Medical queuing and calling method, system and equipment and storage medium

Abstract

A medical queuing and calling method, system and device and a storage medium, the method comprising: acquiring preliminary diagnosis queue information and diagnosis and treatment data of a back-diagnosed patient, the back-diagnosed patient being a patient who submits a back-diagnosed request within a preset time after preliminary diagnosis; in response to the callback request, calculating a diagnosis priority score of a callback patient according to the diagnosis and treatment data; according to the preliminary diagnosis queue information, the diagnosis and treatment data and the diagnosis priority score, constructing a graph model of patients, wherein the patients comprise back-diagnosis patients and all preliminary diagnosis patients in a preliminary diagnosis queue; based on the graph model, determining an insertion point of each callback patient in the preliminary diagnosis queue; and according to the insertion point corresponding to each callback patient, inserting each callback patient into the preliminary diagnosis queue, and generating a waiting queue comprising the preliminary diagnosis patients and the callback patients. According to the invention, the treatment efficiency of the patient can be improved.

Description

Technical Field

[0001] The present application relates to the field of medical information technology, and specifically to a medical queuing calling method, system, equipment and storage medium. Background Art

[0002] With the growth of medical needs and the development of information technology, digital medical information systems have become one of the effective ways to improve medical service efficiency and reduce patient waiting time, especially in the outpatient queuing and calling process, which realizes automated management and scheduling and optimizes patients' medical experience.

[0003] In the prior art, the traditional queuing system usually generates a queuing sequence based on the patient's registration time. Patients wait in order, which optimizes the patient's medical experience to a certain extent.

[0004] However, the traditional queuing system can only generate a single queue sequence according to the patient's registration time, which means that when patients return for follow-up visits, they need to register again and enter a new queue sequence, or jump the queue without a formal registration, disrupting the normal medical order and reducing the patient's medical efficiency. Summary of the invention

[0005] The present application provides a medical queuing calling method, system, device and storage medium for improving the efficiency of medical consultation.

[0006] In a first aspect of the present application, a medical queuing and calling method is provided, which is applied to a server, and the method includes: obtaining initial diagnosis queue information and diagnosis and treatment data of return patients, where the return patients are patients who submit a return diagnosis request within a preset time after the initial diagnosis; in response to the return diagnosis request, calculating the diagnosis priority score of the return patient according to the diagnosis and treatment data; constructing a patient graph model according to the initial diagnosis queue information, the diagnosis and treatment data, and the diagnosis priority score, where the patient includes the return patients and all the initial diagnosis patients in the initial diagnosis queue; based on the graph model, determining the insertion point of each return patient in the initial diagnosis queue; inserting each return patient into the initial diagnosis queue according to the insertion point corresponding to each return patient, and generating a waiting queue including the initial diagnosis patients and the return patients.

[0007] Optionally, the diagnostic priority score of the returning patient is calculated based on the diagnosis and treatment data, including: According to the first formula, the diagnostic priority score is calculated; wherein the first formula is: Among them, P is the diagnostic priority score, S is the speed of change of the patient's condition after the return visit, and W i is the weight of each disease of the returning patient, C iis the severity score of different symptoms of returning patients, E is the predicted probability of emergency risk, k is the interaction weight coefficient between the speed of disease change and emergency risk, ΔT is the delay time of returning patients, τ is the adjustment parameter of time urgency, γ is the fixed weight of target priority, I is the target priority index, log(1+S) is the nonlinear adjustment of the speed of disease change of returning patients, [(∑(W i ×C i ))] is the severity score of the returning patients, (S×E×k) is the interaction effect between the speed of disease change and the risk of emergency, is the time urgency score, and γ×I is the target priority score.

[0008] Optionally, a patient graph model is constructed based on the initial diagnosis cohort information and diagnosis priority scores, including: According to the initial diagnosis queue information, diagnosis and treatment data and diagnosis priority score, the edge weights of the return patients and the target initial diagnosis patients are calculated through the preset weight calculation model. The edge weight is the impact of inserting the return patient before the target initial diagnosis patient on the waiting efficiency of the initial diagnosis patient. The target initial diagnosis patient is any initial diagnosis patient. The initial diagnosis patient is set as a fixed node, and the return patient is set as an insertion node. The graph model is constructed based on the fixed nodes, insertion nodes and edge weights.

[0009] Optionally, before calculating the edge weights of the returning patients and the target first-diagnosis patients by a preset weight calculation model according to the first-diagnosis queue information and the diagnosis priority score, the method further includes: Acquire historical initial diagnosis queue information, historical diagnosis and treatment data, and historical waiting efficiency data of patients within a preset historical time period; extract multiple first features from the historical initial diagnosis queue information, the first feature being a feature whose statistical correlation with the historical waiting efficiency data in the historical initial diagnosis queue information is greater than a preset threshold; extract multiple second features from the diagnosis and treatment data, the second feature being a feature whose statistical correlation with the historical waiting efficiency data in the historical diagnosis and treatment data is greater than a preset threshold; input the multiple first features and the multiple second features into a preset rule model designed based on clinical experience to generate an edge weight function; and construct a preset weight calculation model based on the edge weight function.

