A queuing algorithm for physical examination based on the physical examination system

Abstract

The present invention discloses a guidance and inspection queuing algorithm based on a physical examination system business, and specifically relates to the technical field of physical examination systems; an initial guidance and inspection route is generated based on the physical examinee's appointment time and examination items, and the physical examinee's guidance and inspection route and the priority of each examination item are dynamically optimized through real-time data monitoring and preprocessing, feature extraction, data prediction model analysis and fuzzy logic comprehensive analysis; the problems of unbalanced resource allocation and long waiting time in the existing system during peak hours are solved, and the load balancing and smooth process of each examination item are ensured, thereby significantly improving the physical examination efficiency, reducing the waiting time, improving the physical examinee's satisfaction, and enhancing the operation effect and service quality of the physical examination center.

Description

Technical Field

[0001] The present invention relates to the technical field of physical examination systems, and in particular to a physical examination system service-based inspection queuing algorithm. Background Art

[0002] The physical examination system business refers to the business of comprehensive inspection, recording and analysis of human health status through information technology. It includes full-process services from appointment, examination, data management to report generation, aiming to provide convenient and efficient health management solutions. At present, the inspection and queuing method in the physical examination system mainly relies on the intelligent inspection and queuing system for management. After arriving at the physical examination center, the examinee uses a self-service terminal or mobile phone application to sign in. The system generates a personalized inspection route according to the appointment time and examination items, and updates the queue status in real time. The electronic screen will display the current inspection order and waiting time, and the automatic calling system will prompt the examinee to go to the designated examination room, thereby effectively reducing on-site personnel congestion and waiting time, and improving the overall physical examination efficiency and experience. However, the existing inspection and queuing algorithm is usually based on first-come-first-served or simple appointment time priority rules. This method may work well during non-peak hours, but during peak hours, it will cause a large number of examinees to arrive at the same time, unbalanced resource allocation, and cause serious congestion for certain examination items, and examinees need to wait for a long time. Moreover, long waiting times may lead to dissatisfaction among examinees, reduce satisfaction, and may cause some examinees to give up on the examination or complain, thus affecting the reputation and business of the examination center. Summary of the invention

[0003] The purpose of the present invention is to provide a medical examination system service-based inspection queuing algorithm to address the shortcomings of the background technology.

[0004] In order to achieve the above object, the present invention provides the following technical solution: a medical examination system service-based inspection queuing algorithm, comprising the following steps:

[0005] S1: The physical examination system generates an initial inspection route based on the physical examination subject's appointment time and examination items, uses the initial inspection route to queue the physical examination subjects for various physical examination items, and obtains the queue status data of each physical examination item in real time;

[0006] S2: preprocessing the queue status data of each physical examination item obtained, performing feature extraction on the preprocessed queue status data, and respectively extracting the physical examination room utilization rate feature and the physical examination time deviation feature from the queue status data;

[0007] S3: Build a data prediction model, input the extracted physical examination room utilization rate characteristics and physical examination time deviation characteristics into the model for comprehensive calculation, and determine whether the queue status of the physical examination items is abnormal based on the model output results;

[0008] S4: When the queuing status of the physical examination items is abnormal, the waiting time of each examinee in each physical examination item is obtained through the electronic queuing system, and the waiting time in each physical examination item is analyzed in time series to obtain the floating value of the waiting time;

[0009] S5: After comprehensively analyzing the calculation results of the data prediction model and the floating value of the waiting time by the fuzzy logic, the urgency of adjusting the physical examination items is divided into different levels according to the analysis results, namely, no adjustment, normal adjustment and emergency adjustment;

[0010] S6: For the physical examination items that need emergency adjustment, they are moved to the first place in the inspection route; for the physical examination items that need normal adjustment, they are adjusted to the first Y inspection items, where Y is determined according to the importance and priority of the physical examination items.

[0011] Preferably, in S2, a physical examination room utilization rate fluctuation index is generated according to the utilization rate fluctuation of each physical examination room, and the method for obtaining the physical examination room utilization rate fluctuation index is:

[0012] Collect the utilization data Xt of the physical examination room in the time period s, determine the smoothing coefficient α, and use the first utilization observation value X1 as the initial exponentially weighted moving average , using the exponentially weighted moving average formula to calculate the smoothed value at each time point , the expression is: ; In the formula, is the smoothed value at time point i, where Xt is the actual usage rate at time t, is the smoothed value at time point t, is the smoothed value at the previous time point; the exponentially weighted moving average is used to calculate the physical examination room utilization rate fluctuation index, and the expression is: ; In the formula, is the physical examination room utilization rate fluctuation index, is the mean of the exponentially weighted moving average, and N is the total number of usage observations.

