Full-scene nursing task dynamic generation method

Abstract

The invention provides a full-scene nursing task dynamic generation method, and relates to the technical field of medical treatment. The method comprises the steps of obtaining medical data of a target user in a preset medical institution; performing event identification according to the medical data of the target user and a trigger condition of at least one preset clinical event associated with each clinical nursing business scene in the plurality of clinical nursing business scenes; if the trigger conditions of the target clinical event associated with the clinical nursing business scene are identified to be matched, loading a target event template corresponding to the target clinical event, and extracting a standardized nursing activity set corresponding to the target clinical event and a nursing task set of each nursing activity under the standardized nursing activity set from the target event template; and instantiating the target clinical event by adopting the target event template according to the medical data of the target user, the standardized nursing activity set and the nursing task set of each nursing activity, and generating a full-cycle nursing task for the target clinical event. Therefore, the efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a method for dynamically generating full-scenario nursing tasks. Background Art

[0002] In the existing medical system, the entire cycle of patient care from admission to discharge involves multiple scenarios, including outpatient and emergency departments, inpatient wards, operating rooms, ICUs, rehabilitation centers, and home follow-up. Currently, hospitals generally use electronic medical record (EMR) systems or nursing information management systems (NIS) to generate nursing tasks, usually statically generating task lists based on medical order templates, nursing plans, and nursing pathways. For example, postoperative patient care tasks rely on the preset condition of "monitoring vital signs every 2 hours," but cannot dynamically respond to abnormal events such as sudden infections and sudden increases in blood pressure. As the demand for the construction of clinical nursing information systems towards digitalization and intelligent development becomes increasingly strong, existing nursing task generation technologies have defects such as scenario fragmentation, rigid conditions, and resource fragmentation, resulting in problems such as poor continuity and low efficiency in the nursing process. Summary of the Invention

[0003] The purpose of this application is to address the deficiencies in the above-mentioned prior art and provide a method for dynamically generating nursing tasks in all scenarios to solve the problems of scene fragmentation and rigid conditions in the prior art.

[0004] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for dynamically generating nursing tasks in all scenarios, the method comprising:

[0006] Obtain medical data of target users in preset medical institutions;

[0007] Performing event identification based on the medical data of the target user and a trigger condition of at least one preset clinical event associated with each clinical nursing business scenario in a plurality of clinical nursing business scenarios;

[0008] If it is identified that the trigger condition of the target clinical event associated with the clinical nursing business scenario matches, the target event template corresponding to the target clinical event is loaded, and the standardized nursing activity set corresponding to the target clinical event and the nursing task set of each nursing activity under the standardized nursing activity set are extracted from the target event template;

[0009] According to the medical data of the target user, the standardized nursing activity set and the nursing task set of each nursing activity, the target clinical event is instantiated using the target event template to generate a full-cycle nursing task for the target clinical event.

[0010] Optionally, the loading of a target event template corresponding to the target clinical event includes:

[0011] Obtaining event trigger information of the target clinical event;

[0012] According to the event triggering information of the target clinical event, an event template corresponding to the event triggering information is loaded as the target event template.

[0013] Optionally, the loading, according to the event trigger information of the target clinical event, an event template corresponding to the event trigger information as the target event template includes:

[0014] According to the event triggering information of the target clinical event, obtaining an event template corresponding to the event triggering information;

[0015] If the event template corresponding to the event triggering information is at least two event templates, obtaining the first event association information of the target user from the medical data of the target user;

[0016] According to the first event association information of the target user, the target event template is determined and loaded from the at least two event templates.

[0017] Optionally, instantiating the target clinical event using the target event template based on the target user's medical data, the standardized nursing activity set, and the nursing task set of each nursing activity to generate a full-cycle nursing task for the target clinical event includes:

[0018] Acquire the second event-related information of the target user and the real-time status parameters of the target user from the medical data of the target user;

[0019] According to the second event association information, the standardized nursing activity set and the nursing task set of each nursing activity are sequentially screened to obtain a target nursing activity set and a target nursing task under the target nursing activity set;

[0020] Calculating task parameters for each target nursing task under the target nursing activity set according to the real-time status parameters to obtain task parameters for each target nursing task;

[0021] According to the task parameters of each target nursing task, a full-cycle nursing task for the target clinical event is generated.

[0022] Optionally, generating a full-cycle nursing task for the target clinical event according to the task parameters of each target nursing task includes:

[0023] According to the association relationship between each of the target nursing tasks, the task parameters of the target associated tasks in each of the target nursing tasks are adjusted to generate a full-cycle nursing task for the target clinical event.

[0024] Optionally, the method further includes:

[0025] According to each nursing task in the full-cycle nursing task, the resources of the preset medical institution are matched to obtain resource matching parameters of each nursing task, wherein the resource matching parameters of each nursing task include: matching information of human resources corresponding to each nursing task, and status information of corresponding equipment resources;

[0026] According to the preset task priority, execution time constraint, dependency between tasks and resource matching parameters of each nursing task in the full-cycle nursing task, each nursing task in the full-cycle nursing task is scheduled to generate a task execution queue corresponding to the full-cycle nursing task.

[0027] Optionally, the scheduling of each nursing task in the full-cycle nursing task according to the preset task priority, execution time constraint, dependency between tasks, and resource matching parameters of each nursing task in the full-cycle nursing task to generate a task execution queue corresponding to the full-cycle nursing task includes:

[0028] Acquiring nursing risk parameters of the target user based on the medical data of the target user;

[0029] Determine the priority weight parameters of each nursing task using a preset reinforcement learning model according to the nursing risk parameter of the target user, the execution time constraint of each nursing task, and the resource matching parameter;

[0030] According to the priority weight parameters of each nursing task, the preset task priority of each nursing task and the dependency relationship between the tasks, each nursing task is scheduled to generate a task execution queue corresponding to the full-cycle nursing task.

[0031] Optionally, before performing event identification based on the medical data of the target user and a trigger condition of at least one preset clinical event associated with each clinical nursing business scenario in a plurality of clinical nursing business scenarios, the method further includes:

[0032] Configure scenarios through the visual configuration interface to obtain multiple clinical business scenarios;

[0033] Performing clinical event configuration on each clinical nursing business scenario through the visual configuration interface to obtain the at least one preset clinical event associated with each clinical nursing business scenario;

[0034] Each preset clinical event is configured through the visual configuration interface to obtain an event template for each preset clinical event. The event template for each preset clinical event includes: an event template identifier, an event template name, an associated clinical event identifier, a trigger condition for the associated clinical event, an associated nursing activity set, and a task set for each nursing activity in the nursing activity set.

[0035] Optionally, the method further includes:

[0036] Obtain generation effect evaluation parameters for the full-cycle nursing tasks for the target clinical event; based on the generation effect evaluation parameters, update the event template of the target clinical event, the standardized nursing activity set corresponding to the target clinical event, and the nursing task set of each nursing activity under the standardized nursing activity set.

[0037] Optionally, the method further includes:

[0038] Displaying a nursing event list of the target user in the first area of ​​the event management page;

[0039] Displaying, via the second area of ​​the event management page, an activity set corresponding to a selected nursing event in the nursing event list, a status of each activity in the corresponding activity set, and a task set corresponding to the selected event in the corresponding activity set;

[0040] The statistical analysis results of the execution data corresponding to the selected nursing event are displayed in the third area of ​​the event management page.

[0041] Compared with the prior art, this application has the following beneficial effects:

[0042] The present application provides a method for dynamically generating nursing tasks in all scenarios. The method obtains the medical data of a target user in a preset medical institution; performs event identification based on the medical data of the target user and the trigger conditions of at least one preset clinical event associated with each clinical nursing business scenario in multiple clinical nursing business scenarios; if the trigger conditions of the target clinical event associated with the clinical nursing business scenario are matched, the target event template corresponding to the target clinical event is loaded, and the standardized nursing activity set corresponding to the target clinical event and the nursing task set of each nursing activity under the standardized nursing activity set are extracted from the target event template; based on the medical data of the target user, the standardized nursing activity set and the nursing task set of each nursing activity, the target clinical event is instantiated using the target event template to generate a full-cycle nursing task for the target clinical event. Thus, through the hierarchical modeling technology of events, activities and tasks, various trigger conditions in the clinical scenario are converted into quantifiable event nodes, and automatically decomposed into standardized activities and execution tasks based on event logic, thereby improving the efficiency and quality of nursing work, reducing the cost of generating nursing tasks, and providing patients with more personalized and accurate nursing services. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 A flowchart of a dynamic generation method for full-scenario nursing tasks provided in this application;

[0045] Figure 2 A flowchart of a method for loading a target event template corresponding to a target clinical event provided in an embodiment of the present application;

[0046] Figure 3 A flowchart of a method for determining a target event template from at least two event templates provided in an embodiment of the present application;

[0047] Figure 4 A flowchart of a method for generating a full-cycle nursing task for a target clinical event provided in an embodiment of the present application;

[0048] Figure 5 A flowchart of a method for generating a task execution queue corresponding to a full-cycle nursing task provided in an embodiment of the present application;

[0049] Figure 6A flowchart of a method for generating a task execution queue according to priority weight parameters provided in an embodiment of the present application;

[0050] Figure 7 A flowchart of a method for obtaining an event template for each preset clinical event provided in an embodiment of the present application;

[0051] Figure 8 A flowchart of a method for displaying nursing events provided in an embodiment of the present application;

[0052] Figure 9 A schematic diagram of a dynamic generation device for full-scenario nursing tasks provided in an embodiment of the present application;

[0053] Figure 10 A schematic diagram of an Internet of Vehicles server provided in an embodiment of the present application.

