An intelligent outpatient management system and method based on the Internet of Things

Abstract

This invention discloses an IoT-based smart outpatient management system and method, belonging to the field of data management technology. It includes calculating the supply-demand gap by statistically analyzing patient arrival and treatment completion rates to form an outpatient operation status determination result. Based on this, deviation trend verification is performed to confirm whether a persistent imbalance has formed. Furthermore, combined with adaptive optimization judgment of treatment process rhythm parameters, structural deviation identification of the current treatment completion rate is performed. Subsequently, based on the deviation identification result, consistency verification is performed between the patient status recorded in the outpatient information system and the physical arrival data collected by the IoT to confirm whether the outpatient call rhythm prediction model optimization has been triggered. This achieves progressive closed-loop control from supply-demand load monitoring, trend confirmation, type identification to data authenticity verification, effectively avoiding mis-regulation caused by short-term fluctuations or status delays, and improving the accuracy and stability of outpatient rhythm adjustment.

Description

Technical Field

[0001] This invention relates to the field of data management technology, and in particular to a smart clinic management system and method based on the Internet of Things. Background Technology

[0002] With the continuous advancement of medical informatization and smart hospital construction, outpatient business systems, queuing and calling systems, self-service terminals, and IoT sensing terminals are widely deployed within hospitals. During outpatient operations, a large amount of real-time data related to patient arrival, waiting, treatment, examination, and transfer is generated. This data is stored in a dispersed manner across different business subsystems and constantly changes with the pace of treatment, resource allocation, and patient flow. To ensure outpatient operational efficiency, shorten patient waiting times, and improve the utilization rate of medical resources, hospitals need to build a smart outpatient management system covering the entire process of perception, analysis, decision-making, and control, enabling real-time monitoring and collaborative management of patient arrival rates, treatment completion rates, waiting queue status, and clinic occupancy.

[0003] Currently, most hospitals have deployed various information platforms, including Hospital Information Systems (HIS), outpatient queuing and calling systems, self-service registration and payment terminals, mobile payment platforms, and examination and test appointment systems. These platforms enable electronic management of patient registration, triage, waiting, treatment, payment, and examination appointment processes. Simultaneously, some hospitals have introduced IoT sensing devices, such as access control terminals, waiting area passenger flow statistics devices, smart display terminals, and clinic status data collection devices, to collect operational data such as patient arrival, waiting area distribution, and clinic usage status.

[0004] For example, Chinese invention patent CN116644825B discloses a big data-based outpatient information query and appointment management system, which relates to the field of outpatient information management technology and includes a server, a permission analysis unit, a page analysis unit, a selection analysis unit, a transmission analysis unit, an information display unit, a display execution unit, and an integration and evaluation unit.

[0005] For example, Chinese invention patent CN113408936A discloses an immunization management system, which includes: a vaccine management module for managing and maintaining vaccine types, vaccine characteristics, vaccine manufacturers, vaccine-related biological products, and biological product packaging specifications; a vaccine inventory management module for managing inventory information of several types of vaccines in the clinic, including newly created vaccine batch orders and vaccine arrival information; an immunization program management module for managing and maintaining the vaccination plan; a vaccination process management module for implementing the vaccination process through intelligent equipment, displaying the vaccination progress on smart TVs and LED screens, and monitoring the outpatient process of taking numbers, consultation, registration, payment, vaccination, and observation in real time; and a touch screen vaccination module for inputting relevant information when vaccinating doctors administer vaccines to recipients.

[0006] The above-mentioned technology has at least the following technical problems: Outpatient rhythm control based solely on queuing data or call records from a single business system simply binds the outpatient operation status to the system registration information and adjusts it using static thresholds or empirical rules. When there is a delay or inconsistency between the actual physical arrival of patients and the system registration status, and the management method cannot identify misjudgments of idleness or congestion caused by data lag, the control strategy deviates from the actual operating status. Furthermore, existing rhythm control methods mostly employ fixed parameters or post-event statistical analysis models, lacking a dynamic linkage mechanism based on real-time supply-demand differences, trend changes, and IoT sensing data, and are unable to classify and adaptively optimize outpatient operation imbalances. Summary of the Invention

[0007] To address the technical problems existing in the prior art, embodiments of the present invention provide an Internet of Things-based smart clinic management system, the system comprising: The outpatient supply and demand status determination module is used to statistically analyze the patient arrival rate and treatment completion rate, calculate the supply and demand gap, determine the outpatient operation results, and implement guidance-type adjustments based on the outpatient operation results.

[0008] The trend verification and rhythm adaptive decision-making module is used to verify the deviation trend of outpatient operation results, verify the imbalance trend of supply and demand difference determination, and adaptively optimize the rhythm parameters of diagnosis and treatment process, optimize the outpatient call rhythm prediction model and adjust the examination appointment interval parameters.

[0009] The treatment completion rate deviation identification module is used to identify and judge the deviation of the current treatment completion rate and obtain the deviation identification result of the current treatment completion rate.

[0010] The IoT consistency verification and optimization trigger confirmation module is used to verify the consistency of the patient's physical location in the outpatient information record based on the deviation judgment result of the current completion rate of diagnosis and treatment, and to confirm whether to execute the outpatient call rate prediction model optimization.

[0011] A second aspect of the present invention also provides a smart outpatient management method based on the Internet of Things, comprising: statistically analyzing the patient arrival rate and the rate of completion of treatment and calculating the supply-demand gap, determining the outpatient operation results, and performing guided regulation based on the outpatient operation results.

[0012] The deviation trend of outpatient operation results is verified and judged to verify the imbalance trend of supply and demand difference. At the same time, the rhythm parameters of diagnosis and treatment process are adaptively optimized and judged to optimize the outpatient call rhythm prediction model and adjust the examination appointment interval parameters.