[0013] Preferably, the physical examination time deviation index is generated according to the physical examination progress delay status of each physical examination item, and the method for obtaining the physical examination time deviation index is:

[0014] Collect the actual completion time Tactual and planned completion time Tplanned for each physical examination item, and calculate the time deviation value TimeDeviation of each physical examination item. The expression is: ; Select the window size M and coefficient k, calculate the moving average MA and standard deviation σ of the time deviation value, and determine the physical examination time range under the standard state according to the moving average MA and standard deviation σ of the time deviation value: : Among them, UBT is the maximum physical examination time value, and the expression is: ; LBT is the minimum physical examination time value, the expression is: ; Compare the obtained real-time time deviation value TimeDeviation with the physical examination time range under the standard state, calculate the physical examination time deviation index, when When , the calculation expression of the physical examination time deviation index at this time is: ;when When , the calculation expression of the physical examination time deviation index at this time is: ; In the formula, is the physical examination time deviation index.

[0015] Preferably, the physical examination room utilization rate fluctuation index and the physical examination time deviation index are converted into a first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model predicts the stability value label of the physical examination system with each group of first eigenvectors as the prediction target, and minimizes the sum of prediction errors for the stability value labels of all physical examination systems as the training target. The machine learning model is trained until the sum of prediction errors converges, and the model training is stopped. The stability value of the physical examination system is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0016] Preferably, the obtained stability value of the physical examination system is compared with a preset stability value reference threshold. If the stability value of the physical examination system is greater than or equal to the preset stability value reference threshold, the stability of the physical examination system is high. At this time, a physical examination system operation stability signal is generated to continuously monitor and maintain the existing physical examination process to ensure its stable operation.

[0017] If the stability value of the physical examination system is less than the preset stability value reference threshold, the stability of the physical examination system is low. At this time, an unstable operation signal of the physical examination system is generated, and the data is analyzed in depth to determine the root cause of the instability.

[0018] Preferably, in S4, when the queuing status of the physical examination items is abnormal, the waiting time of each examinee in each physical examination item is obtained through the electronic queuing system, and the waiting time in each physical examination item is analyzed in time series to obtain the floating value of the waiting time, specifically:

[0019] The system records the arrival time, entry time and exit time of each examinee, uses the database to store the collected data, reads the timestamp data of each examination item from the database, and calculates the waiting time of each examinee in each item. The expression is: ;W is the waiting time, Tstart is the time to enter the project, and Tarriva is the arrival time;

[0020] Calculate the average waiting time for each physical examination item, expressed as: ;Wˉ is the average waiting time for a certain item, M is the number of examinees, is the waiting time of the i-th examinee;

[0021] Summarize waiting time data by time period, generate time series data, and calculate the average waiting time for each project per day. The expression is: ;in, is the average waiting time per day, H is the number of people who undergo physical examinations on that day, is the waiting time of the jth examinee on the day; the Prophet model is used to analyze it, and the model expression is: Among them, y(t) is the predicted waiting time, g(t) is the trend function, s(t) is the seasonal component, h(t) is the holiday component, ϵt is the error term, and the floating value of the waiting time is calculated based on the predicted waiting time. The calculation expression is: ; In the formula, is the floating value of waiting time, The peak waiting time is This is the low-peak period for waiting time.

[0022] Preferably, the obtained waiting time floating value is compared with a preset waiting time floating value reference threshold. If the waiting time floating value is greater than or equal to the preset waiting time floating value reference threshold, the waiting time in each physical examination item is still increasing, and a waiting time increasing signal is generated; if the waiting time floating value is less than the preset waiting time floating value reference threshold, the waiting time in each physical examination item decreases, and a waiting time decreasing signal is generated.

[0023] Preferably, in S5, after the calculation results of the data prediction model and the floating value of the waiting time are comprehensively analyzed by the fuzzy logic, the urgency of adjusting the physical examination items is divided into different levels according to the analysis results, specifically:

[0024] The stability value of the queue status of the physical examination items and the floating value of the waiting time are used as the output items of the fuzzy logic, and the urgency of adjusting the physical examination items is used as the output item;

[0025] The stability value of the queue status of the physical examination items, the floating value of the waiting time and the urgency of the adjustment of the physical examination items are converted into fuzzy variables;

[0026] The queue status stability value and waiting time floating value of the physical examination items are input into the fuzzy logic system. The system performs reasoning calculation according to the preset fuzzy rules to determine the urgency of adjusting the inspection route.

[0027] The fuzzy logic reasoning results are defuzzified and converted into specific priority adjustment measures.

[0028] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0029] 1. The present invention generates an initial inspection route using appointment time and inspection items, and dynamically evaluates the queuing status and system stability of physical examination items through real-time data monitoring, feature extraction and data prediction models. When an abnormality is detected, the waiting time of each examinee is obtained through the electronic queuing system, and a time series analysis is performed. The data prediction results and the floating value of the waiting time are comprehensively analyzed in combination with fuzzy logic. The urgency of adjusting the physical examination items is divided into different levels according to the analysis results, and the inspection route and item priority are dynamically adjusted according to the division results, thereby optimizing the physical examination process.

