Nurse handover management system and method

Abstract

The invention relates to a nurse handover management system and method, and relates to the technical field of data processing, and the system comprises a real-time monitoring module which is used for constructing an individualized baseline database of a patient; the data integration module is used for outputting a multi-dimensional structured data set; the intelligent analysis engine is used for identifying clinical state change information of the patient and generating a corresponding risk early warning score; the decision support module is used for generating targeted nursing intervention suggestions; the interactive shift exchange platform is used for generating a structured shift exchange abstract based on the risk early warning score, the clinical change information and the nursing intervention suggestion, and dynamically displaying the structured shift exchange abstract through a mixed reality technology; and the closed-loop optimization module is used for receiving shift-change feedback information and subsequent execution data of the shift-change party, evaluating the completeness of shift-change information, updating a nursing plan, and optimizing and adjusting analysis and recommendation parameters of the system. The system can improve the accuracy and efficiency of nurse handover management.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a nurse shift handover management system, method, electronic device, and non-transient computer-readable storage medium. Background Art

[0002] In nurses' daily work, shift handover is a crucial step in ensuring nursing continuity and patient safety. Currently, hospitals generally use paper handover records, electronic medical record excerpts, or verbal reports for nursing handovers. Typically, the nurse on the previous shift briefly briefs the nurse on the next shift on the patient's basic information, changes in the patient's condition, nursing measures, medication usage, and precautions.

[0003] However, traditional oral handovers rely on the subjective judgment and memory of nurses, which carries risks such as omissions and miscommunication, especially when the handover staff is inexperienced or the patient's condition is complex. Furthermore, while electronic systems have improved information retrieval efficiency, they still primarily display static data and lack intelligent recognition and highlighting of key patient changes. Summary of the Invention

[0004] The present invention addresses the technical problems existing in the prior art and provides a nurse shift handover management system, method, electronic device and non-transitory computer-readable storage medium that can improve the accuracy and efficiency of nurse shift handover management.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: The present invention provides a nurse shift handover management system, the system comprising: Real-time monitoring module, used to collect patients' vital signs data, medical equipment operation data and activity status data to build a personalized baseline database for patients; A data integration module is used to integrate the baseline database with the patient's electronic medical record information and nursing record text to output a multi-dimensional structured data set; An intelligent analysis engine, configured to perform intelligent analysis on the structured data set, identify changes in the patient's clinical status, and generate corresponding risk warning scores; A decision support module, configured to generate targeted nursing intervention recommendations based on the risk warning score and the clinical change information in combination with a preset nursing knowledge graph; An interactive handover platform, configured to generate a structured handover summary based on the risk warning score, the clinical change information, and the nursing intervention recommendations, and dynamically display the summary through mixed reality technology; The closed-loop optimization module is used to receive handover feedback information and subsequent execution data from the successor, evaluate the completeness of the handover information, update the nursing plan, and optimize and adjust the analysis and recommended parameters of the system.

[0006] Optionally, the real-time monitoring module includes: a wearable device unit, configured to continuously collect activity status data and sleep quality data of the patient; an adaptive threshold unit, configured to dynamically adjust an alarm threshold of the medical device based on the baseline database; The data preprocessing unit is used to filter the collected original monitoring data and correct abnormal values, and send the corrected data to the data integration module.

[0007] Optionally, the data integration module is configured to: Receiving pre-processed data output by the real-time monitoring module; Parsing the nursing record text using a natural language processing engine and extracting key clinical entity information; The multi-source data are aligned according to a unified time axis to generate the structured data set.

[0008] Optionally, the intelligent analysis engine includes: a time series analysis unit, configured to process the structured data set using a long short-term memory neural network model to identify fluctuation trends in the patient's vital signs; a risk calculation unit, configured to calculate and generate a quantitative risk score based on the clinical status change information; The false positive suppression unit is used to optimize the triggering logic of risk alerts based on historical false positive records and reduce the false positive rate.

[0009] Optionally, the decision support module is configured to: receiving the risk warning score and the clinical status change information; Matching the corresponding nursing path node in the preset nursing knowledge graph; Combined with the evidence-based nursing rule library, a set of nursing recommendations including nursing diagnosis, nursing goals and intervention measures is generated.

[0010] Optionally, the interactive handover platform includes: A summary generator, configured to encode the risk warning score, the clinical status change information, and the nursing intervention suggestion into hierarchical structured text to generate the structured shift handover summary; A mixed reality rendering engine for dynamically marking the patient's wound location and tube arrangement on a three-dimensional human body model; The voice interaction interface is used to respond to the voice query command of the successor and expand the detailed information level in the structured handover summary.

[0011] Optionally, the interactive handover platform includes: A scene adaptation unit is used to automatically switch between bedside, nurse station, or remote handover display modes based on positioning information; A qualifications adaptation unit, configured to automatically adjust the complexity of medical terms in the handover content based on the identity information of the successor; The collaborative interaction unit is used to support multiple users to simultaneously view and operate the virtual ward view through augmented reality devices.

[0012] Optionally, the closed-loop optimization module includes: A feedback verification unit, configured to store, via blockchain, a record of the successor's reading and confirmation of the structured handover summary; Execution tracking unit, used to compare actual nursing operations with planned tasks and generate execution deviation data; A parameter optimization unit is used to adjust the model parameters of the intelligent analysis engine based on the execution deviation data to achieve system performance optimization.

[0013] Optionally, the system further includes a self-learning engine, wherein the self-learning engine is configured to: Collect data on the nursing staff's adoption or rejection of the nursing intervention suggestions; Performing reinforcement learning updates on the path nodes in the nursing knowledge graph based on the adoption status; The latest clinical care guidelines are introduced regularly to update the rule base content in the decision support module.

