An outpatient examination sequence planning method

Abstract

The application relates to the technical field of intelligent scheduling, and particularly discloses a clinic examination sequence planning method, which comprises the following steps: S1, acquiring an examination item list of a first patient and an on-duty end time of a doctor; S2, acquiring a current queuing number of each examination item; S3, constructing an inter-department path distance matrix and a visual exposure relationship matrix according to pre-stored hospital space layout data; S4, calculating a predicted queuing waiting time length, and accumulating to obtain a predicted re-visit starting time point corresponding to each execution sequence; S5, in the execution sequences satisfying that the predicted re-visit starting time point is not later than the on-duty end time, the execution sequences are sorted from low to high according to compliance risk values, the execution sequences are sorted from early to late according to the predicted re-visit starting time point when the compliance risk values are the same, the first sequence in the sorting is selected as a time-optimized recommended examination sequence, and the time-optimized recommended examination sequence is output. The technical scheme of the application can intelligently plan an examination sequence for a patient within limited time, so as to help the patient to efficiently complete a visit.

Description

Technical Field

[0001] This invention relates to the field of intelligent scheduling technology, and in particular to a method for planning the order of outpatient examinations. Background Technology

[0002] Currently, outpatient volume at large general hospitals is typically high.

[0003] This supply-demand imbalance leads to a high concentration of patients at outpatient clinics on weekends. Patients typically have to complete the following within a very limited half-day: upon arrival at the hospital, they register and obtain a number, then wait in the corresponding department; the doctor issues an order for tests; after paying, the patient signs in and queues at each of the various testing departments to complete the tests; after receiving all the test reports, they return to the original department for a follow-up appointment; the doctor makes a diagnosis and writes a prescription based on the test results; the patient pays again and goes to the pharmacy to pick up the medication. This series of steps presents patients with multiple difficulties: Firstly, since the various departments in the hospital are located on different floors or even in different buildings, patients are not familiar with the hospital layout and circulation, wasting a lot of time searching for departments and traveling back and forth. Patients also find it difficult to accurately judge whether they will have the opportunity to complete all their diagnosis and treatment before the doctor leaves work.

[0004] Secondly, different examinations vary significantly in terms of waiting time, execution speed, and report issuance period. Some examinations are quick and report issuance is fast, while others have long waiting times and slow report issuance. If patients choose the order of examinations based on personal experience or randomness, they often end up having to wait until all reports are issued before the doctor has left work, forcing them to make another appointment on a later day, incurring additional time and financial costs and delaying treatment.

[0005] Third, during weekends and holidays, doctors prescribe tests at a concentrated pace, and the number of patients waiting for certain examinations accumulates rapidly over time. Patients make decisions and go to the hospital based on the queue situation at a certain moment, but by the time they arrive, the queue length may have changed significantly, resulting in actual waiting times far exceeding expectations and further compressing the already tight time window.

[0006] The combination of these problems means that even with the arduous journeys to and from clinics on weekends, many patients often cannot complete their follow-up appointments before the doctor's shift ends, resulting in low patient satisfaction. Therefore, there is an urgent need for a method that can intelligently plan the examination sequence for patients within a limited timeframe, fully considering the dynamic changes in queuing status in different departments, to help patients efficiently complete their medical visits in the complex hospital environment and achieve timely follow-up appointments before the doctor's shift ends. Summary of the Invention

[0007] This invention provides a method for planning the order of outpatient examinations, which can intelligently plan the order of examinations for patients within a limited time to help patients complete their medical visits efficiently.

[0008] To solve the above-mentioned technical problems, this application provides the following technical solution: A method for planning the order of outpatient examinations includes: S1. Obtain the list of examination items for the first patient and the end time of the attending physician's shift; S2. Obtain the current number of people in the queue for each examination item, the average examination time per person, and the time for issuing examination reports. Collect the rate of medical orders issued by each examination department in real time, and obtain the average waiting time for follow-up visits. S3. Based on the pre-stored hospital spatial layout data, construct the inter-department path distance matrix and the visual exposure relationship matrix; the visual exposure relationship matrix is ​​used to record whether the queues of other examination departments are directly visible on the conventional feasible path from the self-service payment machine to any examination department, or from any examination department to another examination department. S4. Based on the travel time calculated from the rate of medical order issuance and the inter-departmental path distance matrix, calculate the predicted number of people in the queue when the first patient arrives at each examination department, then calculate the predicted queuing waiting time, and sum them up to obtain the estimated start time of the follow-up visit corresponding to each execution sequence. S5. Traverse all possible execution sequences and calculate the compliance risk value for each sequence based on the visual exposure relationship matrix. The compliance risk value represents the risk that the first patient will be attracted by non-next-order examination items and deviate during the execution of the sequence. In the execution order that satisfies the requirement that the estimated follow-up visit start time is no later than the end time of the shift, the order is sorted from low to high according to the compliance risk value. If the compliance risk values ​​are the same, the order is sorted from early to late according to the estimated follow-up visit start time. The order with the highest ranking is selected as the recommended examination order for time optimization and output.