[0030] 2. The present invention not only significantly improves the operating efficiency of the physical examination center during peak hours, but also reduces the waiting time of the examinees, improves the overall service quality and the examinees' satisfaction. In addition, the system can detect and handle abnormal situations in the physical examination process in real time, ensure the smooth operation of the physical examination process, enhance the service capabilities and reputation of the physical examination center, and ultimately bring comprehensive improvements to the management of the physical examination center and the examinees' experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0032] Figure 1 This is a flow chart of the inspection queuing algorithm for the physical examination system service. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] For examples, see Figure 1 As shown, the medical examination system service-based inspection queuing algorithm described in this embodiment includes the following steps:

[0035] S1: The physical examination system generates an initial inspection route based on the physical examination subject's appointment time and examination items, uses the initial inspection route to queue the physical examination subjects for various physical examination items, and obtains the queue status data of each physical examination item in real time;

[0036] S2: preprocessing the queue status data of each physical examination item obtained, performing feature extraction on the preprocessed queue status data, and respectively extracting the physical examination room utilization rate feature and the physical examination time deviation feature from the queue status data;

[0037] S3: Build a data prediction model, input the extracted physical examination room utilization rate characteristics and physical examination time deviation characteristics into the model for comprehensive calculation, and determine whether the queue status of the physical examination items is abnormal based on the model output results;

[0038] S4: When the queuing status of the physical examination items is abnormal, the waiting time of each examinee in each physical examination item is obtained through the electronic queuing system, and the waiting time in each physical examination item is analyzed in time series to obtain the floating value of the waiting time;

[0039] S5: After comprehensively analyzing the calculation results of the data prediction model and the floating value of the waiting time by the fuzzy logic, the urgency of adjusting the physical examination items is divided into different levels according to the analysis results, namely, no adjustment, normal adjustment and emergency adjustment;

[0040] S6: For the physical examination items that need emergency adjustment, they are moved to the first place in the inspection route; for the physical examination items that need normal adjustment, they are adjusted to the first Y inspection items, where Y is determined according to the importance and priority of the physical examination items.

[0041] Among them, in S1, the physical examination system generates an initial inspection route based on the physical examinee's appointment time and examination items, queues the physical examinee's various physical examination items using the initial inspection route, and obtains the queue status data of each physical examination item in real time.

[0042] Appointment information collection: collect the physical examinee's appointment time, scheduled examination items, physical examinee's personal information (such as age, gender, medical history, etc.) and the estimated duration of the examination item.

[0043] Inspection item attribute collection: Collect the basic attributes of each inspection item, including the estimated time of each item, equipment availability, inspection room location, and distance between items.

[0044] Priority rule setting: Set priority rules based on the examinee's health status, appointment time, and the particularity of the examination items (such as some examinations need to be done on an empty stomach or in the morning). Urgent or time-limited examination items are given priority.

[0045] Preliminary sorting: According to the priority rules, the various examination items of the examinee are preliminarily sorted to generate a rough examination order.

[0046] Route optimization algorithm: Utilize optimization algorithms (such as the shortest path algorithm, traveling salesman algorithm, etc.), consider the geographical location of each examination room in the physical examination center, optimize the routes between examination items, and reduce unnecessary round-trip and waiting time.

[0047] Inspection sequence confirmation: Combine the results of priority sorting and route planning to generate a preliminary inspection route to ensure that it meets the priority requirements of the inspection items and minimizes the moving distance and time consumption of the inspected person.

[0048] Generate inspection route: Integrate the optimized inspection sequence and route to generate the initial inspection route for the examinee. This route will guide the examinee to complete various inspections in the optimal sequence and path.

[0049] Information feedback: The generated initial inspection route will be pushed to the examinee and provided to the examinee through the self-service terminal, mobile application or printed inspection guide.

[0050] Check-in data collection: When arriving at each examination item, the examinee signs in through the self-service terminal, mobile application or by scanning the QR code. The system records the examinee's check-in time in real time and marks it as entering the queue status.

[0051] Confirmation of completion of examination: At the end of the examination, the examinee or the staff of the physical examination room confirms that the examination is complete. The system records the end time and updates the status of the examination item.

[0052] Data collection of networked equipment: After the examination equipment (such as CT machines, blood analyzers) is connected to the network, it can automatically transmit the start and end time data of the examination to the system in real time to update the queue status.

[0053] Physical examination room data collector: A data collector (such as RFID reader, QR code scanner) is installed at the entrance of each examination room to record the entry and exit of the examinee in real time and update the queuing information in the system.

[0054] Data aggregation: The system aggregates the real-time data collected from each inspection room, check-in point, and inspection equipment, and calculates key status data such as the current number of people in line and estimated waiting time for each inspection item.

[0055] Dynamic status update: Based on the summary data, the queue status of each inspection item is updated in real time, including the current number of queued people, the load of each inspection item, waiting time, etc.

[0056] Electronic screen and mobile application updates: The system pushes the latest queue status data to the electronic screen of the physical examination center and the mobile application of the examinee, displaying the current queue order, estimated waiting time and other information in real time.

[0057] Automatic calling system: Based on the queue status data, the system intelligently calls the number and notifies the examinee to proceed to the next examination item in order, reducing disorderly queuing and waiting time.