[0014] The present invention also provides a nurse shift management method, the method comprising: Collect patients' vital signs data, medical equipment operation data, and activity status data to build a personalized baseline database for patients; Fusing the baseline database with the patient's electronic medical record information and nursing record text to output a multi-dimensional structured data set; Performing intelligent analysis on the structured data set to identify changes in the patient's clinical status and generate corresponding risk warning scores; Based on the risk warning score and the clinical change information, combined with a preset nursing knowledge graph, targeted nursing intervention suggestions are generated; Generate a structured handover summary based on the risk warning score, the clinical change information, and the nursing intervention suggestion, and dynamically display it through mixed reality technology; Receive handover feedback information and subsequent execution data from the successor, evaluate the completeness of the handover information, update the nursing plan, and optimize and adjust the analysis and recommended parameters of the system.

[0015] In addition, to achieve the above-mentioned purpose, the present invention also proposes an electronic device, comprising: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby implementing a nurse shift management method as described above.

[0016] In addition, to achieve the above-mentioned purpose, the present invention also proposes a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, a nurse shift management method as described above is implemented.

[0017] The beneficial effects of the present invention are: (1) This invention introduces real-time collection and structured integration of multi-source data to ensure that the handover content covers key clinical data such as patients' vital signs, equipment status, and behavioral patterns, effectively reducing information omissions and subjective expression deviations.

[0018] (2) The present invention uses a time series deep learning model to analyze the fluctuation trend of vital signs, and combines it with an individualized baseline database to build a refined risk scoring mechanism, which can identify clinically predictive subtle changes in advance and improve the initiative and foresight of nursing work.

[0019] (3) The present invention automatically recommends nursing measures based on the nursing knowledge graph and evidence-based rule base, avoiding reliance on experience, making the nursing plan more targeted and verifiable, and at the same time improving the clinical judgment ability of young nurses or non-specialist nurses.

[0020] In summary, the present invention not only significantly improves the scientificity, systematicness and safety of the nursing handover process, but also lays a technical foundation for the construction of smart nursing, digital wards and clinical decision-making support platforms, and has broad prospects for promotion and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A scene diagram of a nurse shift handover management method provided by the present invention; Figure 2 This is a structural diagram of a nurse shift handover management system provided by the present invention; Figure 3 A flowchart of a nurse shift management method provided by the present invention; Figure 4 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention; Figure 5A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0024] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0025] See also Figure 1 , Figure 1 This is a scene diagram of a nurse shift management method provided by the present invention. Figure 1 As shown, the terminal and server are connected via a network, such as a wired or wireless network. Terminals include, but are not limited to, portable devices such as mobile phones and tablets installed with various network platform applications, as well as fixed devices such as computers, kiosks, and advertising machines. The server provides various business services to users, including service push servers and user recommendation servers.

[0026] It should be noted that Figure 1The scenario diagram of a nurse shift handover management method shown is only an example. The terminal, server, and application scenario described in the embodiment of the present invention are intended to more clearly illustrate the technical solution of the embodiment of the present invention, and do not generate any limitation on the technical solution provided by the embodiment of the present invention. Ordinary technicians in this field can know that with the evolution of the system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present invention is also applicable to similar technical problems.

[0027] Among them, the terminal can be used to: Collect patients' vital signs data, medical equipment operation data, and activity status data to build a personalized baseline database for patients; Fusing the baseline database with the patient's electronic medical record information and nursing record text to output a multi-dimensional structured data set; Performing intelligent analysis on the structured data set to identify changes in the patient's clinical status and generate corresponding risk warning scores; Based on the risk warning score and the clinical change information, combined with a preset nursing knowledge graph, targeted nursing intervention suggestions are generated; Generate a structured handover summary based on the risk warning score, the clinical change information, and the nursing intervention suggestion, and dynamically display it through mixed reality technology; Receive handover feedback information and subsequent execution data from the successor, evaluate the completeness of the handover information, update the nursing plan, and optimize and adjust the analysis and recommended parameters of the system.

[0028] See also Figure 2 , Figure 2 This is a structural diagram of a nurse shift handover management system provided by the present invention.

[0029] like Figure 2 As shown, a nurse shift handover management system proposed in an embodiment of the present invention includes: The real-time monitoring module 201 is used to collect the patient's vital signs data, medical equipment operation data and activity status data to build a personalized baseline database for the patient; The data integration module 202 is used to integrate the baseline database with the patient's electronic medical record information and nursing record text to output a multi-dimensional structured data set; Intelligent analysis engine 203, configured to perform intelligent analysis on the structured data set, identify the patient's clinical status change information, and generate a corresponding risk warning score; A decision support module 204 is configured to generate targeted nursing intervention recommendations based on the risk warning score and the clinical change information in combination with a preset nursing knowledge graph; An interactive handover platform 205 is used to generate a structured handover summary based on the risk warning score, the clinical change information, and the nursing intervention suggestion, and dynamically display it through mixed reality technology; The closed-loop optimization module 206 is used to receive handover feedback information and subsequent execution data from the successor, evaluate the integrity of the handover information, update the nursing plan, and optimize and adjust the analysis and recommended parameters of the system.

[0030] In some embodiments, the real-time monitoring module 201 includes: a wearable device unit, configured to continuously collect activity status data and sleep quality data of the patient; an adaptive threshold unit, configured to dynamically adjust an alarm threshold of the medical device based on the baseline database; The data pre-processing unit is used to filter and correct abnormal values ​​of the collected original monitoring data, and send the corrected data to the data integration module 202.

[0031] In a specific implementation, the real-time monitoring module 201 can be used for continuous, multi-dimensional status perception and data collection of patients. It is the data source entrance of this system. Its structure includes a wearable device unit, which is equipped with a group of distributed wearable sensor devices, including but not limited to accelerometers, heart rate belts, body movement monitoring belts, skin thermometers and sleep monitoring rings, etc., which can be worn on the patient's wrist, chest or waist.