[0010] Optionally, based on the graph model, determine the insertion point of each returning patient in the initial diagnosis cohort, including: According to the edge weights in the graph model, multiple target insertion points for returning patients are selected, and the target insertion points are insertion points corresponding to edge weights that are less than a preset influence threshold. Based on the diagnosis and treatment data, the insertion points are determined among the multiple target insertion points through a preset insertion point algorithm.

[0011] Optionally, before inserting each returning patient into the initial diagnosis queue according to the insertion point corresponding to each returning patient to generate a waiting queue including the initial diagnosis patients and the returning patients, the method further includes: The insertion point is verified for waiting efficiency constraints and fairness constraints through the preset verification model; if both the waiting efficiency constraint verification and the fairness constraint verification fail, the insertion point is re-determined.

[0012] Optionally, if both the waiting efficiency constraint verification and the fairness constraint verification fail, the insertion point is re-determined, including: When the waiting efficiency constraint verification fails and the fairness constraint verification fails, the waiting efficiency score and fairness score of each target insertion point are calculated based on the preset verification model; based on the waiting efficiency score and the fairness score, the comprehensive score of each target insertion point is calculated; based on the comprehensive score, the insertion point is re-determined according to the preset rules.

[0013] In a second aspect of the present application, a medical queuing calling system is provided, comprising: The acquisition module is used to obtain the initial diagnosis queue information and the diagnosis and treatment data of the returning patients. The returning patients are patients who submit a return diagnosis request within a preset time after the initial diagnosis; A calculation module, for calculating a diagnosis priority score of the returning patient according to the diagnosis and treatment data in response to the return consultation request; A construction module is used to construct a graph model of patients based on the initial diagnosis cohort information, diagnosis and treatment data, and diagnosis priority scores. The patients include return patients and all initial diagnosis patients in the initial diagnosis cohort; A determination module, used to determine the insertion point of each returning patient in the initial diagnosis queue based on a graph model; A generation module is used to insert each returning patient into the initial diagnosis queue according to the insertion point corresponding to each returning patient, and generate a waiting queue including initial diagnosis patients and returning patients.

[0014] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0015] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.

[0016] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By obtaining the diagnosis and treatment data of the initial diagnosis queue and return patients and calculating the priority score, combined with the construction of a graph model containing all patients to determine the optimal insertion point, the system can quantitatively evaluate the urgency of return patients, and then use the graph model to comprehensively model and analyze the relationship between initial diagnosis patients and return patients, so as to determine the most suitable insertion point for return patients. The insertion point can meet the return visit needs of return patients and will not have a major impact on the initial diagnosis patients in the initial diagnosis queue. It effectively solves the problem that return patients cannot accurately locate their queue position without re-taking numbers in the traditional queuing system, thereby improving the patient's medical efficiency.

[0017] 2. The diagnostic priority of returning patients is calculated through a comprehensive scoring formula based on multi-dimensional factors. The formula nonlinearly combines key indicators such as the speed of disease change, severity of symptoms, emergency risk prediction, delayed return time and target priority, and introduces an interactive weight coefficient to reflect the mutual influence between indicators. At the same time, it takes into account the regulatory effect of time urgency, so that the system can more accurately quantify and evaluate the priority needs of returning patients, realize accurate assessment of the priority of returning patients, and improve the scientificity and fairness of the medical queuing system.

[0018] 3. By analyzing the features that are highly correlated with waiting efficiency in historical initial visit queue information and medical data, a data-driven feature selection basis is established. The edge weight function is generated by combining the rule model designed based on clinical experience, thereby constructing an accurate preset weight calculation model. Then, by setting initial visit patients as fixed nodes and return patients as insertion nodes, the model is used to accurately calculate the edge weights between nodes to quantify the impact of queue jumping. This technical solution allows the system to take into account the objective laws of historical data and incorporate clinical practice experience when determining the insertion position, making the calculation of edge weights more precise and reasonable, greatly improving the accuracy and scientificity of determining the insertion position of return patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of a medical queuing calling method in an embodiment of the present application; Figure 2 This is a schematic diagram of the structure of a medical queuing and calling system in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application.

[0020] Explanation of the accompanying drawings: 201, acquisition module; 202, calculation module; 203, construction module; 204, determination module; 205, generation module; 206, verification generation module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0021] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0022] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0023] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0024] Figure 1 It is a flow chart of a medical queuing calling method in an embodiment of the present application.

[0025] See also Figure 1 In an embodiment of the present application, a medical queuing calling method is applied to a server, and the method includes: S101, obtaining the initial diagnosis queue information and the diagnosis and treatment data of the returning patient, the returning patient is a patient who submits a return diagnosis request within a preset time after the initial diagnosis; In step S101, the system obtains the current initial patient queue information from the server. This information includes at least the patient's personal information, registration order, appointment time, queue status, waiting time, the current health status of the initial patient and the department category (such as internal medicine, surgery, pediatrics, etc.). The initial diagnosis queue information is the data of all patients waiting for the first visit. In this step, the system also obtains the diagnosis and treatment data of the return patient. Return patients refer to patients who submit a return visit request on the mobile terminal within a preset time (generally the day of the initial visit or the next day). This type of patient usually submits a return visit request on the mobile terminal for a return visit after completing the necessary examinations (such as blood tests, imaging examinations, etc.) and obtaining the relevant examination reports after the initial visit, such as discussing the report results with the doctor, adjusting the treatment plan or conducting further diagnosis. The system can obtain the diagnosis and treatment data of returning patients from the electronic medical record system (EMR), laboratory information system (LIS) and examination report system. The diagnosis and treatment data at least include the preliminary diagnosis results of the initial visit, examination report results (such as imaging reports, blood test data, etc.), medical orders and treatment records, and the current health status of the returning patients.