[0058] S2: preprocessing the obtained queue status data of each physical examination item, performing feature extraction on the preprocessed queue status data, and respectively extracting the physical examination room utilization rate feature and the physical examination time deviation feature from the queue status data.

[0059] There may be missing values ​​in the queue status data (such as missing start or end time of some physical examination items). For these missing values, the following measures can be taken:

[0060] If the missing values ​​are small and do not affect the overall data quality, the corresponding records can be deleted directly.

[0061] For time series data, you can use interpolation methods (such as linear interpolation) to fill missing values. For some fields, you can use the historical mean of the field to fill. Identify and handle outliers in the data (such as abnormal records with extremely short or long queue times). Z-score method: Calculate the Z-score of each data point. If the Z-score exceeds the preset threshold, mark it as an outlier and handle it. Use box plots to identify outliers and use the interquartile range (IQR) to detect and remove outliers.

[0062] Standardize all time data into a unified format, such as converting different timestamp formats (12-hour or 24-hour) into a unified 24-hour format. Standardize numerical data such as the number of queues and waiting time to eliminate the impact of dimension. Common methods include: Min-Max standardization: Scale numerical data to the range of [0, 1]. Convert numerical data to a standard normal distribution with a mean of 0 and a standard deviation of 1.

[0063] Smoothing time series data (such as changes in the number of people in a queue) reduces the impact of short-term fluctuations and highlights long-term trends. For queue time and number of people, exponential smoothing is used to smooth the data to reduce noise and maintain the trend characteristics of the data.

[0064] Align the queue data of different physical examination items by time to ensure that the timestamps between the data are consistent. If the data comes from multiple sources (such as different equipment, different examination rooms), merge these data into integrated data in a unified format.

[0065] The physical examination room utilization rate fluctuation index is generated according to the utilization rate fluctuation of each physical examination room. The method for obtaining the physical examination room utilization rate fluctuation index is as follows:

[0066] Collect the utilization data Xt of the physical examination room in the time period s, determine the smoothing coefficient α, which is usually between 0 and 1, and use the first utilization observation X1 as the initial exponentially weighted moving average , using the exponentially weighted moving average formula to calculate the smoothed value at each time point , the expression is: ; In the formula, is the smoothed value at time point i, where Xt is the actual usage rate at time t, is the smoothed value at time point t, is the smoothed value at the previous time point; the exponentially weighted moving average is used to calculate the physical examination room utilization rate fluctuation index, and the expression is: ; In the formula, is the physical examination room utilization rate fluctuation index, is the mean of the exponentially weighted moving average, and N is the total number of usage observations.

[0067] The physical examination room utilization rate fluctuation index is a key indicator to measure the degree of fluctuation in the physical examination room utilization rate. It reflects the use of the physical examination system in different time periods. A lower fluctuation index indicates that the utilization rate of the physical examination room is relatively stable, indicating that the physical examination system can smoothly handle the needs of the examinees, and the resources of each physical examination room are effectively utilized and reasonably allocated, thereby improving the physical examination efficiency and user satisfaction. On the other hand, a higher fluctuation index indicates that there are large fluctuations in the utilization rate of the physical examination room, indicating that there is greater uncertainty in the physical examination system when handling the needs of the examinees. Such instability may cause some physical examination rooms to be overcrowded, while others are too idle, resource utilization is not high, and bottlenecks may occur in the physical examination process, thereby reducing the overall physical examination efficiency and user satisfaction.

[0068] The physical examination time deviation index is generated according to the physical examination progress delay status of each physical examination item. The method for obtaining the physical examination time deviation index is:

[0069] Collect the actual completion time Tactual and planned completion time Tplanned for each physical examination item, and calculate the time deviation value TimeDeviation of each physical examination item. The expression is: ; Select the window size M and coefficient k, calculate the moving average MA and standard deviation σ of the time deviation value, and determine the physical examination time range under the standard state according to the moving average MA and standard deviation σ of the time deviation value: : Among them, UBT is the maximum physical examination time value, and the expression is: ; LBT is the minimum physical examination time value, the expression is: ; Compare the obtained real-time time deviation value TimeDeviation with the physical examination time range under the standard state, calculate the physical examination time deviation index, when When , the calculation expression of the physical examination time deviation index at this time is: ;when When , the calculation expression of the physical examination time deviation index at this time is: ; In the formula, is the physical examination time deviation index.

[0070] The larger the physical examination time deviation index is, the lower the stability of the physical examination efficiency of the physical examination system is. A larger time deviation index indicates that there is a significant difference between the actual completion time and the planned completion time of the physical examination items, indicating that there are large fluctuations in the system when carrying out the physical examination process as planned. Such fluctuations may lead to uneven resource utilization, longer waiting time for physical examinees, and increased uncertainty in the overall process. When the physical examination time deviation index is large, the physical examination center may encounter difficulties in resource allocation, such as overcrowding or idleness of physical examination equipment and medical staff. Such a situation not only affects the operational efficiency of the physical examination center, but may also reduce the satisfaction and trust of the physical examinees. A high time deviation index often means that a more flexible and efficient scheduling strategy is needed to cope with uncertainty and optimize resource utilization.