[0032] The unit continuously collects the following patient status data: daytime activity level (such as number of steps, frequency of body position changes); nighttime sleep parameters (such as duration of falling asleep, number of tossing and turning, sleep stages); emotion-related physiological signals (such as heart rate variability), etc.

[0033] The collected data can be uploaded to the central processing node via Bluetooth, ZigBee, Wi-Fi or other low-power wireless communication methods, and written into the patient's individualized baseline database within a certain period for subsequent intelligent comparison and risk detection.

[0034] The adaptive threshold unit can be used to dynamically adjust the alarm parameter setting values ​​of bedside equipment (such as ECG monitors, infusion pumps, and ventilators) based on the patient's historical data and current individual status.

[0035] For example, when a patient's heart rate is low but stable at night, the unit can automatically increase the lower heart rate alarm threshold to avoid false alarms due to individual differences.

[0036] Its working mechanism includes: extracting representative resting indicators from the baseline database; calculating the currently applicable device threshold based on set rules or machine learning models; and writing the new threshold into the corresponding device parameter setting module through an interface protocol (such as HL7, Modbus, etc.).

[0037] This unit can significantly reduce the "alarm fatigue" of nursing staff caused by frequent false alarms, and improve the accuracy and practicality of the system's overall response.

[0038] The data preprocessing unit is responsible for ensuring the quality of the raw data collected by the above sensors and devices, mainly including: Filtering: Use algorithms such as Kalman filtering, wavelet denoising, or median filtering to remove signal noise caused by physical jitter, electromagnetic interference, etc. Outlier correction: Discrete values ​​caused by occasional sensor drift, packet loss, etc. are corrected through sliding window averaging, interpolation repair, or Z-score methods; Timestamp alignment: Different data sources have inconsistent time formats. This unit can unify timestamp accuracy and complete preliminary synchronization to ensure the temporal consistency of data integration.

[0039] The processed data will be passed to the data integration module 202 as cleaned structured input for subsequent feature extraction and multimodal fusion analysis.

[0040] In some embodiments, the data integration module 202 is configured to: Receiving pre-processed data output by the real-time monitoring module 201; Parsing the nursing record text using a natural language processing engine and extracting key clinical entity information; The multi-source data are aligned according to a unified time axis to generate the structured data set.

[0041] In a specific implementation, the data integration module 202 is used to uniformly structure data from multiple sources to construct a multi-dimensional, time-consistent patient clinical data set, providing a solid foundation for subsequent intelligent analysis and handover summary generation. This module is configured to include the following functional components: The data receiving and management component is connected to the real-time monitoring module 201 and continuously receives the pre-processed data output by it, including but not limited to: vital sign parameters (such as heart rate, blood pressure, blood oxygen saturation, etc.); equipment operating status (such as ventilator ventilation mode, infusion flow rate); behavioral data (such as activity level, sleep score, etc.).

[0042] All received data are accompanied by a timestamp and source identification. After entering the system, they are automatically stored in a temporary buffer area according to preset rules, providing a scheduling basis for subsequent integration processing.

[0043] The text parsing and information extraction component targets the large amount of unstructured text data in nursing documents. This module integrates a natural language processing (NLP) engine and is configured with Chinese word segmentation, named entity recognition (NER), part-of-speech tagging, and context analysis models. Specific operations include: Perform semantic analysis on electronic medical records, nursing records, oral transcription records, etc. Key clinical entities related to nursing care were extracted, such as symptoms (fever, cough), events (fall, extubation), and nursing measures (positioning change, catheterization); The extracted results are mapped to standard medical terminology systems (such as ICNP and SNOMED CT) and structured tags are attached (such as time, event subject, intensity and other meta-information).

[0044] This component significantly improves the utilization efficiency of unstructured text data and provides more comprehensive data support for intelligent analysis engines.

[0045] Since the acquisition frequencies and formats of various data types vary significantly, the multi-source timing alignment and fusion component implements the time alignment and unified encoding of asynchronous data, including: Map sensor data, device data, and text entity information to a unified timeline and merge them using a time window partitioning strategy (e.g., 1 minute / 5 minutes). For event-type data (such as falls and alarms), an event-driven insertion mechanism is used to anchor them as specific nodes in the time series; Construct a multidimensional structured dataset, whose typical structure is: [timestamp, data type, data value, source label, credibility indicator], and support subsequent feature extraction and modeling.

[0046] The module can also be extended to support healthcare data interoperability standards such as FHIR to facilitate integration with hospital information systems (HIS) or regional health platforms.

[0047] In summary, the data integration module 202 achieves efficient fusion and standardized expression of multi-source heterogeneous clinical data through structural unification, semantic extraction and time sequence alignment, and is the core bridge module connecting original monitoring information and intelligent analysis logic.

[0048] In some embodiments, the intelligent analysis engine 203 includes: a time series analysis unit, configured to process the structured data set using a long short-term memory neural network model to identify fluctuation trends in the patient's vital signs; a risk calculation unit, configured to calculate and generate a quantitative risk score based on the clinical status change information; The false positive suppression unit is used to optimize the triggering logic of risk alerts based on historical false positive records and reduce the false positive rate.

[0049] In specific implementation, the intelligent analysis engine 203, as the core intelligent computing module of this system, is responsible for in-depth modeling and dynamic analysis of the integrated multi-dimensional structured clinical data. It mainly includes the following three functional units: The time series analysis unit is used to model and identify trends in time series indicators (such as heart rate, respiratory rate, body temperature, blood pressure, and blood oxygen) in structured data sets. Its key features are as follows: The LSTM neural network model can effectively handle time dependencies and nonlinear changes in long-sequence data, and is particularly suitable for capturing potential delayed responses and periodic patterns in vital signs. Input features include, but are not limited to, multi-parameter data sequences within the current moment and historical windows (e.g., heart rate per minute over the past hour). Outputs include: trend predictions for key indicators (e.g., a possible upward trend in heart rate); identification of potential abnormal patterns (e.g., acute declines, periodic instability); and support for establishing model weight parameters based on individual patients to achieve personalized predictive adaptability. This unit significantly improves the system's sensitivity to early changes in disease status, providing a dynamic feature foundation for subsequent risk assessment.