[0013] Deviation identification judgment is performed on the current completion rate of diagnosis and treatment to obtain the deviation identification judgment result of the current completion rate of diagnosis and treatment.

[0014] Based on the deviation identification results of the current treatment completion rate, the consistency of the patient's physical location recorded in the outpatient information is checked, and it is confirmed whether to perform outpatient call rate prediction model optimization.

[0015] The beneficial effects of the technical solutions provided by the embodiments of the present invention include at least the following: 1. This invention provides an IoT-based smart outpatient management system. By statistically analyzing patient arrival and treatment completion rates and calculating the supply-demand gap, it establishes an outpatient operation status assessment result. Based on this, deviation trend verification is performed to confirm whether a persistent imbalance has formed. Furthermore, combined with adaptive optimization judgment of treatment process rhythm parameters, structural deviations in the current treatment completion rate are identified. Subsequently, based on the deviation identification results, consistency verification is performed between the patient status recorded in the outpatient information system and the physical arrival data collected by the IoT to confirm whether the outpatient call-up rhythm prediction model optimization has been triggered. This achieves progressive closed-loop control from supply-demand load monitoring, trend confirmation, type identification to data authenticity verification, effectively avoiding mis-regulation caused by short-term fluctuations or status delays, improving the accuracy and stability of outpatient rhythm adjustment, and thus enhancing the IoT-based smart outpatient management system's ability to finely and adaptively control the operating rhythm.

[0016] 2. This invention calculates the patient arrival rate and treatment completion rate by statistically analyzing the number of newly added patients in the waiting area and the number of completed treatments, respectively. The difference between these two rates yields the outpatient service supply-demand gap per unit time, forming a result to determine the outpatient operation status. Based on this result, corresponding guidance and control measures are implemented. This achieves real-time quantitative assessment and interval-based status identification of outpatient service load, enabling the system to upgrade from single-indicator monitoring to dynamic monitoring of supply and demand balance. It promptly distinguishes between stable operation and imbalance risk states, providing a preliminary judgment basis for subsequent trend verification, cycle time optimization, and adaptive parameter adjustment, thereby improving the responsiveness and overall stability of outpatient operation control.

[0017] 3. This invention verifies the trend of abnormal supply-demand imbalance by calculating the change rate of waiting queue length and the fluctuation range of waiting time within a sliding time window. After guided regulation, the supply-demand imbalance value and queue change rate are extracted again for continuous review. When the imbalance trend is confirmed to still exist, the deviation of the current treatment completion rate is identified. The average idle interval of the consultation room and the distribution parameters of the single treatment time are combined to distinguish between the idle state of the supply side and the non-idle state of the demand side. The outpatient call rhythm prediction model and the examination appointment interval ratio are optimized accordingly. This achieves fine identification of the type of imbalance in outpatient operation and targeted rhythm optimization, avoiding simple and extensive adjustment based on a single indicator, and improving the matching efficiency and operational stability of outpatient resource allocation.

[0018] 4. This invention confirms whether the patient has actually arrived within a reasonable response time. When it is determined that the patient has physically arrived, the safety buffer interval in the call rhythm prediction model is reduced by combining the statistical results of the deviation between the predicted completion time and the actual completion time. The physical arrival data of the Internet of Things is introduced to participate in the recalculation of core indicators and parameter correction, which realizes the effective correction of idle misjudgment and the accurate identification of the actual rhythm deviation, improves the accuracy and adaptability of outpatient rhythm control, and thus enhances the stability and refined management level of the system in complex operating scenarios. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A schematic diagram of a smart clinic management system module based on the Internet of Things provided in this application embodiment; Figure 2 A flowchart for regulating the supply-demand deviation of outpatient services provided in this application embodiment; Figure 3A flowchart for the verification and model optimization of the clinic's idle status based on IoT location verification provided in this application embodiment; Figure 4 This is a flowchart of a smart clinic management method based on the Internet of Things, provided as an embodiment of this application. Detailed Implementation

[0021] The technical solution provided in this application will now be described with reference to the accompanying drawings.

[0022] To facilitate understanding of the embodiments of this application, the following points will be explained first: First, in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates an "or" relationship between the preceding and following related objects, but it does not exclude the possibility of indicating an "and" relationship; the specific meaning can be understood in context. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c; a and b; a and c; b and c; or a and b and c. Here, a, b, and c can be single or multiple.

[0023] Second, the use of prefixes such as "first" and "second" in this application is solely for the purpose of distinguishing and describing different things belonging to the same category, and does not constrain the order, size, or quantity of things. For example, "first message" and "second message" are simply different messages, and there is no chronological, size, or priority relationship between them.

[0024] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0025] like Figure 1 The diagram shown is a schematic of a smart clinic management system module based on the Internet of Things provided in an embodiment of this application. The system includes: The outpatient supply and demand status determination module is used to statistically analyze the patient arrival rate and treatment completion rate, calculate the supply and demand gap, determine the outpatient operation results, and implement guidance-type adjustments based on the outpatient operation results.

[0026] The trend verification and rhythm adaptive decision-making module is used to verify the deviation trend of outpatient operation results, verify the imbalance trend of supply and demand difference determination, and adaptively optimize the rhythm parameters of diagnosis and treatment process, optimize the outpatient call rhythm prediction model and adjust the examination appointment interval parameters.

[0027] The treatment completion rate deviation identification module is used to identify and judge the deviation of the current treatment completion rate and obtain the deviation identification result of the current treatment completion rate.

[0028] The IoT consistency verification and optimization trigger confirmation module is used to verify the consistency of the patient's physical location in the outpatient information record based on the deviation judgment result of the current completion rate of diagnosis and treatment, and to confirm whether to execute the outpatient call rate prediction model optimization.