[0071] S3: Build a data prediction model, input the extracted physical examination room utilization rate characteristics and physical examination time deviation characteristics into the model for comprehensive calculation, and determine whether the queuing status of the physical examination items is abnormal based on the model output results.

[0072] The physical examination room utilization rate fluctuation index and the physical examination time deviation index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses each group of first eigenvectors to predict the stability value label of the physical examination item queuing status as the prediction target, and takes minimizing the sum of prediction errors of the stability value labels of the queuing status of all physical examination items as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The stability value of the queuing status of the physical examination items is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0073] The method for obtaining the stability value of the physical examination item queuing status is: obtain the corresponding function expression from the first feature vector training data of the trained machine learning model: ; In the formula, is the output function of the model, is the physical examination room utilization rate fluctuation index, is the physical examination time deviation index, It is the stability value of the queue status of the physical examination items.

[0074] Compare the obtained stability value of the physical examination item queuing status with the pre-set stability value reference threshold. If the stability value of the physical examination item queuing status is greater than or equal to the pre-set stability value reference threshold, it means that the stability of the physical examination item queuing status is high, and a normal signal of the physical examination item queuing status is generated. If the stability value of the physical examination item queuing status is less than the pre-set stability value reference threshold, it means that the stability of the physical examination item queuing status is low, and an abnormal signal of the physical examination item queuing status is generated.

[0075] S4: When the queuing status of the physical examination items is abnormal, the waiting time of each examinee in each physical examination item is obtained through the electronic queuing system, and the waiting time in each physical examination item is analyzed in time series to obtain the floating value of the waiting time.

[0076] An electronic check-in device is installed at the entrance of each physical examination project in the physical examination center. Physical examinees swipe their cards or scan codes to check in when entering and leaving. The system records the arrival time, entry time and exit time of each physical examinee, uses a database to store the collected data, and reads the timestamp data of each physical examination project from the database; calculates the waiting time of each physical examinee in each project, and the expression is: W=Tstart−Tarrival; where W is the waiting time, Tstart is the time to enter the project, and Tarriva is the arrival time;

[0077] The system records the arrival time, entry time and exit time of each examinee, uses the database to store the collected data, reads the timestamp data of each examination item from the database, and calculates the waiting time of each examinee in each item. The expression is: ;W is the waiting time, Tstart is the time to enter the project, and Tarriva is the arrival time;

[0078] Calculate the average waiting time for each physical examination item, expressed as: ;Wˉ is the average waiting time for a certain item, M is the number of examinees, is the waiting time of the i-th examinee;

[0079] Summarize waiting time data by time period, generate time series data, and calculate the average waiting time for each project per day. The expression is: ;in, is the average waiting time per day, H is the number of people who undergo physical examinations on that day, is the waiting time of the jth examinee on the day; the Prophet model is used to analyze it, and the model expression is: Among them, y(t) is the predicted waiting time, g(t) is the trend function, s(t) is the seasonal component, h(t) is the holiday component, ϵt is the error term, and the floating value of the waiting time is calculated based on the predicted waiting time. The calculation expression is: ; In the formula, is the floating value of waiting time, The peak waiting time is This is the low-peak period for waiting time.

[0080] The peak and trough of the waiting time are identified through the timing analysis results. The peak time period indicates the time period when the real-time waiting time is greater than or equal to the average waiting time, and the trough time period indicates the time period when the real-time waiting time is less than the average waiting time.

[0081] Compare the obtained waiting time floating value with the pre-set waiting time floating value reference threshold. If the waiting time floating value is greater than or equal to the pre-set waiting time floating value reference threshold, it means that the waiting time in each physical examination item is still increasing, and a waiting time increasing signal is generated at this time; if the waiting time floating value is less than the pre-set waiting time floating value reference threshold, it means that the waiting time in each physical examination item has decreased, and a waiting time decreasing signal is generated at this time.

[0082] In this application, the waiting time of each examinee in each physical examination item is obtained through the electronic queuing system, and the data are analyzed in time series, so that the changes in the waiting time of each item can be monitored and predicted in real time. This method can accurately identify the peaks and troughs of the waiting time, and generate a signal of rising or falling waiting time based on the results of the time series analysis. When the floating value of the waiting time is greater than or equal to the preset reference threshold, a waiting time rising signal is generated to prompt the manager to take measures to optimize resource allocation and reduce the waiting time during the peak period; conversely, when the floating value of the waiting time is less than the reference threshold, a waiting time falling signal is generated, indicating that the waiting time is decreasing and the system operation is stabilizing. This method not only improves the operational efficiency of the physical examination center, but also improves the satisfaction of the examinees, ensuring the rational use of resources and the smooth progress of the physical examination process.