[0054] Icon: 901 - acquisition module, 902 - identification module, 903 - extraction module, 904 - generation module, 1001 - processor, 1002 - storage medium. DETAILED DESCRIPTION

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0056] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0057] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0058] In addition, the terms "first", "second", etc., if used, are merely used to distinguish and describe, and should not be understood as indicating or implying relative importance.

[0059] It should be noted that, in the absence of conflict, the features in the embodiments of this application can be combined with each other.

[0060] Before explaining a method for dynamically generating nursing tasks in a full-scenario manner provided in an embodiment of the present application, the events, activities, tasks, and event templates involved in the embodiment of the present application are first explained.

[0061] 1. Event Definition

[0062] The event in this application is defined as a formal description of key nodes, state changes, or operation instructions with clear business semantics in the patient care process, which can be identified, associated, and dynamically managed across scenarios through a standardized attribute set. The specific attributes of the event are as follows:

[0063] (1) Event ID

[0064] The UUID v4 algorithm is used to generate a 32-bit string to ensure the uniqueness of events across the entire system.

[0065] It supports combined coding through scene code + timestamp + serial number (such as 020101_20250409_001 represents event No. 1 in the inpatient ward on April 9, 2025), which facilitates manual identification and scene tracing.

[0066] (2) Event Name

[0067] Business semantic naming, such as admission events and patient leave, allows hospitals to customize naming based on actual management models.

[0068] (3) Event Type

[0069] Enumeration types include but are not limited to: nursing operations (such as venipuncture and suctioning), status changes (such as transfer to the ICU and completion of discharge assessment), monitoring and early warning (such as blood oxygen saturation <90%, blood glucose >16.7mmol / L), resource scheduling (such as nurse schedule adjustment and equipment loan application), and financial management (such as patient arrears and supplementary account entry).

[0070] (4) Scene Code

[0071] A 6-digit code is used to identify the scene where the event occurred. The specific definition is:

[0072] 01XXXX: Outpatient and emergency department scenarios (e.g., 010001 is emergency triage, 010002 is outpatient nursing assessment);

[0073] 02XXXX: Inpatient ward scene (e.g., 020101 is preoperative skin preparation, 020203 is postoperative wound dressing change);

[0074] 03XXXX: Operating room scene (e.g., 030001 is pre-anesthesia nursing verification, 030002 is post-operative resuscitation monitoring);

[0075] 04XXXX: ICU scenario (e.g., 040001 is for mechanical ventilation parameter adjustment, 040002 is for sedation score recording);

[0076] 05XXXX: Rehabilitation center scenario (e.g., 050101 is limb function training, 050201 is swallowing disorder assessment);

[0077] 06XXXX: Home follow-up scenario (e.g., 060001 for home medication guidance, 060002 for remote vital sign collection);

[0078] It supports scenario-level association (e.g. 0201XX corresponds to surgical ward, 0202XX corresponds to internal medicine ward), facilitating cross-scenario process modeling.

[0079] (5) Related Entities

[0080] Array type, containing the entities involved in the event and their unique identifiers:

[0081] PatientID: Linked to the patient master index (EMPI) in the electronic medical record;

[0082] Nursing staff (NurseID): nurse ID (e.g. N20250001);

[0083] Device (DeviceID): unique identifier of the IoT device (e.g., DEV_ICU_007);

[0084] Consumables (MaterialID): Medical consumables code (such as 361200000001 in accordance with the UDI standard);

[0085] Medical order (OrderID): The unique identifier of the medical order in the HIS system.

[0086] (6) Trigger Conditions

[0087] Structured expressions support the following trigger types:

[0088] Time trigger: For example, perform basic nursing assessment at 08:00 every day;

[0089] Data trigger: For example, when systolic blood pressure is greater than 180 mmHg and heart rate is greater than 100 beats / min, the hypertensive emergency nursing process is triggered;

[0090] Status trigger: For example, the postoperative monitoring event is automatically initiated after the patient is transferred from the operating room to the ICU;

[0091] Manual triggering: For example, a nurse generates an oral care event after confirming that the patient vomited in the system;

[0092] It uses logical expression syntax (such as [BloodPressure.SBP>180]AND[HeartRate>100]), supports AND / OR / NOT logical combinations and threshold range judgment.

[0093] (7) Time Attributes

[0094] Occurrence Time: the actual time when the event is triggered (accurate to seconds, format: YYYY-MM-DDHH:MM:SS);

[0095] Scheduled Time: The preset execution time of the event (supports time window setting, such as 2025-04-09 14:00±30 minutes);

[0096] Duration: Estimated execution time (e.g., PT30M means 30 minutes, in line with ISO 8601);

[0097] End Time: The actual stop time of the event (accurate to seconds, format: YYYY-MM-DD HH:MM:SS).

[0098] (8) Event State

[0099] Define the event lifecycle state using the finite state machine (FSM) model, including:

[0100] Pending: The event has been generated and is waiting for resource allocation;

[0101] Ongoing: The nurse has signed and started to execute;

[0102] OnHold: Temporary interruption due to patient status change or resource conflict;

[0103] Completed: The task is completed and the results are uploaded;

[0104] Terminated: premature termination due to cancellation of medical advice or patient outcome (e.g., discharge, death);

[0105] The status transition must record the operator, time, and reason (e.g., from Pending → Ongoing, nurse N20250001 signed for it on 2025-04-09 09:15).

[0106] (9) Priority Level

[0107] Integer type (level 1-5, the larger the value, the higher the priority), supports dynamic calculation;

[0108] Basic priority: preset according to event type (e.g. monitoring and early warning defaults to level 4, routine care defaults to level 2);

[0109] Dynamic adjustment factor: combined with the severity of the patient's condition (such as APACHE II score > 20 points, +2 levels) and time urgency (such as the remaining planned time is <10 minutes, +1 level).

[0110] (10) Dependency Relations

[0111] Define event execution order constraints, supporting:

[0112] PredecessorEventID: For example, the "postoperative wound dressing change" event must be triggered after the "surgical dressing removal" event is completed;

[0113] Parallel events (ParallelEventID): For example, "vital signs monitoring" and "medication guidance" can be executed at the same time;

[0114] Using directed acyclic graph (DAG) modeling, the system automatically checks event dependency conflicts (such as circular dependencies, triggering subsequent events before the predecessor event is completed).

[0115] Through the above-mentioned attribute definitions, the event model of this application can realize the formal expression of key nodes in the full-cycle nursing process, support intelligent association, dynamic scheduling and visual management of cross-scenario events, and provide a standardized data foundation for subsequent task generation, resource allocation and process monitoring.

[0116] 2. Activity Definition

[0117] In this application, an activity is defined as a process-based operation unit consisting of a set of logically related nursing tasks, centered around a specific nursing goal. It uses a standardized set of attributes to abstractly model complex nursing scenarios and establish a mapping relationship with the underlying tasks. The definition of an activity follows the Business Process Modeling Notation (BPMN 2.0) specification and uses XML Schema structured descriptions. The specific attributes are as follows:

[0118] (1) Activity unique identifier (ActivityID)

[0119] The combination of scene code + stage code + serial number is used for coding (such as WR_ICU_001 represents postoperative resuscitation activities in the ICU scene). The first two digits are the scene code (the same as the SceneCode in the event definition), the middle two digits are the stage code (such as PR represents preoperative, PO represents postoperative, and RC represents rehabilitation), and the last three digits are the serial number.

[0120] It supports association with the process instance ID (such as EMR_20250409_001_ACT01) of the electronic medical record system (EMR) to ensure traceability of the entire process cycle.

[0121] (2) Activity Name

[0122] Business semantic naming, such as admission assessment activities and admission education activities in admission events, allows hospitals to customize naming based on actual management models.

[0123] (3) Activity Type

[0124] Enumeration types are divided into four basic categories based on nursing business scenarios:

[0125] Assessment: such as admission nursing assessment (including tasks such as vital sign collection and allergy history inquiry);

[0126] Intervention: such as postoperative analgesia management (including analgesia pump parameter setting, pain score recording, etc.);

[0127] Monitoring: such as 24-hour monitoring of critically ill patients (including hourly vital sign recording, abnormal indicator warning, and other tasks);

[0128] Education: such as home care guidance for diabetic patients (including medication training, blood sugar monitoring method teaching, etc.);

[0129] Each type is associated with clinical pathway standards (such as the chapter coding of the Clinical Nursing Practice Guidelines) and supports semantic annotation using SNOMEDCT terminology.

[0130] (4) Related Events

[0131] Array type, records the associated event IDs that trigger the start or end of an activity, and supports many-to-many associations:

[0132] Initiating events: For example, the patient's transfer to the ICU event (EventID: ICU_20250409_001) triggers ICU intensive care activities;

[0133] Termination event: For example, the patient is transferred out of the ICU (EventID: ICU_20250411_003), which terminates the current monitoring activity.

[0134] (5) Activity dependency attributes (NIS ACTIVITY EXPRESSION)

[0135] Define the predecessor and successor dependencies of the activity: a list of predecessor task IDs (e.g. TaskID_003 must be executed after TaskID_001 and TaskID_002 are completed).

[0136] (6) Time Attributes

[0137] Scheduled Start Time: The scheduled start time of the activity (supports time windows, such as within 6-8 hours after surgery).

[0138] Scheduled End Time: The scheduled completion time of the activity (strongly associated with the nursing goal time constraint).

[0139] Execution Cycle: For periodic activities (such as daily rehabilitation training), define the repetition frequency (such as every 12 hours, every Monday / Wednesday / Friday).

[0140] (7) State Machine

[0141] Define the activity lifecycle status and link it with the task status:

[0142] Pending: The activity has been generated and is waiting for a pre-conditioning event to trigger it (e.g., completion of the admission assessment).

