment are extended from the last code of the inspection item, as shown below:
[0097] D1=B1,D2=B2,...,D i =B i , ..., D n =B n , D n+1 =B n +1
[0098] From D n Previously included D n is the status number corresponding to the inspection item, D n After that, some special states of the device are numbered;
[0099] (5) Collect the time data T of the patient examination, that is, the time required for each patient examination, which can be the time from the end of the previous patient examination to the end of the next patient examination on the equipment.
[0100] Step S1.2: The above five types of data for each patient are combined into a data set for training the model:
[0101] N={P,T}
[0102] Among them, P is the prerequisite for collecting time data, which is composed of collecting patient basic data A, collecting examination item data B, collecting technician operator data C, and collecting current equipment status data D. P = {A, C, D, B}; T is the actual time T required for the collected patient examination.
[0103] Construct the datasets of all patients into a training dataset:
[0104] N={N1,N2,...,N n}
[0105] Among them, N n is the dataset N of the nth patient.
[0106] Step S1.3: Based on the training data set and using a clustering algorithm, a machine learning prediction model for predicting patient examination time and waiting time is trained and constructed.
[0107] A patient service time prediction model is constructed based on the collected data, and the prediction model can be constructed based on a statistical learning method. The present invention can be based on a clustering algorithm, such as a K-MEANS clustering algorithm. Since the training and construction processes of such algorithms are conventional methods, they are described in many books and textbooks and will not be repeated in this application.
[0108] Embodiment 2 Medical equipment resource intelligent load sharing system and load sharing method thereof
[0109] Based on the machine learning prediction model that has been built to predict patient examination time and waiting time, such as Figure 1 As shown, the medical equipment resource intelligent load sharing system includes: a data acquisition module and a medical equipment resource intelligent load sharing module. The data acquisition module collects the data of the current patient and inputs it into the medical equipment resource intelligent load sharing module. The medical equipment resource intelligent load sharing module uses the machine learning prediction model that has been built to predict the patient's examination time and waiting time to predict the patient's examination time and waiting time for the input data.
[0110] The method of using the medical equipment resource intelligent load sharing system to perform medical equipment resource intelligent load sharing includes the following two situations: (1) a method for allocating medical equipment resources for a single patient; (2) a method for allocating medical equipment resources for the entire patient population.
[0111] (1) Methods for allocating medical equipment resources for a single patient
[0112] When a new patient needs to use medical equipment resources, assuming that L equipment are available, the predicted waiting time for assigning the patient to the waiting queue of each equipment resource can be calculated. Patients can be arranged in the predicted waiting time and the waiting queue with the shortest predicted waiting time can be selected. The specific process is as follows:
[0113] Step S1: The data acquisition module acquires the basic data of the current patient Check project data Collect data of technicians on duty for each device And current device status data Constructing input parameters for machine learning prediction models Then the input parameters are input into the intelligent load sharing module for medical device resources:
[0114]
[0115] Among them, L means there are L devices or L waiting queues; it should be noted that the basic data of patients For all L devices, the value is the same. Check the project data The same value is used for all L devices, and the data of technicians on duty is The value for all L devices is different; the current device status data The values of all L equipment are closely related to the equipment status before the inspection project;
[0116] Step S2: Figure 2 As shown in the figure, the intelligent load sharing module of medical equipment resources obtains input parameters After that, the machine learning prediction model is used to perform the following data processing in sequence:
[0117] Step S2.1: Input the input parameters of the current patient into the machine learning prediction model to calculate the predicted examination time of the current patient:
[0118]
[0119] in, Indicates the predicted examination time of the i-th patient in the patient queue with the current number of equipment resource l;
[0120] Step S2.2: Calculate the predicted waiting time of the current patient based on the predicted examination time: in The calculation method is:
[0121]
[0122] Among them, the current number is the waiting time required for the i-th patient in the patient queue of the equipment resource l That is, the sum of the patient examination times predicted for all the patients in the previous queue;
[0123] Step S2.3: Compare the predicted waiting time of the current patient in each device waiting queue Select the waiting queue with the shortest waiting time and arrange the current patient (new patient) in this queue. The calculation process is as follows:
[0124]
[0125] Among them, min means taking the minimum value of the above predicted waiting time.
