Physical examination queuing method, computer device, storage medium and program product
Through machine learning models, analyzing historical physical examination queuing information is generated and predictive models are generated to output physical examination queuing rules, which solves the efficiency problems of the existing system when the number of physical examinations changes and doctor time fluctuations, and achieves better queuing control and resource allocation.
Patent Information
- Application Number
- CN202510270181.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-07
- Publication Date
- 2025-06-27
AI Technical Summary
When the number of physical examinations increases or the duration of medical examinations fluctuates, the existing physical examination queuing system can easily lead to delays in queues and waste of resources, and traditional algorithms fail to effectively consider the actual effect.
By obtaining historical physical examination queue information, analyzing and training machine learning models, generating prediction models to output physical examination queue rules, real-time queue control of the optimal or suboptimal distribution mode, avoiding manual configuration of parameters.
It improves the efficiency of queuing for physical examinations, reduces delays in queuing and waste of resources, and ensures reasonable allocation of time for doctors and physical examinations.
Smart Images
Figure CN120220991A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and in particular, to a physical examination queuing method, a computer device, a storage medium, and a program product. Background Art
[0002] In a health management (physical examination) center, during a physical examination, an examinee usually needs to complete multiple physical examination items. Different physical examination items are usually in different consulting rooms, and the examinee needs to queue up in multiple consulting rooms to complete the physical examination. How to provide a better physical examination path for the queuing examinees, so as to optimize the order at the physical examination site and improve the satisfaction of the physical examination personnel, is a problem to be solved currently.
[0003] An existing solution is to map specific physical examination items to experience services, and then set corresponding queuing queues for each experience service. When an examinee completes the current queue inspection, the next or multiple consulting rooms that the examinee needs to queue for are calculated in real time through a parameter configuration algorithm. The current problem is that the configuration parameters are usually manually configured according to the actual situation of the hospital. When the number of examinees increases or there are large fluctuations in the duration of the doctor's physical examination items, there will be queuing delays for examinees, while there will be idle waiting for fast physical examination items.
[0004] In response to the above problems, the traditional solution is to allow an examinee to queue in 2 queues at the same time, and set a virtual person's position when an examinee needs to jump the queue, and replace the real examinee with a virtual person. Since the name of the virtual person does not match that of the real person, it is easy to be noticed by other examinees after replacement. In addition, the traditional queuing algorithm makes the doctor only focus on the number of examinees and does not consider the actual effect. Summary of the Invention
[0005] The first object of the present invention is to provide a physical examination queuing method for improving the physical examination queuing efficiency.
[0006] The second object of the present invention is to provide a computer device for implementing the above physical examination queuing method.
[0007] The third object of the present invention is to provide a computer-readable storage medium for implementing the above physical examination queuing method.
[0008] The fourth object of the present invention is to provide a computer program product for implementing the above physical examination queuing method.
[0009] To achieve the above first objective, a physical examination queuing method provided by the present invention includes the following steps: obtaining historical physical examination queuing information; analyzing the historical physical examination queuing information to obtain a historical optimal distribution pattern and a historical sub-optimal distribution pattern; training a machine learning model based on the historical physical examination queuing information, the historical optimal distribution pattern, and the historical sub-optimal distribution pattern to obtain a first prediction model; obtaining real-time physical examination queuing information; inputting the real-time physical examination queuing information into the first prediction model to obtain a physical examination queuing rule; and controlling the physical examination queue according to the physical examination queuing rule, where the physical examination queuing rule is used to achieve a real-time optimal distribution pattern or a real-time sub-optimal distribution pattern.
[0010] As can be seen from the above solution, the present invention obtains and analyzes historical physical examination queuing information, and learns the relationship between the input historical physical examination queuing information and the output historical optimal distribution pattern and historical sub-optimal distribution pattern in a machine learning manner to obtain a first prediction model. Thus, based on this prediction model, by inputting real-time physical examination queuing information, a physical examination queuing rule is obtained, and then the physical examination queue is controlled according to the physical examination queuing rule to achieve good physical examination time sequence control. The present invention outputs the physical examination queuing rule by means of model prediction, without manually configuring parameters, improving the physical examination queuing efficiency.