[0026] S102, in response to the return visit request, calculating the diagnosis priority score of the return visit patient according to the diagnosis and treatment data; Specifically, according to the first formula, the diagnostic priority score is calculated; wherein the first formula is: Among them, P is the diagnostic priority score, S is the speed of change of the patient's condition after the return visit, and W i is the weight of each disease of the returning patient, C i is the severity score of different symptoms of returning patients, E is the predicted probability of emergency risk, k is the interaction weight coefficient between the speed of disease change and emergency risk, ΔT is the delay time of returning patients, τ is the adjustment parameter of time urgency, γ is the fixed weight of target priority, that is, the fixed weight of special priority (such as the elderly, children, pregnant women, etc.), I is the target priority index, log(1+S) is the nonlinear adjustment of the speed of disease change of returning patients, [(∑(W i ×C i ))] is the severity score of the returning patients, (S×E×k) is the interaction effect between the speed of disease change and the risk of emergency, is the time urgency score, and γ×I is the target priority score.

[0027] In response to the follow-up request of the returning patient, the system analyzes the diagnosis and treatment data. First, by comparing the current health status of the initial patient with the current examination results, the system calculates the speed of disease change (S). For example, the system quantifies the speed of disease deterioration or improvement through trend analysis of key biochemical indicators, imaging changes or physical sign data. At the same time, based on the specific diagnosis information and examination results of the disease, combined with the preset disease weight (W) in the medical knowledge database in the system, the system calculates the disease weight (W) of the initial patient. i ), calculate the severity score of each symptom of the returning patients (C i ), and the total score of the overall severity of the symptoms of the returning patients is obtained by weighted summation (∑(W i ×C i )). In addition, the system uses a preset emergency risk prediction model to predict the possibility of developing an emergency (E) based on the patient's condition data and disease characteristics, and evaluates the interaction effect (S×E×k) between the rate of change of the condition and the emergency risk. The preset emergency risk prediction model is built based on historical medical data, machine learning technology, and medical expert knowledge. It combines the patient's current diagnosis and treatment data and outputs the emergency risk probability (E) through statistical laws and prediction models. On this basis, the system further combines the delayed return time (ΔT) of the returning patient and calculates the time urgency score of the returning patient through the time urgency adjustment parameter (τ) Based on the above analysis and calculation of the diagnosis and treatment data of the returning patients, the hospital's preset rules are used to determine whether the returning patients belong to special priority groups (such as critically ill patients, pregnant women or children). If the returning patients belong to the special priority groups, the diagnostic priority score is adjusted in combination with the target priority fixed weight (γ) and the target priority index (I). If the returning patients do not belong to the special priority groups, the target priority fixed weight (γ) and the target priority index (I) are both 1.

[0028] S103, constructing a patient graph model based on the initial diagnosis cohort information, diagnosis and treatment data, and diagnosis priority scores, where the patients include return patients and all initial diagnosis patients in the initial diagnosis cohort; Before step S103, a preset weight calculation model is first constructed. Specifically, historical initial diagnosis queue information, historical diagnosis and treatment data, and historical waiting efficiency data of patients within a preset historical time period are obtained; multiple first features are extracted from the historical initial diagnosis queue information, and the first feature is a feature whose statistical correlation with the historical waiting efficiency data in the historical initial diagnosis queue information is greater than a preset threshold; multiple second features are extracted from the diagnosis and treatment data, and the second feature is a feature whose statistical correlation with the historical waiting efficiency data in the historical diagnosis and treatment data is greater than a preset threshold; multiple first features and multiple second features are input into a preset rule model designed based on clinical experience to generate an edge weight function; and a preset weight calculation model is constructed based on the edge weight function.

[0029] Among them, the system obtains the daily medical data within a preset historical time period (for example, the past 3 months or 6 months) from the medical database, and the medical data at least includes historical initial diagnosis queue information, diagnosis and treatment data of return patients, and historical waiting efficiency data. The historical initial diagnosis queue information includes the registration time, appointment time, queue order, waiting time, treatment time of the daily initial diagnosis patients, and the patient's personal information (such as gender, age) and department category (such as internal medicine, surgery, pediatrics, etc.). When the doctor visits the initial diagnosis patient, a unique corresponding return visit tag is added to the system for each initial diagnosis patient who needs to be returned. After the return visit, the system associates the diagnosis and treatment data of the return patient (such as the preliminary diagnosis results, examination reports, treatment records, etc. at the time of the initial visit) with the return visit tag corresponding to the return patient. The system obtains the diagnosis and treatment data of the return patient within the preset historical time period through the return visit tag. The historical waiting efficiency data records the patient's actual waiting time, the waiting queue flow efficiency, the patient's diagnosis priority score, and the waiting completion rate satisfaction score.