[0083] S5: After comprehensively analyzing the calculation results of the data prediction model and the floating value of the waiting time by the fuzzy logic, the urgency of adjusting the physical examination items is divided into different levels according to the analysis results, namely, no adjustment, normal adjustment and emergency adjustment;

[0084] The stability value of the queue status of the physical examination items and the floating value of the waiting time are used as the output items of the fuzzy logic, and the urgency of adjusting the physical examination items is used as the output item;

[0085] The stability values ​​of the queuing status of physical examination items are converted into fuzzy variables, and possible fuzzy sets are defined, such as three fuzzy sets of "high stability", "medium stability" and "low stability".

[0086] The waiting time floating values ​​are converted into fuzzy variables, and possible fuzzy sets are defined, such as "low floating", "medium floating", and "high floating".

[0087] The urgency of adjusting the physical examination items is converted into fuzzy variables, and possible fuzzy sets are defined, such as "no adjustment required", "normal adjustment", and "urgent adjustment".

[0088] According to the combination of the stability value of the queue status and the floating value of the waiting time, fuzzy rules are set to determine the urgency of adjusting the physical examination items. For example:

[0089] Rule 1: If the stability value of the queue status is "high stability" and the waiting time fluctuation value is "low fluctuation", the urgency of adjusting the physical examination items is "no adjustment required". For example: If the queue status of a B-ultrasound examination item is very stable and the waiting time fluctuation is very small, the system determines that there is no need to adjust the priority of the item, and the examinee can proceed with the examination as originally planned.

[0090] Rule 2: If the stability value of the queue status is "medium stability" and the waiting time fluctuation value is "medium fluctuation", the urgency of adjusting the physical examination items is "normal adjustment". For example: If the queue status of a blood test item fluctuates to a certain extent and the waiting time also changes to a moderate degree, the system will make normal adjustments to this item, for example, advance the inspection order of the physical examination item.

[0091] Rule 3: If the stability value of the queue status is "low stability" and the waiting time fluctuation value is "high fluctuation", the urgency of adjusting the physical examination items is "urgent adjustment". For example, if the queue status of an electrocardiogram examination item is extremely unstable and the waiting time fluctuates greatly, the system will make urgent adjustments to this item, such as immediately raising the priority and arranging the examination in advance to avoid long-term congestion.

[0092] The queue status stability value and waiting time floating value of the physical examination items are input into the fuzzy logic system. The system performs reasoning calculations based on the preset fuzzy rules to determine the urgency of adjusting the inspection route. The fuzzy logic reasoning results are defuzzified and converted into specific priority adjustment measures.

[0093] S6: For the physical examination items that need emergency adjustment, they are moved to the first place in the inspection route; for the physical examination items that need normal adjustment, they are adjusted to the first Y inspection items, where Y is determined according to the importance and priority of the physical examination items.

[0094] For the physical examination items that need to be adjusted urgently, they will be moved to the first place on the inspection route, specifically:

[0095] The system identifies the medical examination items that need urgent adjustments. Identify all currently affected examinees who have urgent adjustments to be made in their examination routes.

[0096] Prioritize the medical examination items that need urgent adjustment to the highest level. This item will be arranged at the first place in the inspection route. The system re-plans the inspection route to put the urgent adjustment items first. For example, if the electrocardiogram examination needs urgent adjustment, the system arranges the electrocardiogram examination as the first examination item for the examinee.

[0097] The system detects whether the adjustment causes multiple examinees to go to the same examination room at the same time. If there is a conflict, the system will assign different time periods or sort them according to other priority criteria. According to the load of the examination room, the examination time is reasonably arranged to avoid new congestion.

[0098] The system updates the inspection routes of all affected examinees in batches, putting the emergency adjustment items at the top of the route. Through self-service terminals, mobile applications or text messages, examinees are promptly notified of the new inspection order and schedule to ensure that they follow the new route for physical examination.

[0099] The examinees follow the new inspection route for physical examinations, and the system monitors the queue status and the load of the examination room in real time. The system collects the examinees' feedback and the data of the examination room, and further optimizes and adjusts the plan when necessary.

[0100] For the normal adjusted physical examination items, they will be adjusted to the first Y examination items, specifically:

[0101] The system identifies the physical examination items that need to be adjusted normally. Identify all currently affected examinees who have normal adjustment items to be made in their inspection routes. Raise the priority of the physical examination items to be adjusted normally to the first Y examination items in the examinee's inspection route. For example, if Y is 3, adjust this item to one of the first 3 items in the inspection route. Based on the results calculated by the system, arrange the items for normal adjustment between the 1st and Yth positions in the inspection route, where the specific position of Y is determined according to the importance of the physical examination item and the priority of the physical examination item. After determining the new order, the system optimizes the examinee's movement path to avoid unnecessary round trips and ensure a smooth physical examination process.