[0143] InProgress: At least one task is in the Ongoing or Completed state;

[0144] OnHold: All tasks are paused, usually due to changes in the patient's condition or resource shortages (such as emergency deployment of nurses);

[0145] Completed: All required tasks are completed and the sub-goal achievement rate is ≥ 80%;

[0146] Terminated: If the treatment is terminated early due to cancellation of medical advice or patient outcome (e.g., discharge), the reason for termination shall be recorded;

[0147] State transition rule: Activity state = logical aggregation of subtask states (e.g., the in-progress state requires at least one subtask to be in the executing state).

[0148] (8) Correspondence model with tasks (activity template)

[0149] There is a one-to-many mapping relationship between activities and tasks. Activities and their corresponding task sets constitute activity templates.

[0150] An activity contains multiple tasks (such as postoperative monitoring activities contain 12 nursing tasks). A task is the smallest execution unit of an activity, and an activity is a logical container for tasks.

[0151] Tasks can be reused by multiple activities (for example, a vital signs monitoring task can belong to both an ICU monitoring activity and a general ward nursing activity), and the reuse relationship is recorded through the activity-task association table.

[0152] (9) Status linkage mechanism

[0153] Task status changes affect activity status in real time:

[0154] When the last required task is completed, the activity automatically enters the completed state;

[0155] When an activity is activated, the tasks contained in the activity automatically enter the waiting state;

[0156] Through the above attribute definitions, this application's activity model achieves a hierarchical abstraction of complex nursing processes, meeting the overall planning requirements of clinical pathways while ensuring execution accuracy through fine-grained task-level control. The correspondence between activities and tasks, through structured mapping and state linkage mechanisms, provides a standardized data foundation for dynamic modeling, resource scheduling, and effectiveness evaluation of the full-cycle nursing process.

[0157] 3. Task Definition

[0158] In this application's full-cycle nursing task generation system, a Task is defined as the smallest nursing execution unit with a clear execution subject, operation steps, and quality standards. It uses a standardized attribute set to achieve fine-grained description and precise control of nursing operations. Task definitions follow the HL7CDA document specification and are structured in JSON format. They support multiple execution methods, including textual measures and structured input. The specific attributes are as follows:

[0159] (1) Task unique identifier (TaskID)

[0160] The code is composed of scenario code + task category code + timestamp + serial number. For example, WR_02_OP_20250409_001 represents the first task of the operation category (OP) in the inpatient ward (WR) on April 9, 2025.

[0161] Compatible with electronic medical record system (EMR) task ID mapping, supporting tracing back to HIS doctor order system and nursing record system through TaskID.

[0162] (2) Activity name (TaskName)

[0163] Business semantic naming, such as the physical sign measurement task and risk assessment task in the admission assessment activity in the admission event, allows hospitals to customize naming based on actual management models.

[0164] (3) Task Type

[0165] Based on the attributes of nursing operations, it is divided into four basic types:

[0166] Assessment: such as Glasgow Coma Scale (GCS eye opening / language / motor scores must be entered);

[0167] Operation: such as intravenous infusion (need to record parameters such as puncture site, drug name, drip rate, etc.);

[0168] Education: such as diabetes diet guidance (supports the association of text education records and multimedia materials);

[0169] Documentation: such as nursing handover records (which require structured entry of vital signs, changes in condition, etc.);

[0170] Each type is associated with national standard codes such as the "Basic Nursing Service Specification" (WS / T 508-2016) to ensure operational compliance.

[0171] (4) Execution mode attributes

[0172] The execution methods of nursing tasks include but are not limited to textual measures, structured entry, health education, and document entry.

[0173] Structured Entry:

[0174] ①. Preset field types: radio button (such as puncture site: left hand back / right forearm), numerical input (such as body temperature: 36.5℃, accuracy 0.1℃), date and time selection (such as medication time: 2025-04-09 10:30).

[0175] ②. Support drop-down menu to associate medical terminology database (such as ICD-11 code, LOINC laboratory indicator code) to ensure data standardization.

[0176] Textual measures:

[0177] ①. Free text input box (e.g., patient complaint: chest pain worsens when coughing), built-in keyword verification (e.g., automatic recognition of crisis terms such as "dyspnea" and "confusion" and triggering an alert).

[0178] ②. Support rich text formatting (such as bold and numbered lists), and intelligent association of mobile input methods (such as automatically suggesting "blood pressure" when entering "BP").

[0179] Blend Mode:

[0180] ① For wound care tasks: first enter the wound area (length × width × depth, cm) and the nature of the exudate (serous / purulent) in a structured manner, and then add a text description (such as whether the wound edge is red and swollen and tender).

[0181] health education

[0182] ①. When executing nursing tasks, you can directly set up related health education content, such as admission education tasks: the task is directly related to the corresponding content of admission education. When executing the task, you can open the health education module, enter information such as the education object and education method, and view the education content at the same time.

[0183] Nursing Documents

[0184] ②. The execution of a nursing task can be directly linked to a nursing document, such as the admission assessment task: the task is directly linked to the admission assessment form, and a complete admission assessment form will be directly opened when the task is executed.

[0185] (5) Execution Carrier

[0186] Define the terminal device and interaction method for task execution:

[0187] PC: Supports complex form entry (such as the six-dimensional structured data of the Braden score of the pressure ulcer assessment form);

[0188] Mobile terminal (App / Pad): Optimize touch interaction, use sliding selection (such as a slider with a pain score of 1-10 points) and scan code entry (scanning the consumables UDI code to automatically fill in the specification information);

[0189] IoT device linkage: For example, blood glucose monitoring tasks can directly synchronize smart blood glucose meter data (read the Glucometer device value via Bluetooth and automatically fill in the form).

[0190] (6) Time Attributes

[0191] Task execution cycle:

[0192] Scheduled execution time (ScheduledTime): supports absolute time (e.g., 2025-04-09 15:00) or relative time (e.g., 6 hours after surgery), and can set a time tolerance window (e.g., ±15 minutes);

[0193] Actual execution time (ActualTime): records the start and end time of the task (accurate to the second), automatically generates a timestamp and associates it with the nurse's work number and name;

[0194] Timeout Threshold: If an emergency rescue task is not executed within 30 minutes, a red alert will be triggered; if a routine nursing task is overdue for 2 hours, a yellow alert will be triggered.

[0195] (7) State Machine

[0196] Define task lifecycle states and support state transitions:

[0197] To Do: The task has been generated but not executed (icon: hollow circle);

[0198] Doing: The nurse starts executing the task and locks the task editing permission (icon: rotating progress ring);

[0199] Done: Enter the execution results and submit them, which will be automatically synchronized to the electronic medical record (icon: green check mark);

[0200] Cancelled: The procedure was terminated due to the doctor's order or the patient's contraindication. The reason for termination was recorded (e.g., the patient refused catheterization).

[0201] State transition rules: The completion state requires verification of the completeness of required fields (e.g., vital sign monitoring, no vital sign data entered).

[0202] (8) Priority Level

[0203] Adopt a 5-level scoring system (1-5, 5 is the highest), supporting dynamic calculation:

[0204] Basic priority: preset according to the task type (e.g., cardiopulmonary resuscitation tasks are set to level 5 by default, and routine temperature measurement tasks are set to level 1 by default);

[0205] Dynamic queue-jumping for urgent tasks: If a subtask triggers an emergency event (e.g., "blood glucose level > 20mmol / L"), the priority of subsequent tasks will be automatically increased and the intervals between tasks will be shortened (e.g., original rule: blood glucose monitoring three times a day (07:00, 12:00, 18:00), abnormal event: blood glucose level detected at 12:00 is 22mmol / L, after adjustment: an additional task (retest at 13:00) will be generated, and the interval between subsequent tasks will be shortened to 2 hours);

[0206] Visual presentation: Through task list color marking (red - level 5, orange - level 4, yellow - level 3, green - level 2, blue - level 1), the mobile terminal supports associating vibration intensity with priority (strong vibration reminder for level 5 tasks).

[0207] (9) Task splitting rules

[0208] The task execution plan is structured and split based on the preset cycle type and time constraints. It supports two core modes: frequency (fixed number of times / number of cycles) and time interval (equal length / dynamic interval). The specific rules are as follows:

[0209] Fixed frequency: Generates a fixed number of subtasks within a specified period, evenly distributed or executed at preset time points;

[0210] Loop frequency: Dynamically generate subtasks based on the task completion status until the termination condition is met (such as "wound healing score ≥ 8 points");

[0211] Equal interval: Generates subtasks at fixed time intervals, suitable for regular nursing operations;

[0212] Execution time drift compensation: When a task is delayed due to resource conflicts, the next task time point is automatically calculated (avoiding cumulative errors);

[0213] Task instantiation: Based on the task template issued by the activity layer, the execution cycle, frequency, and time are analyzed to generate the initial execution plan.

[0214] Dynamic Adjustment:

[0215] ①. Capture execution exceptions (such as task timeout, resource unavailability) through the task listener, triggering interval recalculation or frequency increase.

[0216] ②. Update the splitting rules in real time based on contextual data (such as patient vital signs). For example, if the original task of splitting the vital sign measurement task is to measure once a day at 14:00, and if the measured temperature is ≥38.5, a hyperthermia event occurs, the task splitting rule is updated to measure 6 times a day, with one measurement each at 3:00, 7:00, 11:00, 15:00, and 23:00.

[0217] ③. Conflict resolution: When multiple tasks overlap in time, they are executed in order of activity priority (e.g., rescue activities > routine care).

[0218] (10) Quality Check

[0219] Automatic verification rules: By providing a visual verification rule maintenance page, dynamic configuration and boundary value adjustment of verification rules are achieved, and logical verification and time verification can be set through rule expressions.