[0050] The risk calculation unit calculates the patient's current health risk score based on trend change information generated by time-series analysis, combined with variables such as severity factors, medical history, and nursing compliance. Specifically, it constructs a multifactorial risk scoring model with input features such as the slope of vital sign changes, threshold crossing frequency, behavioral changes (such as decreased movement), and intervention response. The output is a quantitative risk score (e.g., 0-100), which is categorized as normal (0-20), concern (21-50), warning (51-80), and high-risk (81-100). A "risk contribution analysis" can be further output, indicating the contribution of each feature to the current score, helping nursing staff understand the sources of risk. This unit provides clear quantitative criteria for handover information, facilitating clinical prioritization and target selection.

[0051] To avoid frequent false positives caused by model allergies, the false positive suppression unit introduces a false positive identification and optimization mechanism with the following functions: Based on the system's historical alarm records and nursing staff's confirmation feedback, identify and record alarm samples that "did not actually lead to nursing intervention" and build a false alarm sample library; Reinforcement learning mechanisms or rule-updating logic are used to dynamically adjust alarm thresholds and trigger conditions. Specifically, this includes adjusting the sensitivity of the warning thresholds in the model output; optimizing feature weights to reduce sensitivity to occasional fluctuations that are clinically insignificant; and supporting the setting of individual adaptive false alarm filtering rules, such as customizing hypotension tolerance for specific patients. This unit effectively reduces "alarm fatigue" and improves the credibility and clinical adoption of system risk alerts.

[0052] In summary, the intelligent analysis engine 203 realizes continuous assessment of patient status, dynamic early warning and stability control through deep time series modeling, multi-factor scoring and alarm optimization mechanism, and is the key supporting module for the system to realize intelligent nursing handover.

[0053] In some embodiments, the decision support module 204 is configured to: receiving the risk warning score and the clinical status change information; Matching the corresponding nursing path node in the preset nursing knowledge graph; Combined with the evidence-based nursing rule library, a set of nursing recommendations including nursing diagnosis, nursing goals and intervention measures is generated.

[0054] In specific implementations, the decision support module 204 is used to generate scientific, individualized, and structured nursing recommendations based on the risk scores and status change information output by the intelligent analysis engine, combined with the preset professional knowledge map and evidence-based rule base. It is a key reasoning module that connects clinical intelligent identification and action execution. This module is configured to include the following functional components: The risk reception and status analysis component is used to receive the following outputs from the intelligent analysis engine 203: the patient's current risk warning score (e.g., a quantitative score or risk level); and clinical status change information associated with the score, such as abnormal vital sign trends, behavioral changes, and alarm triggering events. By analyzing the score value and status change parameters, this component can determine the patient's current health level and their stage in the care pathway (e.g., postoperative recovery day N, stable chronic disease stage, etc.).

[0055] The nursing knowledge graph matching component loads and calls the preset nursing knowledge graph, which consists of a semantic network consisting of "specialized diseases - symptoms - nursing measures - nursing goals" and has the following functions: Based on the feature labels corresponding to the state changes, the matching nodes are located in the knowledge graph to identify the most relevant nursing scenario path for the current patient. For example, when the state change is "continuously elevated heart rate + second day after surgery", it can be matched to the "early identification of postoperative infection" path. Considering the logical relationship, path weight and confidence between the nodes in the graph, the optimal reasoning path is selected, and multi-path intersection is supported. The matching results include recommended nursing questions (diagnosis), priority goals (expected state) and optional intervention sets (such as operation, observation, and record).

[0056] This component improves the system's understanding and reasoning capabilities of clinical semantics, enabling care recommendations to be based on professional knowledge rather than simply on statistical data.

[0057] The evidence-based rule fusion and recommendation generation component is used to combine the knowledge graph matching results with the content in the evidence-based nursing rule library to ultimately form a structured set of nursing recommendations, including: Retrieve research evidence, clinical guidelines, and operational standards (e.g., evidence-based levels A / B / C) from the evidence-based database that match the current nursing problem; compare current patient data with evidence-based adaptation conditions to screen out feasible interventions that are suitable for the institution's conditions. The output content is structured into the following three categories: Nursing diagnosis: such as "pain", "potential risk of infection"; Nursing goals: such as "maintaining normal body temperature within 48 hours after surgery" and "restoring autonomous urination function"; Nursing intervention measures: such as "measure body temperature every 4 hours, record and report abnormalities", "assist with turning over and encourage deep breathing", etc.

[0058] The set of recommendations can be adapted and tailored based on the patient's cultural background, nursing staff level, and implementation resources, supporting hierarchical classification and implementation priority sorting.

[0059] In summary, the decision support module 204 realizes intelligent, structured, and individualized nursing advice recommendations for specific patients through a combination mechanism of semantic matching, knowledge graph reasoning, and evidence-based fusion generation, significantly improving the scientificity, pertinence, and guidance of nursing handovers.

[0060] In some embodiments, the interactive handover platform 205 includes: A summary generator, configured to encode the risk warning score, the clinical status change information, and the nursing intervention suggestion into hierarchical structured text to generate the structured shift handover summary; A mixed reality rendering engine for dynamically marking the patient's wound location and tube arrangement on a three-dimensional human body model; The voice interaction interface is used to respond to the voice query command of the successor and expand the detailed information level in the structured handover summary.