[0009] Furthermore, in step S3, based on the location information of each examination department, follow-up visit department, and self-service payment machine in the pre-stored hospital spatial layout data, a path distance matrix between departments is constructed. Based on the path distance matrix and the preset walking speed, the movement time between the self-service payment machine and each examination department, between each examination department and each examination department and the follow-up visit department is obtained.

[0010] Furthermore, step S4 specifically includes: S41. For a certain examination item i, calculate the time required for the first patient to move from the current location to the corresponding department i of the examination item i. ; S42, Calculate the arrival time of the first patient at the examination department. Predicted queue length The formula is: ; in, This represents the current number of people who have actually checked in and are queuing for this inspection department. For the examination department i, the time spent moving Within, the number of new sign-in patients expected to be ahead of the first patient after the doctor's orders are issued and payments are made is calculated. The rate at which medical orders are issued in this examination department i The preset conversion rate for doctor's order check-in; S43, Based on predicted queue length Calculate the predicted queuing time for examination item i based on the preset average examination time per person for the corresponding examination item i in the examination department; S44. For any execution order of the examination items list, sequentially accumulate the predicted queuing waiting time for each examination item, the average examination time per person for that examination item, and the travel time from the previous location to the examination department. After all examinations are completed, accumulate the travel time from the last examination department to the follow-up examination department, the longest waiting time required to issue all examination reports, and the average waiting time for follow-up examinations to obtain the estimated follow-up examination start time corresponding to that order.

[0011] Furthermore, step S5 specifically includes: S51. Traverse all possible execution orders of the examination item list. For each execution order, simulate the movement process of each examination item in that order. Identify whether the first patient will pass through or directly see a non-next-order examination item j on the path from the attending physician's department to the self-service payment machine, from the self-service payment machine to the first examination item, or from executing the current examination item i to the next examination item i+1. If so, and the temptation index of the non-next-order examination item j at the current moment exceeds the preset threshold, then record a temptation exposure. Temptation Index The calculation is based on a weighted average of the current number of people queuing for the corresponding examination item j, the convenience of the examination type, the patient's expected time, and the time remaining until the end of the attending physician's shift; the calculation formula is: ; in, The function is monotonically decreasing; the fewer people in the queue, the greater the temptation. The predicted number of people queuing when the first patient passes by or directly sees the examination department; As a monotonically decreasing function, the more complex the project, the less tempting it becomes; To check the complexity factor of project j; As it is a monotonically decreasing function, the shorter the estimated time, the greater the temptation. The estimated time required for the examination item j in the patient's mind; This represents the remaining time until the attending physician's shift ends at the current moment; Let the time pressure function satisfy: ,in, It is a very small positive number; These are the weighting coefficients; Calculate the compliance risk value for this order. The formula is: ; S52. Determine whether there is at least one execution sequence that satisfies the condition that the estimated start time of the follow-up visit is not later than the end time of the shift. If it exists, calculate the proportion of the number of sequences that meet the above conditions to the total number of sequences. If the proportion is not higher than the preset proportion threshold, sort all sequences that meet the conditions from low to high according to compliance risk value. If the risk values ​​are the same, sort them from early to late according to the estimated follow-up visit start time. Select the first-ranked sequence as the recommended examination sequence for time optimization and output it to end the process. If it does not exist, generate and output the first prompt message indicating that the follow-up visit cannot be safely completed before the doctor leaves work.

[0012] Furthermore, in step S52, if there is no execution order that satisfies the condition that the estimated start time of the follow-up visit is not later than the end time of the shift, then a first prompt message indicating that the follow-up visit cannot be safely completed before the doctor leaves work is generated and output, and the process jumps to step S6. S6. Obtain the association information of all second patients in the current queue for each examination item. The association information includes: the ranking of each second patient in the queue, the set of examination items that the second patient must perform to complete their own follow-up visit, and the end time of the shift of the attending physician corresponding to the second patient.

[0013] Furthermore, it also includes step S7: based on the list of examination items for the first patient and the association information of the second patient, simulate adjusting the execution order of at least one examination item for the first patient backward, so that the examination item makes way for some second patients behind it in the queue; calculate whether each second patient who benefits from the advanced ranking can make their estimated follow-up visit start time no later than the end time of their corresponding attending physician's shift, and record the estimated number of second patients who can benefit from the follow-up visit. The recommended examination order for the first patient was generated with the shortest total walking distance as the optimization objective; and the recommended examination order for the first patient was generated with the maximum benefit to the second patient as the optimization objective. The system outputs the recommended examination order based on time optimization, the recommended examination order based on the shortest total walking distance, and the recommended examination order based on the order that benefits the second patient the most. It also receives the recommended examination order selected by the first patient.

