An event-driven medical scenario data management system and method

Through the event-driven medical treatment scenario data management system, the process node associations in medical treatment scenarios are analyzed, real-time location and prediction driving coefficients are obtained, and the problem of online and offline processes in medical treatment scenarios is solved, the medical treatment path and time are optimized, and the patients are improved Experience and data management effects.

CN118471411BActive Publication Date: 2024-12-06SHENKANG MEDICAL RES INST (BEIJING) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410614153.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-17
Publication Date
2024-12-06
Estimated Expiration
2044-05-17

AI Technical Summary

Technical Problem

In the medical treatment scenario, the online and offline process nodes are broken, resulting in the inability of the patient to achieve coherence in the process and lack of offline position guidance, resulting in too long waiting time before diagnosis and poor medical experience.

Method used

An event-driven medical treatment scenario data management system is adopted to analyze the correlation between each process node, and construct the patient's medical treatment scenario, obtain real-time location, predict the driving coefficient and department busyness, and optimize the medical treatment path and time.

Benefits of technology

It realizes personalized consultations in patients, reduces unnecessary medical treatment steps, shortens waiting time, and improves medical experience and data management effects.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118471411B_ABST
    Figure CN118471411B_ABST
Patent Text Reader

Abstract

The present invention discloses a medical scene data management system and method based on event-driven, which relates to the technical field of data management. The present invention includes: S10: constructing a medical scene for a patient; S20: after the patient completes each event, the medical terminal sends real-time location request information to the patient appointment terminal, and after the patient authorizes, the medical terminal obtains the patient's real-time location information; S30: predicting the patient's real-time driving coefficient for the associated event to be executed; S40: determining the patient's best medical time period in the department where the associated event to be executed is located. The present invention reduces the patient's waiting time for medical treatment, and at the same time, it can avoid the poor medical experience of the patient due to the imbalance of idleness and busyness in the department. The present invention is conducive to realizing the patient's personalized consultation, avoiding the patient from executing some unnecessary events, reducing the patient's medical time, and further improving the system's management effect on medical scene data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to an event-driven medical scenario data management system and method. Background Art

[0002] At present, most hospitals have built convenient mobile medical services based on their own APPs, mini-programs and other channels, including appointment registration, online payment, waiting in line, report viewing, etc. However, in actual application, since part of the process nodes in the medical scene are online and the other part are offline, some process nodes in the medical scene are broken and discontinuous, making it impossible for patients to connect the online process nodes with the offline process nodes. At the same time, the online process nodes lack guidance on the location of the offline medical area, resulting in too long execution time for patients at the offline process nodes.

[0003] Most hospitals generally have problems such as long waiting times before consultation and poor medical experience. Optimizing the medical process and shortening patient waiting times have become urgent needs for the digital transformation of medical services.

[0004] Therefore, people are in urgent need of an event-driven medical scenario data management system and method to solve the above technical problems. Summary of the invention

[0005] The purpose of the present invention is to provide an event-driven medical scenario data management system and method to solve the problems raised in the prior art.

[0006] To achieve the above object, the present invention provides the following technical solution: an event-driven medical scene data management method, the method comprising:

[0007] S10: Treat each process node in the medical treatment scenario as an event, analyze the correlation between the events according to the triggering conditions of each event and the patient's appointment registration information on the patient terminal, and construct the patient's medical treatment scenario based on the analysis results;

[0008] S20: After the patient completes each event, the medical terminal sends real-time location request information to the patient reservation terminal. After the patient authorizes, the medical terminal obtains the patient's real-time location information;

[0009] S30: In the constructed patient medical treatment scenario, when the patient completes each event, the medical treatment terminal sends a navigation route to the patient reservation terminal based on the patient's real-time location information. The patient goes to the execution location of the to-be-executed associated event according to the navigation route received by the patient reservation terminal. During the patient navigation process, the medical treatment terminal obtains the patient's real-time motion trajectory, and predicts the patient's real-time driving coefficient for the to-be-executed associated event based on the obtained real-time motion trajectory.

[0010] S40: Based on the patient's real-time driving coefficient for the associated event to be executed, the medical terminal predicts the busyness of each department. According to the prediction result, the medical terminal determines the patient's best consultation time period in the department where the associated event to be executed is located.