[0102] Check whether there are examinees who are concentrated in the same time period for multiple of the first Y items. If there is a conflict, make reasonable time allocation. Reasonably allocate the number of examinees within the first Y examination items to ensure balanced use of examination room resources. The system batch updates the inspection routes of relevant examinees and moves the normal adjustment items to one of the first Y examination items. Notify the examinees of the new inspection route through mobile applications, self-service terminals or text messages, and indicate the specific inspection sequence and time. The examinees complete the physical examination according to the new inspection route, and the system continuously monitors the use and queue status of the examination room. Further optimize the inspection route and adjustment strategy based on the actual situation and feedback information.

[0103] For example, the system detects severe congestion and long queues for B-ultrasound examinations and determines that urgent adjustments are needed. The adjustment steps include: promoting the B-ultrasound examination to the first place in the inspection route to ensure that the examinees complete the B-ultrasound examination first. Check whether there are examinees who are concentrated in the same time period for B-ultrasound examinations. If conflicts are found, the system adjusts the respective examination times to balance the load. The examinees are notified of the updated inspection route through the mobile phone application, prompting them to go to the B-ultrasound examination first. The examinees are examined along the new route, and the system monitors the situation in the B-ultrasound examination room in real time and further optimizes the arrangement based on feedback.

[0104] For example, if the blood test item has a moderate queue fluctuation, normal adjustments are required. The adjustment steps include: raising the priority of the blood test item to one of the top three test items on the inspection route. Ensure that the adjusted blood test does not conflict with the other top three test items. The examinee receives the notification of the adjusted inspection route, advances the blood test to a position within the top three items, and performs the examination in the new order. The system monitors the use of the inspection room to ensure load balance and adjusts the schedule based on feedback.

[0105] In this application, the specific value of Y should be determined relative to the total number of examination items. For example, if the physical examination route usually includes 10 examination items, it may be appropriate to set Y to 2 or 3; if the total number of items is small (such as 5), Y may be set to 1 or 2. If some examination items are more complicated or time-consuming, you can consider setting a smaller Y value, for example, Y may be 1, to avoid too many complex items being concentrated in the first few examination items.

[0106] In this embodiment, an initial inspection route is generated by the physical examination system based on the physical examination subject's appointment time and examination items, and the initial inspection route is used to queue the physical examination subjects for various physical examination items, and the queuing status data of each physical examination item is obtained in real time; the obtained queuing status data of each physical examination item is preprocessed, and feature extraction is performed on the preprocessed queuing status data, and the physical examination room utilization rate characteristics and physical examination time deviation characteristics in the queuing status data are respectively extracted; a data prediction model is constructed, and the extracted physical examination room utilization rate characteristics and physical examination time deviation characteristics are input into the model for comprehensive calculation, and whether the queuing status of the physical examination items is abnormal is determined according to the output results of the model; when the queuing status of the physical examination items is abnormal, the waiting time of each physical examination subject in each physical examination item is obtained through the electronic queuing system, and the waiting time in each physical examination item is analyzed in time series to obtain the waiting time floating value; after comprehensively analyzing the calculation results of the data prediction model and the waiting time floating value through fuzzy logic, the physical examination subject's inspection route and the priority of each physical examination item are dynamically adjusted. Monitor and analyze the queue status and waiting time of each physical examination item in real time, quickly identify abnormal situations, and immediately adjust the inspection order and priority, so as to effectively balance resource utilization, reduce the waiting time of examinees, improve physical examination efficiency and satisfaction, and ultimately improve the operation effect and service quality of the physical examination center.