[0014] Furthermore, it also includes step S8: calculating the expected check-in time of the first patient in each examination department based on the recommended examination order selected by the first patient; The first patient's current planning is recorded as a collaborative event in the collaborative planning event table. The collaborative planning event table includes: the first patient's identifier, the relevant examination departments, the expected check-in time for each department, and the changes in the queuing sequence of the examination department caused by this order adjustment.

[0015] Furthermore, step S4 specifically includes: S41. For a certain examination item i, calculate the time required for the first patient to move from the current location to the corresponding department i of the examination item i. ; S42, Calculate the arrival time of the first patient at the examination department. Predicted queue length The formula is: ; in, This represents the current number of people who have actually checked in and are queuing for this inspection department. For the examination department i, the time spent moving Within, the number of new sign-in patients expected to be ahead of the first patient after the doctor's orders are issued and payments are made is calculated. The rate at which medical orders are issued in this examination department i The preset conversion rate for doctor's order check-in; To coordinate the adjustment of net increase in personnel, its value is calculated based on all registered collaborative events of the inspection department in the collaborative planning event table; S43, Based on predicted queue length Calculate the predicted queuing time for examination item i based on the preset average examination time per person for the corresponding examination item i in the examination department; S44. For any execution order of the examination items list, sequentially accumulate the predicted queuing waiting time for each examination item, the average examination time per person for that examination item, and the travel time from the previous location to the examination department. After all examinations are completed, accumulate the travel time from the last examination department to the follow-up examination department, the longest waiting time required to issue all examination reports, and the average waiting time for follow-up examinations to obtain the estimated follow-up examination start time corresponding to that order.

[0016] Furthermore, in step S42, the process of calculating the net increase in the number of people in the collaborative adjustment is as follows: all events in which the patient's expected check-in time is not later than the estimated time of the first patient's arrival at the examination department, and the event will cause a change in the number of people queuing in front of the first patient, are selected, the net increase in the number of people queuing in front of the first patient caused by the event is calculated, the net increase in the number of people = the number of people with positive changes - the number of people with negative changes, and the net increase in the number of people in the collaborative adjustment is accumulated.

[0017] Existing methods only display the current number of people in the queue. Once a patient sets off, new patients may join the queue at other departments along the way, leading to actual waiting times far exceeding expectations. This solution effectively compensates for this deficiency through incremental prediction, making time estimates more accurate and providing a reliable foundation for subsequent sequence planning. Furthermore, this solution, by constructing a visual exposure relationship matrix and calculating compliance risk values, is the first to incorporate patient behavioral compliance into the consideration of examination sequence planning. During the planning phase, it pre-identifies the existence of such exposure risks in each execution sequence and quantifies their threat level to patient compliance, prioritizing examination sequences less likely to trigger deviations, thus improving the actual executability of the planning scheme from the source. The solution also iterates through all possible execution sequences and optimizes them under the dual constraints of time feasibility and controllable compliance. When time and queue conditions are relatively relaxed, no intervention is deemed necessary, reducing unnecessary restrictions on patient freedom. When most sequences carry the risk of not being able to re-attend, the optimal sequence that balances time efficiency and behavioral compliance is output.

[0018] In summary, this solution takes into account dynamic queue increments, patient compliance, and time urgency, providing patients with feasible examination sequence planning within the limited time available to doctors on duty. This effectively reduces the probability of rescheduling follow-up visits due to improper planning, and improves the overall operational efficiency of the outpatient department and the patient experience. Attached Figure Description

[0019] Figure 1 This is a flowchart of an embodiment of an outpatient examination sequence planning method; Figure 2 This is a flowchart of an embodiment of an outpatient examination sequence planning method. Detailed Implementation

[0020] The following detailed description illustrates the specific implementation method: Example 1 like Figure 1 As shown in the figure, this embodiment of an outpatient examination sequence planning method includes the following steps: S1. Obtain the list of examination items for the first patient, as well as the end time of the shift for the doctor who treated the first patient.

[0021] S2. For each examination item in the list of examination items, obtain the current number of people in the queue, the average examination time per person, and the time for issuing the examination report; at the same time, collect the order issuance rate of each examination department in real time, that is, the number of newly added paid and pending examination orders for that examination department per unit time, and obtain the average waiting time for the first patient's corresponding attending physician to make a follow-up visit.