[0011] A further solution is that the physical examination queuing rule is: T = ∑w i *T ij , where T represents the total time, w i represents the optimization weight of the physical examination time of the examinee, and T ij represents the predicted occupation time of the examinee i in the physical examination item j.
[0012] A further solution is that the physical examination queuing method further includes the following steps: fusing the historical physical examination queuing information and the real-time physical examination queuing information actually collected in a preset period to obtain fused physical examination queuing information; analyzing the fused physical examination queuing information to obtain a fused optimal distribution pattern and a fused sub-optimal distribution pattern; and training a machine learning model based on the fused physical examination queuing information, the fused optimal distribution pattern, and the fused sub-optimal distribution pattern to obtain a second prediction model.
[0013] Thus, it can be seen that by fusing real-time physical examination queuing information for model parameter adjustment, the accuracy of model prediction can be improved.
[0014] A further solution is that during the process of controlling the physical examination queuing according to the physical examination queuing rule, the current physical examination queuing information is obtained, the current physical examination queuing information is evaluated, and when the current physical examination queuing information meets the rule update requirement, the physical examination queuing rule is updated, and the physical examination queue is controlled according to the updated physical examination queuing rule.
[0015] It can be seen that it is possible to determine whether to adjust the physical examination queuing rules by evaluating the current physical examination queuing information. In addition, when the physical examination doctor exceeds the set regular time to complete the physical examination items, the doctor will not quickly follow up the examinees, thus increasing the number of examinees. This ensures the objective physical examination time of the doctor and avoids the traditional algorithm from compressing the doctor's physical examination time in order to increase the number of examinees.
[0016] A further solution is that when the current physical examination queuing information meets the rule update requirements, including that the actual occupation time of an examinee on a physical examination item is greater than the predicted occupation time.
[0017] A further solution is that when updating the physical examination queuing rules, it includes: obtaining a parameter adjustment instruction, and updating the physical examination queuing rules according to the parameter adjustment instruction to obtain the updated physical examination queuing rules.
[0018] It can be seen that the physical examination queuing rules can be updated by directly adjusting the parameters of the physical examination queuing rules.
[0019] A further solution is that when updating the physical examination queuing rules, it includes: updating the real-time physical examination queuing information according to the current physical examination queuing time sequence information; inputting the real-time physical examination queuing information into the first prediction model again to obtain the updated physical examination queuing rules.
[0020] It can be seen that the generated physical examination data of the current day, for example, the physical examination time sequence data within a period of time of the current day, can be used to update the real-time physical examination queuing information, and then input into the first prediction model to obtain the updated physical examination queuing rules, improving the prediction accuracy.
[0021] To achieve the above second objective, a computer device provided by the present invention includes a processor and a memory, wherein: a computer program is stored on the memory, and when the computer program is executed by the processor, the above physical examination queuing method is implemented.
[0022] To achieve the above third objective, the computer program provided by the present invention implements the above physical examination queuing method when executed by the processor.
[0023] To achieve the above fourth objective, the computer instructions provided by the present invention implement the above physical examination queuing method when executed by the processor. Description of the Drawings
[0024] Figure 1 It is a schematic diagram of the physical examination queuing method of the present invention.
[0025] Figure 2 It is a schematic diagram of the physical examination queuing system in the first embodiment of the physical examination queuing method of the present invention.
[0026] Figure 3It is the flowchart for determining the physical examination queuing rules in the first embodiment of the physical examination queuing method of the present invention.
[0027] Figure 4 It is the flowchart for controlling the physical examination queue by applying the physical examination queuing rules in the first embodiment of the physical examination queuing method of the present invention.