[0061] In specific implementation, the interactive handover platform 205 is the core human-computer interaction module in the nursing handover process. It combines structured information display technology, mixed reality visualization, and voice recognition interaction to achieve intuitive presentation and intelligent acquisition of multi-dimensional handover information. It mainly includes the following three functional components: The summary generator is used to integrate the results from the intelligent analysis engine 203 and the decision support module 204 and encode them into a hierarchical handover text summary. The specific functions include: Content integration and coding: Automatically call data elements such as risk warning scores, clinical status change information, and nursing intervention recommendations, and perform field mapping and hierarchical classification based on the set summary template; for example, "Score: 83 (high risk)", "Event: Continuous increase in body temperature on the first day after surgery", and "Recommendation: Focus on observing wound exudation" can be structured as follows: ①

Key concerns

Trend change

[0062] Through this component, nurses can obtain structured and focused handover content in a short time, improving understanding efficiency and handover quality.

[0063] The mixed reality rendering engine is used to spatially visualize key physiological and nursing information in the shift summary, including: 3D human body modeling: Automatically generate a 3D human body model based on the patient's gender, height, and body shape data, and allow loading of personalized appearance features; Dynamic information labeling: The patient's wound site, tubes (such as intravenous infusion, urinary catheter, drainage tube, etc.) and key nursing locations are highlighted in a layered manner; for example: "Drainage tube outlet" is marked on the left abdomen, and the color code shows "exudation↑"; "Infusion tube" is marked on the right wrist, and "Frequent alarms" are displayed; Real-time switching of view levels: supports switching from the overview layer (whole body distribution map) to the detail layer (local wound surface map), and can overlay historical photos, nursing record diagrams, etc. Multi-terminal adaptation: Compatible with AR glasses, tablets and nursing workstations, supporting bedside display and remote handover modes.

[0064] This component significantly improves the spatial understanding and intuitiveness of the handover process, reduces textual misunderstandings, and is particularly suitable for complex cases or ICU scenarios.

[0065] The voice interaction interface, as an intelligent query and control module, supports natural language interaction between caregivers and the system through voice commands. Its main functions include: Speech recognition and command parsing: An integrated speech recognition engine (supporting Chinese) converts the voice instructions of the successor into control commands in real time; Example commands include: "Show the wound condition on the left leg", "Expand the temperature change trend", "What is the patient's recent medication record?"; Information hierarchical expansion and follow-up question response: Automatically expand the corresponding shift summary according to instructions, and support related question tracking (multi-round interaction); Identity identification and terminology adaptation: Adjust the professional depth of the response content based on the successor's identity (e.g., student nurse / specialist nurse), and add terminology explanations or recommended reading links when necessary; Voice review and memory tracking: Record the query path and key points during the handover process for handover quality assessment and knowledge base construction.

[0066] This interface lowers the operational threshold and improves the immediacy and pertinence of information acquisition during shift handovers. It is particularly suitable for mobile operations or scenarios where both hands are busy.

[0067] In summary, the interactive handover platform 205 has achieved a leap from static expression to dynamic cognition in the handover mode through the collaborative design of structured summary generation, mixed reality visualization presentation and voice interactive query, significantly improving the efficiency, accuracy and security of information transmission.

[0068] In some embodiments, the interactive handover platform 205 includes: A scene adaptation unit is used to automatically switch between bedside, nurse station, or remote handover display modes based on positioning information; A qualifications adaptation unit, configured to automatically adjust the complexity of medical terms in the handover content based on the identity information of the successor; The collaborative interaction unit is used to support multiple users to simultaneously view and operate the virtual ward view through augmented reality devices.

[0069] In a specific implementation, in order to adapt to the actual handover requirements of multiple scenarios and multiple roles in clinical nursing work, the interactive handover platform 205 further includes the following three intelligent adaptation and collaboration sub-modules: The scene adaptation unit is used to automatically switch the information display mode according to the positioning information or equipment usage scenario during the handover process to adapt to the handover methods in different spatial environments. Specifically, it includes: Positioning information acquisition: Integrate Bluetooth beacons, UWB tags, or Wi-Fi triangulation to identify whether the current user is at the bedside of the ward, the nurse station work area, or a remote access terminal outside the hospital.

[0070] Adaptive adjustment of the display interface: Bedside mode: Patient-centered, emphasizing pipeline location, daily events, and equipment parameters, with a simple and intuitive interface; Nurse station mode: Supports parallel display of multiple patient information, highlighting risk warning rankings and nursing task allocation; Remote mode: Focuses on overview and interactivity, combined with voice query and video assistance to facilitate multi-point collaborative participation; Input and output mode switching: Switches the operation method according to the scenario, such as gestures, voice, clicks, sliding and other multi-modal input methods are automatically enabled.

[0071] This unit enhances the flexibility of the system, enabling the handover platform to adapt to different clinical application scenarios such as mobile work, centralized reporting, and remote ward rounds.

[0072] The qualification adaptation unit is used to dynamically adjust the information expression level and terminology complexity in the handover content based on the professional qualifications and professional level of the successor, including: Identity recognition mechanism: Confirm the identity of the person handing over the shift through user login information, IC card authentication or facial recognition, and extract their professional background data (such as whether they are specialist nurses, nurse interns, training nurses, etc.); Terminology adjustment strategy: For experienced nurses: retain professional terms and technical details (e.g., "CAPD catheter access abnormality"); for interns or multidisciplinary nurses: use simplified expressions and add terminology explanations (e.g., "Peritoneal dialysis catheter abnormality: pay attention to outlet exudate"); Personalized learning assistance prompts: For unfamiliar terms or care pathways, the system can pop up explanation links, knowledge graph node overviews, or training video recommendations.

[0073] This module enhances the comprehensibility and adaptability of the handover platform, and is particularly suitable for high-mobility and highly heterogeneous nursing team environments.