[0022] S3. Based on the pre-stored hospital spatial layout data, including the location information of each examination department, follow-up department (i.e., the department of the attending physician), and self-service payment machine, construct a path distance matrix between departments. In this embodiment, the path distance matrix refers to the shortest path length between any two departments, calculated in advance based on the department locations and feasible passages marked in the hospital spatial layout data, with each examination department and follow-up department as nodes, and stored in matrix form for direct query and retrieval in subsequent steps. Based on the path distance matrix and the preset walking speed, obtain the movement time between the self-service payment machine and each examination department, between each examination department and each examination department, and between each examination department and the follow-up department; in this embodiment, the walking speed is set according to different age ranges.

[0023] Simultaneously, a visual exposure relationship matrix is ​​constructed to record whether the queuing situation of other examination departments, such as waiting areas or call number displays, is directly visible along the conventional feasible path from the self-service payment machine to any examination department, or from any examination department to another. In this embodiment, the waiting areas or call number displays of each examination department are pre-marked manually in the hospital spatial layout data. If a manually marked waiting area or call number display exists within a preset range (e.g., 2-5m) of the conventional feasible path from the self-service payment machine to any examination department, or from any examination department to another, it is considered visible.

[0024] S4. Establish a time estimation model with queuing increment prediction to estimate the predicted start time of follow-up visits for any execution order, specifically including: S41. For examination item i in a certain examination department i, calculate the time required for the first patient to move from the current location to the examination department i corresponding to examination item i. The unit is minutes; the current location of the first patient refers to the initial location (e.g., self-service payment machine) or the previous examination department i-1 in the execution sequence.

[0025] S42, Calculate the arrival time of the first patient at the examination department. Predicted queue length The formula is:

[0026] in: This represents the current number of people who have actually checked in and are queuing for this inspection department. For the examination department i, the time spent moving Within, the number of new sign-in patients expected to be ahead of the first patient after the doctor's orders are issued and payments are made is calculated. , The rate at which medical orders are issued in department i is expressed in person / minute (i.e., the number of newly issued, paid, pending medical orders per unit of time). The preset conversion rate for doctor's order check-in is 0.8 in this embodiment; To predict the expected value, non-integer values ​​are allowed for subsequent sequential sorting.

[0027] S43, Based on predicted queue length Given the preset average examination time per person for examination item i in the corresponding examination department, calculate the predicted queuing waiting time for examination item i. In this embodiment, the predicted queuing waiting time is the product of the predicted number of people in the queue and the preset average examination time per person.

[0028] S44. For any execution order of the examination items list, sequentially accumulate the predicted queuing waiting time for each examination item, the average examination time per person for that examination item (i.e., the predicted time spent by the patient on that examination item), and the travel time from the previous location to the examination department. After all examinations are completed, accumulate the travel time from the last examination department to the follow-up examination department, the longest waiting time required to issue all examination reports, and the average waiting time for the follow-up examination to obtain the estimated start time of the follow-up examination corresponding to that order.

[0029] S5. The execution order that simultaneously satisfies the condition that the estimated start time of the follow-up appointment is no later than the end time of the shift includes: S51. Traverse the list of all possible execution orders for the check items, and for each execution order, perform temptation exposure analysis based on the visual exposure relationship matrix to calculate the compliance risk value. Specifically: Simulate the movement process of each examination item in this sequence, and identify whether the first patient will pass through or directly see a non-next-order examination item j on the path from the attending physician's department to the self-service payment machine, from the self-service payment machine to the first examination item, or from the current examination item i to the next examination item i+1. If so, and the temptation index of the non-next-order examination item j at the current moment exceeds a preset threshold, then record a temptation exposure. The allure index is calculated by weighting the current number of people queuing for the corresponding examination item j, the convenience of the examination type, the patient's expected time, and the time remaining until the end of the attending physician's shift; for example, the allure index of examination item j... The calculation formula is:

[0030] in: The function is monotonically decreasing; the fewer people in the queue, the greater the temptation. In this embodiment... The range is (0,1]. The predicted number of people queuing when the first patient passes by or directly sees the examination department. ; This is a preset positive number used to avoid the denominator being zero; in this embodiment, it is set to 1. The function is a monotonically decreasing function, indicating that the more complex the inspection items, the less tempting they become; in this embodiment... The range is (0,1]. To assess the complexity factor of item j, a pre-set value is generated based on the actual preparation requirements and operational complexity of the examination item. For example, examinations requiring no special preparation and performed immediately upon arrival, such as blood draws, urine or stool sample collection, are classified as low complexity; ultrasound examinations requiring fasting or a full bladder are classified as medium complexity; and enhanced imaging examinations requiring appointments, contrast agent injections, or special body positions are classified as high complexity. The higher the complexity level, the higher the complexity factor. The larger the value, the better.