[0220] Logic check: If the systolic blood pressure is > 260 mmHg, the prompt "Abnormal value, please reconfirm" will appear.

[0221] Time verification: If the time interval between two adjacent blood glucose measurements is less than 15 minutes, the system will prompt “does not meet the monitoring frequency requirements”.

[0222] Through the above attribute definitions, the task model of this application achieves standardized and fine-grained management of nursing operations, supporting digital control of the entire process from task generation to execution result feedback. Flexible adaptation of different execution methods (structured input to ensure data quality, textual measures to meet personalized scenarios), combined with the state machine and priority mechanism, provides underlying data support for intelligent scheduling, resource scheduling, and quality traceability.

[0223] 4. Event template definition

[0224] In the full-cycle nursing task generation system of this application, the event template is defined as: a reusable event structured framework preset based on clinical guidelines and scenario requirements, used to quickly generate event instances that comply with specific rules. The event template implements parameterized configuration of events, triggering rules, associated activities, and tasks through a standardized attribute set, supporting differentiated template configurations for the same event under different rule engines. The specific attributes are as follows:

[0225] (1) Template unique identifier (TemplateID)

[0226] The code is composed of ET_event type code_scenario code_version number. For example, ET_MON_ICU_V1.0 indicates the monitoring and warning event template (version 1.0) in the ICU scenario, which consists of three parts:

[0227] ET: fixed prefix of event template;

[0228] Event type code: same as EventType in the event definition (e.g. MON for monitoring and warning, OPE for nursing operation);

[0229] Scenario code: Same as the scenario code in the activity definition (e.g. ICU for intensive care unit, WR for general ward).

[0230] (2) Template Name

[0231] Semantic business naming, such as postoperative infection warning event - regular ward version and postoperative infection warning event - ICU enhanced version, clarifies the applicable scenarios and rule differences.

[0232] (3) Associated events (EventID)

[0233] Bind the EventID in the event definition (such as pressure ulcer event). The same template supports binding multiple defined events.

[0234] (4) Event template trigger rules (TriggerRuleSet)

[0235] Define the rule conditions for event-corresponding template matching and support multi-rule engine adaptation: For example, for patient pressure ulcer events, the condition for triggering pressure ulcers is that the patient develops a pressure ulcer, but adult pressure ulcers and pediatric pressure ulcers require matching different event templates based on age rules to meet the patient's differentiated activity and task set triggering requirements.

[0236] Rule engine type: Rules are visually set through relational expressions. Conditions include time-based, data-based (such as data elements, medical orders, etc.), state-based, and interface-based:

[0237] ①. Time-Based: For example, automatically generate morning care events at 07:00 every day;

[0238] ② Data-Driven: For example, when procalcitonin (PCT) is greater than 2.0 ng / mL and body temperature is ≥38.5°C, an infection warning event is triggered (expression syntax: [PCT>2.0]AND[BodyTemperature≥38.5]);

[0239] ③ State-Based: For example, the first postoperative assessment event is triggered after the patient is transferred from the operating room to the general ward;

[0240] (5) Activity Set

[0241] Defines a collection of nursing activities associated with the template. Each activity object contains:

[0242] Activity ID: refers to the standard code in the activity definition;

[0243] Activity name: reference the activity name in the activity definition;

[0244] Activity Priority: 1-5 (linked with event priority, e.g. emergency activity priority automatically inherits the highest event priority);

[0245] Trigger condition: Association rule engine rule (e.g., activate ECG monitoring enhancement activity only when the patient's heart rate is greater than 120 beats / min).

[0246] (6) Task Set

[0247] Define the specific tasks included in the activity and support task-level rule configuration. The activity template contains a basic task set. Different event templates allow adding and deleting tasks during template maintenance:

[0248] Task ID (TaskID): refers to the standard code in the activity definition;

[0249] Task name: reference the task name in the task definition;

[0250] Activity Priority: 1-5 (linked with event priority, e.g., the priority of an emergency task automatically inherits the highest event priority);

[0251] Trigger condition: Association rule engine rule (e.g., the temperature retest task is activated only when the patient's temperature is ≥1.5 times the difference from the last measurement).

[0252] (7) Multi-Engine Mapping

[0253] Multiple templates can be configured for the same event to adapt to different rule engines and scenario requirements. For example: Event: Postoperative infection warning event.

[0254] Template A (routine ward version):

[0255] ② Trigger rule: PCT > 2.0 ng / mL OR body temperature ≥ 38.5°C (single indicator trigger);

[0256] ②Activity set: [Postoperative infection screening activities (priority 3), antibiotic medication guidance activities (priority 2)];

[0257] ③Task set: including blood culture specimen collection task (must be completed within 2 hours) and infection site assessment task (optional);

[0258] Template B (ICU enhanced version):

[0259] ① Triggering rules: PCT > 5.0 ng / mL AND body temperature ≥ 39.0°C AND respiratory rate > 25 breaths / min (multiple indicators combined triggering);

[0260] ② Activity set: [Septic shock prevention activities (priority 5, marked as special activities), continuous blood purification preparation activities (priority 4)];

[0261] ③. Task set: including the task of monitoring vital signs every 15 minutes (mandatory high-frequency execution) and the task of monitoring antibiotic blood concentration (required);

[0262] (8) Template Version Management

[0263] Supports iterative template updates. The version number follows the major version. minor version. revision number rule (such as V2.1.3). Change logs are recorded:

[0264] V2.1.0: Added AI risk prediction rules and adjusted the activity priority algorithm;

[0265] V2.1.3: Fixed the task trigger time window configuration error in the ICU scenario.

[0266] (9) Event template and instance generation logic

[0267] When the monitored patient data meets the template triggering rules, the system automatically instantiates the event and event template:

[0268] Dynamic parameter injection: Variable parameters in the template are automatically replaced with real-time patient data upon instantiation. For example, the [patient age] parameter in the template is replaced with a specific value (such as 75 years old) upon instantiation, which is used for standard calculations of task execution (such as infusion rate ≤ 75 drops / minute).

[0269] Through the above-mentioned attribute definitions, the event template in this application implements parameterized modeling and rule-based management of nursing events, supporting differentiated configuration of the same event in different scenarios and rule engines. The flexible combination of activity sets, task sets, and triggering rules in the template provides a reusable, standardized framework for the dynamic generation and precise adaptation of the full-cycle nursing process.

[0270] The following is an explanation of a dynamic generation method of full-scenario nursing tasks provided by this application through specific examples. Figure 1 This is a flow chart of a method for dynamically generating nursing tasks in all scenarios provided by this application. The execution subject of this method is an electronic device that has computing and processing functions. Figure 1 As shown, the method includes:

[0271] S101. Obtain medical data of a target user in a preset medical institution.

[0272] Capture target users' medical data accurately and in real time from multiple sources. For example, sources of medical data may include: sensors / wearable devices, HIS information systems, doctor's station systems, nurse's station systems, nursing medical record systems, medical technology systems, and other in-hospital systems.

[0273] Sensors and wearable devices. Data type: Continuously collects patient vital signs data, such as heart rate, blood pressure, blood oxygen saturation, and body temperature. It also collects information such as movement data and sleep quality. Access method: Using wireless communication protocols such as Bluetooth, ZigBee, and Wi-Fi, sensors and wearable devices are connected to the hospital's IoT gateway. The gateway performs preliminary encryption and format conversion on the data before transmitting it to the event collection server via the hospital's intranet.

[0274] HIS information system. Data types: Contains basic patient information (such as name, age, gender, allergy history, etc.), registration information, hospitalization information, medical order information, and cost information. Access method: Connect to the HIS system through a standard Web Service interface or RESTful API, pulling updated data at preset intervals (such as every 5 minutes). It also supports the HIS system to actively push data when the data changes.

[0275] Doctor's Station System. Data types: Patient diagnosis results, treatment plans, and order issuance and modification information entered by doctors. Access method: Using database middleware technology, the Doctor's Station system database is monitored in real time. When data is inserted or updated in relevant tables in the database, the data is captured and synchronized to the event collection server.

[0276] Nursing station system. Data types include nurses' records of patient care, vital sign measurements, and nursing operation execution information. Access method: Asynchronous data transmission is achieved through message queues (such as RabbitMQ). When new data is generated, the nurse station system encapsulates the data into messages and sends them to the message queue. The event collection server consumes the messages from the queue to obtain the data.

[0277] Nursing Medical Record System. Data Type: Patient nursing records, including text information such as nursing assessments, nursing plans, and implementation status of nursing measures. Access Method: Using file sharing and FTP protocols, the nursing medical record system regularly uploads updated medical records to a designated file server. The event collection server then downloads and parses the document content from the file server.

[0278] Medical technology system. Data type: Test results (such as blood routine, biochemical indicators, imaging reports, etc.). Access method: Uses the DICOM (Digital Imaging and Communications in Medicine) protocol to connect to the Picture Archiving and Communication System (PACS) and the HL7 (Health Information Exchange Standard) protocol to connect to the Laboratory Information Management System (LIS), enabling real-time access to test results.

[0279] Other in-hospital systems. Data types: Specific data generated by different systems, such as surgical time and anesthesia method information from the surgical anesthesia system, and drug dispensing information from the pharmacy management system. Access methods: Customized data access methods are used based on the interface specifications of each system, such as API calls and database synchronization.

[0280] Furthermore, data preprocessing is required. Cleaning: Remove noise, duplicate data, and erroneous data from the collected data. For example, smooth abnormal fluctuations in sensor data and filter out vital sign data that exceeds a reasonable range. Conversion: Convert data from different data sources to a standard format. For example, convert blood pressure data from sensors from different manufacturers to mmHg. Association: Associate data from different data sources related to the same patient. For example, associate a patient's basic information, vital sign data, and test results.

