A Visual IoT Integrated Management Platform

Abstract

This invention discloses a visualized IoT integrated management platform, comprising a device and data acquisition layer, a network and protocol conversion layer, a data processing layer, and a visualization application layer. By leveraging IoT technology, this invention connects patient flow, doctor flow, material flow, and information flow, enabling real-time perception and transparent management of hospital operational status. Through a built-in intelligent analysis engine, it not only achieves post-event statistics but also provides in-process early warning and pre-event prediction, such as early detection of emerging epidemics and prediction of resource bottlenecks. It transforms complex multi-source data into intuitive graphics, charts, and 3D models, significantly reducing management complexity and improving decision-making efficiency.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and in particular to a visual IoT integrated management platform. Background Technology

[0002] With the rapid development of the Internet of Things (IoT), big data, and artificial intelligence technologies, smart healthcare has become an inevitable trend in the modernization of hospital management. Currently, hospitals have multiple independent information systems, such as Hospital Information Systems (HIS), Laboratory Information Systems (LIS), and Picture Archiving and Communication Systems (PACS). These systems often have inconsistent data standards and closed interfaces, forming "information silos." This makes it difficult for hospital management to obtain a comprehensive, real-time, and visualized operational view, hindering efficient resource allocation, epidemic early warning, and continuous improvement of medical quality.

[0003] In existing technologies, some IoT platforms are dedicated to device access and data integration, or provide general device management frameworks. However, most of them focus on industrial or building scenarios and lack in-depth customization for the specific needs of the medical industry. For example, medical scenarios require close integration of patients' full-process diagnosis and treatment data, doctors' behavioral data, and hospital logistical resource data, and multi-dimensional cross-analysis to support clinical decision-making and refined management.

[0004] Therefore, there is an urgent need for an IoT integrated management platform that can connect the entire chain of front-end reception, patient diagnosis and treatment, doctor's work, and back-end operations, and has powerful visualization and intelligent analysis capabilities. Summary of the Invention

[0005] The purpose of this invention is to provide a visual IoT integrated management platform to solve the problems existing in the prior art.

[0006] To achieve the above objectives, the present invention provides the following solution: The present invention provides a visual Internet of Things integrated management platform, including a device and a data acquisition layer, for collecting multi-source heterogeneous data related to hospital operations; including front desk reception data, patient diagnosis and treatment data, doctor work data, and logistics resource data;

[0007] The network and protocol conversion layer is used to access and unify the data protocols and formats uploaded by the device and the data acquisition layer;

[0008] The data platform processing layer is used to integrate, manage, model, and analyze the unified data; it includes a perception data management module, a resource information model construction module, an information management module, and an intelligent analysis engine module.

[0009] The visualization application layer is used to display and interact with the analysis results of the data platform processing layer in a graphical manner in multiple dimensions.

[0010] The intelligent analysis engine module includes an epidemic monitoring submodule, which is used to perform real-time scanning and abnormal clustering early warning of syndrome data throughout the hospital based on time series analysis and spatial clustering algorithms;

[0011] The operations analysis submodule is used to calculate the department's workload and allocate follow-up examination, hospitalization and bed resources to patients based on optimization algorithms;

[0012] The scheduling optimization submodule is used to generate doctor outpatient and surgical scheduling plans based on historical data and real-time needs.

[0013] The network and protocol conversion layer includes an edge computing gateway and a protocol conversion module; the edge computing gateway is deployed near the data source for local data preprocessing and caching; the protocol conversion module supports medical and IoT protocols including HL7, FHIR, DICOM, Modbus and MQTT.

[0014] The resource information model building module is used to create and maintain a hospital digital twin model, which maps physical entities into digital objects with attributes, states, and relationships.

[0015] The visualization application layer provides views including a comprehensive view of the hospital's overall operations, a panoramic view of the patient's entire disease course, a doctor's performance analysis view, and a back-end management decision-making dashboard view.

[0016] The information management module provides unified full lifecycle management functions for devices, gateways, certificates, applications, and users within the platform.

[0017] The present invention discloses the following technical effects: full-element interconnection, through the Internet of Things technology to connect the flow of patients, doctors, materials and information, realizing real-time perception and transparent management of hospital operation status;

[0018] Intelligent decision-making, through its built-in intelligent analysis engine, not only enables post-event statistics but also provides real-time early warnings and pre-event predictions, such as early detection of emerging epidemics and prediction of resource bottlenecks.