[0011] Further, the S10 includes:

[0012] S101: Acquire all process nodes in the medical treatment scenario, including appointment registration, registration payment, check-in waiting, prescription payment, department examination, report review, admission and discharge, hospitalization prepayment, discharge medication and evaluation feedback. Treat each process node in the medical treatment scenario as an event, and number each event according to the execution order of each event. The numbering result is: i=1,2,…,m, where m represents the total number of process nodes in the medical treatment scenario;

[0013] S102: According to the patient's appointment registration information on the patient terminal, the patient's visiting department and condition description are obtained. The medical terminal predicts the correlation coefficient between various events based on the patient's condition description. The specific prediction method is:

[0014] The medical terminal matches the patient's condition description with the condition description stored in the medical terminal database, and calculates the probability value of the patient executing each event according to the event that needs to be executed according to the condition description with a matching degree higher than the k value. The specific calculation formula is: i =y i / Y, where Y represents the number of disease descriptions stored in the medical terminal database with a matching degree higher than the k value, y i represents the number of times event i needs to be executed in the disease description with a matching degree higher than k, 0.7≤k≤1, μ i represents the probability value of the patient performing event i;

[0015] After the patient has made an appointment and paid for the registration, event j is randomly selected from the remaining events, and the triggering conditions of event j and the registration and payment event are obtained. The number of overlapping triggering conditions S of the registration and payment event and event j is calculated. j2 Determine, according to β j2 =μ j *(|x j -x2| / Sj2 ) predicts the correlation coefficient between event j and registration and payment event, where j = 1, 2, ..., m and j ≠ 1, 2, x j represents the number of triggering conditions for event j, x2 represents the number of triggering conditions for registration and payment events, μ j represents the probability value of the patient performing event j, β j2 represents the correlation coefficient between event j and registration and payment event;

[0016] S103: maxβ j2 The value is searched, if maxβ j2 >0.6, the j value is determined, and it is considered that event j remains in the patient's medical treatment scenario. If maxβ j2 ≤0.6, then event j is considered not to be retained in the patient's medical treatment scenario, and event j is removed from the remaining events, where max represents the maximum value symbol;

[0017] S104: Repeat the operations in S102-S103 until there are no selectable events in the remaining events, determine the retention status of events in the patient's medical scene, determine the execution location of each retained event according to the location of the patient's treatment department, and based on the determination result, construct the patient's medical scene in the three-dimensional modeling model of the hospital.

[0018] Furthermore, the specific method of predicting the real-time driving coefficient of the patient for the associated event to be executed in S30 is:

[0019] In the constructed patient medical treatment scenario, the execution order of each event retained in the patient medical treatment scenario is determined according to the determination order of the j value. After the patient completes event i, the patient's associated events to be executed are determined according to the patient's execution order of each event;

[0020] Based on the patient's real-time motion trajectory, the medical terminal calculates the distance a between the patient and the location where the associated event to be executed is executed at time t. t , and when the patient completes event i, the distance D between the patient and the location where the associated event to be executed is obtained, according to w t =d t / D predicts the real-time driving coefficient of the patient's execution of the associated events to be executed, where w t It represents the driving coefficient of the patient to perform the associated event at time t.

[0021] Further, the S40 includes:

[0022] S401: Determine the number of patients visiting the department where the associated event is to be executed based on the patient's real-time driving coefficient for the associated event to be executed.t <1, indicating that the number of patients in the department where the associated event to be executed is increased by 1;

[0023] S402: According to u t =(h*H t ) / (Tt), predict the busyness of the department where the associated event is to be executed, where H t represents the total number of patients visiting the department where the associated event is to be executed at time t, h represents the average consultation time of a single patient in the department where the associated event is to be executed, T represents the most recent rest time in the department where the associated event is to be executed, and u t Indicates the busyness value of the department where the associated event to be executed is located at time t;

[0024] S403: With time t as the horizontal axis, u t Construct the linear equation u for the ordinate t =f (t-r)→t *t+b, where f (t-r)→t represents the weight coefficient of the linear equation from tr to t, b represents the bias of the linear equation, if -f (t-2r)→(t-r) *ε≤f (t-r)→t -f (t-2r)→(t-r) ≤f (t-2r)→(t-r) *ε and max{f (t-r)→t ,f (t-2r)→(t-r)}<0,7, it means that the time from t to t+r is the best time for the patient to visit the department where the associated event to be executed is located. Otherwise, it means that the time from t to t+r is not the best time for the patient to visit the department where the associated event to be executed is located. Among them, ε represents the proportionality coefficient, 0<ε<0.4, r=5;

[0025] S404: The medical terminal sends the patient's best consultation time period to the patient reservation terminal. The patient goes to the department where the associated event to be executed is located within the best consultation time period received by the patient reservation terminal.