[0281] Therefore, relying on full-scene data perception and fusion technology, the system integrates multi-source data such as electronic medical records, equipment monitoring, and scheduling systems in real time, and builds a dynamic model of patient status through data cleaning, feature extraction, and machine learning algorithms. For example, combined with data such as the patient's allergy history, medication frequency, and test results, contraindication verification rules can be automatically triggered during the "medication task" generation stage to avoid 15%-20% of potential medication errors; by analyzing nurse skill labels and real-time workload, intelligent matching of tasks and manpower can be achieved, reducing the problem of unbalanced task distribution by more than 30%. In addition, the predictive model trained based on historical event data can predict high-risk events (such as postoperative complications) 4-6 hours in advance, pre-generate preventive nursing tasks, transform passive responses into active interventions, and improve the foresight of nursing services.

[0282] S102: Perform event identification based on the medical data of the target user and a trigger condition of at least one preset clinical event associated with each clinical nursing business scenario in a plurality of clinical nursing business scenarios.

[0283] The trigger conditions are explained below.

[0284] Trigger condition definition.

[0285] 1. Condition type: It is divided into time trigger conditions (such as nursing tasks performed at a specific time every day), condition trigger conditions (such as the patient's heart rate exceeding the threshold triggers the corresponding event) and combination trigger conditions (multiple conditions combined to trigger an event).

[0286] 2. Conditional expression: This is expressed using a conditional language based on a conditional engine (such as Drools). Conditions consist of a conditional part and an action part. The conditional part describes the conditions for event triggering, and the action part describes the operation to be performed after the event is triggered.

[0287] Condition matching and event triggering.

[0288] 1. Real-time monitoring: The event collection server monitors the pre-processed data in real time and matches the data with the preset trigger conditions.

[0289] 2. Event triggering: When the data meets a trigger condition, the corresponding event is immediately triggered. After the event is triggered, the system will record detailed information about the event, including event type, trigger time, associated patient ID, trigger condition, etc.

[0290] 3. Multi-condition processing: When multiple conditions are met at the same time, they are processed according to their priority, and the conditions with higher priority are executed first.

[0291] Visual configuration interface.

[0292] 1. Condition creation: Provides a graphical interface that allows medical staff and system administrators to create new trigger conditions by dragging, dropping, selecting, etc. For example, select a data type (such as heart rate), a comparison operator (such as greater than), and a threshold (such as 120) to define a simple trigger condition.

[0293] 2. Condition editing: supports editing and modifying existing trigger conditions, including modifying the conditions, actions, and priorities.

[0294] 3. Condition deletion: You can easily delete trigger conditions that are no longer needed.

[0295] Condition preview and verification.

[0296] 1. Condition preview: Before saving the conditions, a preview function is provided to visually display the detailed content and logical relationship of the conditions.

[0297] 2. Condition Verification: Perform syntax and logic verification on newly created or modified conditions to ensure the correctness of the conditions. If there are any errors in the conditions, the system will give corresponding prompts.

[0298] Furthermore, the above steps are implemented using a distributed architecture design, comprising data collection nodes, data processing nodes, and rule engine nodes. The data collection nodes are responsible for collecting data from various data sources, the data processing nodes pre-process the collected data, and the rule engine nodes perform rule matching and event triggering. Nodes communicate and share data through message queues and distributed caches, improving system scalability and reliability.

[0299] For example, data collection uses Python's Requests library to perform HTTP requests to obtain data, and uses the PySerial library for serial communication to collect sensor data.

[0300] For example, data processing uses Spark Streaming for real-time data processing, and NLTK and SpaCy for natural language processing of text data.

[0301] For example, rule engine: Drools is selected as the rule engine to support the definition and efficient matching of complex rules.

[0302] For example, visual interface: React.js is used as the front-end framework, combined with the Ant Design component library to develop a beautiful and easy-to-use visual configuration interface.

[0303] S103. If the trigger conditions of the target clinical event associated with the clinical nursing business scenario are identified to match, the target event template corresponding to the target clinical event is loaded, and the standardized nursing activity set corresponding to the target clinical event and the nursing task set of each nursing activity under the standardized nursing activity set are extracted from the target event template.

[0304] Once the trigger conditions match the target clinical event associated with the clinical nursing business scenario, the system will obtain event-related information (such as event type, trigger time, and associated patient ID). Then, based on the target event template, it will match the corresponding event template from the event template library. For example, if the trigger is the "patient returns to the ward after surgery" event, the system will match it to the "postoperative nursing event template."

[0305] Event triggers are used to convert clinical emergencies (such as worsening of a patient's condition or surgical changes) into executable task chains. For example, when a patient's blood oxygen saturation is detected below 90%, the system automatically triggers an "emergency care event" and associates it with standardized activities such as "bedside assessment," "doctor's order review," and "equipment commissioning," ultimately breaking it down into specific tasks such as "adjusting oxygen flow," "notifying the doctor," and "recording vital signs."

[0306] It can automatically match tasks across departments (such as the ICU and obstetrics and gynecology). For example, in an obstetrics scenario, the "newborn delivery" event will automatically invoke a task package containing "Apgar score," "umbilical cord management," and "vaccination." In the ICU, the same event will trigger tasks such as "circulatory support," "respiratory management," and "infection prevention and control."

[0307] Medical staff can customize the event-activity-task association logic through a visual rule editor. For example, they can bind a "patient fall" event to activities such as "injury assessment," "family communication," and "safety hazard investigation," and set the time window and resource requirements for task execution.

[0308] S104 , based on the medical data of the target user, the standardized nursing activity set, and the nursing task set of each nursing activity, the target clinical event is instantiated using the target event template to generate a full-cycle nursing task for the target clinical event.

[0309] Through the hierarchical modeling technology of events, activities, and tasks, various trigger conditions in clinical scenarios are converted into quantifiable event nodes, and automatically decomposed into standardized activities and execution tasks based on event logic. Compared with the traditional static task allocation model, this application realizes the transformation of nursing tasks from "manual experience driven" to "event rule driven". For example, when the system detects abnormal vital signs of patients (triggering events), it can automatically associate "emergency assessment" activities and generate specific tasks such as "bedside monitoring", "medication verification", and "indicator retesting", and synchronously match the responsible nurse with the execution time, thereby improving the efficiency of task generation, avoiding the response delay problem caused by manual missed judgment and wrong judgment, and significantly enhancing the flexibility of task scheduling in complex clinical scenarios.

[0310] Furthermore, the full-cycle nursing task for the target clinical event is assigned to the corresponding executor (such as a nurse), and the executor is notified through the system. The executor can receive the task information on a mobile terminal or workstation and start to perform the task.

[0311] Furthermore, a status label of "to be executed - in progress - completed - abnormal" is set for each task, and information such as the task start / end time, execution steps, and abnormal reasons are recorded to form a traceable digital twin log. For example, the timeline view can intuitively identify timed tasks, and the transparency of task execution is improved by 90%. The system automatically calculates indicators such as task completion rate, abnormal event incidence rate, and nurse load rate, and displays the overall picture of ward task execution through the BI dashboard. For example, by analyzing the delayed data of "blood glucose monitoring tasks" in a department for three consecutive days, the root causes such as equipment failure or unreasonable staff scheduling are located. Experience accumulation and knowledge reuse: Expert experience is converted into a reusable task template library. For example, the "acute left heart failure rescue" event is broken down into 12 standard activities and 36 execution tasks, so that junior nurses can complete difficult nursing tasks through system guidance.

[0312] In summary, in this embodiment, the medical data of the target user in the preset medical institution is obtained; event identification is performed based on the medical data of the target user and the trigger conditions of at least one preset clinical event associated with each clinical nursing business scenario in multiple clinical nursing business scenarios; if the trigger conditions of the target clinical event associated with the clinical nursing business scenario are matched, the target event template corresponding to the target clinical event is loaded, and the standardized nursing activity set corresponding to the target clinical event and the nursing task set of each nursing activity under the standardized nursing activity set are extracted from the target event template; based on the medical data of the target user, the standardized nursing activity set and the nursing task set of each nursing activity, the target clinical event is instantiated using the target event template to generate a full-cycle nursing task for the target clinical event. Thus, through the hierarchical modeling technology of events, activities and tasks, various trigger conditions in the clinical scenario are converted into quantifiable event nodes, and automatically decomposed into standardized activities and execution tasks based on event logic, thereby improving the efficiency and quality of nursing work, reducing the cost of generating nursing tasks, and providing patients with more personalized and accurate nursing services.

[0313] In another embodiment of the present application, the embodiment of the present application also provides a method for loading a target event template corresponding to a target clinical event. Figure 2 A flow chart of a method for loading a target event template corresponding to a target clinical event provided in an embodiment of the present application. Figure 2 As shown, the target event template corresponding to the target clinical event loaded in S103 includes:

[0314] S201. Acquire event trigger information of a target clinical event.

[0315] The event trigger information includes: target event type, event trigger time, and associated patient ID.

[0316] Each target clinical event has a corresponding event type, and the event type corresponding to the target clinical event can be obtained according to the target clinical event.

[0317] S202: According to the event triggering information of the target clinical event, load an event template corresponding to the event triggering information as a target event template.

[0318] Based on the target event type, a corresponding event template is retrieved. First, the scope of event templates is narrowed. Then, from the event templates corresponding to the target event type, the event template that matches the event trigger time and associated patient ID is retrieved as the target event template. Using the event template corresponding to the target event type is more accurate and efficient in executing the target clinical event. Specifically, the target clinical event is matched with a template in the event template library. If a match is successful, the corresponding event template is loaded.