[0029] It should be noted that the outpatient operation results are interval judgment indicators formed by comparing the value of the supply and demand difference of outpatient services within a unit of time with the historical supply and demand difference interval. They are used to characterize whether the current supply and demand relationship of outpatient services is within the historical stable interval. The outpatient operation results are used to characterize the interval state of the supply and demand relationship, while the interval comparison of the waiting queue length change rate is used to verify whether the state formed by the supply and demand difference shows a continuous evolution trend. The two correspond to static state judgment and dynamic trend verification, respectively.

[0030] like Figure 2 As shown, Figure 2 The flowchart for outpatient service supply-demand deviation control provided in this application embodiment illustrates the outpatient service supply-demand control process based on IoT data. After the guided control is executed, the system first extracts the outpatient service supply-demand difference value and the waiting queue length change rate within a unit time, and determines whether the supply-demand difference continuously exceeds the set interval and the waiting queue change rate is positive. If the conditions are met, the system will make a deviation judgment on the current completion rate of diagnosis and treatment, then execute the outpatient call rate prediction model optimization, and dynamically adjust the examination appointment interval parameter to increase the number of diagnosis and treatment completed per unit time and reduce the supply-demand difference; if the conditions are not met, the current control strategy is maintained and subsequent changes are monitored. Through real-time deviation identification and control strategy optimization, the efficiency of outpatient process operation and service supply-demand balance are achieved.

[0031] The outpatient operation results are determined, and guidance-based adjustments are implemented based on these results. The specific process is as follows: Within a preset sliding time window, the number of newly added patients entering the outpatient waiting area is counted, and the number of newly added patients is divided by the duration of the sliding time window to obtain an estimated value of the patient arrival rate. At the same time, the treatment completion rate is counted within the same sliding time window.

[0032] Extract the estimated patient arrival rate and the treatment completion rate, and subtract the estimated patient arrival rate and the treatment completion rate to obtain the outpatient service supply and demand difference value per unit time.

[0033] The outpatient service supply-demand difference value per unit time is compared with the patient outpatient service supply-demand difference interval stored in the database to obtain the outpatient operation results, and guidance-type regulation is implemented based on the outpatient operation results.

[0034] The outpatient operation results include a first result and a second result. If the difference between the supply and demand of outpatient services within a unit of time does not exceed the range of the difference between the supply and demand of outpatient services within a patient, the outpatient operation result is recorded as the first result; otherwise, the outpatient operation result is recorded as the second result.

[0035] It should be noted that the estimated patient arrival rate is used to represent the number of new patients entering the effective waiting state per unit of time.

[0036] It's important to note that in outpatient operations, patient status is monitored in real-time. When a patient's status changes from "waiting" or "in progress" to "completed," a completion event with a timestamp is generated. Using a sliding time window of, for example, five or ten minutes, the number of patients whose status changes to completion is counted within the current window. This number is then divided by the window duration to obtain the number of patients completed per unit of time; this value is the completion rate for the current time period. To avoid fluctuations caused by short-term jitter, the rate results from several consecutive windows are usually smoothed, for example, by taking the average, as an estimate of the current effective completion rate. This rate reflects the outpatient department's actual capacity to handle patients at the current pace and is the core basis for comparing it with the patient arrival rate and determining whether there is an imbalance between supply and demand.

[0037] It should be noted that the specific process of implementing guided adjustments based on outpatient operation results is as follows: If the first result is obtained, that is, the outpatient operation is in a stable state, the system will not adjust resources or processes, but will instead enter maintenance adjustment, while continuing to monitor the rate of change in queue length and the fluctuation range of waiting time. The specific process of maintenance adjustment is as follows: the system maintains the current call-out rhythm prediction parameters unchanged, maintains the current examination appointment interval ratio unchanged, and only slightly smooths the frequency of waiting information display to avoid frequent refreshes causing patient anxiety, while maintaining the weight of recommended appointment time slots at the baseline level.

[0038] It should be noted that the queuing rhythm prediction parameter refers to the time interval setting used to guide the outpatient system in triggering the next queuing operation. This parameter is a comprehensive control parameter that includes factors such as the average treatment time for current patients and the idle interval of consultation rooms. It reflects the rhythmic pattern of patients entering the consultation room within a unit of time. This parameter can be used to predict the arrival time of the next patient, thereby balancing the use of consultation room resources and patient waiting time, ensuring a smooth outpatient process. The waiting information display frequency refers to the update frequency of the waiting queue status, estimated waiting time, and recommended consultation information displayed in the outpatient hall or on mobile terminals. This is used to control the information refresh speed, avoid patient anxiety caused by overly frequent queue changes, and ensure the real-time nature and reference value of the information. Smooth display reduces visual interference and enhances the patient experience.

[0039] The deviation trend of outpatient operation results is verified and judged to verify the imbalance trend of the supply and demand gap. The specific process is as follows: Within a sliding time window, the change in the length of the waiting queue in real time is obtained to get the rate of change of the waiting queue length.

[0040] It should be noted that the length of the waiting queue at each time point is counted within a preset sliding time window, and the change is obtained by calculating the difference in queue length within the window. The rate of change is the average value of the change in queue length per unit time, that is, the change in queue length is divided by the length of the sliding window to obtain the rate at which the queue grows or decreases per unit time, thus reflecting the dynamic trend of the waiting area.

[0041] The waiting time fluctuation range is obtained based on the estimated waiting time of patients who have completed their visits and the system's predicted waiting time of current patients.