[0028] Figure 5 Is Figure 4 The specific flowchart of step S22 in
[0029] Figure 6 It is the flowchart for determining the second prediction model in the first embodiment of the physical examination queuing method of the present invention.
[0030] Figure 7 Is Figure 5 Another specific flowchart of step S22 in
[0031] The present invention will be further described below with reference to the accompanying drawings and embodiments. Specific embodiments
[0032] See Figure 1 , the physical examination queuing method of the present invention utilizes the real-time data and past data of physical examination queuing, through optimization and sub-optimal distribution analysis, evaluates to suit the current hospital operation characteristics, and generates a prediction model through machine learning. This prediction model is used to generate physical examination queuing rules, and the physical examination queuing rules are used to generate a queuing queue for the physical examination time sequence queuing. The queuing queue will also be evaluated in real time according to the execution results to optimize the next queue configuration. The present invention also provides a computer device, a computer-readable storage medium, and a computer program product for implementing the above physical examination queuing method.
[0033] It should be noted that the following expressions of "first" and "second" are used to distinguish similar things and do not have the meaning of sequence.
[0034] The first embodiment of the physical examination queuing method:
[0035] See Figure 2 , the physical examination queuing system for implementing this embodiment includes a historical data acquisition module 1, a real-time data acquisition module 2, a historical data intelligent analysis module 3, a real-time data intelligent analysis module 4, a historical and real-time data fusion intelligent analysis module 5, a rule parameter configuration module 6, a rule generation module 7, a rule evaluation module 8, and a rule output module 9.
[0036] The historical data acquisition module 1 is respectively connected to the real-time data intelligent analysis module 3 and the historical and real-time data fusion intelligent analysis module 5. The real-time data acquisition module 2 is connected to the real-time data intelligent analysis module 4 and the historical and real-time data fusion intelligent analysis module 5. The historical data intelligent analysis module 3, the real-time data intelligent analysis module 4, the historical and real-time data fusion intelligent analysis module 5, and the rule parameter configuration module 6 are respectively connected to the rule generation module 7. The rule generation module 7 is connected to the rule evaluation module 8. The rule parameter configuration module 6 and the rule generation module 7 are respectively connected to the rule output module 9.
[0037] The historical data acquisition module 1 is used to obtain historical physical examination queuing information. The historical physical examination queuing information includes the information of examinees and physical examination items, the status information of physical examination rooms, the operation record data of doctors and nurses, the physical examination business rule data, the queue-jumping information data, and the physical examination queuing data for each preset period within a certain period. Among them, the information of examinees and physical examination items includes the correspondence between each examinee and the physical examination items to be done. The physical examination room queuing information includes the location distribution among physical examination rooms and the physical examination items provided by each physical examination room. The operation record data of physical examination doctors and nurses includes the physical examination time generated by doctors during the physical examination process and the physical examination time generated by nurses when manually operating the queue, etc. The physical examination business rule data includes the rules that different physical examination items need to follow. For example, some physical examination items require the blood drawing item to be completed first. The queue-jumping information data includes the situation of queue-jumpers and the physical examination items they jump the queue for. The physical examination queuing data records the historical physical examination time-sequence queuing information, and the historical physical examination time-sequence queuing information includes the change of the queue of each physical examination item over time and the time-sequence correspondence between each examinee and the physical examination item (for example, the correspondence formed between a certain examinee and the time period occupying a certain physical examination item on the time axis of a certain day). Different physical examination institutions have different historical physical examination queuing information.
[0038] In this embodiment, the preset period is one day, and an explanation is given on how to control the daily physical examination queue according to the physical examination queuing rules. It can be understood that the preset period can be adjusted according to actual needs.
[0039] The historical data acquisition module 1 obtains physical examination-related data by directly obtaining from the physical examination software system on the public network, offline copying, or intranet data, etc., and then completes the acquisition and collation of physical examination-related data through operations such as format conversion and adjustment of data correspondence relationships to obtain historical physical examination queuing information.