[0019] Visual interaction transforms complex multi-source data into intuitive graphics, charts, and 3D models, significantly reducing management complexity and improving decision-making efficiency;

[0020] It is flexible and scalable, adopts a middleware architecture and modular design, can easily connect to new devices and systems through the protocol conversion module, and can quickly develop upper-layer business applications through the application programming interface (API), with good openness and adaptability. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the overall structure of the present invention; Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] This invention provides a visual IoT integrated management platform, including devices and a data acquisition layer, for collecting multi-source heterogeneous data related to hospital operations, including front desk reception data, patient treatment data, doctor work data, and logistics resource data.

[0026] The network and protocol conversion layer is used to access and unify the data protocols and formats uploaded by the device and the data acquisition layer;

[0027] The data platform processing layer is used to integrate, manage, model, and analyze the unified data; it includes a perception data management module, a resource information model construction module, an information management module, and an intelligent analysis engine module.

[0028] The visualization application layer is used to display and interact with the analysis results of the data platform processing layer in a graphical manner in multiple dimensions.

[0029] In a specific embodiment of the present invention, the device and data acquisition layer includes a data acquisition module for connecting to and acquiring heterogeneous data sources from various units of the hospital via wired or wireless means.

[0030] Furthermore, it specifically includes a front-end data collection unit; real-time collection of registration data from registration windows, self-service machines, and online channels, as well as real-time data on patient flow, waiting time, and patient reception status in outpatient and emergency departments.

[0031] Patient data acquisition unit: Collects patients' vital signs, medical records (initial visit / follow-up visit), and historical electronic medical record (EMR) data through IoT sensing devices (such as smart bracelets, bedside terminals), medical device interfaces (such as monitors, testing equipment) and information system interfaces.

[0032] Doctor data collection unit: Collects data on doctors' outpatient visits, single patient treatment time, surgical records, and departmental on-duty status through doctor workstations, mobile terminals, and IoT devices in operating rooms / clinics.

[0033] Environmental and resource data acquisition unit; collects data on bed occupancy rate, medical equipment (such as ventilators and infusion pumps) usage status, drug inventory, and energy consumption.

[0034] In a specific embodiment of this invention, the network and protocol conversion layer includes a protocol conversion module and an edge computing gateway. The protocol conversion module has built-in driver libraries for various communication protocols, supporting RS485, Modbus, BACnet, HL7, FHIR, DICOM, MQTT, HTTP, and others. It uniformly converts heterogeneous data formats uploaded from the acquisition layer into standard data formats within the platform (such as JSON or Protocol Buffers). The edge computing gateway is deployed at the network edge to perform local preprocessing of the raw data (such as filtering, deduplication, and preliminary aggregation) to alleviate the pressure on the core network and data platform.

[0035] In a specific embodiment of the present invention, the perception data management module cleans (de-errors, deduplication, alignment), stores, archives, calculates, parses, and distributes the incoming data stream; this module establishes a unified patient master index, doctor master index, and device master index.

[0036] Furthermore, the resource information model construction module: based on the cyber-physical system concept, constructs a digital twin model of the hospital. This model maps hospital entities in the physical world (patients, doctors, beds, equipment, departments) to computable objects in the information world, and defines their attributes, states, and relationships.

[0037] Furthermore, the information management module, based on the hyperconverged platform concept, performs full lifecycle management of all entities within the platform, including device management, gateway management, certificate management, application management, and user and permission management.

[0038] Furthermore, the intelligent analysis engine module includes an epidemic monitoring submodule; it uses time series analysis (such as the ARIMA model) and clustering algorithms (such as DBSCAN) to perform real-time scanning of syndrome data across the hospital or region, expressed by the formula: Alert = f(Σ(Symptom_i, t), Threshold);

[0039] Here, Symptom_i represents the number of visits for the i-th type of symptom, t is the time window, and an alert is triggered when the aggregated value exceeds the historical baseline threshold Threshold.

[0040] Operational Analysis Submodule: Analyzes monthly data discrepancies and calculates departmental workload.

[0041] Workload = α*(Patient_Count / Avg_Time) + β*Surgery_Complexity; where α and β are weighting coefficients. Based on this, an optimized resource scheduling algorithm is used to allocate follow-up examination time and hospital beds to patients. The objective function is to minimize the average waiting time Min(Σ(Wait_Time_j)).

[0042] The scheduling optimization submodule generates doctor scheduling and surgical arrangement plans based on historical patient data, doctors' expertise, and real-time needs using constrained programming or genetic algorithms.

[0043] In a specific embodiment of the present invention, the visualization application layer includes a comprehensive situation visualization unit; in the form of a hospital digital twin 3D map or a 2D cockpit, it dynamically displays global information such as registration status, number of patients waiting in each department, bed occupancy rate, and doctors' online status.