[0030] The system analyzes the historical initial diagnosis queue information and extracts multiple first features that have significant statistical correlation with the waiting efficiency data. The analysis method can be correlation analysis (such as Pearson correlation coefficient) and feature screening, and the screening criterion is that the correlation between the feature and the waiting efficiency data is greater than a preset threshold (such as 0.7). The first feature may include registration time, appointment time period, type of disease, patient age, etc. For example, the analysis found that the "registration time" has a significant impact on the waiting efficiency in different time periods (such as morning and evening shifts), with a correlation of 0.8, which exceeds the threshold, so it is extracted as the first feature. The first feature will be used to evaluate the waiting efficiency baseline of initial patients.

[0031] The system further analyzes the diagnosis and treatment data of returning patients and extracts multiple second features that are significantly correlated with the waiting efficiency data. Through correlation analysis, the system screens out features that are closely related to waiting efficiency from data such as the diagnosis results, number of examinations, complexity of treatment, and trend of disease changes of returning patients. For example, the correlation between the "diagnosis priority score" and the waiting efficiency is 0.85, which exceeds the preset threshold, indicating that the severity of the disease significantly affects the insertion priority of returning patients; the correlation between the "number of examinations" and the waiting efficiency is 0.78, which is also extracted as the second feature, which will be used to evaluate the impact of returning patients on the waiting efficiency.

[0032] The extracted first feature (such as registration time, type of disease, etc.) and second feature (such as diagnosis priority score, disease change trend, etc.) are input into a preset rule model designed based on clinical experience. The model is used to quantify the impact of returning patients on waiting efficiency when they are inserted before the target first-time patients, and generate an edge weight function. The preset rule model is designed by historical data analysis and clinical expert experience, and defines the impact ratio of the first feature and the second feature on waiting efficiency and their interactive relationship. For example, the rule model may stipulate that the interactive effect between the "registration time" of first-time patients and the "diagnosis priority score" of returning patients has a greater impact on waiting efficiency, while the "disease change trend" plays a key role in the insertion of high-priority patients. The model generates an edge weight function formula by calculating the weighted combination of these features. For example, in one possible case, the generated edge weight function formula is ω=μ×P+∑(α i ×f i ), where ω is the edge weight, P is the diagnostic priority score of the returning patient, μ is the priority score weight, which indicates the importance of the diagnostic priority score P in the edge weight calculation, μ is determined by the preset rule model based on clinical experience and historical data analysis, and α i is the feature weight of the ith feature, indicating the proportion of the influence of the ith feature on the edge weight, which is determined by the preset rule model based on clinical experience and historical data analysis. For example: the influence of the registration time of the first-visit patient on the waiting efficiency; the influence of the diagnosis priority score of the returning patient on the waiting efficiency; the influence of the condition change trend of the returning patient on the waiting efficiency. i is the influencing factor of the ith feature, which is calculated by the rule model based on the actual value of the feature (such as the specific value of the registration time, disease type or diagnosis priority score). For example, if the weight of the registration time is 0.3, it means that the impact of the registration time on the waiting efficiency accounts for 30% of the total impact; if the weight of the diagnosis priority score is 0.5, it means that the diagnosis priority score is the main factor affecting the waiting efficiency, accounting for 50% of the total impact.

[0033] Based on the generated edge weight function, the system constructs a preset weight calculation model to calculate the edge weight value of the return patient inserted before the target first-visit patient. The input of the weight calculation model includes the specific values ​​of the first feature (registration time, disease type, etc. of the first-visit patient) and the second feature (diagnosis priority score, disease change trend, etc. of the return patient). Combined with the edge weight function formula, the preset weight calculation model outputs an edge weight value, which represents the specific degree of impact of the return patient insertion operation on the waiting efficiency.

[0034] In step S103, a patient graph model is constructed based on the initial diagnosis queue information and the diagnosis priority score.

[0035] Specifically, according to the initial diagnosis queue information, diagnosis and treatment data and diagnosis priority score, the edge weights of the follow-up patients and the target initial diagnosis patients are calculated through the preset weight calculation model. The edge weight is the impact of inserting the follow-up patient before the target initial diagnosis patient on the waiting efficiency of the initial diagnosis patient. The target initial diagnosis patient is any initial diagnosis patient. The initial diagnosis patient is set as a fixed node, and the follow-up patient is set as an insertion node. The graph model is constructed based on the fixed nodes, insertion nodes and edge weights.

[0036] Among them, the edge weight between each returning patient and any target initial diagnosis patient is calculated using the preset weight calculation model through the initial diagnosis queue information (such as the registration time, symptom type, queuing order, etc. of the initial diagnosis patient), diagnosis and treatment data (such as the speed of change of the condition of the returning patient, previous diagnosis and treatment records, etc.) and the diagnosis priority score of each returning patient.

[0037] Subsequently, all first-visit patients are set as fixed nodes to represent all first-visit patients in the current first-visit queue. Each fixed node represents a first-visit patient, and its information includes attributes such as registration time, disease type, and queue order. The arrangement order of these fixed nodes reflects the established waiting order of first-visit patients, which is the basis of queue stability, and their positions are fixed in the model and will not change. The main function of fixed nodes is to serve as a reference point to evaluate the degree of interference with the waiting efficiency of first-visit patients when returning patients are inserted into the queue. For example, if there are three first-visit patients A1, A2, and A3 in the first-visit queue, they will be defined as fixed nodes N1, N2, and N3, respectively, and arranged in a predetermined order. These fixed nodes constitute the basic framework of the graph model.