[0026] An event-driven medical scene data management system, the system includes a patient medical scene construction module, a location acquisition module, a to-be-executed associated event drive coefficient prediction module and a medical time period determination module;

[0027] The patient medical treatment scenario construction module constructs the patient's medical treatment scenario according to the correlation between various events;

[0028] The location acquisition module acquires the patient's real-time location information through the medical terminal after the patient completes each event;

[0029] The to-be-executed associated event driving coefficient prediction module predicts the patient's real-time driving coefficient for the to-be-executed associated event according to the execution position of the to-be-executed associated event and the patient's real-time motion trajectory;

[0030] The consultation time period determination module determines the best consultation time for the patient in the department where the associated event to be executed is located according to the busyness of each department.

[0031] Furthermore, the patient medical treatment scenario construction module includes an event determination unit, a correlation coefficient prediction unit, an event retention judgment unit and a patient medical treatment scenario construction unit;

[0032] The event determination unit regards each process node in the medical treatment scenario as an event and numbers each event according to the execution order of each event;

[0033] The correlation coefficient prediction unit obtains the patient's visiting department and condition description according to the patient's appointment registration information at the patient terminal. The medical terminal calculates the probability value of the patient executing each event according to the patient's condition description, and predicts the correlation coefficient between the events based on the calculation result;

[0034] The event retention judgment unit compares the maximum prediction result transmitted by the correlation coefficient prediction unit with the set threshold value, and judges whether the event is retained in the patient's medical treatment scene according to the comparison result;

[0035] The patient medical treatment scene construction unit determines the retention status of events in the patient medical treatment scene according to the judgment result transmitted by the event retention judgment unit, and constructs the patient medical treatment scene in combination with the execution position of each retained event.

[0036] Furthermore, the location acquisition module constructs a patient medical scenario, and after the patient completes each event, the medical terminal sends real-time location request information to the patient appointment terminal. After the patient authorizes, the medical terminal acquires the patient's real-time location information.

[0037] Further, the to-be-executed associated event driving coefficient prediction module includes a to-be-executed associated event determination unit, a real-time motion trajectory acquisition unit and a driving coefficient prediction unit;

[0038] The to-be-executed associated event determination unit determines the to-be-executed associated events of the patient after the patient completes a certain event according to the execution order of each reserved event in the patient's medical treatment scenario;

[0039] In the patient medical treatment scenario constructed by the real-time motion trajectory acquisition unit, when the patient completes each event, the medical treatment terminal sends a navigation route to the patient reservation terminal based on the patient's real-time location information. The patient goes to the execution location of the associated event to be executed according to the navigation route received by the patient reservation terminal. The medical treatment terminal acquires the patient's real-time motion trajectory during the patient navigation process;

[0040] The real-time driving coefficient prediction unit predicts the real-time driving coefficient of the patient for the associated event to be performed according to the real-time motion trajectory acquired by the actual motion trajectory acquisition unit.

[0041] Furthermore, the consultation time period determination module includes a busyness prediction unit, a consultation time period determination unit and a consultation management unit;

[0042] The busyness prediction unit determines the number of patients visiting the department where the associated event is to be executed according to the real-time driving coefficient of the patient for the associated event to be executed, and based on the determination result, constructs a mathematical model to predict the busyness of the department where the associated event is to be executed;

[0043] The consultation time period determination module determines the best consultation time period for the patient in the department where the associated event to be executed is located according to the constructed linear equation and the judgment condition of the best consultation time period;

[0044] The medical consultation management unit sends the patient's best medical consultation time period to the patient reservation terminal through the medical consultation terminal. The patient goes to the department where the associated event to be executed is located within the best medical consultation time period according to the best medical consultation time period received by the patient reservation terminal.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. The present invention matches the patient's condition description with the condition description stored in the medical terminal database, calculates the probability value of the patient's execution at each time, and predicts the correlation coefficient between each event in the medical scene based on the calculation result. Based on the prediction result, the retention status of the event in the patient's medical scene is determined. According to the determination result, the patient's medical scene is constructed in the three-dimensional modeling model of the hospital, which is conducive to realizing personalized consultation for the patient, avoiding the patient from performing some unnecessary events, reducing the patient's medical time, and further improving the system's management effect on medical scene data.