[0040] The real-time data acquisition module 2 is used to obtain the physical examination data generated in real time. During the operation of the physical examination queuing system in this embodiment, real-time physical examination queuing information will be generated. The real-time data acquisition module 2 is responsible for extracting and organizing the real-time physical examination queuing information to form a data set that can be used for intelligent algorithms. The acquisition of multiple physical examination institutions belonging to a group is also completed by the real-time data acquisition module 2, and the generated data set can be conveniently used for multiple physical examination institutions.
[0041] The historical data intelligent analysis module 3 analyzes and organizes based on the historical physical examination queuing information, inputs it into machine learning software for training, and generates a first prediction model that can obtain the physical examination queuing rules. The first prediction model is then verified through test data. The physical examination queuing rules describe the corresponding relationship between the predicted examinees and the physical examination items.
[0042] The real-time data intelligent analysis module 4 uses the parameterized first prediction model, takes the real-time physical examination queuing information as input, and generates the physical examination queuing rules required for the current physical examination institution.
[0043] The historical and real-time data fusion intelligent analysis module 5 is used to fuse the historical physical examination queuing information and the real-time physical examination queuing information of one or more preset periods that have actually occurred for training to generate a second prediction model. The second prediction model is then verified through test data. The fusion training generates a parameter model and transmits it to the rule parameter configuration module 6.
[0044] The rule parameter configuration module 6 is used to adjust the specific physical examination queuing rules. The physical examination queuing rule is parameterized as T = ∑w i *T ij , where T represents the total time, w i represents the optimization weight of the examinee's physical examination time, and T ij represents the predicted occupancy time of examinee i in physical examination item j. By adjusting the parameter w i , the best physical examination time can be correctly obtained for rule generation. For example, the optimal and sub-optimal outputs are selected (the optimal is the shortest total time for all examinees to complete the physical examination on a certain day, and the sub-optimal is the shortest waiting time for a certain examinee). The parameter w i can be manually modified by the rule parameter configuration module and can be adjusted at any time for unexpected situations during the physical examination to eliminate the uncertainty of the prediction model.
[0045] The rule generation module 7 is used to call the functions of the historical data intelligent analysis module 3, the real-time data intelligent analysis module 4, the historical and real-time data fusion intelligent analysis module 5, and the rule parameter configuration module 6 to generate physical examination queuing rules, which are used for real-time queuing to arrange the best queue for newly arrived examinees.
[0046] The rule evaluation module 8 is used to evaluate the current physical examination queuing information according to the accumulated queuing information, analyze the distribution of the total time T, and give the recommended weight wi for reference in the subsequent queuing rules.
[0047] The rule output module 9 is used to output the specific physical examination queuing rules for physical examination queue control.
[0048] See Figure 3 , the steps for determining the physical examination queuing rules in this embodiment include:
[0049] S11: Obtain the historical physical examination queuing information.
[0050] Among them, it includes obtaining the historical physical examination queuing information of multiple physical examination institutions.
[0051] S12: Analyze the historical physical examination queuing information to obtain the historical optimal distribution pattern and the historical sub-optimal distribution pattern.
[0052] Among them, analyze the historical physical examination queuing information of each physical examination institution to obtain the historical optimal distribution pattern and the historical sub-optimal distribution pattern. The specific analysis method can be implemented by existing technologies, such as F-statistic, K-square, and Bayesian maximum likelihood estimation, etc. The historical optimal distribution pattern refers to the distribution pattern under the shortest total time for all physical examination patients to complete the physical examination on the same day after analyzing the historical physical examination queuing information of a certain physical examination institution. The historical sub-optimal distribution pattern refers to the distribution pattern under the shortest waiting time for a certain physical examination patient after analyzing the historical physical examination queuing information of a certain physical examination institution.
[0053] S13: Based on the historical physical examination queuing information, the historical optimal distribution pattern, and the historical sub-optimal distribution pattern, perform machine learning model training to obtain the first prediction model.