[0038] All returning patients are set as insertion nodes, and each insertion node represents a returning patient. Its information includes dynamic attributes such as diagnostic priority score, disease change speed, and waiting time. The key feature of the insertion node is that the position is not fixed, and it can be inserted into any position in the initial diagnosis queue. The role of the insertion node is to quantify the impact of the insertion of returning patients into a certain target position on the waiting efficiency of initial diagnosis patients by establishing a connection with the fixed node. The dynamic nature of the insertion nodes requires them to calculate edge weights with each fixed node in the model to evaluate the degree of interference of different insertion positions. For example, if there are two returning patients B1 and B2, they will be defined as insertion nodes M1 and M2 respectively, and these nodes are connected to the fixed nodes of the initial diagnosis patients through edge weights.

[0039] Edge weight is a set of values ​​connecting the insertion node and the fixed node in the graph model, which is used to quantify the specific impact of the return patient on the waiting efficiency when it is inserted before a target first-visit patient. The weight of each edge is calculated by a preset weight calculation model, which takes into account multiple factors such as the diagnostic priority score of the return patient, the registration time of the first-visit patient, and the type of disease. The higher the value of the edge weight, the greater the interference of the insertion operation on the waiting efficiency. The role of the edge weight is to provide a quantitative basis for modeling the relationship between the insertion node and the fixed node, so as to evaluate the advantages and disadvantages of different insertion positions. For example, when the return patient M1 is inserted before the first-visit patient N1, its edge weight ω(M1→N1) represents the specific impact of the insertion operation on the waiting efficiency of N1. Similar edge weights will be calculated and used for subsequent optimization.

[0040] The graph model is constructed based on fixed nodes, inserted nodes and edge weights. The construction of the graph model is centered on fixed nodes and inserted nodes, and the two are connected by edge weights to form a weighted directed graph. First, all first-visit patients are set as fixed nodes {N1, N2, ..., Nn}, indicating the fixed order of the current first-visit queue; then, all return patients are set as inserted nodes {M1, M2, ..., Mm}, indicating patients who need to be dynamically inserted. Then, the edge weight between each inserted node and each fixed node is calculated, and the weight value represents the degree of interference with the waiting efficiency when the return patient is inserted before a certain first-visit patient. Finally, the inserted nodes and fixed nodes are connected by edges and weights to construct a complete graph model. For example, if there are 3 first-visit patients and 2 return patients, the nodes of the graph model include N1, N2, N3 and M1, M2, and the edges include the connection from each inserted node to each fixed node, such as M1→N1, M1→N2, M1→N3, etc., and the edge weights are added to form a complete graph model. The graph model comprehensively describes the impact of returning patients inserting into the initial diagnosis queue on the waiting efficiency through the structured expression of fixed nodes, insertion nodes, and edge weights. Fixed nodes provide the established order of initial diagnosis patients, insertion nodes represent the dynamic insertion requirements of returning patients, and edge weights quantify the specific interference of the insertion operation on the waiting efficiency.

[0041] S104, selecting multiple target insertion points for the return patient according to the edge weights in the graph model, where the target insertion points are insertion points corresponding to edge weights less than a preset influence threshold; In the graph model, each returning patient (insertion node) can be connected to all first-visit patients (fixed nodes) through edges. The weight of each edge (i.e., edge weight) indicates the degree of influence of the returning patient on the waiting efficiency when inserted before the first-visit patient. First, the calculated edge weight is compared with the preset influence threshold, and the insertion point with an edge weight less than the threshold is selected as the target insertion point. The preset influence threshold indicates the maximum acceptable interference range for the waiting efficiency. Only when the edge weight is lower than this value, the insertion point is considered as a candidate position with acceptable waiting efficiency. For example, if the edge weight of a returning patient M1 is {ω(M1→N1)=0.3, ω(M1→N2)=0.5, ω(M1→N3)=0.7}, and the preset influence threshold is 0.6, then the target insertion points are N1 and N2, and M1 can be inserted before N1 or N2.

[0042] S105, determining an insertion point from a plurality of target insertion points by using a preset insertion point algorithm based on the diagnosis and treatment data; For each returning patient, the optimal insertion point is further determined from the multiple target insertion points selected in step S104 through a preset insertion point algorithm combined with the diagnosis and treatment data. The diagnosis and treatment data include the severity of the returning patient's condition, diagnostic priority score, waiting time, etc., as well as the registration time, queue position and other information of the target initial patient. The insertion point algorithm comprehensively evaluates these data and selects an optimal position among the target insertion points according to preset optimization rules (for example, giving priority to the insertion point with the least impact, the position close to the patient with higher priority, or the insertion point that reduces waiting delays). For example, if the target insertion points of M1 are N1 and N2, and the diagnosis and treatment data show that the condition priority match before inserting to N1 is higher or the interference with waiting efficiency is smaller, then N1 is finally determined as the insertion point.

[0043] S106, inserting each returning patient into the initial diagnosis queue according to the insertion point corresponding to each returning patient, and generating a waiting queue including the initial diagnosis patients and the returning patients; After completing the selection of the best insertion point for each returning patient, each returning patient is inserted into the initial diagnosis queue according to the determined insertion point, generating a final waiting queue containing initial diagnosis patients and returning patients. The insertion operation is performed sequentially according to the insertion points determined in the graph model to ensure that each returning patient is inserted into the specified target position while keeping the original order of the initial diagnosis queue unchanged. The generated waiting queue not only reflects the insertion priority of returning patients, but also minimizes the impact on the waiting efficiency of initial diagnosis patients. For example, if the initial diagnosis patient queue is [N1, N2, N3], the insertion point of returning patient M1 is before N1, and the insertion point of M2 is before N3, then the final queue is [M1, N1, N2, M2, N3]. This queue combines the priority of returning patients and the fairness of waiting for initial diagnosis patients, optimizing the overall waiting process.