[0047] 2. The present invention predicts the real-time driving coefficient of the patient for the associated events to be executed based on the patient's real-time motion trajectory, which is beneficial for the medical terminal to know the patient's medical status and enhances the driving management effect between various events.

[0048] 3. The present invention predicts the busyness of each department of the hospital through the predicted real-time driving coefficient, which is conducive to determining the best time for patients to see a doctor, reducing the waiting time for patients to see a doctor. At the same time, it can avoid the poor medical experience of patients due to uneven busyness of departments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A schematic diagram of the workflow of an event-driven medical scenario data management system and method of the present invention;

[0050] Figure 2 The present invention is a schematic diagram of the working principle of an event-driven medical scenario data management system and method. DETAILED DESCRIPTION

[0051] Next, the technical solution of the present invention will be clearly and completely explained through specific case analysis to ensure that those skilled in the art can implement the present invention according to this embodiment.

[0052] like Figure 1 and Figure 2 As shown, the present invention provides the following technical solution, a method for managing medical scene data based on event-driven, the method comprising:

[0053] S10: Treat each process node in the medical treatment scenario as an event, analyze the correlation between the events according to the triggering conditions of each event and the patient's appointment registration information on the patient terminal, and construct the patient's medical treatment scenario based on the analysis results;

[0054] S10 includes:

[0055] S101: Acquire all process nodes in the medical scene, including appointment registration, registration payment, check-in and waiting, prescription payment, department examination, report review, admission and discharge, prepayment of hospitalization, discharge with medicine, and evaluation feedback. Treat each process node in the medical scene as an event, and number each event according to the execution order of each event. The numbering result is: i=1,2,…,m, where m represents the total number of process nodes in the medical scene. According to the execution order of each event, the trigger condition for registration payment is that the patient successfully makes an appointment, and the trigger condition for check-in and waiting is that the patient successfully makes an appointment and successfully pays the registration.

[0056] S102: According to the patient's appointment registration information on the patient terminal, the patient's visiting department and condition description are obtained. The medical terminal predicts the correlation coefficient between various events based on the patient's condition description. The specific prediction method is:

[0057] The medical terminal matches the patient's condition description with the condition description stored in the medical terminal database, and the event to be executed according to the condition description with a matching degree higher than the k value. The matching degree refers to the text similarity between the patient's condition description and the condition description stored in the medical terminal database. The calculation method of the text similarity is the existing technology. The probability value of the patient executing each event is calculated. The specific calculation formula is: μ i =y i / Y, where Y represents the number of disease descriptions stored in the medical terminal database with a matching degree higher than the k value, y i represents the number of times event i needs to be executed in the disease description with a matching degree higher than k, 0.7≤k≤1, μ i represents the probability value of the patient performing event i;

[0058] After the patient makes an appointment and pays for the registration, randomly select event j from the remaining events. The remaining events refer to other events in the medical scene except for the appointment and registration, and obtain the triggering conditions of event j and the registration and payment event. The number of overlapping triggering conditions S of the registration and payment event and event j is calculated. j2 Determine, according to β j2 =μ j *(|x j -x2| / S j2 ) predicts the correlation coefficient between event j and registration and payment event, where j = 1, 2, ..., m and j ≠ 1, 2, x j represents the number of triggering conditions for event j, x2 represents the number of triggering conditions for registration and payment events, μ j represents the probability value of the patient performing event j, β j2 represents the correlation coefficient between event j and registration and payment event;

[0059] S103: maxβ j2 The value is searched, if maxβ j2 >0.6, the j value is determined, and it is considered that event j remains in the patient's medical treatment scenario. If maxβ j2 ≤0.6, then event j is considered not to be retained in the patient's medical treatment scenario, and event j is removed from the remaining events, where max represents the maximum value symbol;

[0060] S104: Repeat the operations in S102-S103 until there is no selectable event in the remaining events, determine the retention status of the events in the patient's medical scene, determine the execution location of each reserved event according to the location of the patient's medical department, and construct the patient's medical scene in the three-dimensional modeling model of the hospital based on the determination result, which is conducive to realizing personalized consultation for patients, avoiding patients from executing some unnecessary events, and reducing patients' medical treatment time;

[0061] For example, the events retained in the patient medical scene include appointment registration, registration payment, check-in waiting, prescription payment, discharge medication, and evaluation feedback. According to the patient's treatment department, the location of the patient's treatment department is determined in the hospital's 3D modeling model. In the order of hospital entrance location → patient treatment department location → hospital payment location → hospital pharmacy location → and hospital entrance location, the patient's medical scene is constructed in the hospital's 3D modeling model.