[0319] For example, if the triggered target clinical event is "the patient returns to the ward after surgery", the target event template that will be matched is "postoperative care event template".

[0320] In summary, in this embodiment, event trigger information of a target clinical event is obtained; based on the event trigger information of the target clinical event, an event template corresponding to the event trigger information is loaded as the target event template. Thus, by loading the corresponding event module, the target clinical event can be processed more accurately and efficiently.

[0321] In another embodiment of the present application, the embodiment of the present application further provides a method for determining a target event template from at least two event templates. Figure 3 The present invention provides a flow chart of a method for determining a target event template from at least two event templates. Figure 3 As shown, in S202, based on the event trigger information of the target clinical event, the event template corresponding to the event trigger information is loaded as the target event template, including:

[0322] S301. According to event triggering information of a target clinical event, obtain an event template corresponding to the event triggering information.

[0323] Each event triggering information corresponds to at least one event template, and the corresponding event template can be obtained according to the event triggering information.

[0324] S302: If the event templates corresponding to the event triggering information are at least two event templates, obtain first event association information of the target user from the medical data of the target user.

[0325] For example, the first event-related information includes at least: the department and condition score of the target user.

[0326] S303: Determine and load a target event template from at least two event templates according to the first event association information of the target user.

[0327] According to the first event association information of the target user, an event template that best matches the first event association information is determined from at least two event templates as the target event template.

[0328] The specific determination method is not limited here. For example, a value is assigned and calculated based on the correlation between the first event correlation information and the event template, and the event template with the highest correlation score is determined as the target event template.

[0329] In summary, in this embodiment, based on the event trigger information of the target clinical event, the event template corresponding to the event trigger information is obtained. If the event trigger information corresponds to at least two event templates, the target user's first event association information is obtained from the target user's medical data. Based on the target user's first event association information, the target event template is determined and loaded from the at least two event templates. Thus, the target event template is accurately determined from the at least two event templates.

[0330] In another embodiment of the present application, the embodiment of the present application also provides a method for generating a full-cycle nursing task for a target clinical event. Figure 4 A flow chart of a method for generating a full cycle nursing task for a target clinical event provided in an embodiment of the present application. Figure 4 As shown, in S104, based on the medical data of the target user, the standardized nursing activity set, and the nursing task set of each nursing activity, the target clinical event is instantiated using the target event template to generate a full-cycle nursing task for the target clinical event, including:

[0331] S401: Acquire the second event association information of the target user and the real-time status parameters of the target user from the medical data of the target user.

[0332] For example, the second event association information may be: the target user is allergic to drug A. The real-time status parameter of the target user may be: the blood sugar level of the target user.

[0333] S402: Screen the standardized nursing activity set and the nursing task set of each nursing activity in sequence according to the second event association information to obtain a target nursing activity set and a target nursing task under the target nursing activity set.

[0334] For example, if the target user is allergic to drug A, tasks related to the use of drug A will be excluded.

[0335] S403: Calculate task parameters for each target nursing task under the target nursing activity set according to the real-time status parameters to obtain task parameters for each target nursing task.

[0336] The task parameters for each target care task are dynamically calculated based on the target user's real-time status parameters. For example, for a "blood sugar monitoring task," the next monitoring interval is determined based on the target user's diet, exercise status, and current blood sugar level. This interval is the task parameter.

[0337] S404: Generate a full-cycle nursing task for the target clinical event based on the task parameters of each target nursing task.

[0338] As can be seen from the above steps, the task parameters of each target nursing task are calculated dynamically in real time. Therefore, dynamic generation of full-cycle nursing tasks for target clinical events makes nursing tasks more timely and accurate.

[0339] In summary, in this embodiment, the target user's second event association information and real-time status parameters are obtained from the target user's medical data. Based on the second event association information, the standardized nursing activity set and the nursing task set of each nursing activity are sequentially screened to obtain the target nursing activity set and the target nursing tasks under the target nursing activity set. Based on the real-time status parameters, task parameters are calculated for each target nursing task under the target nursing activity set to obtain the task parameters of each target nursing task. Based on the task parameters of each target nursing task, a full-cycle nursing task for the target clinical event is generated. This makes nursing tasks more timely and accurate.

[0340] In another embodiment of the present application, in S404, a full-cycle nursing task for a target clinical event is generated based on the task parameters of each target nursing task, including:

[0341] According to the correlation between each target nursing task, the task parameters of the target-related tasks in each target nursing task are adjusted to generate a full-cycle nursing task for the target clinical event.

[0342] Furthermore, the relationship between tasks is considered and the parameters of related tasks are adjusted collaboratively. For example, when performing the "insulin injection task", the insulin injection dosage will be adjusted based on the results of the "blood sugar monitoring task".

[0343] In summary, in this embodiment, based on the association between target nursing tasks, the task parameters of the target-associated tasks in each target nursing task are adjusted to generate a full-cycle nursing task for the target clinical event. This makes the nursing task more timely and accurate.

[0344] In another embodiment of the present application, the embodiment of the present application also provides a method for generating a task execution queue corresponding to a full-cycle nursing task. Figure 5 A flow chart of a method for generating a task execution queue corresponding to a full cycle nursing task provided in an embodiment of the present application. Figure 5 As shown, the method further includes:

[0345] S501. According to each nursing task in the full-cycle nursing task, the resources of the preset medical institution are matched to obtain the resource matching parameters of each nursing task, wherein the resource matching parameter package of each nursing task includes: matching information of the human resources corresponding to each nursing task, and status information of the corresponding equipment resources.

[0346] Matching nursing tasks with the resources of medical institutions (human resources, equipment resources). Manpower needs will be reasonably allocated based on factors such as nurses' skill level and workload.

[0347] S502. Schedule each nursing task in the full-cycle nursing task according to its preset task priority, execution time constraint, dependency between tasks, and resource matching parameters, and generate a task execution queue corresponding to the full-cycle nursing task.

[0348] Nursing tasks are sorted based on preset task priorities, execution time constraints, dependencies between tasks, and resource matching parameters, ensuring that high-priority tasks are executed first. At the same time, dependencies between tasks are considered to ensure that tasks are executed in the correct order.

[0349] In summary, in this embodiment, the resources of the preset medical institutions are matched according to each nursing task in the full-cycle nursing task to obtain the resource matching parameters of each nursing task. The resource matching parameters of each nursing task include: matching information of the human resources corresponding to each nursing task, and status information of the corresponding equipment resources; according to the preset task priority, execution time constraint, dependency relationship between tasks, and resource matching parameters of each nursing task in the full-cycle nursing task, each nursing task in the full-cycle nursing task is scheduled to generate the task execution queue corresponding to the full-cycle nursing task. Thus, the task execution queue corresponding to the full-cycle nursing task is accurately determined.

[0350] In another embodiment of the present application, the embodiment of the present application also provides a method for generating a task execution queue according to priority weight parameters. Figure 6 The flowchart of a method for generating a task execution queue according to priority weight parameters provided in an embodiment of the present application is as follows. Figure 6As shown, in S502, each nursing task in the full cycle nursing task is scheduled according to the preset task priority, execution time constraint, dependency between tasks, and resource matching parameters of each nursing task in the full cycle nursing task, and a task execution queue corresponding to the full cycle nursing task is generated, including:

[0351] S601. Obtain nursing risk parameters of the target user based on the target user's medical data.

[0352] For example, the MEWS scoring mechanism is used to perform risk assessment on the medical data of the target user to obtain the nursing risk parameters of the target user.

[0353] S602: Based on the nursing risk parameters of the target user, the execution time constraints of each nursing task, and the resource matching parameters, a preset reinforcement learning model is used to determine the priority weight parameters of each nursing task.

[0354] For example, the preset reinforcement learning model is the PPO (Proximal Policy Optimization) algorithm. The nursing risk parameter of the target user, the execution time constraint of each nursing task, and the resource matching parameter are input into the PPO algorithm, and the PPO algorithm outputs the priority weight parameter of each nursing task.

[0355] S603. Schedule each nursing task according to the priority weight parameter of each nursing task, the preset task priority of each nursing task, and the dependency relationship between tasks, and generate a task execution queue corresponding to the full-cycle nursing task.

[0356] According to the priority weight parameters of each nursing task, the preset task priority of each nursing task and the dependency relationship between tasks, the nursing tasks are sorted, the order of each nursing task is determined, and the task execution queue corresponding to the full-cycle nursing task is generated.

[0357] Thus, the system can optimize the task queue in real time based on event priority, resource occupancy status, and task execution feedback. For example, when an emergency surgery event is triggered, the system automatically raises the priority of perioperative nursing tasks to the highest level, suspends non-urgent tasks, and reallocates resources. The task scheduling time is shortened from 10-15 minutes in the traditional mode to 1-2 minutes. During the execution of the task, if abnormal situations such as drug shortages and equipment failures occur, the system captures the abnormal signal in real time and triggers backup plans (such as switching to alternative drugs and deploying nearby equipment). At the same time, it pushes early warning information to the responsible nurses and managers, shortening the abnormal handling response time by more than 60%. This mechanism effectively solves the drawbacks of the "one-size-fits-all" execution model in traditional task management, ensuring that nursing resources are always focused on high-value tasks and reducing safety risks caused by rigid processes.

[0358] In summary, in this embodiment, the target user's nursing risk parameters are obtained based on their medical data. A preset reinforcement learning model is used to determine the priority weight parameters of each nursing task based on the target user's nursing risk parameters, the execution time constraints of each nursing task, and the resource matching parameters. Based on the priority weight parameters of each nursing task, the preset task priorities of each nursing task, and the dependencies between tasks, each nursing task is scheduled to generate a task execution queue corresponding to the full-cycle nursing task. This allows the task execution queue corresponding to the full-cycle nursing task to be accurately determined.