[0042] It should be noted that the estimated waiting time is obtained by recording the difference between the time a patient enters the waiting queue and the actual time they begin their consultation; the system's predicted waiting time is calculated sequentially for patients in the current waiting queue. Specifically, firstly, the number of people ahead of each patient in the current waiting queue is counted, and the average consultation time for each consultation room is obtained; then, combined with the calling rhythm prediction parameter, i.e., the system's estimated average time interval from each patient's number being called to entering the consultation room, the estimated consultation time for patients ahead of them is summed up to obtain the total estimated waiting time for the current patient. The waiting time fluctuation range is a statistical measure of the difference between the predicted waiting time and the actual waiting time for each patient in the waiting queue, used to quantify the stability of the waiting time. The specific calculation method is as follows: First, within a preset sliding time window, the actual waiting time of each patient who has completed their consultation is extracted, and combined with the system's predicted waiting time, the deviation value of each patient is calculated, which is the actual waiting time minus the system's predicted waiting time. Then, the deviation value is statistically analyzed within the window to obtain indicators such as average deviation, maximum deviation, and standard deviation. The standard deviation or maximum deviation is used as the fluctuation range of the waiting time, reflecting the fluctuation of the waiting time within the same time window. The larger the fluctuation range, the more unstable the supply and demand relationship in the outpatient department, and the more abnormal the waiting rhythm.

[0043] The rate of change in waiting queue length is compared with the historical stable range. At the same time, the deviation trend of outpatient operation results is verified by combining the rate of change in waiting queue length. If the rate of change in waiting queue length is positive and the fluctuation of waiting time is higher than the historical normal range, the second result is confirmed. Otherwise, the second result is not confirmed.

[0044] It should be noted that if the second result is not confirmed, it is judged as "trend deviation but no substantial backlog." In this case, full guidance and control are not implemented directly, but rather in an enhanced monitoring state. In the enhanced monitoring state, the data update frequency is increased, the sliding time window step is shortened, the frequency of waiting information display is temporarily increased without changing the recommendation weight, and the intensity of diversion prompts is not strengthened. The purpose is to observe whether the supply-demand deviation is a short-term fluctuation. If the supply-demand difference returns to the historical range within several consecutive windows, it automatically reverts to the first result; if the queue change rate becomes consistently positive and the waiting time fluctuations widen in subsequent windows, the second result is confirmed, and guidance-type control is formally implemented.

[0045] It should be noted that if the second result is true, guidance-based regulation will be initiated first, with the goal of directly affecting the patient arrival rate. The regulation process involves: increasing the frequency of displaying waiting information so that patients can see their current predicted waiting time in real time, strengthening the prompts for diverting patients to adjacent departments, and guiding patients with symptoms that can be replaced to departments with less pressure.

[0046] The adaptive optimization of the diagnostic and treatment process cycle parameters is performed as follows: Extract the difference between supply and demand of outpatient services and the rate of change of waiting queue length within a unit time after the implementation of the guiding regulation. If the difference between supply and demand of outpatient services continues to exceed the range within a unit time after the implementation of the guiding regulation, and the rate of change of waiting queue length is still positive, then make a deviation judgment on the current completion rate of diagnosis and treatment, optimize the outpatient call rhythm prediction model, and adjust the examination appointment interval parameter.

[0047] It should be noted that optimizing the call-call rhythm prediction model and adjusting the examination appointment interval parameters improves the completion rate of diagnosis and treatment per unit time, thereby narrowing the supply-demand gap. This call-call rhythm prediction model stores the actual time consumption of a single diagnosis and treatment in a database under different time periods and doctor scheduling structures for each department. It then categorizes and statistically analyzes this data according to operating conditions, forming a set of diagnosis and treatment time distribution parameters for each condition, including at least the median time consumption, the upper quantile time consumption, and the fluctuation range. When entering the real-time operation phase, the system identifies the current department, current time period, and current scheduling structure, and reads the matching historical time consumption distribution parameters from the database as the current prediction benchmark. For ongoing diagnosis and treatment tasks, the system records the used time in real time and maps this used time to the historical time consumption distribution to determine whether the current diagnosis and treatment is in the early, middle, or late range of the historical distribution, thereby estimating the remaining time. If the used time is lower than the historical median time consumption, the predicted remaining time is longer; if the used time is close to or exceeds the historical upper quantile time consumption, the predicted remaining time is shorter. This prediction does not rely on complex neural networks, but rather on a dynamic interval mapping method based on historical statistical distributions. The model outputs the estimated completion time of the current diagnosis and treatment. Based on this, the system combines the average buffer time required for a patient to move from the waiting area to the examination room to calculate the pre-notification trigger time for the next waiting patient, sending a "prepare for treatment" prompt to the patient a certain time before the estimated completion time. This buffer time parameter is an adjustable control variable. In the system, after the guidance-type adjustments are executed, the examination appointment interval parameter is dynamically adjusted based on the current waiting queue and the distribution of examination tasks. Some examination tasks that can be postponed are reallocated to subsequent time windows to reduce process congestion caused by high-density concentration. Specifically, the recommended appointment interval is recalculated based on the historical average completion time and the treatment completion rate of each examination room, allocating some examination tasks that can be postponed to subsequent, less busy time windows, thereby reducing concentration. For off-peak periods or idle examination rooms, the examination interval can be appropriately shortened to improve resource utilization. Ultimately, a new appointment interval ratio is formed based on the recalculated appointment intervals for each examination task within each time window. This ratio reflects a distribution strategy of dispersing peak hours, concentrating off-peak hours, and achieving overall supply-demand balance. This enables dynamic control of the examination process, helps reduce waiting time and increases the completion rate of treatment per unit time. Ultimately, this improves the overall effective completion rate of treatment per unit time, achieving a rebalancing of outpatient supply and demand.

[0048] Deviation assessment is performed on the current treatment completion rate to obtain the deviation assessment result. The specific process is as follows: The average idle time in the consultation room was calculated. The idle time in the consultation room is the time difference between when the previous patient finishes their consultation and when the next patient enters the consultation room to begin their consultation. At the same time, the distribution parameters of the actual time spent in a single consultation were calculated, and the proportion of waiting time in each step in the total consultation time of the patient was also calculated. The distribution parameters of the actual time spent in a single consultation include the median and high percentile values ​​of the distribution parameters of the actual time spent in a single consultation.