[0062] S20: After the patient completes each event, the medical terminal sends real-time location request information to the patient reservation terminal. After the patient authorizes, the medical terminal obtains the patient's real-time location information;

[0063] S30: In the constructed patient medical treatment scenario, when the patient completes each event, the medical treatment terminal sends a navigation route to the patient reservation terminal based on the patient's real-time location information. The patient goes to the execution location of the to-be-executed associated event according to the navigation route received by the patient reservation terminal. During the patient navigation process, the medical treatment terminal obtains the patient's real-time motion trajectory, and predicts the patient's real-time driving coefficient for the to-be-executed associated event based on the obtained real-time motion trajectory.

[0064] The specific method of S30 predicting the real-time driving coefficient of the patient for the associated event to be executed is:

[0065] In the constructed patient medical treatment scenario, the execution order of each event retained in the patient medical treatment scenario is determined according to the determination order of the j value. After the patient completes event i, the patient's to-be-executed associated events are determined according to the patient's execution order of each event. The to-be-executed associated events refer to the events that need to be executed next after the patient completes event i.

[0066] Based on the patient's real-time motion trajectory, the medical terminal calculates the distance d between the patient and the location where the associated event to be executed is to be executed at time t. t , and when the patient completes event i, the distance value D of the patient from the execution position of the associated event to be executed is obtained, and the distance value is determined according to the navigation route, according to w t =d t / D predicts the real-time driving coefficient of the patient's execution of the associated events to be executed, where w t It represents the driving coefficient of the patient to perform the associated event at time t;

[0067] S40: Based on the patient's real-time driving coefficient for the associated event to be executed, the medical terminal predicts the busyness of each department, and the medical terminal determines the patient's best consultation time period in the department where the associated event to be executed is located according to the prediction result;

[0068] S40 includes:

[0069] S401: Determine the number of patients visiting the department where the associated event is to be executed based on the patient's real-time driving coefficient for the associated event to be executed. t <1, indicating that the number of patients in the department where the associated event to be executed is increased by 1;

[0070] S402: According to u t =(h*H t ) / (Tt), predict the busyness of the department where the associated event is to be executed, where H t represents the total number of patients visiting the department where the associated event is to be executed at time t, h represents the average consultation time of a single patient in the department where the associated event is to be executed, T represents the most recent rest time in the department where the associated event is to be executed, and u t Indicates the busyness value of the department where the associated event to be executed is located at time t;

[0071] S403: With time t as the horizontal axis, u t Construct the linear equation u for the ordinate t =f (t-r)→t *t+b, the scale interval of the horizontal axis is 5 minutes, and the scale interval refers to the distance between two adjacent scales on the horizontal axis, where f (t-r)→t represents the weight coefficient of the linear equation from tr to t, b represents the bias of the linear equation, if -f (t-2r)→(t-r) *ε≤f (t-r)→t -f (t-2r)→(t-r) ≤f (t-2r)→(t-r) *ε and max{f (t-r)→t ,f (t-2r)→(t-r)}<0,7, it means that the time from t to t+r is the best time for the patient to visit the department where the associated event to be executed is located. Otherwise, it means that the time from t to t+r is not the best time for the patient to visit the department where the associated event to be executed is located. Among them, ε represents the proportional coefficient, 0<ε<0.4, r=5, unit: minute;

[0072] S404: The medical terminal sends the patient's best consultation time period to the patient reservation terminal. The patient goes to the department where the associated event to be executed is located within the best consultation time period received by the patient reservation terminal. This helps to reduce the patient's waiting time for consultation. At the same time, it can avoid the patient's poor consultation experience due to uneven busyness of the department.