[0054] Among them, the first prediction model is trained through the historical data intelligent analysis module. The first prediction model can output the corresponding physical examination queuing rules according to the input real-time physical examination queuing information.
[0055] S14: Obtain the real-time physical examination queuing information.
[0056] Among them, the real-time physical examination queuing information comes from the physical examination institution that needs to apply the first prediction model. The real-time physical examination queuing information includes the information of the physical examination patients and physical examination items set on the same day by this physical examination institution, the queuing status information of the physical examination consulting rooms, the operation record data of doctors and nurses, the physical examination business rule data, and the queue-jumping information data. It should be noted that since the actual physical examination queuing has not started, the physical examination queuing data is missing at this time.
[0057] S15: Input the real-time physical examination queuing information into the first prediction model to obtain the physical examination queuing rules.
[0058] Thus, according to the user's selection, the first prediction model can output a physical examination queuing rule for implementing a real-time optimal distribution pattern or a real-time sub-optimal distribution pattern. The real-time optimal distribution pattern is the distribution pattern with the shortest total physical examination completion time for all physical examination participants on the day obtained by analyzing the real-time physical examination queuing information of the current physical examination institution. The current sub-optimal distribution pattern refers to the distribution pattern with the shortest waiting time for a certain physical examination participant obtained by analyzing the real-time physical examination queuing information of the current physical examination institution.
[0059] In the process of controlling the physical examination queue according to the physical examination queuing rule, the physical examination queuing system will generate a virtual queue library of the maximum number of physical examination participants that the physical examination institution can objectively bear on the day based on the predicted actual consumption time of each physical examination item (the predicted actual consumption time is not a single time length, but multiple time lengths with a probability distribution). The virtual queue library includes several virtual queues, each virtual queue corresponds to a physical examination item, and each virtual queue includes several virtual queuers. Each virtual queuer includes a queuing position number and a predicted actual consumption time under the virtual queue.
[0060] For the actual physical examination participants, according to the physical examination items included in the physical examination package they purchased, the queuing position number of the physical examination participant in each physical examination item is allocated according to the virtual queue library. For the physical examination participants, they can view their current ranking in different physical examination items and the approximate waiting time through the client connected to the physical examination queuing system of this embodiment (the client runs on a small program or an App). The physical examination items will be sorted in ascending order of waiting time for the physical examination participants to choose. When a physical examination participant completes a physical examination item, the queuing information of the remaining physical examination items will be updated, and the physical examination participant can choose the fastest physical examination item by viewing the position information.
[0061] When controlling the physical examination queue according to the physical examination queuing rule, the real-time data acquisition module will collect the real-time generated physical examination data to obtain the current physical examination time sequence queuing information. The rule evaluation module will evaluate whether the current physical examination time sequence queuing information meets the rule update requirements. For example, if the actual occupancy time of a physical examination item by a physical examination participant is greater than the predicted occupancy time given by the physical examination queuing rule (the predicted occupancy time is the time range with the highest predicted probability), it means that the physical examination queuing rule needs to be adjusted. See Figure 4 , and in this process, it specifically includes the following steps:
[0062] S21: Obtain the current physical examination time sequence queuing information.
[0063] S22: Evaluate the current physical examination time sequence queuing information. When the current physical examination time sequence queuing information meets the rule update requirements, update the physical examination queuing rule to obtain the updated physical examination queuing rule.
[0064] When the actual occupation time of the examinee in a physical examination item is greater than the predicted occupation time, the physical examination queuing rule needs to be updated at this time. The predicted occupation time is a period corresponding to the predicted maximum probability time range.
[0065] S23: Control the physical examination queue according to the updated physical examination queuing rule.
[0066] Thus, control the physical examination queue according to the updated physical examination queuing rule to better conform to the current actual physical examination situation.
[0067] See Figure 5 In the above step S22, it specifically includes the following steps:
[0068] S221: Update the real-time physical examination queuing information according to the current physical examination time sequence queuing information.