[0074] The collaborative interaction unit supports multiple users to access the handover system at the same time, and collaborate to view, discuss and operate virtual ward information in the same virtual space through augmented reality (AR) or virtual reality (VR) technology. Specifically, it includes: building a collaborative environment for the virtual ward: building a virtual space shared by multiple users to display the three-dimensional distribution, pipeline layout, nursing matters, etc. of the patients currently on handover.

[0075] Synchronous operation mechanism: multiple people can click, mark, ask questions, and annotate at the same time; it supports command broadcast mechanism, and the main nurse can guide the view focus to move.

[0076] Multi-terminal support and synchronization mechanism: supports collaborative access of AR glasses, mobile tablets, and desktop touch devices; achieves real-time synchronization of data views and status changes, ensuring that multiple people obtain consistent information.

[0077] Collaborative recording and replay function: records the interaction process and key feedback for nursing quality tracking and teaching review.

[0078] This unit significantly improves the team collaboration efficiency during the handover process, and is particularly suitable for multiple-party rapid handover scenarios such as operating rooms, intensive care units (ICUs), and emergency rescue.

[0079] In summary, the interactive handover platform 205 realizes the intelligent adaptation and collaborative control of handover content and interface by introducing mechanisms such as scene perception, user qualification recognition and multi-person interactive collaboration, promotes the evolution of the nursing handover process from "one-way statement" to "immersive collaboration", and further enhances the safety, standardization and visual management capabilities of nursing work.

[0080] In some embodiments, the closed-loop optimization module 206 includes: A feedback verification unit, configured to store, via blockchain, a record of the successor's reading and confirmation of the structured handover summary; Execution tracking unit, used to compare actual nursing operations with planned tasks and generate execution deviation data; A parameter optimization unit is used to adjust the model parameters of the intelligent analysis engine 203 based on the execution deviation data to achieve system performance optimization.

[0081] In specific implementation, the closed-loop optimization module 206 is a key module for achieving nursing handover quality supervision and system self-evolution tuning. Through full-process feedback collection, actual execution tracking, and dynamic updating of model parameters, a continuous optimization mechanism for the handover system is established. It includes the following three functional units: The feedback verification unit is used to ensure the validity of the handover information received and the traceability of responsibilities. Its main functions include: Reading confirmation mechanism: After the successor views the structured handover summary through the interactive handover platform 205, the system automatically records the reading behavior (such as completion time, click level, voice query content, etc.); Blockchain evidence storage: Introducing a consortium chain or private chain mechanism to generate an unalterable data hash for each reading confirmation operation; the evidence content includes: successor ID, handover time, summary content version number, reading completion mark, interactive summary trajectory, etc.; all confirmation records are saved according to the time chain structure to ensure that the information transmission process is "verifiable, traceable, and verifiable"; abnormal prompt function: If the confirmation process is not completed, or the successor does not browse the key information items, the system will automatically remind and record the abnormal handover risk prompt.

[0082] This unit ensures the compliance and transparency of the handover process, and prevents nursing risks caused by missing information or misunderstandings.

[0083] The execution tracking unit is used to compare and analyze planned nursing tasks with actual execution behaviors, identify execution deviations and track the causes. Its main functions include: Nursing task plan call: extract the nursing items that need to be performed (such as dressing change, temperature monitoring, turning, drainage observation, etc.) from the handover summary or nursing plan system; Actual execution behavior collection: Collect nursing behavior data through electronic record systems (NIS), mobile nursing terminals, IoT devices or sensor interfaces to extract operation time, performers, frequency, completion status, etc. Deviation analysis and classification: Compare task requirements with actual execution and generate execution deviation reports (e.g., non-execution, delayed execution, insufficient frequency, etc.). Deviations are categorized and labeled (e.g., system misjudgment, manual oversight, resource limitations, etc.) and fed back to the optimization engine. Abnormal closed-loop reminder: If a high-priority nursing task is not performed, a closed-loop reminder will be automatically sent to the responsible nurse or head nurse.

[0084] The unit has built a closed-loop chain of "planning-execution-verification" after the shift handover to ensure that key nursing operations are not missed or delayed.

[0085] The parameter optimization unit dynamically updates the model parameters in the intelligent analysis engine 203 based on the aforementioned execution deviation data to achieve adaptive optimization of system performance. Its main functions include: Model bias detection and evaluation: Analyze the deviation between risk score results and actual nursing execution and patient status, identify model prediction errors or unreasonable phenomena; establish an error matrix (such as high score and low intervention, high score and low event) to evaluate model performance.

[0086] Parameter adjustment mechanism: Fine-tune key parameters (such as learning rate, feature weight, and time window) in deep models such as LSTM and attention mechanism; adjust the path matching weight, alarm threshold, and recommendation algorithm priority of the decision support module; and support iterative training of systems based on reinforcement learning.

[0087] Local adaptive optimization: Based on the characteristics of specific hospitals, departments or patient groups, local historical data can be loaded to perform local model retraining to achieve personalized model customization.

[0088] Through this unit, the system can continuously "learn-adapt-optimize" in actual operation, continuously improving the accuracy of risk warnings and the applicability of nursing recommendations.

[0089] The closed-loop optimization module 206 constructs a full-process feedback path from information transmission, task execution to the intelligent engine through a three-layer mechanism of reading confirmation, execution tracking, and model re-optimization, so that the system not only has the ability of "intelligent recommendation", but also has the characteristics of "self-evolution", and achieves "more accurate with use, more stable with delivery" in continuous operation.

[0090] In some embodiments, the system further comprises a self-learning engine configured to: Collect data on the nursing staff's adoption or rejection of the nursing intervention suggestions; Performing reinforcement learning updates on the path nodes in the nursing knowledge graph based on the adoption status; The latest clinical care guidelines are introduced regularly to update the rule base content in the decision support module 204.