[0073] An event-driven medical scene data management system, the system includes a patient medical scene construction module, a location acquisition module, a to-be-executed associated event drive coefficient prediction module and a medical time period determination module;

[0074] The patient medical scene construction module constructs the patient's medical scene according to the correlation between various events;

[0075] The patient medical treatment scenario construction module includes an event determination unit, a correlation coefficient prediction unit, an event retention judgment unit and a patient medical treatment scenario construction unit;

[0076] The event determination unit treats each process node in the medical treatment scenario as an event and numbers each event according to the execution order of each event;

[0077] The correlation coefficient prediction unit obtains the patient's visiting department and condition description according to the patient's appointment registration information on the patient terminal. The medical terminal calculates the probability value of the patient executing each event according to the patient's condition description, and predicts the correlation coefficient between the events based on the calculation result;

[0078] The event retention judgment unit compares the maximum prediction result transmitted by the correlation coefficient prediction unit with the set threshold value, and judges whether the event is retained in the patient's medical treatment scene according to the comparison result;

[0079] The patient medical scene construction unit determines the retention status of the events in the patient medical scene according to the judgment result transmitted by the event retention judgment unit, and constructs the patient medical scene in combination with the execution position of each retained event;

[0080] After the patient completes each event, the location acquisition module acquires the patient's real-time location information through the medical terminal;

[0081] The location acquisition module is based on the patient medical scenario. After the patient completes each event, the medical terminal sends real-time location request information to the patient appointment terminal. After the patient authorizes, the medical terminal obtains the patient's real-time location information.

[0082] The to-be-executed associated event driving coefficient prediction module predicts the patient's real-time driving coefficient of the to-be-executed associated event according to the execution position of the to-be-executed associated event and the patient's real-time motion trajectory;

[0083] The to-be-executed associated event driving coefficient prediction module includes a to-be-executed associated event determination unit, a real-time motion trajectory acquisition unit and a driving coefficient prediction unit;

[0084] The to-be-executed associated event determination unit determines the to-be-executed associated events of the patient after the patient completes a certain event according to the execution order of each reserved event in the patient's medical treatment scenario;

[0085] In the patient medical treatment scenario constructed by the real-time motion trajectory acquisition unit, when the patient completes each event, the medical terminal sends a navigation route to the patient appointment terminal based on the patient's real-time location information. The patient goes to the execution location of the associated event to be executed according to the navigation route received by the patient appointment terminal. During the patient navigation process, the medical terminal acquires the patient's real-time motion trajectory;

[0086] The real-time driving coefficient prediction unit predicts the real-time driving coefficient of the patient for the associated event to be performed according to the real-time motion trajectory obtained by the actual motion trajectory acquisition unit;

[0087] The consultation time period determination module determines the best consultation time for the patient in the department where the associated event to be executed is located according to the busyness of each department;

[0088] The consultation time period determination module includes a busyness prediction unit, a consultation time period determination unit and a consultation management unit;

[0089] The busyness prediction unit determines the number of patients visiting the department where the associated event is to be executed according to the real-time driving coefficient of the patient for the associated event to be executed, and based on the determination result, constructs a mathematical model to predict the busyness of the department where the associated event is to be executed;

[0090] The consultation time period determination module determines the best consultation time period for the patient in the department where the associated event to be executed is located based on the constructed linear equation and the judgment conditions of the best consultation time period;

[0091] The medical consultation management unit sends the patient's best consultation time period to the patient reservation terminal through the medical consultation terminal. The patient goes to the department where the associated event is to be executed within the best consultation time period received by the patient reservation terminal.