[0044] Patient Panoramic View Unit: Visually displays the entire disease course timeline of a single patient, integrating initial visit records, follow-up visit records, medical records, examination results, and etiology labels. Provides etiology distribution cloud maps or statistical charts for all patients in the hospital.

[0045] The Physician Performance View unit displays the number of patients seen, average consultation time, and workload curve for individual physicians and their departments.

[0046] The back-end management cockpit unit provides hospital administrators with an epidemic early warning dashboard, a resource allocation suggestion panel (such as bed prediction and equipment allocation), and tools for editing and simulating doctor scheduling.

[0047] In one embodiment of the present invention, the platform further includes an epidemic monitoring method, specifically including the following steps: S1: Extracting syndrome visit data from the data platform within a specified time window, with the department as the spatial unit and time as the dimension;

[0048] S2: Using the spatial-temporal scanning statistical method, calculate the likelihood ratio between the observed value and the expected value for each spatial-temporal unit;

[0049] S3: Determine the significance threshold through Monte Carlo simulation, and mark the cells with a likelihood ratio exceeding the threshold as anomalous clusters;

[0050] S4: Generate warning information and highlight it in the background management dashboard of the visualization application layer.

[0051] In one embodiment of the present invention, the platform further includes a resource scheduling method, which specifically includes the following steps: S1: Aggregating real-time bed, equipment and medical staff status data reported by edge nodes of each ward;

[0052] S2: Construct a resource scheduling optimization model with the objective function of minimizing the average patient waiting time and the constraints of department capacity, physician expertise, and treatment continuity.

[0053] S3: Solve the optimization model to obtain the patient-to-bed allocation scheme and doctor scheduling suggestion scheme;

[0054] S4: Distribute the scheduling plan to the edge nodes of the corresponding wards and update the status of each local digital twin model.

[0055] In Embodiment 1 of the present invention, a hospital integrated management platform based on cloud computing architecture is provided, which is suitable for large general hospitals or medical groups.

[0056] System Deployment: The terminal hardware of the data acquisition module (such as IoT gateways and protocol converters) is deployed in various departments, wards, and equipment points throughout the hospital. The network transmission layer utilizes the hospital's existing wired and wireless networks (such as Wi-Fi 6 and 5G private networks) to upload data to the cloud data center; both the data platform processing layer and the visualization application layer are deployed as cloud services on a cloud server cluster.

[0057] Data Flow and Processing:

[0058] Data Access: Emergency department monitors send patient vital sign data to the edge gateway via the Modbus protocol. After local caching and outlier filtering, the gateway publishes the data to the cloud message queue via the MQTT protocol. Simultaneously, the HIS system pushes patient registration information to the platform's data access API via the HTTPS-based FHIR standard interface.

[0059] Data fusion and modeling: After receiving the data, the perception data management module uses the patient's ID number or medical insurance card number as the key to associate the data from the monitor and HIS with the same patient digital twin and update its "real-time vital signs" and "medical treatment status" attributes.

[0060] Intelligent Analysis Example – Epidemic Surveillance:

[0061] The epidemiological monitoring submodule in the intelligent analysis engine extracts the diagnostic symptom tags (such as fever, cough, diarrhea) of all outpatients in the past 24 hours from the data lake every day.

[0062] The spatial-temporal scan statistical method (Kulldorff's ScanStatistic) was used, with departments as spatial units and days as temporal units, to calculate the likelihood ratio (LR) between the observed number of cases and the expected number of cases in each spatial-temporal unit.

[0063] The simplified formula for calculation is: LR = (c / E)^c * ((Cc) / (CE))^(Cc);

[0064] Where c is the actual number of cases in the unit, E is the expected number of cases calculated based on the historical baseline, and C is the total number of cases.

[0065] When the LR value of a certain unit (such as "Pediatrics - Fever") exceeds the significance threshold obtained through Monte Carlo simulation, the system automatically triggers an early warning. The early warning information, along with the relevant spatiotemporal clustering area and symptom characteristics, is pushed in real time to the back-end management dashboard and the mobile terminals of relevant personnel in the disease control department.

[0066] Visual Presentation: Hospital administrators can view a dynamically updated hospital map heatmap in the back-end management dashboard, with red highlighted areas indicating abnormally clustered departments. Clicking on a department allows users to drill down to view a list of suspected patients, detailed symptom composition, and trend curves.

[0067] This embodiment achieves the intensive use of data and computing power through a centralized cloud computing model, which is particularly suitable for global analysis tasks that require large-scale historical data training and complex model calculations, such as cross-year disease trend prediction and hospital-wide resource optimization simulation.