[0031] The function is monotonically decreasing; the shorter the estimated time, the greater the temptation. In this embodiment... The range is (0,1]. This is a preset positive number used to avoid the denominator being zero; in this embodiment, the value is 0.1. The estimated time for a patient to undergo a specific examination (j) can be pre-set based on the historical average examination time or patient group perception survey data. For example, a routine blood test is expected to take 5 to 10 minutes, a plain CT scan is expected to take 15 to 20 minutes, and an enhanced CT scan is expected to take more than 30 minutes. These settings can be stored in the system database and adjusted according to the actual situation during implementation.

[0032] Let be a time pressure function, satisfying when The smaller the value, the larger the function value, and when The function value increases sharply as it approaches zero: The range is (0,1], where, To avoid the denominator being zero, a very small positive number is typically chosen, usually much smaller than the planning time granularity (e.g., 1 minute). For example, setting... =0.01 minutes. This represents the remaining time until the attending physician's shift ends. This function ensures that when there is ample remaining time, time pressure contributes less to the temptation index, while as the end of the shift approaches, time pressure dramatically amplifies the temptation effect of the low queuing window, enabling the system to predict and avoid irrational deviations by patients in this situation.

[0033] Here are the weighting coefficients, where It can be dynamically adjusted based on the patient's historical compliance data; for example, each deviation increases by 0.2, with a maximum of 2.0. In this embodiment, .

[0034] Calculate the compliance risk value for this order. The formula is:

[0035] In the formula, each examination item j belonging to temptation exposure corresponds to a temptation index. After squaring, the high values ​​are significantly amplified, while the low values ​​are relatively compressed. Summing the squared values ​​achieves multi-point accumulation, and taking the square root brings the result back to the same dimension as the original seduction index.

[0036] For example, in scenario A, a patient's temptation indices for five examination items are 2.0, 1.7, 2.0, 1.7, and 2.0, respectively, all exceeding the preset threshold (set to 1.5 in this embodiment), indicating temptation exposure. The calculated compliance risk value is approximately 4.21. In scenario B, a patient's temptation index for only one examination item is 4.2, exceeding the threshold, indicating temptation exposure. The calculated compliance risk value is approximately 4.2. The risk values ​​of scenarios A and B are very close, which can accurately reflect the overall risk of patients deviating from their plans due to multiple moderate temptations versus a single high temptation.

[0037] S52. Determine whether there is at least one execution sequence that satisfies the condition that the estimated start time of the follow-up visit is not later than the end time of the shift. If it exists, calculate the proportion of the number of sequences that meet the above conditions out of the total number of sequences. If the proportion is higher than the preset proportion threshold (e.g., 80%), it indicates that the current time and queue status are relatively relaxed, and the patient can arrange it themselves, so the process ends. If the proportion is not higher than the preset proportion threshold, it indicates that most sequences cannot be successfully followed up. Then, sort all the sequences that meet the conditions from low to high according to the compliance risk value. If the risk values ​​are the same, sort them from early to late according to the estimated follow-up start time. Select the sequence with the first ranking as the recommended examination sequence for time optimization and output it, then end the process. If it does not exist, generate and output the first prompt message indicating that the follow-up visit cannot be safely completed before the doctor leaves work.

[0038] The proposed solution establishes a time estimation model with incremental queue prediction, incorporating the rate of medical order issuance into the calculation of the number of people in the queue. This makes the predicted queue situation when patients arrive at the examination department more closely reflect the actual dynamics. Existing methods only display the current number of people in the queue. After a patient sets off based on this, new patients may have already joined the queue at the department, leading to actual waiting times far exceeding expectations. For example, during peak hours like weekend half-day outpatient clinics, this estimation bias can often be the final straw that jeopardizes follow-up appointments. This solution effectively compensates for this deficiency through incremental prediction, making time estimation more accurate and providing a reliable foundation for subsequent sequence planning.

[0039] This solution, by constructing a visual exposure relationship matrix and calculating adherence risk values, is the first to incorporate patient behavioral adherence into the consideration of examination sequence planning. In a hospital environment, if patients pass by other examination windows with shorter queues on their way to their target department, they are highly likely to change their plans on the spot. This deviation often disrupts the optimal sequence for overall time, ultimately causing them to miss follow-up appointments. This solution identifies the existence of such exposure risks in each execution sequence during the planning phase, quantifies their threat level to patient adherence, and prioritizes examination sequences less likely to trigger deviations, thereby improving the actual executability of the planning solution from the outset.