Claims

1. An event-driven medical scenario data management method, characterized in that: The method comprises: S10: Treat each process node in the medical treatment scenario as an event, analyze the correlation between the events according to the triggering conditions of each event and the patient's appointment registration information on the patient terminal, and construct the patient's medical treatment scenario based on the analysis results; The S10 includes: S101: Acquire all process nodes in the medical treatment scenario, including appointment registration, registration payment, check-in waiting, prescription payment, department examination, report review, admission and discharge, hospitalization prepayment, discharge medication and evaluation feedback. Treat each process node in the medical treatment scenario as an event, and number each event according to the execution order of each event. The numbering result is: i=1,2,…,m, where m represents the total number of process nodes in the medical treatment scenario; S102: According to the patient's appointment registration information on the patient terminal, the patient's visiting department and condition description are obtained. The medical terminal predicts the correlation coefficient between various events based on the patient's condition description. The specific prediction method is: The medical terminal matches the patient's condition description with the condition description stored in the medical terminal database, and calculates the probability value of the patient executing each event according to the event that needs to be executed according to the condition description with a matching degree higher than the k value. The specific calculation formula is: i =y i / Y, where Y represents the number of disease descriptions stored in the medical terminal database with a matching degree higher than the k value, y i represents the number of times event i needs to be executed in the disease description with a matching degree higher than k, 0.7≤k≤1, μ i represents the probability value of the patient performing event i; After the patient has made an appointment and paid for the registration, event j is randomly selected from the remaining events, and the triggering conditions of event j and the registration and payment event are obtained. The number of overlapping triggering conditions S of the registration and payment event and event j is calculated. j2 Determine, according to β j2 =μ j *(|x j -x2| / S j2 ) predicts the correlation coefficient between event j and registration and payment event, where j = 1, 2, ..., m and j ≠ 1, 2, x j represents the number of triggering conditions for event j, x2 represents the number of triggering conditions for registration and payment events, μ j represents the probability value of the patient performing event j, β j2 represents the correlation coefficient between event j and registration and payment event; S103: maxβ j2 The value is searched, if maxβ j2 >0.6, the j value is determined, and it is considered that event j remains in the patient's medical treatment scenario. If maxβ j2 ≤0.6, then event j is considered not to be retained in the patient's medical treatment scenario, and event j is removed from the remaining events, where max represents the maximum value symbol; S104: Repeat the operations in S102-S103 until there is no selectable event in the remaining events, determine the retention status of the events in the patient's medical treatment scene, determine the execution location of each retained event according to the location of the patient's medical department, and construct the patient's medical treatment scene in the three-dimensional modeling model of the hospital based on the determination result; S20: After the patient completes each event, the medical terminal sends real-time location request information to the patient reservation terminal. After the patient authorizes, the medical terminal obtains the patient's real-time location information; S30: In the constructed patient medical treatment scenario, when the patient completes each event, the medical treatment terminal sends a navigation route to the patient appointment terminal based on the patient's real-time location information. The patient goes to the execution location of the associated event to be executed according to the navigation route received by the patient appointment terminal. During the patient navigation process, the medical treatment terminal obtains the patient's real-time motion trajectory, and based on the obtained real-time motion trajectory, predicts the patient's real-time driving coefficient for the associated event to be executed. The specific method is: In the constructed patient medical treatment scenario, the execution order of each event retained in the patient medical treatment scenario is determined according to the determination order of the j value. After the patient completes event i, the patient's associated events to be executed are determined according to the patient's execution order of each event; Based on the patient's real-time motion trajectory, the medical terminal calculates the distance d between the patient and the location where the associated event to be executed is to be executed at time t. t , and when the patient completes event i, the distance D between the patient and the location where the associated event to be executed is obtained, according to w t =d t / D predicts the real-time driving coefficient of the patient's execution of the associated events to be executed, where w t It represents the driving coefficient of the patient to perform the associated event at time t; S40: Based on the patient's real-time driving coefficient for the associated event to be executed, the medical terminal predicts the busyness of each department, and the medical terminal determines the patient's best consultation time period in the department where the associated event to be executed is located according to the prediction result; The S40 includes: S401: Determine the number of patients visiting the department where the associated event is to be executed based on the patient's real-time driving coefficient for the associated event to be executed. t <1, indicating that the number of patients in the department where the associated event to be executed is increased by 1; S402: According to u t =(h*H t ) / (Tt), predict the busyness of the department where the associated event is to be executed, where H t represents the total number of patients visiting the department where the associated event is to be executed at time t, h represents the average consultation time of a single patient in the department where the associated event is to be executed, T represents the most recent rest time in the department where the associated event is to be executed, and u t Indicates the busyness value of the department where the associated event to be executed is located at time t; S403: With time t as the horizontal axis, u t Construct the linear equation u for the ordinate t =f (t-r)→t *t+b, where f (t-r)→t represents the weight coefficient of the linear equation from tr to t, b represents the bias of the linear equation, if -f (t-2r)→(t-r) *ε≤f (t-r)→t -f (t-2r)→(t-r) ≤f (t-2r)→(t-r) *ε and max{f (t-r)→t ,f (t-2r)→(t-r) }<0,7, it means that the time from t to t+r is the best time for the patient to visit the department where the associated event to be executed is located. Otherwise, it means that the time from t to t+r is not the best time for the patient to visit the department where the associated event to be executed is located. Among them, ε represents the proportionality coefficient, 0<ε<0.4, r=5; S404: The medical terminal sends the patient's best consultation time period to the patient reservation terminal. The patient goes to the department where the associated event to be executed is located within the best consultation time period received by the patient reservation terminal.