[0107] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0108] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0109] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A medical examination queuing algorithm based on the medical examination system service, characterized by: The steps include: S1: The physical examination system generates an initial inspection route based on the physical examination subject's appointment time and examination items, uses the initial inspection route to queue the physical examination subjects for various physical examination items, and obtains the queue status data of each physical examination item in real time; S2: preprocessing the queue status data of each physical examination item obtained, performing feature extraction on the preprocessed queue status data, and respectively extracting the physical examination room utilization rate feature and the physical examination time deviation feature from the queue status data; Step S2 specifically includes: generating a physical examination room utilization rate fluctuation index according to the utilization rate fluctuation of each physical examination room, and the method for obtaining the physical examination room utilization rate fluctuation index is: Collect the utilization data of the physical examination room in the time period s, determine the smoothing coefficient α, and use the first utilization observation value X1 as the initial exponentially weighted moving average , use the exponentially weighted moving average formula to calculate the smoothed value at each time point, the expression is: ; In the formula, is the smoothed value at time point i, where Xt is the actual usage rate at time t, is the smoothed value at time point t, is the smoothed value at the previous time point; the exponentially weighted moving average is used to calculate the physical examination room utilization rate fluctuation index, and the expression is: ; In the formula, is the physical examination room utilization rate fluctuation index, is the mean of the exponentially weighted moving average, and N is the total number of usage observations; The physical examination time deviation index is generated according to the physical examination progress delay status of each physical examination item. The method for obtaining the physical examination time deviation index is: Collect the actual completion time Tactual and planned completion time Tplanned for each physical examination item, and calculate the time deviation value TimeDeviation of each physical examination item. The expression is: ; Select the window size M and coefficient k, calculate the moving average MA and standard deviation σ of the time deviation value, and determine the physical examination time range under the standard state according to the moving average MA and standard deviation σ of the time deviation value: : Among them, UBT is the maximum physical examination time value, and the expression is: ; LBT is the minimum physical examination time value, the expression is: ; Compare the obtained real-time time deviation value TimeDeviation with the physical examination time range under the standard state, calculate the physical examination time deviation index, when When , the calculation expression of the physical examination time deviation index at this time is: ;when When , the calculation expression of the physical examination time deviation index at this time is: ; In the formula, is the physical examination time deviation index; S3: Build a data prediction model, input the extracted physical examination room utilization rate characteristics and physical examination time deviation characteristics into the model for comprehensive calculation, and determine whether the queue status of the physical examination items is abnormal based on the model output results; Step S3 specifically includes: converting the physical examination room utilization rate fluctuation index and the physical examination time deviation index into a first eigenvector, taking the first eigenvector as the input of the machine learning model, the machine learning model predicting the stability value label of the physical examination system with each group of first eigenvectors as the prediction target, minimizing the sum of prediction errors of the stability value labels of all physical examination systems as the training target, training the machine learning model until the sum of prediction errors reaches convergence, stopping the model training, and determining the stability value of the physical examination system according to the model output result, wherein the machine learning model is a polynomial regression model; The obtained stability value of the physical examination system is compared with the preset stability value reference threshold. If the stability value of the physical examination system is greater than or equal to the preset stability value reference threshold, the stability of the physical examination system is high. At this time, a physical examination system operation stability signal is generated to continuously monitor and maintain the existing physical examination process to ensure its stable operation; If the stability value of the physical examination system is less than the preset stability value reference threshold, the stability of the physical examination system is low, and an unstable operation signal of the physical examination system is generated at this time, and the data is deeply analyzed to determine the root cause of the instability; S4: When the queuing status of the physical examination items is abnormal, the waiting time of each examinee in each physical examination item is obtained through the electronic queuing system, and the waiting time in each physical examination item is analyzed in time series to obtain the floating value of the waiting time; Step S4 specifically includes: when the queuing status of the physical examination items is abnormal, the waiting time of each examinee in each physical examination item is obtained through the electronic queuing system, and the waiting time in each physical examination item is analyzed in time series to obtain the floating value of the waiting time, specifically: The system records the arrival time, entry time and exit time of each examinee, uses the database to store the collected data, reads the timestamp data of each examination item from the database, and calculates the waiting time of each examinee in each item. The expression is: ;W is the waiting time, Tstart is the time to enter the project, and Tarrival is the arrival time; Calculate the average waiting time for each physical examination item, expressed as: ;Wˉ is the average waiting time for a certain item, M is the number of examinees, is the waiting time of the i-th examinee; Summarize waiting time data by time period, generate time series data, and calculate the average waiting time for each project per day. The expression is: ;in, is the average daily waiting time, H is the number of people undergoing physical examinations on that day, is the waiting time of the jth examinee on the day; the Prophet model is used to analyze it, and the model expression is: Among them, y(t) is the predicted waiting time, g(t) is the trend function, s(t) is the seasonal component, h(t) is the holiday component, ϵt is the error term, and the floating value of the waiting time is calculated based on the predicted waiting time. The calculation expression is: ; In the formula, is the floating value of waiting time, The peak waiting time is It is the low peak period of waiting time; Compare the obtained waiting time floating value with the preset waiting time floating value reference threshold. If the waiting time floating value is greater than or equal to the preset waiting time floating value reference threshold, the waiting time in each physical examination item is still increasing, and a waiting time increase signal is generated at this time; if the waiting time floating value is less than the preset waiting time floating value reference threshold, the waiting time in each physical examination item decreases, and a waiting time decrease signal is generated at this time; S5: After comprehensively analyzing the calculation results of the data prediction model and the floating value of the waiting time by the fuzzy logic, the urgency of adjusting the physical examination items is divided into different levels according to the analysis results, namely, no adjustment, normal adjustment and emergency adjustment; Step S5 specifically includes: after comprehensively analyzing the calculation results of the fuzzy logic data prediction model and the floating value of the waiting time, the urgency of adjusting the physical examination items is divided into different levels according to the analysis results, specifically: The stability value of the queue status of the physical examination items and the floating value of the waiting time are used as the output items of the fuzzy logic, and the urgency of adjusting the physical examination items is used as the output item; The stability value of the physical examination item queue status, the floating value of the waiting time and the urgency of the physical examination item adjustment are converted into fuzzy variables; The queue status stability value and waiting time floating value of the physical examination items are input into the fuzzy logic system. The system performs reasoning calculation according to the preset fuzzy rules to determine the urgency of adjusting the inspection route. And defuzzify the fuzzy logic reasoning results and convert them into specific priority adjustment measures; S6: For the physical examination items that need emergency adjustment, they are moved to the first place in the inspection route; for the physical examination items that need normal adjustment, they are adjusted to the first Y inspection items, where Y is determined according to the importance and priority of the physical examination items.

Images