[0044] Optional, in Figure 1 The following steps may be performed before step S106 of the illustrated embodiment: The insertion point is verified for waiting efficiency constraints and fairness constraints through the preset verification model; if both the waiting efficiency constraint verification and the fairness constraint verification fail, the insertion point is re-determined; if both the waiting efficiency constraint verification and the fairness constraint verification fail, the insertion point is re-determined.

[0045] Among them, the preset verification model is a verification framework designed based on the core goals of waiting queue management (efficiency and fairness) and actual diagnosis and treatment needs. It is mainly used to evaluate whether the overall waiting efficiency and fairness of the queue meet the expected standards after the return patient is inserted into the initial diagnosis queue. The design basis of this model includes at least historical diagnosis and treatment data analysis, waiting efficiency optimization algorithm, medical fairness research results and specific operating rules of medical institutions. The role of the preset verification model is to accurately evaluate the selected insertion point to ensure that the insertion operation will not significantly reduce the overall waiting efficiency of the queue, nor will it cause unreasonable impact on the rights and interests of the initial diagnosis patients. Specifically, the model evaluates whether the insertion point meets the efficiency optimization goals in terms of waiting time, diagnosis and treatment resource allocation, etc. through efficiency constraint verification (such as the total delay in waiting time is within the specified range); through fairness constraint verification, it analyzes whether the insertion operation avoids unfair interference with initial diagnosis patients of different priorities while giving priority to return patients (such as avoiding excessive impact of high-priority patients by low-priority return patients).

[0046] If both the waiting efficiency constraint verification and the fairness constraint verification fail, the insertion point is re-determined.

[0047] Specifically, when the waiting efficiency constraint verification fails and the fairness constraint verification fails, the waiting efficiency score and fairness score of each target insertion point are calculated based on the preset verification model; based on the waiting efficiency score and the fairness score, the comprehensive score of each target insertion point is calculated; based on the comprehensive score, the insertion point is re-determined according to the preset rules.

[0048] Among them, when the waiting efficiency constraint verification and fairness constraint verification fail, the waiting efficiency score and fairness score of each target insertion point are calculated based on the preset verification model to quantify the performance of the insertion point in terms of efficiency and fairness. The waiting efficiency score is calculated by evaluating the impact of returning patients inserted into the target position on the total waiting time of the first-visit patient queue. The specific formula is: Among them, H is the waiting efficiency score, ΔT is the increment of the total waiting time of the initial diagnosis queue caused by the insertion operation, and T maxis the maximum tolerable delay time, and the waiting efficiency score is in the range of [0, 1]. The closer to 1, the less efficiency is affected. The fairness score is calculated by evaluating the degree of interference of the insertion operation on the balance of resource allocation. The specific formula is: Where F is the fairness score, ΔP represents the impact of insertion on the priority of newly diagnosed patients, and ω i is the priority weight of different patients, P max It is the tolerance range of fairness interference. The closer the fairness score is to 1, the less fairness is affected.

[0049] After calculating the waiting efficiency score and fairness score of each target insertion point, the comprehensive score is calculated through a weighted formula to uniformly measure the overall performance of the insertion point in terms of efficiency and fairness. The calculation formula for the comprehensive score is: comprehensive score = (waiting efficiency score × efficiency weight) + (fairness score × fairness weight), where the efficiency weight and fairness weight are set by the medical institution according to actual needs, and the sum of the two is 1. For example, the efficiency weight can be set to 0.6 and the fairness weight can be set to 0.4. The value range of the comprehensive score is [0, 1]. The higher the value, the better the balance between efficiency and fairness of the insertion point. Through the comprehensive score, the performance of the two dimensions of waiting efficiency and fairness can be converted into a single indicator, which is convenient for direct comparison and ranking of each target insertion point, and provides a decision-making basis for the selection of the final insertion point.

[0050] After calculating the comprehensive score of each target insertion point, the insertion point with the highest comprehensive score is selected as the final insertion point according to the preset rules, so as to ensure that the insertion of the returning patient has the best balance for the overall efficiency and fairness of the waiting queue. The preset rules are formulated by the medical institution according to actual needs, and usually the insertion point with the highest comprehensive score is given priority; when the comprehensive scores are the same, they can be further selected according to special priority rules, such as giving priority to the insertion point with the least impact on high-priority first-visit patients, or giving priority to the urgency of returning patients in special cases. Through these rules, it is ensured that the final selected insertion point not only meets the comprehensive score results of efficiency and fairness, but also meets the actual operation goals of the medical institution. For example, when the comprehensive scores of the target insertion points of a returning patient are N1=0.85, N2=0.78, and N3=0.92, the insertion point N3 with the highest comprehensive score is selected according to the rules, and the returning patient is inserted to the position before N3 to optimize the efficiency and fairness of the queue.