[0049] It should be noted that the average idle interval time of a consultation room is calculated as follows: First, the timestamps of each consultation completion are recorded, i.e., the time when the previous patient finished their consultation and the time when the next patient entered the consultation room to begin their consultation. The time difference between these two times is calculated to obtain the idle interval time series for a single consultation room session. Then, the arithmetic mean of this time series is calculated to obtain the average idle interval time of the consultation room. This indicator reflects the idle status of consultation room resources per unit time and is used to determine whether the consultation room is idling. The distribution parameters for the actual time consumption of a single consultation session are obtained by recording the time from each patient's entry into the consultation room to the completion of their consultation, resulting in a single consultation session time series. This series is then statistically analyzed, calculating distribution parameters including at least the median and high quantile values, such as the 90th or 95th percentile, reflecting longer consultation sessions. The percentage of waiting time in the total patient visit duration is calculated by recording the waiting time for each stage of the treatment process, such as registration, consultation, and examination. The total waiting time is obtained by summing up the waiting times for all stages and then dividing it by the total time from when the patient enters the outpatient clinic to when the visit is completed.

[0050] When the average idle interval time of the consultation room is higher than or equal to the upper limit of the historical benchmark interval stored in the database, and the median and high percentile values ​​of the actual time spent on a single consultation are still within the historical normal fluctuation range stored in the database, the deviation identification and judgment result of the current completion rate of consultation is recorded as the first side idle state; otherwise, the deviation identification and judgment result of the current completion rate of consultation is recorded as the second side non-idle state, and the examination appointment interval ratio is redistributed.

[0051] It should be noted that when the system is identified as being in a first-side idle state, the time interval parameter in the call prediction model is reduced to increase the probability of patients entering the consultation room per unit time, reduce the proportion of idle consultation rooms, and restore the completion rate of consultations to the historical baseline range. When the system is identified as being in a second-side non-idle state, the examination appointment interval parameter within the current time window is reconstructed to reduce the examination appointment density within the same time period, i.e., the number of examination tasks arranged per unit time. Examination tasks with the possibility of being postponed are allocated to subsequent time windows to disperse the backflow peak, reduce the proportion of waiting for examinations, thereby compressing non-treatment time and increasing the number of effective consultations completed per unit time. The time interval parameter is a lead time parameter, i.e., predicting that the doctor will complete the current consultation in T minutes. Therefore, at time T-Δ, a preparation prompt is sent to the next patient, where Δ is the time interval parameter. If the time interval control parameter is too small, patients may not be able to arrive in time, resulting in waiting after being called; if the time interval control parameter is too large, patients may gather at the consultation room door too early, causing congestion.

[0052] It's important to note that when the system is identified as being in a first-side idle state, it indicates a time lag between the doctor's completion of the consultation and the patient's arrival in the examination room, meaning the patient's arrival pace is slower than the doctor's. In this case, the conservative interval in the prediction error needs to be reduced so that the next patient receives the preparation prompt earlier, thereby improving the connection probability. As for the second-side non-idle state, it means the doctor is not waiting for the patient, but rather the patient is occupying time during examinations, diluting the effective time of a single consultation. Adjusting the call-out rhythm is meaningless in this case, as the examination rooms are not idle; the real problem lies in the concentration of examination appointments. In this situation, it is necessary to reconstruct the examination appointment interval parameter to reduce the examination density per unit time. The specific process of reducing the examination density per unit time and distributing some deferred examinations to subsequent windows is as follows: First, calculate the average idle interval of the examination rooms within several consecutive time windows and its difference from the historical upper limit of the idle interval. Based on the difference, look up the corresponding suggested correction amount in the preset "Idle Deviation - Advance Adjustment Comparison Table" in the database. In actual implementation, add a correction amount to the original advance amount, thereby slightly increasing and correcting the original advance amount parameter.

[0053] like Figure 3 As shown, Figure 3The flowchart for the clinic idle status verification and model optimization based on IoT arrival verification provided in this application embodiment first retrieves the entry event data collected by the IoT terminal, and extracts the timestamp of the doctor completing the previous patient's treatment and the timestamp of triggering the next call operation. Within a preset reasonable response time range, it searches for whether there is a valid entry event record. If it exists and the difference between the entry time and the call time is within the historical normal range, the entry time recorded by the IoT is used to replace the system registration time, the average value of the clinic idle interval time is recalculated, and the completion rate deviation identification judgment is performed again. If the average value of the clinic idle interval time after recalculation falls back to the historical benchmark range, the first side idle status judgment is cancelled. If there is no valid entry event or the time difference is abnormal, the first side idle status is confirmed to be established, and the outpatient call rhythm prediction model optimization and safety buffer interval reduction are performed. Finally, the idle status verification and model optimization results are output.

[0054] Based on the deviation identification results of the current treatment completion rate, the consistency of the patient's physical location recorded in the outpatient information is verified. The specific process is as follows: Retrieve entry event data collected by IoT terminals, and extract the timestamp of the doctor completing the previous patient's treatment and the timestamp of triggering the next call operation.

[0055] Based on the timestamp that triggers the next call operation, search for whether there is an entry event record at the clinic entrance within a preset reasonable response time range.

[0056] If an entry event occurs within the response time range, and the time difference between the entry time and the call time is within the historical normal response range, then the patient is determined to have arrived physically; otherwise, the patient is determined not to have arrived physically.