[0040] This solution also iterates through all possible execution sequences and optimizes them under the dual constraints of time feasibility and controllable compliance. When time and queue status are relatively relaxed, no intervention is required, reducing unnecessary restrictions on the patient's freedom. When most sequences pose a risk of not being able to return for follow-up visits, the solution outputs the optimal sequence that balances time efficiency and behavioral compliance, helping patients take the initiative in the race against time.

[0041] In summary, this solution takes into account dynamic queue increments, patient compliance, and time urgency, providing patients with a practical examination sequence plan within the limited time available to doctors on duty. This effectively reduces the probability of having to reschedule a follow-up visit due to improper planning, thereby improving the overall operational efficiency of the outpatient department and the patient's experience.

[0042] Example 2 like Figure 2 As shown, the outpatient examination sequence planning method of this embodiment differs from that of Embodiment 1 in that, in step S42 of this embodiment, the formula for predicting the number of people in the queue is adjusted, specifically: Calculate the arrival of the first patient at the examination department Predicted queue length The formula is:

[0043] Among them, the newly added To coordinate the adjustment of the net increase in the number of patients, its value is calculated based on all registered collaborative events for that examination department in the collaborative planning event table. Specifically, events are selected where the patient's expected check-in time is no later than the estimated time of the first patient's arrival at examination department i, and the event causes a change in the number of people ahead of the first patient in the queue. The net increase in the number of patients ahead of the first patient caused by this event is calculated, where net increase = positive change in number of patients - negative change in number of patients. The net increase in the number of patients from all valid events is then summed to obtain the net increase in the number of patients ahead of the first patient. Collaborative events already registered by the first patient are not included in this calculation.

[0044] In step S52 of this embodiment, it is determined whether there is at least one execution order that satisfies the estimated start time of the follow-up visit being no later than the end time of the shift; if not, a first prompt message is generated and output that the follow-up visit cannot be safely completed before the doctor leaves work, and the process jumps to step S6.

[0045] This embodiment also includes an additional step: S6. Obtain the association information of all second patients in the current queue for each examination item. The association information includes: the ranking of each second patient in the queue, the set of examination items that the second patient must perform to complete their own follow-up visit, and the end time of the shift of the attending physician corresponding to the second patient.

[0046] S7. Based on the list of examination items for the first patient and the association information of the second patient, use a time prediction model with queuing increment prediction to simulate adjusting the execution order of at least one examination item for the first patient backward, so that the examination item can make way for some second patients in the queuing queue; calculate whether each second patient who benefits from the advanced ranking can make their own estimated follow-up visit start time no later than the end time of their corresponding attending physician's shift, and record the estimated number of second patients who can benefit from the follow-up visit. The recommended examination order for the first patient was generated with the shortest total walking distance as the optimization objective; and the recommended examination order for the first patient was generated with the maximum benefit to the second patient as the optimization objective.

[0047] The recommended examination order is optimized based on time, the recommended examination order with the shortest total walking distance, and the recommended examination order that benefits the second patient the most. The recommended examination order selected by the first patient is received. S8. Calculate the expected check-in time of the first patient in each examination department according to the recommended examination order selected by the first patient. In this embodiment, according to the recommended examination order, starting from the current time, the travel time of the first patient to each examination department, the predicted queuing waiting time in that examination department, and the examination execution time are accumulated item by item. The accumulated time points are the expected check-in time of the first patient in each examination department.

[0048] The first patient's current planning is recorded as a collaborative event in the collaborative planning event table. The collaborative planning event table includes: the first patient's identifier, the relevant examination departments, the expected check-in time of each examination department, and the changes in the queuing sequence of the examination department caused by this order adjustment (i.e., which other patients' relative positions have changed due to the first patient's delay or advancement).

[0049] Based on the solution in Embodiment 1, this embodiment adds collaboration among multiple patients. If a single patient is assessed as unable to complete a follow-up visit before the doctor leaves work, the service is not simply terminated. Instead, the examination order is proactively adjusted to coordinate examination resources among patients.

[0050] By delaying the examination order of the first patient, and proactively making room for the second patient in the queue, the second patient, who would otherwise also face the risk of failed follow-up visits, can complete their examination earlier and have their follow-up visit within the corresponding doctor's shift. Especially during tight time windows such as weekend half-day clinics, this transforms the time constraints of individual patients into improved group efficiency, effectively reducing large-scale follow-up visit failures caused by improper queuing order, and alleviating the social pain points of idle medical resources and repeated trips for patients.

[0051] This embodiment does not simply and crudely ask patients to give up the examination. Instead, it generates multiple recommended sequences with different optimization focuses for the first patient at the same time—taking into account the shortest time, the shortest path, or the greatest benefit to the second patient. The choice is returned to the patient. While ensuring the patient's right to make independent decisions, it maximizes the synergistic benefits and avoids the shortcomings of unilaterally sacrificing the experience of individual patients.