[0126] At the implementation level, there may be situations where patients in the waiting queue cancel their examinations, technicians on duty change, equipment failure, etc. At this time, it is necessary to check the input parameters of the prediction model for each patient behind the patient in the queue according to the above method. Check whether there is any change. If there is any change, the forecast inspection time needs to be recalculated. Based on this, the predicted waiting time is calculated
[0127] When the previous patient completes the examination, the patient's predicted waiting time needs to be dynamically updated based on the actual examination time baseline
[0128] At the application level, patients can be predicted to have their examination time and predicted waiting time The data is provided to patients in the form of services such as APP, which makes it convenient for patients to arrange diagnostic items reasonably, and reminder times can be set to provide reminder services to patients. At the same time, patients can let the patients behind them to be examined first according to their own needs.
[0129] The above method of sorting each new patient in turn according to the predicted time is actually the result of optimization from the perspective of each individual patient.
[0130] (2) Overall patient medical equipment resource allocation method
[0131] In fact, the optimization of personal goals does not mean the optimization of organizational system goals. For example, switching between equipment states may take more time. From the perspective of the organizational system, it may be hoped that the same examination items will be completed before switching the equipment to another state for examination, but this violates the principle of fairness. However, in actual operation, a compromise can be made between the two. For example, select patients within a period of time, such as 10 minutes, and optimize resources according to the above method; or select new patients with a certain data, such as 5 new patients, and optimize resources according to the above method; this not only takes into account the patient service experience, without waiting too long, but also takes into account the improvement of overall efficiency. At this time, the above steps need to be fine-tuned, as follows:
[0132] (2.1) Calculate the predicted examination time for this batch of patients according to the above method Assuming that there are K new patients in the batch, k represents the serial number of the patients in the batch, and l represents the serial number of all equipment resources. The calculation process is as follows:
[0133]
[0134] (2.2) Calculate the predicted waiting time for this batch of patients according to the above method
[0135]
[0136] (2.3) Compare the predicted waiting time of this batch of patients in each device waiting queue Select the waiting queue with the shortest waiting time and arrange the patients who spend the shortest time in this queue. The calculation process is as follows:
[0137]
[0138] (2.4) In this way, one patient is scheduled, and the above method will be repeated for the remaining patients to arrange equipment resources until the last patient in the batch.
[0139] It should be noted that the embodiments of the present invention have better practicability and do not impose any form of limitation on the present invention. Any technician familiar with the field may use the technical content disclosed above to change or modify it into an equivalent effective embodiment. However, any modification or equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.
Claims
1. A method for intelligent load sharing of medical equipment resources. It is characterized in that include: Step S1: Obtain the basic data of the current patient Check project data Collect data of technicians on duty for each device And current device status data Constructing input parameters for machine learning prediction models The input parameters are then fed into a machine learning prediction model for predicting patient exam times and wait times: Where L means there are L devices or L waiting queues; Step S2: Obtaining input parameters After that, the machine learning prediction model performs the following data processing in sequence: First, calculate the patient's predicted examination time: in, Indicates the predicted examination time of the i-th patient in the patient queue with the current number of equipment resource l; Then, calculate the patient's predicted waiting time: in The calculation method is: Among them, the current number is the waiting time required for the i-th patient in the patient queue of the equipment resource l That is, the sum of the patient examination times predicted for all the patients in the previous queue; Finally, the predicted waiting time for patients in each device waiting queue was compared Select the waiting queue with the shortest waiting time and arrange the new patient in this queue. The calculation process is as follows: Among them, min means taking the minimum value of the above predicted waiting time.
2. The medical equipment resource intelligent load sharing method according to claim 1, It is characterized in that In step S1, the method for constructing a machine learning prediction model for predicting patient examination time and waiting time includes: Step S1.1: Collect basic patient data A, examination item data B, technician operator data C, current equipment status data D and actual time data T required for patient examination of several patients; Step S1.2: The above five types of data for each patient are organized into a data set: N={P,T} Where P = (A, C, D, B}; Construct the datasets of all patients into a training dataset: N={N 1 N 2 ,…,N n } Among them, N n is the dataset N of the nth patient; Step S1.3: Based on the training data set and using a clustering algorithm, a machine learning prediction model for predicting patient examination time and waiting time is trained and constructed.
3. The medical equipment resource intelligent load sharing method according to claim 1, It is characterized in that Further comprising step S3: real-time update of the input parameters of the current patient When the input parameter When a change occurs, steps S1 and S2 are repeated.