[0091] In its specific implementation, the system further includes a self-learning engine, which serves as the long-term learning and dynamic evolution module of the handover system. It is configured to extract effective learning samples from the actual feedback of nursing staff, optimize the nursing knowledge graph structure and decision support rules, and thus improve the accuracy, practicality and adaptability of nursing recommendations. The self-learning engine includes the following three functional components: The Nursing Suggestion Adoption Behavior Collection Component is used to collect the nursing staff's response behavior to the nursing intervention suggestions provided by the system during the shift execution phase. It mainly includes: Adoption / rejection marking mechanism: During the implementation of the nursing plan, nurses can choose to "adopt", "adopt after modification", or "reject" the nursing suggestions recommended by the system through mobile terminals or interactive interfaces; for the operation of rejecting the suggestions, the system can pop up an auxiliary selection menu to record the subjective reasons (such as "not applicable", "patient's condition is stable", "insufficient supplies", etc.).

[0092] Behavior logging: Automatically records metadata such as operation time, user identity, patient status, shift, and suggested content version; binds each adopted behavior to its corresponding clinical context to build a structured feedback dataset.

[0093] This component ensures that the system can "see" the nurses' true judgments and collect dynamic feedback data from front-line nursing work as model learning samples.

[0094] The knowledge graph reinforcement learning update component is used to perform reinforcement learning optimization on the "disease-symptom-intervention" path nodes in the nursing knowledge graph based on adoption behavior data. Specifically, it includes: Adoption behavior scoring mechanism: Assign adoption weights to each nursing pathway node in the knowledge graph, and make weighted corrections based on indicators such as adoption frequency, feedback timeliness, and number of rejections. The weights of nodes in pathways with high adoption frequency increase, while the weights of connections in pathways with low adoption or frequent rejection decrease or are marked as nodes requiring review.

[0095] Path structure optimization: Reinforcement learning algorithms (such as Q-learning and policy gradient) are introduced to iteratively update the path selection strategy; optimize the transition probability between nodes, the path recommendation order, and the combination structure of intervention measures.

[0096] Scenario-specific adaptation: Based on the source context of the adopted data (such as ICU, internal medicine, night shift, postoperative period, etc.), scenario-adaptive sub-graphs are trained to achieve localized evolution and refined matching of the graph in different clinical environments.

[0097] This component enables the system's knowledge structure to no longer statically rely on expert rules, but to continuously iterate and optimize with clinical practice, making it more in line with real workflows.

[0098] The rule base dynamic update component is responsible for maintaining the timeliness and scientificity of the evidence-based rule base content in the decision support module 204 and supports synchronization with external clinical standards. Its main functions include: Guideline subscription and interface docking: The system regularly accesses the nursing guideline database published by the state or authoritative institutions, such as the "China Clinical Nursing Practice Guidelines", "AACN Critical Care Protocols", "NICE Clinical Guidance", etc.; parses the latest guideline content through the API interface or regular import mechanism, and extracts the recommendation level, applicable conditions and clinical intervention points.

[0099] Rule fusion and conflict detection mechanism: Conduct consistency analysis with existing rules and provide manual review prompts for conflicting content; set version control for specific rules and support the coexistence of multiple versions to facilitate internal evidence-based comparison within the organization.

[0100] Post-update evaluation and adoption monitoring mechanism: After the update, track the actual adoption effect and feedback of the new rules, judge their applicability and acceptance, and reversely modify the rule parameters.

[0101] This component ensures that care recommendations are always based on the latest evidence and industry standards, ensuring that the system has the ability to continuously "learn medicine."

[0102] The self-learning engine in this application realizes the transformation of the intelligent system from "static recommendation" to "dynamic evolution" by collecting clinical practice feedback, strengthening nursing knowledge paths, and automatically integrating the latest guidelines. It ensures that the system continuously optimizes its own logic, adapts to different scenarios, and conforms to user habits in actual operation. It is the core supporting module for realizing the long-term sustainable intelligence of the intelligent nursing handover system.

[0103] See also Figure 3 , provides a flowchart of a nurse shift management method of the present invention, comprising the following steps: Step 301: Collect the patient's vital signs data, medical equipment operation data, and activity status data to build a personalized baseline database for the patient; Fusing the baseline database with the patient's electronic medical record information and nursing record text to output a multi-dimensional structured data set; Performing intelligent analysis on the structured data set to identify changes in the patient's clinical status and generate corresponding risk warning scores; Based on the risk warning score and the clinical change information, combined with a preset nursing knowledge graph, targeted nursing intervention suggestions are generated; Generate a structured handover summary based on the risk warning score, the clinical change information, and the nursing intervention suggestion, and dynamically display it through mixed reality technology; Receive handover feedback information and subsequent execution data from the successor, evaluate the completeness of the handover information, update the nursing plan, and optimize and adjust the analysis and recommended parameters of the system.

[0104] It should be noted that, for the specific implementation and beneficial effects of the above steps 301-306, please refer to the above description of modules 201-206, which will not be repeated here.

[0105] See also Figure 4 , Figure 4 Schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented: Collect patients' vital signs data, medical equipment operation data, and activity status data to build a personalized baseline database for patients; Fusing the baseline database with the patient's electronic medical record information and nursing record text to output a multi-dimensional structured data set; Performing intelligent analysis on the structured data set to identify changes in the patient's clinical status and generate corresponding risk warning scores; Based on the risk warning score and the clinical change information, combined with a preset nursing knowledge graph, targeted nursing intervention suggestions are generated; Generate a structured handover summary based on the risk warning score, the clinical change information, and the nursing intervention suggestion, and dynamically display it through mixed reality technology; Receive handover feedback information and subsequent execution data from the successor, evaluate the completeness of the handover information, update the nursing plan, and optimize and adjust the analysis and recommended parameters of the system.