[0359] In another embodiment of the present application, the embodiment of the present application also provides a method for obtaining an event template for each preset clinical event. Figure 7 A flow chart of a method for obtaining an event template for each preset clinical event provided in an embodiment of the present application. Figure 7 As shown, before performing event identification in S102 based on the medical data of the target user and the triggering condition of at least one preset clinical event associated with each clinical nursing business scenario in multiple clinical nursing business scenarios, the method further includes:

[0360] S701. Configure scenarios through a visual configuration interface to obtain multiple clinical business scenarios.

[0361] Pre-organize multiple clinical business scenarios to ensure full coverage. Configure scenarios through a visual configuration interface. Regularly update clinical business scenarios to ensure effectiveness.

[0362] S702: Perform clinical event configuration for each clinical nursing business scenario through a visual configuration interface to obtain at least one preset clinical event associated with each clinical nursing business scenario.

[0363] Each clinical care scenario is associated with at least one pre-set clinical event, and each pre-set clinical event can be associated with multiple clinical care scenarios. Clinical events and their associations are regularly updated to ensure effectiveness.

[0364] S703. Configure each preset clinical event through a visual configuration interface to obtain an event template for each preset clinical event. The event template for each preset clinical event includes: an event template identifier, an event template name, an associated clinical event identifier, a trigger condition for the associated clinical event, an associated nursing activity set, and a task set for each nursing activity in the nursing activity set.

[0365] The event templates for clinical events are updated regularly to ensure effectiveness.

[0366] In summary, in this embodiment, scenario configuration is performed through a visual configuration interface to obtain multiple clinical business scenarios; clinical event configuration is performed for each clinical nursing business scenario through the visual configuration interface to obtain at least one preset clinical event associated with each clinical nursing business scenario; and each preset clinical event is configured through the visual configuration interface to obtain an event template for each preset clinical event. Each event template for each preset clinical event includes: an event template identifier, an event template name, an associated clinical event identifier, a trigger condition for the associated clinical event, an associated nursing activity set, and a task set for each nursing activity in the nursing activity set. Thus, configuration through the visual configuration interface ensures full scenario coverage and effectiveness.

[0367] In another embodiment of the present application, the method further includes:

[0368] Obtain generation effect evaluation parameters for the full-cycle nursing tasks for the target clinical event; based on the generation effect evaluation parameters, update the event template of the target clinical event, the standardized nursing activity set corresponding to the target clinical event, and the nursing task set of each nursing activity under the standardized nursing activity set.

[0369] During the execution of a task, the executor provides real-time feedback on the task's execution status (such as task start time, completion time, and execution results). The task's status is updated based on the execution status, and subsequent tasks are dynamically adjusted. For example, if an exception occurs during the execution of a task, the system will re-evaluate the task's priority and execution order, and may generate a new task (such as an emergency task).

[0370] The effectiveness of task generation is regularly evaluated, and event templates, standardized nursing activity sets, and nursing task sets are updated based on the evaluation parameters. For example, if resource conflicts are frequently observed for a certain type of task, the resource requirements or scheduling strategy for that task will be adjusted.

[0371] Therefore, with the help of task execution tracking and feedback technology, the system digitally records the entire life cycle of tasks from generation, allocation, execution to archiving, forming a traceable task execution log. By collecting task start / end time, executors, operation steps and abnormal data in real time, managers can monitor the progress of ward task execution in real time through a visual dashboard. For example, through the timeline view, they can intuitively identify timed tasks and missed tasks, and the transparency of task execution is improved by more than 90%. Combined with the statistical analysis module, the system automatically generates quality indicators such as task completion rate, abnormal event rate, and nurse load rate to provide data support for nursing management decisions. For example, by analyzing the delayed data of "blood sugar monitoring tasks" in a department for three consecutive days, the root causes such as equipment failure or unreasonable staff scheduling can be located, and the process can be optimized in a targeted manner to promote continuous improvement of nursing quality.

[0372] In summary, in this embodiment, generation effect evaluation parameters for the full-cycle nursing task for a target clinical event are obtained; based on the generation effect evaluation parameters, the event template for the target clinical event, the standardized nursing activity set corresponding to the target clinical event, and the nursing task sets for each nursing activity under the standardized nursing activity set are updated. This ensures the timeliness and accuracy of the tasks.

[0373] In another embodiment of the present application, the embodiment of the present application also provides a method for displaying nursing events. Figure 8 This is a flow chart of a method for displaying nursing events provided in an embodiment of the present application. Figure 8 As shown, the method further includes:

[0374] S801. Display a nursing event list of a target user in the first area of ​​an event management page.

[0375] For example, the left side of the main page of the event management page displays a list of nursing events in the form of cards. The card information includes but is not limited to the name, status, occurrence time and other information of the nursing event. If it is a surgical event, the surgical name information is also displayed.

[0376] S802. Display the activity set corresponding to the selected nursing event in the nursing event list, the status of each activity in the corresponding activity set, and the task set corresponding to the selected event in the corresponding activity set in the second area of ​​the event management page.

[0377] For example, the center section of the event management page displays the corresponding activity set for the event, with icons indicating the activity status. Activities can be expanded to view the corresponding task set, enabling monitoring of the execution of event tasks. Additionally, activities can be manually changed in status, such as from active to completed.

[0378] Furthermore, the main interface presents to-do tasks in a timeline format, with tasks divided into multi-patient and single-patient overviews, allowing nurses to switch between them as needed. Each time node displays all to-do tasks within the corresponding time period, including task name, task type, and estimated execution time.

[0379] Tasks are categorized by type (e.g., medication administration, examination, nursing procedures, etc.), allowing nurses to quickly locate specific tasks using the filtering function. Additionally, tasks can be filtered by status (pending, completed, overdue, etc.), allowing them to focus on tasks in different states.

[0380] Clicking a task on the timeline will pop up a task details preview box, displaying detailed information about the task, such as task description, patient information, execution steps, precautions, etc. Nurses can quickly understand the task status without having to enter the task execution interface.

[0381] Execution Plan Splitting: Each task is broken down into subtasks based on the execution steps, and these subtasks are also arranged chronologically on the timeline. For example, a medication task can be broken down into subtasks such as medication collection, medication verification, medication administration, and record keeping. Each subtask has a clearly defined planned execution time. Different task types support different execution methods, including but not limited to text-based measures, nursing documentation, and structured data entry, as mentioned above.

[0382] During the task execution process, the system updates the task status and progress in real time, and nursing staff can check the task execution status at any time.

[0383] As the scheduled execution time of a task approaches, the system will remind the caregiver to perform the task through pop-up windows, sounds, etc. For tasks that have not been completed on time, the system will continue to remind them and mark them as overdue so that management personnel can intervene in time.

[0384] S803. Display the statistical analysis results of the execution data corresponding to the selected nursing event in the third area of ​​the event management page.

[0385] Conduct statistical analysis on event execution data, such as event completion rate, task execution time distribution, abnormal event rate, etc. Users can evaluate the effectiveness of event management based on statistical results and optimize nursing processes and resource allocation.

[0386] It provides a visual nursing task execution page, which combines the timeline view with structured task classification, can dynamically match the standardized execution path, and reduce the cognitive load and human omissions of operators during task execution.

[0387] Thus, through human-computer interaction and visualization technology, the system uses multi-dimensional views such as timeline, Gantt chart, and task heat map to present task information. Nursing staff can manage tasks through convenient interactive methods such as dragging, filtering, and batch operations. For example, in the timeline view, different colors mark task types (medication / nursing operation / education), and flashing reminders indicate that the task is about to be performed. Clicking on the task card can view the patient's basic information, execution steps and precautions, which improves operational efficiency by more than 40%; it supports personalized configuration of interface layout, reminder methods and data display dimensions to adapt to the work habits of nurses of different seniority and reduce operational errors caused by complex interfaces. This design significantly reduces the cognitive load of nursing staff, allowing them to focus more on the clinical operations themselves, improving work experience and task execution accuracy.

[0388] In summary, in this embodiment, the first area of ​​the event management page displays the target user's nursing event list; the second area of ​​the event management page displays the activity set corresponding to the selected nursing event in the nursing event list, the status of each activity in the corresponding activity set, and the task set corresponding to the selected event in the corresponding activity set; and the third area of ​​the event management page displays the statistical analysis results of the execution data corresponding to the selected nursing event. Thus, the management of events, activities, and tasks can be displayed in multiple ways.

[0389] The following describes the dynamic generation device, equipment, and storage medium for executing the full-scene nursing tasks provided by this application. The specific implementation process and technical effects are described above and will not be repeated below.

[0390] Figure 9 This is a schematic diagram of a dynamic generation device for full-scenario nursing tasks provided by an embodiment of the present application. Figure 9 As shown, the device includes:

[0391] The acquisition module 901 is used to acquire the medical data of the target user in the preset medical institution.

[0392] The identification module 902 is used to perform event identification based on the medical data of the target user and the triggering condition of at least one preset clinical event associated with each clinical nursing business scenario in multiple clinical nursing business scenarios.

[0393] The extraction module 903 is used to load the target event template corresponding to the target clinical event if it is identified that the trigger conditions of the target clinical event associated with the clinical nursing business scenario match, and extract the standardized nursing activity set corresponding to the target clinical event and the nursing task set of each nursing activity under the standardized nursing activity set from the target event template.

[0394] The generation module 904 is used to instantiate the target clinical event using the target event template based on the medical data of the target user, the standardized nursing activity set and the nursing task set of each nursing activity, and generate a full-cycle nursing task for the target clinical event.