4. The medical equipment resource intelligent load sharing method according to claim 1, It is characterized in that The step S1 also includes: obtaining basic data of the current batch of patients Check project data Collect data of technicians on duty for each device And current device status data Constructing input parameters for machine learning prediction models The input parameters are then fed into the trained machine learning prediction model: Where L means there are L devices or L waiting queues; The step S2 also includes: obtaining the input parameters of the current batch of patients After that, the trained machine learning prediction model performs the following data processing in sequence: First, calculate the predicted examination time for the current batch of patients Among them, there are K new patients in the current batch of patients, k represents the serial number of the patients in this batch, and l represents the serial number of all equipment resources; Secondly, calculate the predicted waiting time for this batch of patients Then, compare the predicted waiting time of the batch of patients in each device waiting queue Select the waiting queue with the shortest waiting time and arrange the patients who spend the shortest time in this queue. The calculation process is as follows: Finally, the above method is repeated for the remaining patients to arrange equipment resources until the last patient in the batch.
5. A medical equipment resource intelligent load sharing system, It is characterized in that include: Data acquisition module and medical equipment resource intelligent load sharing module; The data acquisition module is used to acquire the basic data of the current patient Check project data Collect data of technicians on duty for each device And current device status data Constructing input parameters for machine learning prediction models Then the input parameters are input into the intelligent load sharing module for medical device resources: Where L means there are L devices or L waiting queues; The medical equipment resource intelligent load sharing module is used to obtain input parameters After that, the machine learning prediction model is used to perform the following data processing in sequence: First, calculate the patient's predicted examination time: in, Indicates the predicted examination time of the i-th patient in the patient queue with the current number of equipment resource l; Then, calculate the patient's predicted waiting time: in The calculation method is: Among them, the current number is the waiting time required for the i-th patient in the patient queue of the equipment resource l That is, the sum of the patient examination times predicted for all the patients in the previous queue; Finally, the predicted waiting time for patients in each device waiting queue was compared Select the waiting queue with the shortest waiting time and arrange the new patient in this queue. The calculation process is as follows: Among them, min means taking the minimum value of the above predicted waiting time.
6. The medical equipment resource intelligent load sharing system as claimed in claim 5, It is characterized in that In the medical equipment resource intelligent load sharing module, the method for constructing a machine learning prediction model for predicting patient examination time and waiting time includes: Step S1.1: Collect basic patient data A, examination item data B, technician operator data C, current equipment status data D and actual time data T required for patient examination of several patients; Step S1.2: The above five types of data for each patient are organized into a data set: N={P,T} Where, P = {A, C, D, B}; Construct the datasets of all patients into a training dataset: N={N 1 ,N 2 ,…,N n } Among them, N n is the dataset N of the nth patient; Step S1.3: Based on the training data set and using a clustering algorithm, a machine learning prediction model for predicting patient examination time and waiting time is trained and constructed.
7. The medical equipment resource intelligent load sharing system as claimed in claim 5, It is characterized in that It further comprises a real-time update module, which is used to update the input parameter P of the current patient in real time. i l , when the input parameter P i l When a change occurs, the data acquisition module and the medical equipment resource intelligent load sharing module are called.
8. The medical equipment resource intelligent load sharing system as claimed in claim 5, It is characterized in that The data acquisition module is also used to: obtain basic data of the current batch of patients Check project data Collect data of technicians on duty for each device And current device status data Construct the input parameter P of the machine learning prediction model i l , and then input the input parameters into the trained machine learning prediction model: Where L means there are L devices or L waiting queues; The medical equipment resource intelligent load sharing module is also used to: obtain the input parameter P of the current batch of patients i l After that, the trained machine learning prediction model performs the following data processing in sequence: First, calculate the predicted examination time T for the current batch of patients i kl : Among them, there are K new patients in the current batch of patients, k represents the serial number of the patients in this batch, and l represents the serial number of all equipment resources; Secondly, calculate the predicted waiting time for this batch of patients Then, compare the predicted waiting time of the batch of patients in each device waiting queue Select the waiting queue with the shortest waiting time and arrange the patients who spend the shortest time in this queue. The calculation process is as follows: Finally, the above method is repeated for the remaining patients to arrange equipment resources until the last patient in the batch.
Citation Information
Patent Citations
System and method for providing real-time feedback for patient waiting time
CN116157874A
Medical examination process dynamic planning method and device and electronic equipment
CN116665870A
Method for checking dynamic allocation of reserved resources
CN117438061A
Rehabilitation medical intelligent scheduling method and system and storage medium
CN118297318A
Medical inspection support system and medical inspection support method
JP2009134424A