[0106] See also Figure 5 , Figure 5 Schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 5 As shown, this embodiment provides a computer-readable storage medium 500 on which a computer program 411 is stored. When the computer program 411 is executed by a processor, the following steps are implemented: Collect patients' vital signs data, medical equipment operation data, and activity status data to build a personalized baseline database for patients; Fusing the baseline database with the patient's electronic medical record information and nursing record text to output a multi-dimensional structured data set; Performing intelligent analysis on the structured data set to identify changes in the patient's clinical status and generate corresponding risk warning scores; Based on the risk warning score and the clinical change information, combined with a preset nursing knowledge graph, targeted nursing intervention suggestions are generated; Generate a structured handover summary based on the risk warning score, the clinical change information, and the nursing intervention suggestion, and dynamically display it through mixed reality technology; Receive handover feedback information and subsequent execution data from the successor, evaluate the completeness of the handover information, update the nursing plan, and optimize and adjust the analysis and recommended parameters of the system.

[0107] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0108] Those skilled in the art will appreciate that embodiments of the present invention may be provided as systems, methods, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or boxes.

[0110] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system that is implemented in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0112] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0113] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A nurse shift handover management system, characterized in that: The system comprises: Real-time monitoring module, used to collect patients' vital signs data, medical equipment operation data and activity status data to build a personalized baseline database for patients; A data integration module is used to integrate the baseline database with the patient's electronic medical record information and nursing record text to output a multi-dimensional structured data set; An intelligent analysis engine, configured to perform intelligent analysis on the structured data set, identify changes in the patient's clinical status, and generate corresponding risk warning scores; A decision support module, configured to generate targeted nursing intervention recommendations based on the risk warning score and the clinical change information in combination with a preset nursing knowledge graph; An interactive handover platform, configured to generate a structured handover summary based on the risk warning score, the clinical change information, and the nursing intervention recommendations, and dynamically display the summary through mixed reality technology; The closed-loop optimization module is used to receive handover feedback information and subsequent execution data from the successor, evaluate the completeness of the handover information, update the nursing plan, and optimize and adjust the analysis and recommended parameters of the system.

2. The nurse shift management system according to claim 1, characterized in that: The real-time monitoring module includes: a wearable device unit, configured to continuously collect activity status data and sleep quality data of the patient; an adaptive threshold unit, configured to dynamically adjust an alarm threshold of the medical device based on the baseline database; The data preprocessing unit is used to filter the collected original monitoring data and correct abnormal values, and send the corrected data to the data integration module.

3. The nurse shift management system according to claim 2, characterized in that: The data integration module is configured to: Receiving pre-processed data output by the real-time monitoring module; Parsing the nursing record text using a natural language processing engine and extracting key clinical entity information; The multi-source data are aligned according to a unified time axis to generate the structured data set.

4. The nurse shift management system according to claim 3, characterized in that: The intelligent analysis engine includes: a time series analysis unit, configured to process the structured data set using a long short-term memory neural network model to identify fluctuation trends in the patient's vital signs; a risk calculation unit, configured to calculate and generate a quantitative risk score based on the clinical status change information; The false positive suppression unit is used to optimize the triggering logic of risk alerts based on historical false positive records and reduce the false positive rate.

5. The nurse shift management system according to claim 4, characterized in that: The decision support module is configured to: receiving the risk warning score and the clinical status change information; Matching the corresponding nursing path node in the preset nursing knowledge graph; Combined with the evidence-based nursing rule library, a set of nursing recommendations including nursing diagnosis, nursing goals and intervention measures is generated.

6. The nurse shift handover management system according to claim 5, characterized in that: The interactive handover platform includes: A summary generator, configured to encode the risk warning score, the clinical status change information, and the nursing intervention suggestion into hierarchical structured text to generate the structured shift handover summary; A mixed reality rendering engine for dynamically marking the patient's wound location and tube arrangement on a three-dimensional human body model; The voice interaction interface is used to respond to the voice query command of the successor and expand the detailed information level in the structured handover summary.

7. The nurse shift handover management system according to claim 6, characterized in that: The interactive handover platform includes: A scene adaptation unit is used to automatically switch between bedside, nurse station, or remote handover display modes based on positioning information; A qualifications adaptation unit, configured to automatically adjust the complexity of medical terms in the handover content based on the identity information of the successor; The collaborative interaction unit is used to support multiple users to simultaneously view and operate the virtual ward view through augmented reality devices.

8. The nurse shift handover management system according to claim 7, characterized in that: The closed-loop optimization module includes: A feedback verification unit, configured to store, via blockchain, a record of the successor's reading and confirmation of the structured handover summary; Execution tracking unit, used to compare actual nursing operations with planned tasks and generate execution deviation data; A parameter optimization unit is used to adjust the model parameters of the intelligent analysis engine based on the execution deviation data to achieve system performance optimization.

9. The nurse shift handover management system according to claim 8, characterized in that: The system further includes a self-learning engine configured to: Collect data on the nursing staff's adoption or rejection of the nursing intervention suggestions; Performing reinforcement learning updates on the path nodes in the nursing knowledge graph based on the adoption status; The latest clinical care guidelines are introduced regularly to update the rule base content in the decision support module.

10. A nurse shift management method, characterized in that: The method comprises: Collect patients' vital signs data, medical equipment operation data, and activity status data to build a personalized baseline database for patients; Fusing the baseline database with the patient's electronic medical record information and nursing record text to output a multi-dimensional structured data set; Performing intelligent analysis on the structured data set to identify changes in the patient's clinical status and generate corresponding risk warning scores; Based on the risk warning score and the clinical change information, combined with a preset nursing knowledge graph, targeted nursing intervention suggestions are generated; Generate a structured handover summary based on the risk warning score, the clinical change information, and the nursing intervention suggestion, and dynamically display it through mixed reality technology; Receive handover feedback information and subsequent execution data from the successor, evaluate the completeness of the handover information, update the nursing plan, and optimize and adjust the analysis and recommended parameters of the system.

Images