[0051] See also Figure 2 , is a schematic diagram of the structure of a medical queuing and calling system provided in an embodiment of the present application, a medical queuing and calling system 200 specifically includes: Acquisition module 201, for acquiring the initial diagnosis queue information and the diagnosis and treatment data of the returning patients, where the returning patients are patients who submit a return diagnosis request within a preset time after the initial diagnosis; A calculation module 202, for calculating the diagnosis priority score of the returning patient according to the diagnosis and treatment data in response to the return diagnosis request; A construction module 203 is used to construct a graph model of patients according to the initial diagnosis queue information, diagnosis and treatment data, and diagnosis priority scores, where the patients include return patients and all initial diagnosis patients in the initial diagnosis queue; A determination module 204 is used to determine the insertion point of each returning patient in the initial diagnosis queue based on the graph model; The generation module 205 is used to insert each returning patient into the initial diagnosis queue according to the insertion point corresponding to each returning patient, and generate a waiting queue including the initial diagnosis patients and the returning patients.

[0052] Optionally, the calculation module 202 is specifically configured to: According to the first formula, the diagnostic priority score is calculated; wherein the first formula is: Among them, P is the diagnostic priority score, S is the speed of change of the patient's condition after the return visit, and W i is the weight of each disease of the returning patient, C i is the severity score of different symptoms of returning patients, E is the predicted probability of emergency risk, k is the interaction weight coefficient between the speed of disease change and emergency risk, ΔT is the delay time of returning patients, τ is the adjustment parameter of time urgency, γ is the fixed weight of target priority, I is the target priority index, log(1+S) is the nonlinear adjustment of the speed of disease change of returning patients, [(∑(W i ×C i ))] is the severity score of the returning patients, (S×E×k) is the interaction effect between the speed of disease change and the risk of emergency, is the time urgency score, and γ×I is the target priority score.

[0053] Optionally, the construction module 203 is specifically used for: According to the initial diagnosis queue information, diagnosis and treatment data and diagnosis priority score, the edge weights of the return patients and the target initial diagnosis patients are calculated through the preset weight calculation model. The edge weight is the impact of inserting the return patient before the target initial diagnosis patient on the waiting efficiency of the initial diagnosis patient. The target initial diagnosis patient is any initial diagnosis patient. The initial diagnosis patient is set as a fixed node, and the return patient is set as an insertion node. The graph model is constructed based on the fixed nodes, insertion nodes and edge weights.

[0054] Optionally, the construction module 203 is further specifically used for: Acquire historical initial diagnosis queue information, historical diagnosis and treatment data, and historical waiting efficiency data of patients within a preset historical time period; extract multiple first features from the historical initial diagnosis queue information, the first feature being a feature whose statistical correlation with the historical waiting efficiency data in the historical initial diagnosis queue information is greater than a preset threshold; extract multiple second features from the diagnosis and treatment data, the second feature being a feature whose statistical correlation with the historical waiting efficiency data in the historical diagnosis and treatment data is greater than a preset threshold; input the multiple first features and the multiple second features into a preset rule model designed based on clinical experience to generate an edge weight function; and construct a preset weight calculation model based on the edge weight function.

[0055] Optionally, the determination module 204 is specifically configured to: According to the edge weights in the graph model, multiple target insertion points for returning patients are selected, and the target insertion points are insertion points corresponding to edge weights that are less than a preset influence threshold. Based on the diagnosis and treatment data, the insertion points are determined among the multiple target insertion points through a preset insertion point algorithm.

[0056] Optionally, the system further includes a verification module 206, which is specifically used to: The insertion point is verified for waiting efficiency constraints and fairness constraints through the preset verification model; if both the waiting efficiency constraint verification and the fairness constraint verification fail, the insertion point is re-determined.

[0057] Optionally, the verification module 206 is further specifically configured to: When the waiting efficiency constraint verification fails and the fairness constraint verification fails, the waiting efficiency score and fairness score of each target insertion point are calculated based on the preset verification model; based on the waiting efficiency score and the fairness score, the comprehensive score of each target insertion point is calculated; based on the comprehensive score, the insertion point is re-determined according to the preset rules.

[0058] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0059] This embodiment also discloses an electronic device, referring to Figure 3 The electronic device may include: at least one processor 301 , at least one communication bus 302 , a user interface 303 , a network interface 304 , and at least one memory 305 .

[0060] The communication bus 302 is used to realize the connection and communication between these components.

[0061] The user interface 303 may include a display screen (Display) and a camera (Camera). The optional user interface 303 may also include a standard wired interface and a wireless interface.

[0062] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0063] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or more combinations of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0064] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a medical queuing calling method.

[0065] exist Figure 3 In the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 301 can be used to call an application program for a medical queuing calling method stored in the memory 305. When executed by one or more processors 301, the electronic device executes one or more methods in the above-mentioned embodiments.

[0066] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0067] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0068] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0069] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0070] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0071] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory 305. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory 305 and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory 305 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk.

[0072] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A medical queuing method, characterized in that: Applied in a server, the method comprises: Obtaining the initial diagnosis queue information and the diagnosis and treatment data of the returning patients, wherein the returning patients are patients who submit a return diagnosis request within a preset time after the initial diagnosis; In response to the return visit request, calculating a diagnosis priority score of the return visit patient according to the diagnosis and treatment data; Constructing a patient graph model according to the initial diagnosis cohort information, the diagnosis and treatment data, and the diagnosis priority score, wherein the patient includes the return patients and all the initial diagnosis patients in the initial diagnosis cohort; Based on the graph model, determining the insertion point of each of the returning patients in the initial diagnosis cohort; According to the insertion point corresponding to each returning patient, each returning patient is inserted into the initial diagnosis queue to generate a waiting queue including the initial diagnosis patients and the returning patients.