[0069] S222: Input the real-time physical examination queuing information into the first prediction model again to obtain the updated physical examination queuing rule.
[0070] Thus, controlling the physical examination queue by the updated physical examination queuing rule re-obtained by the first prediction model is more in line with the physical examination situation of the physical examination institution on that day.
[0071] After the physical examination on the same day is completed, the real-time data acquisition module will collect the actual real-time physical examination queuing information on that day. The actual real-time physical examination queuing information on that day includes the information of the examinees and physical examination items actually generated on that day, the information of the physical examination consulting room status, the operation record data of doctors and nurses, the physical examination business rule data, the queue-jumping information data, and the physical examination queuing data. Thus, fine-tune the parameters of the first prediction model according to the actual real-time physical examination queuing information on that day to obtain a second prediction model more suitable for the physical examination institution. See Figure 6 Specifically, it includes the following steps:
[0072] S31: After the physical examination on the same day is completed, collect the actual real-time physical examination queuing information generated on that day.
[0073] S32: Obtain the integrated physical examination queuing information according to the actual real-time physical examination queuing information generated on that day and the historical physical examination queuing information.
[0074] Among them, since the historical physical examination queuing information includes the examinees and physical examination items of different physical examination institutions every day, it is necessary to screen the historical physical examination queuing information with the same physical examination items as those of the physical examination institution corresponding to the real-time physical examination queuing information actually generated on the same day, so as to obtain the integrated physical examination queuing information. The integrated physical examination queuing information includes the real-time physical examination queuing information actually generated on the same day and the screened historical physical examination queuing information. The physical examination items offered in the screened historical physical examination queuing information are the same as those of the physical examination institution corresponding to the real-time physical examination queuing information actually generated on the same day. Optionally, in different embodiments, the screened historical physical examination queuing information may also be the historical physical examination queuing information of the physical examination institution corresponding to the real-time physical examination queuing information actually generated on the same day.
[0075] S33: Based on the integrated physical examination queuing information, the integrated optimal distribution mode, and the integrated sub-optimal distribution mode, perform machine learning model training to obtain the second prediction model.
[0076] Among them, analyze each item of integrated physical examination queuing information to obtain the corresponding integrated optimal distribution mode and integrated sub-optimal distribution mode, and then train the second prediction model through the historical and real-time data fusion intelligent analysis module. Since the second prediction model is adjusted for the same physical examination items, it has better prediction performance.
[0077] Thus, the physical examination institution can subsequently predict the physical examination queuing rules according to the second prediction model, so as to achieve a better queue control effect.
[0078] Second embodiment:
[0079] The difference between this embodiment and the above first embodiment lies in the specific steps of step S22. In this embodiment, refer to Figure 7 , step S22 specifically includes:
[0080] S221': Obtain a parameter adjustment instruction.
[0081] S222': Update the physical examination queuing rules according to the parameter adjustment instruction to obtain the updated physical examination queuing rules.
[0082] Thus, the updated physical examination queuing rules are obtained by adjusting the physical examination queuing rules according to the externally input parameter adjustment instruction.
[0083] In summary, the present invention obtains historical physical examination queuing information, combines optimal and sub-optimal distribution analysis to evaluate the operation characteristics of physical examination institutions, learns the relationship between the input historical physical examination queuing information and the output historical optimal distribution pattern and historical sub-optimal distribution pattern based on machine learning training to obtain a first prediction model, and then inputs real-time physical examination queuing information into the prediction model to obtain physical examination queuing rules. The physical examination queue is controlled according to the physical examination queuing rules, and a suitable current or next consulting room is allocated to the examinee. The present invention outputs physical examination queuing rules through model prediction, without manual parameter configuration, improving the physical examination queuing efficiency.
[0084] Embodiment of computer device:
[0085] The computer device of this embodiment includes a processor and a memory. The memory stores a computer program, and when the processor executes the computer program, the above-described embodiment of the physical examination queuing method is implemented.