[0395] Furthermore, the extraction module 903 is specifically configured to obtain event triggering information of the target clinical event; and according to the event triggering information of the target clinical event, load an event template corresponding to the event triggering information as a target event template.

[0396] Furthermore, the extraction module 903 is specifically used to obtain the event template corresponding to the event trigger information based on the event trigger information of the target clinical event; if the event template corresponding to the event trigger information is at least two event templates, the first event association information of the target user is obtained from the medical data of the target user; based on the first event association information of the target user, the target event template is determined and loaded from at least two event templates.

[0397] Furthermore, the generation module 904 is specifically used to obtain the second event association information of the target user and the real-time status parameters of the target user from the medical data of the target user; according to the second event association information, the standardized nursing activity set and the nursing task set of each nursing activity are screened in turn to obtain the target nursing activity set and the target nursing task under the target nursing activity set; according to the real-time status parameters, the task parameters of each target nursing task under the target nursing activity set are calculated to obtain the task parameters of each target nursing task; according to the task parameters of each target nursing task, a full-cycle nursing task for the target clinical event is generated.

[0398] Furthermore, the generating module 904 is specifically configured to adjust the task parameters of the target-associated tasks in each target nursing task according to the association relationship between each target nursing task, and generate a full-cycle nursing task for the target clinical event.

[0399] Furthermore, the generation module 904 is also used to match the resources of the preset medical institutions according to each nursing task in the full-cycle nursing task, and obtain the resource matching parameters of each nursing task, wherein the resource matching parameter package of each nursing task includes: matching information of human resources corresponding to each nursing task, and status information of corresponding equipment resources; according to the preset task priority, execution time constraint, dependency relationship between tasks and resource matching parameters of each nursing task in the full-cycle nursing task, each nursing task in the full-cycle nursing task is scheduled to generate a task execution queue corresponding to the full-cycle nursing task.

[0400] Furthermore, the generation module 904 is specifically used to obtain the nursing risk parameters of the target user based on the medical data of the target user; based on the nursing risk parameters of the target user, the execution time constraints of each nursing task and the resource matching parameters, a preset reinforcement learning model is used to determine the priority weight parameters of each nursing task; based on the priority weight parameters of each nursing task, the preset task priority of each nursing task and the dependency relationship between tasks, each nursing task is scheduled to generate a task execution queue corresponding to the full-cycle nursing task.

[0401] Furthermore, the generation module 904 is also used to configure scenarios through a visual configuration interface to obtain multiple clinical business scenarios; configure clinical events for each clinical nursing business scenario through the visual configuration interface to obtain at least one preset clinical event associated with each clinical nursing business scenario; configure each preset clinical event through the visual configuration interface to obtain an event template for each preset clinical event, and the event template for each preset clinical event includes: an event template identifier, an event template name, an associated clinical event identifier, a trigger condition for the associated clinical event, an associated nursing activity set, and a task set for each nursing activity in the nursing activity set.

[0402] Furthermore, the acquisition module 901 is also used to obtain the generation effect evaluation parameters of the full-cycle nursing tasks for the target clinical event; based on the generation effect evaluation parameters, the event template of the target clinical event, the standardized nursing activity set corresponding to the target clinical event, and the nursing task set of each nursing activity under the standardized nursing activity set are updated.

[0403] Furthermore, generation module 904 is also used to display the nursing event list of the target user through the first area of ​​the event management page; display the activity set corresponding to the selected nursing event in the nursing event list, the status of each activity in the corresponding activity set, and the task set corresponding to the selected event in the corresponding activity set through the second area of ​​the event management page; and display the statistical analysis results of the execution data corresponding to the selected nursing event through the third area of ​​the event management page.

[0404] Figure 10 A schematic diagram of an Internet of Vehicles server provided in an embodiment of the present application, which may be a device with computing and processing capabilities.

[0405] The Internet of Vehicles server includes: a processor 1001 and a storage medium 1002. The processor 1001 and the storage medium 1002 are connected via a bus.

[0406] The storage medium 1002 is used to store programs, and the processor 1001 calls the programs stored in the storage medium 1002 to execute the above method embodiment. The specific implementation methods and technical effects are similar and will not be repeated here.

[0407] Optionally, the present application also provides a storage medium, including a program, which is used to execute the above-mentioned method embodiment when executed by a processor. In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units 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 interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0408] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0409] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0410] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (English: Read-Only Memory, abbreviated: ROM), a random access memory (English: Random Access Memory, abbreviated: RAM), a magnetic disk or an optical disk, and other media that can store program code.

Claims

1. A method for dynamically generating nursing tasks in all scenarios, characterized in that: The method comprises: Obtain medical data of target users in preset medical institutions; Performing event identification based on the medical data of the target user and a trigger condition of at least one preset clinical event associated with each clinical nursing business scenario in a plurality of clinical nursing business scenarios; If it is identified that the trigger condition of the target clinical event associated with the clinical nursing business scenario matches, the target event template corresponding to the target clinical event is loaded, and the standardized nursing activity set corresponding to the target clinical event and the nursing task set of each nursing activity under the standardized nursing activity set are extracted from the target event template; According to the medical data of the target user, the standardized nursing activity set and the nursing task set of each nursing activity, the target clinical event is instantiated using the target event template to generate a full-cycle nursing task for the target clinical event.

2. The method according to claim 1, characterized in that The loading of the target event template corresponding to the target clinical event includes: Obtaining event trigger information of the target clinical event; According to the event triggering information of the target clinical event, an event template corresponding to the event triggering information is loaded as the target event template.

3. The method according to claim 2, characterized in that The step of loading, according to the event triggering information of the target clinical event, an event template corresponding to the event triggering information as the target event template comprises: According to the event triggering information of the target clinical event, obtaining an event template corresponding to the event triggering information; If the event template corresponding to the event triggering information is at least two event templates, obtaining the first event association information of the target user from the medical data of the target user; According to the first event association information of the target user, the target event template is determined and loaded from the at least two event templates.

4. The method according to claim 1, wherein The step of instantiating the target clinical event using the target event template based on the target user's medical data, the standardized nursing activity set, and the nursing task set of each nursing activity to generate a full-cycle nursing task for the target clinical event includes: Acquire the second event-related information of the target user and the real-time status parameters of the target user from the medical data of the target user; According to the second event association information, the standardized nursing activity set and the nursing task set of each nursing activity are sequentially screened to obtain a target nursing activity set and a target nursing task under the target nursing activity set; Calculating task parameters for each target nursing task under the target nursing activity set according to the real-time status parameters to obtain task parameters for each target nursing task; According to the task parameters of each target nursing task, a full-cycle nursing task for the target clinical event is generated.

5. The method according to claim 4, characterized in that Generating a full-cycle nursing task for the target clinical event according to the task parameters of each target nursing task includes: According to the association relationship between each of the target nursing tasks, the task parameters of the target associated tasks in each of the target nursing tasks are adjusted to generate a full-cycle nursing task for the target clinical event.

6. The method according to claim 1, characterized in that The method further comprises: According to each nursing task in the full-cycle nursing task, the resources of the preset medical institution are matched to obtain resource matching parameters of each nursing task, wherein the resource matching parameters of each nursing task include: matching information of human resources corresponding to each nursing task, and status information of corresponding equipment resources; According to the preset task priority, execution time constraint, dependency between tasks and resource matching parameters of each nursing task in the full-cycle nursing task, each nursing task in the full-cycle nursing task is scheduled to generate a task execution queue corresponding to the full-cycle nursing task.

7. The method according to claim 6, characterized in that The method of scheduling each nursing task in the full-cycle nursing task according to the preset task priority, execution time constraint, dependency between tasks, and resource matching parameters of each nursing task in the full-cycle nursing task to generate a task execution queue corresponding to the full-cycle nursing task includes: Acquiring nursing risk parameters of the target user based on the medical data of the target user; Determine the priority weight parameters of each nursing task using a preset reinforcement learning model according to the nursing risk parameter of the target user, the execution time constraint of each nursing task, and the resource matching parameter; According to the priority weight parameters of each nursing task, the preset task priority of each nursing task and the dependency relationship between the tasks, each nursing task is scheduled to generate a task execution queue corresponding to the full-cycle nursing task.

8. The method according to claim 1, characterized in that Before performing event identification based on the medical data of the target user and a trigger condition of at least one preset clinical event associated with each clinical nursing business scenario in a plurality of clinical nursing business scenarios, the method further includes: Configure scenarios through the visual configuration interface to obtain multiple clinical business scenarios; Performing clinical event configuration on each clinical nursing business scenario through the visual configuration interface to obtain the at least one preset clinical event associated with each clinical nursing business scenario; Each preset clinical event is configured through the visual configuration interface to obtain an event template for each preset clinical event. The event template for each preset clinical event includes: an event template identifier, an event template name, an associated clinical event identifier, a trigger condition for the associated clinical event, an associated nursing activity set, and a task set for each nursing activity in the nursing activity set.

9. The method according to claim 1, characterized in that The method further comprises: Obtain generation effect evaluation parameters for the full-cycle nursing tasks for the target clinical event; based on the generation effect evaluation parameters, update the event template of the target clinical event, the standardized nursing activity set corresponding to the target clinical event, and the nursing task set of each nursing activity under the standardized nursing activity set.

10. The method according to claim 1, characterized in that The method further comprises: Displaying a nursing event list of the target user in the first area of ​​the event management page; Displaying, via the second area of ​​the event management page, an activity set corresponding to a selected nursing event in the nursing event list, a status of each activity in the corresponding activity set, and a task set corresponding to the selected event in the corresponding activity set; The statistical analysis results of the execution data corresponding to the selected nursing event are displayed in the third area of ​​the event management page.

Images