2. The method according to claim 1, characterized in that The step of calculating the diagnostic priority score of the returning patient according to the diagnosis and treatment data specifically includes: Calculating the diagnostic priority score according to a first formula; Among them, the first formula is: Wherein, P is the diagnostic priority score, S is the speed of change of the patient's condition, and W is i is the weight of each disease of the returning patient, C i is the severity score of different symptoms of the returning patients, E is the predicted probability of emergency risk, k is the interaction weight coefficient between the speed of disease change and emergency risk, ΔT is the delayed return time of the returning patients, τ is the adjustment parameter of time urgency, γ is the fixed weight of target priority, I is the target priority index, log(1+S) is the nonlinear adjustment of the speed of disease change of the returning patients, [(∑(W i ×C i ))] is the severity score of the patient's condition, (S×E×k) is the interaction effect between the rate of disease change and the risk of emergency, is the time urgency score, and γ×I is the target priority score.

3. The method according to claim 1, characterized in that The step of constructing a patient graph model according to the initial diagnosis queue information and the diagnosis priority score specifically includes: According to the initial diagnosis queue information, the diagnosis and treatment data and the diagnosis priority score, the edge weights of the return patient and the target initial diagnosis patient are calculated by a preset weight calculation model, wherein the edge weight is the impact of inserting the return patient before the target initial diagnosis patient on the waiting efficiency of the initial diagnosis patient, and the target initial diagnosis patient is any of the initial diagnosis patients; The first-visit patients are set as fixed nodes, the returning patients are set as inserted nodes, and the graph model is constructed based on the fixed nodes, the inserted nodes and the edge weights.

4. The method according to claim 3, characterized in that Before calculating the edge weights of the return patient and the target first-visit patient by a preset weight calculation model according to the first-visit queue information and the diagnosis priority score, the method further includes: Obtaining historical initial diagnosis queue information, historical diagnosis and treatment data, and historical waiting efficiency data of the patient within a preset historical time period; Extracting a plurality of first features from the historical initial diagnosis queue information, wherein the first features are features in the historical initial diagnosis queue information where the statistical correlation with the historical waiting efficiency data is greater than a preset threshold; Extracting a plurality of second features from the diagnosis and treatment data, wherein the second features are features in the historical diagnosis and treatment data whose statistical correlation with the historical waiting efficiency data is greater than a preset threshold; Inputting a plurality of the first features and a plurality of the second features into a preset rule model designed based on clinical experience to generate an edge weight function; The preset weight calculation model is constructed based on the edge weight function.

5. The method according to claim 1, characterized in that: Determining the insertion point of each of the returning patients in the initial diagnosis queue based on the graph model specifically includes: According to the edge weights in the graph model, multiple target insertion points of the return patient are selected, wherein the target insertion points are insertion points corresponding to edge weights less than a preset influence threshold; Based on the diagnosis and treatment data, the insertion point is determined among the multiple target insertion points by using a preset insertion point algorithm.

6. The method according to claim 1, characterized in that Before inserting each of the returning patients into the initial diagnosis queue according to the insertion point corresponding to each of the returning patients to generate a waiting queue including the initial diagnosis patients and the returning patients, the method further includes: Performing waiting efficiency constraint verification and fairness constraint verification on the insertion point through a preset verification model; If both the waiting efficiency constraint verification and the fairness constraint verification fail, the insertion point is re-determined.

7. The method according to claim 6, characterized in that If both the waiting efficiency constraint verification and the fairness constraint verification fail, then re-determining the insertion point specifically includes: When the waiting efficiency constraint verification fails and the fairness constraint verification fails, calculating the waiting efficiency score and the fairness score of each target insertion point based on the preset verification model; Calculating a comprehensive score for each of the target insertion points based on the waiting efficiency score and the fairness score; According to the comprehensive score, the insertion point is re-determined by a preset rule.

8. A medical queuing system, characterized in that: include: An acquisition module is used to acquire the initial diagnosis queue information and the diagnosis and treatment data of the returning patients, wherein the returning patients are patients who submit a return diagnosis request within a preset time after the initial diagnosis; A calculation module, configured to calculate a diagnosis priority score of the patient to be returned for consultation based on the diagnosis and treatment data in response to the return consultation request; A construction module, used to construct a graph model of patients according to the initial diagnosis queue information, the diagnosis and treatment data and the diagnosis priority score, wherein the patients include the return patients and all the initial diagnosis patients in the initial diagnosis queue; A determination module, used for determining an insertion point of each of the returning patients in the initial diagnosis queue based on the graph model; A generation module is used to insert each returning patient into the initial diagnosis queue according to the insertion point corresponding to each returning patient, and generate a waiting queue including the initial diagnosis patients and the returning patients.

9. A medical queuing device, characterized in that: include: one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the medical queuing device to execute the method as described in any one of claims 1-7.

10. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a medical queuing and calling device, the medical queuing and calling device executes the method as described in any one of claims 1-7.

Images