[0052] By establishing a collaborative planning event table, the results of each collaborative adjustment are recorded as structured events, which are then used to correct the queuing prediction basis for any subsequent patient. This allows for the perception of the cumulative impact of all previous collaborative adjustments on the queue structure when planning for different patients, avoiding the distortion of queuing state predictions caused by independent planning for each patient, thus achieving closed-loop coordination for optimizing patient movement at a global level.

[0053] The above are merely embodiments of the present invention. The invention is not limited to the fields covered by these embodiments. Commonly known structures and characteristics in the solutions are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are able to access all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A method for planning the order of outpatient examinations, characterized in that, include: S1. Obtain the list of examination items for the first patient and the end time of the attending physician's shift; S2. Obtain the current number of people in the queue for each examination item, the average examination time per person, and the time for issuing examination reports. Collect the rate of medical orders issued by each examination department in real time, and obtain the average waiting time for follow-up visits. S3. Based on the pre-stored hospital spatial layout data, construct the inter-departmental path distance matrix and visual exposure relationship matrix; The visual exposure matrix is ​​used to record whether the queues of other examination departments are directly visible on the conventional feasible path from the self-service payment machine to any examination department, or from any examination department to another examination department; S4. Based on the travel time calculated from the rate of medical order issuance and the inter-departmental path distance matrix, calculate the predicted number of people in the queue when the first patient arrives at each examination department, then calculate the predicted queuing waiting time, and sum them up to obtain the estimated start time of the follow-up visit corresponding to each execution sequence. S5. Traverse all possible execution sequences and calculate the compliance risk value for each sequence based on the visual exposure relationship matrix. The compliance risk value represents the risk that the first patient will be attracted by non-next-order examination items and deviate during the execution of the sequence. In the execution order that satisfies the requirement that the estimated follow-up visit start time is no later than the end time of the shift, the order is sorted from low to high according to the compliance risk value. If the compliance risk values ​​are the same, the order is sorted from early to late according to the estimated follow-up visit start time. The order with the highest ranking is selected as the recommended examination order for time optimization and output.

2. The outpatient examination sequence planning method according to claim 1, characterized in that: In step S3, based on the location information of each examination department, follow-up visit department, and self-service payment machine in the pre-stored hospital spatial layout data, a path distance matrix between departments is constructed. Based on the path distance matrix and the preset walking speed, the movement time between the self-service payment machine and each examination department, between each examination department and each examination department and the follow-up visit department is obtained.

3. The outpatient examination sequence planning method according to claim 2, characterized in that: Step S4 specifically includes: S41. For a certain examination item i, calculate the time required for the first patient to move from the current location to the corresponding department i of the examination item i. ; S42, Calculate the arrival time of the first patient at the examination department. Predicted queue length The formula is: ； in, This represents the current number of people who have actually checked in and are queuing for this inspection department. For the examination department i, the time spent moving Within, the number of new sign-in patients expected to be ahead of the first patient after the doctor's orders are issued and payments are made is calculated. The rate at which medical orders are issued in this examination department i The preset conversion rate for doctor's order check-in; S43, Based on predicted queue length Calculate the predicted queuing time for examination item i based on the preset average examination time per person for the corresponding examination item i in the examination department; S44. For any execution order of the examination items list, sequentially accumulate the predicted queuing waiting time for each examination item, the average examination time per person for that examination item, and the travel time from the previous location to the examination department. After all examinations are completed, accumulate the travel time from the last examination department to the follow-up examination department, the longest waiting time required to issue all examination reports, and the average waiting time for follow-up examinations to obtain the estimated follow-up examination start time corresponding to that order.