2. An event-driven medical scene data management system applied to the event-driven medical scene data management method according to claim 1, characterized in that: The system includes a patient medical treatment scenario construction module, a location acquisition module, a to-be-executed associated event driving coefficient prediction module, and a medical treatment time period determination module; The patient medical treatment scenario construction module constructs the patient's medical treatment scenario according to the correlation between various events; The location acquisition module acquires the patient's real-time location information through the medical terminal after the patient completes each event; The to-be-executed associated event driving coefficient prediction module predicts the patient's real-time driving coefficient for the to-be-executed associated event according to the execution position of the to-be-executed associated event and the patient's real-time motion trajectory; The consultation time period determination module determines the best consultation time for the patient in the department where the associated event to be executed is located according to the busyness of each department.

3. The event-driven medical scenario data management system according to claim 2, characterized in that: The patient medical treatment scenario construction module includes an event determination unit, a correlation coefficient prediction unit, an event retention judgment unit and a patient medical treatment scenario construction unit; The event determination unit regards each process node in the medical treatment scenario as an event and numbers each event according to the execution order of each event; The correlation coefficient prediction unit obtains the patient's visiting department and condition description according to the patient's appointment registration information at the patient terminal. The medical terminal calculates the probability value of the patient executing each event according to the patient's condition description, and predicts the correlation coefficient between the events based on the calculation result; The event retention judgment unit compares the maximum prediction result transmitted by the correlation coefficient prediction unit with the set threshold value, and judges whether the event is retained in the patient's medical treatment scene according to the comparison result; The patient medical treatment scene construction unit determines the retention status of events in the patient medical treatment scene according to the judgment result transmitted by the event retention judgment unit, and constructs the patient medical treatment scene in combination with the execution position of each retained event.

4. The event-driven medical scenario data management system according to claim 3, characterized in that: The location acquisition module is based on the constructed patient medical scenario. After the patient completes each event, the medical terminal sends real-time location request information to the patient appointment terminal. After the patient authorizes, the medical terminal acquires the patient's real-time location information.

5. The event-driven medical scenario data management system according to claim 4, characterized in that: The to-be-executed associated event driving coefficient prediction module includes a to-be-executed associated event determination unit, a real-time motion trajectory acquisition unit and a driving coefficient prediction unit; The to-be-executed associated event determination unit determines the to-be-executed associated events of the patient after the patient completes a certain event according to the execution order of each reserved event in the patient's medical treatment scenario; In the patient medical treatment scenario constructed by the real-time motion trajectory acquisition unit, when the patient completes each event, the medical treatment terminal sends a navigation route to the patient reservation terminal based on the patient's real-time location information. The patient goes to the execution location of the associated event to be executed according to the navigation route received by the patient reservation terminal. The medical treatment terminal acquires the patient's real-time motion trajectory during the patient navigation process; The real-time driving coefficient prediction unit predicts the real-time driving coefficient of the patient for the associated event to be performed according to the real-time motion trajectory acquired by the actual motion trajectory acquisition unit.

6. The event-driven medical scenario data management system according to claim 5, characterized in that: The consultation time period determination module includes a busyness prediction unit, a consultation time period determination unit and a consultation management unit; The busyness prediction unit determines the number of patients visiting the department where the associated event is to be executed according to the real-time driving coefficient of the patient for the associated event to be executed, and based on the determination result, constructs a mathematical model to predict the busyness of the department where the associated event is to be executed; The consultation time period determination module determines the best consultation time period for the patient in the department where the associated event to be executed is located according to the constructed linear equation and the judgment condition of the best consultation time period; The medical consultation management unit sends the patient's best medical consultation time period to the patient reservation terminal through the medical consultation terminal. The patient goes to the department where the associated event to be executed is located within the best medical consultation time period according to the best medical consultation time period received by the patient reservation terminal.