[0057] It's important to note that the timestamp for a doctor completing the previous patient's consultation refers to the time the doctor marks "This consultation is over" in the information system. It can also be obtained from the completion time automatically recorded by the diagnostic equipment or electronic medical record system. The timestamp triggering the next call is the time the system sends the signal "Next patient, please prepare to enter the consultation room / see you." Calling can typically be done via electronic display, voice prompts, or app notifications; this time is recorded in the system. Entry time refers to the time the patient moves from the waiting area to the consultation room entrance, collected by an IoT terminal. For example, this could be the time detected by a patient's GPS wristband, QR code scanning access control, or camera entering the consultation room. Calling time is the time the system notifies the patient "Please enter the consultation room," which is the time the signal for the next patient to be seated is triggered.

[0058] Confirm whether to implement the outpatient call rate prediction model optimization. The specific process is as follows: If it is determined that the patient has physically arrived, the entry time recorded by the Internet of Things will replace the original patient entry time registered by the system. The average value of the idle interval time in the examination room will be recalculated, and deviation identification judgment on the current completion rate of treatment will be performed again.

[0059] If the average value of the recalculated clinic idle interval time falls back to the historical baseline range, the determination of the first side idle status will be revoked.

[0060] If it is determined that the patient has not physically arrived, the first side is confirmed to be in an idle state, and the outpatient call rate prediction model is optimized.

[0061] It should be noted that the entry event data refers to the perception record of a person entering the buffer area before entering the consultation room at a specific timestamp. The entry event data comes from the positioning terminal in the waiting area or the sensing device at the entrance of the consultation room. The system counts whether the called patient has entered the preset sensing area at the entrance of the consultation room within the current time window, and the timestamp of the entry into the area. If the positioning data shows that the patient has gathered at the entrance of the consultation room, and the physical arrival time is earlier than or close to the calling time recorded by the system, but the information system status still shows "waiting in progress", it is determined that the idle interval statistical error is due to the delay in status update or the lag in terminal operation, rather than insufficient connection of actual patients. In this case, the consultation room idle interval time is corrected, the physical arrival time is used instead of the system status time to recalculate the average idle interval, and the deviation judgment is re-executed; if the average value of the consultation room idle interval time after correction falls back to the historical normal range, the first side idle status judgment is cancelled, and rhythm-based control is not entered.

[0062] It should be noted that the outpatient call-out rhythm prediction model is a residual treatment time prediction model based on historical statistical distribution. It belongs to the data-driven time series estimation model category. The model establishes a time distribution model based on historical single-treatment time data, such as median time, quantile time intervals, and time distribution curves for different time periods. In real-time operation, it estimates the remaining treatment time based on the position of the current elapsed time in the historical distribution. Essentially, this is a distribution mapping prediction model, an interpretable model built on statistical regularities. The model outputs the estimated completion time of the current treatment. Based on this, combined with the average buffer time parameter required for a patient to move from the waiting area to the consultation room, the model calculates the pre-notification trigger time for the next waiting patient, i.e., sending a "prepare for treatment" prompt to the patient a certain time before the estimated completion time. This buffer time parameter is an adjustable control variable. When the system identifies a first-side idle state, the buffer time is incrementally corrected according to the deviation of the idle interval, appropriately advancing the pre-notification time to improve the probability of patient arrival. When the system returns to a stable state, the buffer time parameter is gradually restored to the historical baseline level according to a preset regression rule. Its essence is an interpretable time distribution prediction and beat matching model, rather than an automated call system that replaces doctors' decisions.

[0063] The optimization process for the outpatient call rate prediction model is as follows: After confirming that the patient has not physically arrived, retrieve the time deviation record between the predicted completion time and the actual completion time in the most recent sliding time window, perform statistical analysis on the direction of the prediction error, and reduce the safety buffer interval in the prediction.

[0064] It's important to note that the predicted completion time is the estimated time the doctor will take to complete the current patient's treatment, based on the outpatient call rate prediction model. This is essentially the estimated time the next patient can enter the consultation room. It's a model output value. Specifically, it's calculated from the outpatient call rate prediction model based on the current patient's completed treatment time and historical time distribution. This is typically obtained through database queries or real-time model calculations. The actual completion time, on the other hand, is the time the doctor records the actual end of the patient's treatment in the information system—the point in time the consultation room truly becomes available. It's obtained by reading the timestamp of the "treatment completed" event from the outpatient information system or IoT terminal event database, usually obtained by the doctor manually ending the treatment or by the system automatically recording the completion time of the treatment equipment.

[0065] It should be noted that if the average predicted completion time is lower than or equal to the actual completion time, the current prediction model is considered to have a conservative bias. Based on this trend, the advance warning parameter in the outpatient call rhythm prediction model is corrected. That is, while keeping the original historical distribution baseline parameter unchanged, the safety buffer interval in the prediction is reduced. Specifically, the average difference between the predicted completion time and the actual completion time in the most recent sliding time window is calculated. This average difference is used as the bias indicator and matched with a pre-established prediction deviation-buffer adjustment table in the database to find the corresponding safety buffer interval adjustment amount. After obtaining the adjustment amount, a proportional correction is made to the original buffer interval parameter, that is, the adjustment amount obtained from the table is subtracted from the original buffer interval. At the same time, the magnitude of this correction is recorded and the rhythm control parameters of the current operating cycle are updated. After the adjustment is completed, the change in the idle interval of the consultation room is continuously monitored in the next sliding time window. If the idle interval falls back to the historical baseline range, the current parameters are maintained. If there is still a deviation, small corrections are made according to the progressive rules of the table until the preset maximum adjustment limit is reached or the stable range is restored. The reduced buffer interval will be used as the new basis for triggering pre-warnings, and the magnitude of this reduction will be recorded and included in the model's running log.