[0086] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the computer device may include more or fewer components, or combine certain components, or different components. For example, the computer device may also include input / output devices, network access devices, buses, etc.
[0087] For example, the processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microcontroller or the processor may also be any conventional processor, etc. The processor is the control center of the computer device, connecting various parts of the entire computer device through various interfaces and lines.
[0088] The memory can be used to store computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory, and invoking the data stored in the memory, the controller realizes various functions of the computer device. For example, the memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as voice reception function, voice-to-text conversion function, etc.); the data storage area can store the data created according to the use of the mobile phone (such as audio data, text data, etc.). In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as hard disks, memory, plug-in hard disks, smart media cards (SMC), secure digital (SD) cards, flash cards, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.
[0089] Embodiment of computer-readable storage medium:
[0090] If the modules integrated in the computer device of the above embodiment are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the process of the embodiment of the physical examination queuing method, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the controller, the steps of the above embodiment of the physical examination queuing method can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The storage medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.
[0091] Embodiment of computer program product:
[0092] The computer program product of this embodiment includes computer instructions, which are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes each step of the above-mentioned embodiment of the physical examination queuing method.
Claims
1. A physical examination queuing method, characterized in that: The following steps are involved: Get historical physical examination queue information; Analyze the historical physical examination queuing information to obtain a historical optimal distribution mode and a historical suboptimal distribution mode; Perform machine learning model training based on the historical physical examination queuing information, the historical optimal distribution pattern, and the historical suboptimal distribution pattern to obtain a first prediction model; Get real-time physical examination queue information; Inputting the real-time physical examination queuing information into the first prediction model to obtain a physical examination queuing rule; The physical examination queue is controlled according to the physical examination queue rule, and the physical examination queue rule is used to realize a real-time optimal distribution mode or a real-time suboptimal distribution mode.
2. The medical examination queuing method according to claim 1, characterized in that: The physical examination queuing rule is: T = ∑w i *T ij , where T represents the total time, w i represents the optimal weight of the examinee’s physical examination time, T ij It indicates the predicted time that examinee i will spend on examination item j.
3. The physical examination queuing method according to claim 1, characterized in that: Also includes: The historical physical examination queue information is integrated with the real-time physical examination queue information actually collected in a preset period to obtain integrated physical examination queue information; Analyze the fusion physical examination queue information to obtain a fusion optimal distribution mode and a fusion suboptimal distribution mode; A machine learning model is trained based on the fused physical examination queuing information, the fused optimal distribution pattern and the fused suboptimal distribution pattern to obtain a second prediction model.
4. The physical examination queuing method according to any one of claims 1 to 3, characterized in that: In the process of controlling the physical examination queue according to the physical examination queue rules, the current physical examination queue timing information is obtained, and the current physical examination queue timing information is evaluated. When the current physical examination queue timing information meets the rule update requirements, the physical examination queue rules are updated, and the physical examination queue control is performed according to the updated physical examination queue rules.
5. The medical examination queuing method according to claim 4, characterized in that: When the current physical examination time sequence queuing information meets the rule update requirement, including that the actual occupancy time of the examinee on a physical examination item is greater than the predicted occupancy time.
6. The medical examination queuing method according to claim 4, characterized in that: When updating the physical examination queuing rules, it includes: Obtain a parameter adjustment instruction, and update the physical examination queuing rule according to the parameter adjustment instruction.
7. The medical examination queuing method according to claim 4, characterized in that: When updating the physical examination queuing rules, it includes: Update the real-time physical examination queuing information according to the current physical examination time sequence queuing information; The real-time physical examination queuing information is input into the first prediction model again to obtain the updated physical examination queuing rules.
8. A computer device comprising a processor and a memory, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the physical examination queuing method according to any one of claims 1 to 7 is implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the physical examination queuing method described in any one of claims 1 to 7 is implemented.
10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the physical examination queuing method described in any one of claims 1 to 7 is implemented.