4. The outpatient examination sequence planning method according to claim 2, characterized in that: Step S5 specifically includes: S51. Traverse all possible execution orders of the examination item list. For each execution order, simulate the movement process of each examination item in that order. Identify whether the first patient will pass through or directly see a non-next-order examination item j on the path from the attending physician's department to the self-service payment machine, from the self-service payment machine to the first examination item, or from executing the current examination item i to the next examination item i+1. If so, and the temptation index of the non-next-order examination item j at the current moment exceeds the preset threshold, then record a temptation exposure. Temptation Index The calculation is based on a weighted average of the current number of people queuing for the corresponding examination item j, the convenience of the examination type, the patient's expected time, and the time remaining until the end of the attending physician's shift; the calculation formula is: ； in, The function is monotonically decreasing; the fewer people in the queue, the greater the temptation. The predicted number of people queuing when the first patient passes by or directly sees the examination department; As a monotonically decreasing function, the more complex the project, the less tempting it becomes; To check the complexity factor of project j; As it is a monotonically decreasing function, the shorter the estimated time, the greater the temptation. The estimated time required for the examination item j in the patient's mind; This represents the remaining time until the attending physician's shift ends at the current moment; Let the time pressure function satisfy: ,in, It is a very small positive number; These are the weighting coefficients; Calculate the compliance risk value for this order. The formula is: ； S52. Determine whether there is at least one execution sequence that satisfies the condition that the estimated start time of the follow-up visit is not later than the end time of the shift. If it exists, calculate the proportion of the number of sequences that meet the above conditions to the total number of sequences. If the proportion is not higher than the preset proportion threshold, sort all sequences that meet the conditions from low to high according to compliance risk value. If the risk values ​​are the same, sort them from early to late according to the estimated follow-up visit start time. Select the first-ranked sequence as the recommended examination sequence for time optimization and output it to end the process. If it does not exist, generate and output the first prompt message indicating that the follow-up visit cannot be safely completed before the doctor leaves work.

5. The outpatient examination sequence planning method according to claim 4, characterized in that: In step S52, if there is no execution order that satisfies the estimated start time of the follow-up visit not being later than the end time of the shift, then generate and output the first prompt message that the follow-up visit cannot be safely completed before the doctor leaves work, and jump to step S6. S6. Obtain the association information of all second patients in the current queue for each examination item. The association information includes: the ranking of each second patient in the queue, the set of examination items that the second patient must perform to complete their own follow-up visit, and the end time of the shift of the attending physician corresponding to the second patient.

6. The outpatient examination sequence planning method according to claim 5, characterized in that: It also includes step S7, which simulates adjusting the execution order of at least one examination item of the first patient backward based on the examination item list of the first patient and the association information of the second patient, so that the examination item makes way for some of the second patients in the queue. Calculate whether each second patient who benefits from the earlier ranking can therefore estimate that their follow-up appointment start time is no later than the end time of their corresponding attending physician's shift, and record the estimated number of second patients who can benefit from the follow-up appointment. The recommended examination order for the first patient was generated with the shortest total walking distance as the optimization objective; and the recommended examination order for the first patient was generated with the maximum benefit to the second patient as the optimization objective. The system outputs the recommended examination order based on time optimization, the recommended examination order based on the shortest total walking distance, and the recommended examination order based on the order that benefits the second patient the most. It also receives the recommended examination order selected by the first patient.

7. The outpatient examination sequence planning method according to claim 6, characterized in that: It also includes step S8, calculating the expected check-in time of the first patient in each examination department based on the recommended examination order selected by the first patient; The first patient's current planning is recorded as a collaborative event in the collaborative planning event table. The collaborative planning event table includes: the first patient's identifier, the relevant examination departments, the expected check-in time for each department, and the changes in the queuing sequence of the examination department caused by this order adjustment.

8. The outpatient examination sequence planning method according to claim 7, characterized in that: Step S4 specifically includes: S41. For a certain examination item i, calculate the time required for the first patient to move from the current location to the corresponding department i of the examination item i. ; S42, Calculate the arrival time of the first patient at the examination department. Predicted queue length The formula is: ； in, This represents the current number of people who have actually checked in and are queuing for this inspection department. For the examination department i, the time spent moving Within, the number of new sign-in patients expected to be ahead of the first patient after the doctor's orders are issued and payments are made is calculated. The rate at which medical orders are issued in this examination department i The preset conversion rate for doctor's order check-in; To coordinate the adjustment of net increase in personnel, its value is calculated based on all registered collaborative events of the inspection department in the collaborative planning event table; S43, Based on predicted queue length Calculate the predicted queuing time for examination item i based on the preset average examination time per person for the corresponding examination item i in the examination department; S44. For any execution order of the examination items list, sequentially accumulate the predicted queuing waiting time for each examination item, the average examination time per person for that examination item, and the travel time from the previous location to the examination department. After all examinations are completed, accumulate the travel time from the last examination department to the follow-up examination department, the longest waiting time required to issue all examination reports, and the average waiting time for follow-up examinations to obtain the estimated follow-up examination start time corresponding to that order.

9. The outpatient examination sequence planning method according to claim 8, characterized in that: In step S42, the process of calculating the net increase in the number of people in the collaborative adjustment is as follows: all events in which the patient's expected check-in time is no later than the estimated time of the first patient's arrival at the examination department, and the event will cause a change in the number of people queuing in front of the first patient, are selected, the net increase in the number of people queuing in front of the first patient caused by the event is calculated, the net increase in the number of people = the number of people with positive changes - the number of people with negative changes, and the net increase in the number of people in the collaborative adjustment is accumulated.

Images