[0066] like Figure 4 As shown, Figure 4 The flowchart of the IoT-based smart outpatient management method provided in this application embodiment includes: statistically analyzing the patient arrival rate and treatment completion rate and calculating the supply-demand gap, determining the outpatient operation result, and performing guided regulation based on the outpatient operation result.

[0067] The deviation trend of outpatient operation results is verified and judged to verify the imbalance trend of supply and demand difference. At the same time, the rhythm parameters of diagnosis and treatment process are adaptively optimized and judged to optimize the outpatient call rhythm prediction model and adjust the examination appointment interval parameters.

[0068] Deviation identification judgment is performed on the current completion rate of diagnosis and treatment to obtain the deviation identification judgment result of the current completion rate of diagnosis and treatment.

[0069] Based on the deviation identification results of the current treatment completion rate, the consistency of the patient's physical location recorded in the outpatient information is checked, and it is confirmed whether to perform outpatient call rate prediction model optimization.

[0070] The various features and processes described above can be used independently of each other or can be combined in various ways. All possible combinations and sub-combinations are intended to fall within the scope of this disclosure. Furthermore, certain method or process blocks may be omitted in some embodiments. The methods and processes described herein are not limited to any particular order, and the blocks or states associated with them may be performed in other suitable orders. For example, the described blocks or states may be performed in an order different from the order specifically disclosed, or multiple blocks or states may be combined in a single block or state. Example blocks or states may be performed serially, in parallel, or in some other manner. Blocks or states may be added to or removed from the disclosed example embodiments. The exemplary cases and components described herein may be configured differently from those described. For example, elements may be added to, removed from, or rearranged compared to the disclosed example embodiments.

[0071] The various operations of the example methods described herein can be performed at least in part by an algorithm. This algorithm can be contained in program code or instructions stored in memory (e.g., the aforementioned non-transitory computer-readable storage medium). Such an algorithm may include a machine learning algorithm. In some embodiments, the machine learning algorithm may not be explicitly programmed into the computer to perform the function, but can learn from training data to create a predictive model that performs the function.

[0072] The various operations of the example methods described herein can be performed, at least in part, by one or more processors that are temporarily configured (e.g., by software) or permanently configured to perform the relevant operations. Whether temporarily or permanently configured, such processors can constitute the engine of a processor implementation that operates to perform one or more of the operations or functions described herein.

[0073] Similarly, the methods described herein can be implemented at least in part by a processor, where one or more specific processors are examples of hardware. For example, at least some operations of a method can be performed by one or more processors or an engine implemented by a processor. Furthermore, one or more processors can also be operated to support the performance of related operations in a “cloud computing” environment or as “Software as a Service” (SaaS). For example, at least some operations can be performed by a set of computers (as an example of a machine including processors), where these operations are accessible via a network (e.g., the Internet) and via one or more suitable interfaces (e.g., application programming interfaces (APIs)).

[0074] The performance of certain operations can be distributed across processors, residing not only within a single machine but also deployed across multiple machines. In some example embodiments, the processor or processor-implemented engine may reside in a single geographic location (e.g., within a home environment, office environment, or server cluster). In other example embodiments, the processor or processor-implemented engine may be distributed across multiple geographic locations.

[0075] In this specification, multiple instances may implement components, operations, or structures described as single instances. Although individual operations of one or more methods are shown and described as separate operations, one or more of the separate operations may be performed simultaneously and do not need to be performed in the order shown. Structures and functions presented as separate components in the example configuration may be implemented as composite structures or components. Similarly, structures and functions presented as single components may be implemented as separate components. These and other variations, modifications, additions, and improvements fall within the scope of this document.

[0076] While an overview of the subject matter has been described with reference to specific example embodiments, various modifications and changes can be made to these embodiments without departing from the broader scope of embodiments of this disclosure. Such embodiments of the subject matter are referred to herein, individually or collectively, by the term "invention," and are used for convenience only and are not intended to limit the scope of this application to any single disclosure or concept, should more than one disclosure or concept be disclosed in fact.

[0077] The embodiments described herein have been described in sufficient detail to enable those skilled in the art to practice the disclosed teachings. Other embodiments may be used and derived therefrom, such that structural and logical substitutions and changes may be made without departing from the scope of this disclosure. Therefore, the detailed description should not be construed as limiting, and the scope of the various embodiments is defined only by the appended claims and the full scope of their equivalents.

Claims

1. A smart outpatient management system based on the Internet of Things, characterized in that, Includes the following steps: The outpatient supply and demand status determination module is used to statistically analyze the patient arrival rate and treatment completion rate, calculate the supply and demand gap, determine the outpatient operation results, and implement guidance-type adjustments based on the outpatient operation results. The trend verification and rhythm adaptive decision-making module is used to verify the deviation trend of outpatient operation results, verify the imbalance trend of supply and demand difference, and adaptively optimize the rhythm parameters of the diagnosis and treatment process, optimize the outpatient call rhythm prediction model and adjust the examination appointment interval parameters. The treatment completion rate deviation identification module is used to identify and judge the deviation of the current treatment completion rate and obtain the deviation identification result of the current treatment completion rate. The IoT consistency verification and optimization trigger confirmation module is used to verify the consistency of the patient's physical location in the outpatient information record based on the deviation judgment result of the current completion rate of diagnosis and treatment, and to confirm whether to execute the outpatient call rate prediction model optimization.

2. The smart clinic management system based on the Internet of Things as described in claim 1, characterized in that: The determination yields the outpatient operation results, and guidance-based adjustments are implemented based on these results. The specific process is as follows: Within a preset sliding time window, the number of newly added patients entering the outpatient waiting area is counted, and the number of newly added patients is divided by the duration of the sliding time window to obtain an estimated value of the patient arrival rate. At the same time, the treatment completion rate is counted within the same sliding time window. Extract the estimated patient arrival rate and the treatment completion rate, and subtract the estimated patient arrival rate and the treatment completion rate to obtain the outpatient service supply and demand difference value per unit time. The outpatient service supply-demand difference value per unit time is compared with the patient outpatient service supply-demand difference interval stored in the database to obtain the outpatient operation results, and guidance-type regulation is implemented based on the outpatient operation results.

3. The smart clinic management system based on the Internet of Things as described in claim 2, characterized in that: The outpatient operation results include a first result and a second result. If the difference between the supply and demand of outpatient services within a unit of time does not exceed the range of the difference between the supply and demand of outpatient services within a patient, then the outpatient operation result is recorded as the first result; otherwise, the outpatient operation result is recorded as the second result.

4. The smart clinic management system based on the Internet of Things as described in claim 1, characterized in that: The process of verifying the deviation trend of outpatient operation results and verifying the imbalance trend of supply and demand gap determination is as follows: Within a sliding time window, the change in the real-time waiting queue length is obtained to determine the rate of change in the waiting queue length. The waiting time fluctuation range is obtained based on the estimated waiting time of patients who have completed their visits and the system's predicted waiting time of current patients. The rate of change in waiting queue length is compared with the historical stable range. At the same time, the deviation trend of outpatient operation results is verified by combining the rate of change in waiting queue length. If the rate of change in waiting queue length is positive and the fluctuation of waiting time is higher than the historical normal range, the second result is confirmed. Otherwise, the second result is not confirmed.

5. The smart clinic management system based on the Internet of Things as described in claim 4, characterized in that: The specific process for adaptively optimizing the timing parameters of the diagnosis and treatment process is as follows: Extract the difference between supply and demand of outpatient services and the rate of change of waiting queue length within a unit time after the implementation of the guiding regulation. If the difference between supply and demand of outpatient services continues to exceed the range within a unit time after the implementation of the guiding regulation, and the rate of change of waiting queue length is still positive, then make a deviation judgment on the current completion rate of diagnosis and treatment, optimize the outpatient call rhythm prediction model, and adjust the examination appointment interval parameter.

6. The smart clinic management system based on the Internet of Things as described in claim 1, characterized in that: The process of identifying and judging deviations from the current completion rate of diagnosis and treatment, and obtaining the deviation judgment result of the current completion rate of diagnosis and treatment, is as follows: The average value of the consultation room idle interval time is calculated. The consultation room idle interval time is the time difference between the completion of the previous patient's treatment and the entry of the next patient into the consultation room to start treatment. At the same time, the distribution parameters of the actual time spent in a single consultation are calculated and the proportion of the waiting time in the total consultation time of the patient is calculated. The distribution parameters of the actual time spent in a single consultation include the median value and the high percentile value of the distribution parameters of the actual time spent in a single consultation. When the average idle interval time of the consultation room is higher than or equal to the upper limit of the historical benchmark interval stored in the database, and the median and high percentile values ​​of the actual time spent on a single consultation are still within the historical normal fluctuation range stored in the database, the deviation identification and judgment result of the current completion rate of consultation is recorded as the first side idle state; otherwise, the deviation identification and judgment result of the current completion rate of consultation is recorded as the second side non-idle state, and the examination appointment interval ratio is redistributed.

7. The smart clinic management system based on the Internet of Things as described in claim 6, characterized in that: The process of verifying the consistency of the patient's physical location in the outpatient information record based on the deviation identification and judgment results of the current completion rate of diagnosis and treatment is as follows: Retrieve entry event data collected by IoT terminals, and extract the timestamp of the doctor completing the previous patient's treatment and the timestamp of triggering the next call operation; Based on the timestamp that triggers the next call operation, search for whether there is an entry event record at the clinic entrance within a preset reasonable response time range; If an entry event occurs within the response time range, and the time difference between the entry time and the call time is within the historical normal response range, then the patient is determined to have arrived physically; otherwise, the patient is determined not to have arrived physically.

8. The smart clinic management system based on the Internet of Things as described in claim 7, characterized in that: The specific process for confirming whether to perform outpatient call rate prediction model optimization is as follows: If it is determined that the patient has physically arrived, the entry time recorded by the Internet of Things will replace the original patient entry time registered by the system, the average value of the idle interval time in the examination room will be recalculated, and the deviation identification judgment on the current completion rate of treatment will be performed again. If the average value of the recalculated clinic idle interval time falls back to the historical baseline range, the determination of the first side idle status will be cancelled. If it is determined that the patient has not physically arrived, the first side is confirmed to be in an idle state, and the outpatient call rate prediction model is optimized.

9. The smart clinic management system based on the Internet of Things as described in claim 8, characterized in that: The optimization process of the outpatient call rate prediction model is as follows: After confirming that the patient has not physically arrived, retrieve the time deviation record between the predicted completion time and the actual completion time in the most recent sliding time window, perform statistical analysis on the direction of the prediction error, and reduce the safety buffer interval in the prediction.

10. A method applied to the Internet of Things-based smart clinic management system according to any one of claims 1-9, comprising: The outpatient arrival rate and treatment completion rate are statistically analyzed, and the supply-demand gap is calculated to determine the outpatient operation results. Based on the outpatient operation results, guidance-type adjustments are implemented. The deviation trend of outpatient operation results is verified and judged to verify the imbalance trend of supply and demand difference. At the same time, the rhythm parameters of diagnosis and treatment process are adaptively optimized and judged to optimize the outpatient call rhythm prediction model and adjust the examination appointment interval parameters. Deviation identification and judgment are performed on the current completion rate of diagnosis and treatment to obtain the deviation identification and judgment result of the current completion rate of diagnosis and treatment; Based on the deviation identification results of the current treatment completion rate, the consistency of the patient's physical location recorded in the outpatient information is checked, and it is confirmed whether to perform outpatient call rate prediction model optimization.

Images