[0068] In the second embodiment of the present invention, which focuses on real-time management of the ward and is based on an edge-cloud collaborative architecture, it is applicable to scenarios such as intensive care units (ICUs) and operating rooms with high real-time requirements.

[0069] System Deployment: High-performance edge computing nodes are deployed within the wards. Data acquisition layer devices are directly connected to these edge nodes. The edge nodes carry lightweight data platform processing functions (such as real-time data cleaning, local rule engines, and ward digital twin models); simultaneously, the edge nodes maintain synchronization with the cloud center, uploading anonymized aggregated data to the cloud for long-term analysis and hospital-wide collaboration.

[0070] Data Flow and Processing:

[0071] Real-time response at the edge:

[0072] The patient data acquisition unit continuously collects data such as blood pressure, blood oxygen, and heart rate from patients through bedside IoT devices.

[0073] The edge node's perception data management module cleans data with millisecond-level latency. The resource information model construction module maintains a local digital twin of a ward, reflecting the patient status and equipment usage of each bed in real time.

[0074] The local intelligent analysis engine runs preset clinical rules. For example, the function f(HR,SpO2) = HR>120 && SpO2<90% is defined. When a patient's data meets this condition, the edge node immediately sends an audible and visual alarm to the nurse station's visualization screen and the nurse's handheld terminal, and automatically records the event log. This real-time response based on edge computing avoids the delay of data uploading to the cloud and then returning, which is crucial for alarms of critical values.

[0075] Cloud-edge collaborative resource scheduling:

[0076] The edge nodes synchronize the ward's bed occupancy rate, expected number of discharges, and equipment load data to the cloud every day.

[0077] The cloud-based operations analytics submodule integrates data reported from edge nodes across all wards in the hospital and runs resource scheduling optimization algorithms. Factors considered in the algorithm include: patient waiting times in each department, differences in disease types, physician specialties, and bed cleaning and preparation time.

[0078] Once the algorithm calculates the optimal scheduling scheme (for example, assigning three patients awaiting hospitalization in the emergency department to the internal medicine ward A, the surgery ward B, and the ICU respectively), the scheme is sent to the edge nodes of the corresponding wards.

[0079] On the ward head nurse's visual terminal, a new bed allocation task notification will pop up, and the effect of virtual bed reservations can be seen on the local ward digital twin model. For example: green represents empty beds, yellow represents reserved beds, and red represents occupied beds.

[0080] Visualization: At the ward nurses' station, a large visual screen displays real-time vital sign trend curves, remaining IV fluid volume, and alarm lists for all patients in the ward. Doctors can use mobile tablets to view a panoramic view of all patients under their care, including the latest test results, imaging reports, and nursing records. This data is provided in real-time by edge nodes from various hospital systems.

[0081] This embodiment utilizes edge-cloud collaboration to offload real-time control and analysis tasks to the edge, ensuring low latency and high reliability for critical business operations. Simultaneously, it leverages the powerful computing capabilities of the cloud for global optimization and macro-analysis, achieving an optimal balance between efficiency and intelligence.

[0082] In the description of this invention, it should be understood that the terms "longitudinal", "lateral", "up", "down", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this invention, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention.

[0083] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A visual IoT integrated management platform, characterized in that, include: The equipment and data acquisition layer is used to collect multi-source heterogeneous data related to hospital operations. This includes front desk reception data, patient treatment data, doctor work data, and logistical resource data; The network and protocol conversion layer is used to access and unify the data protocols and formats uploaded by the device and the data acquisition layer; The data platform processing layer is used to integrate, manage, model, and analyze the unified data; It includes a perception data management module, a resource information model construction module, an information management module, and an intelligent analysis engine module; The visualization application layer is used to display and interact with the analysis results of the data platform processing layer in a graphical manner in multiple dimensions.

2. The visualized IoT integrated management platform according to claim 1, characterized in that, The intelligent analysis engine module includes: The epidemic monitoring submodule is used to perform real-time scanning and early warning of abnormal clustering of syndrome data throughout the hospital based on time series analysis and spatial clustering algorithms; The operations analysis submodule is used to calculate the department's workload and allocate follow-up examination, hospitalization and bed resources to patients based on optimization algorithms; The scheduling optimization submodule is used to generate doctor outpatient and surgical scheduling plans based on historical data and real-time needs.

3. The visualized IoT integrated management platform according to claim 1, characterized in that, The network and protocol conversion layer includes an edge computing gateway and a protocol conversion module; the edge computing gateway is deployed near the data source for local data preprocessing and caching; the protocol conversion module supports medical and IoT protocols including HL7, FHIR, DICOM, Modbus and MQTT.

4. The visualized IoT integrated management platform according to claim 1, characterized in that, The resource information model building module is used to create and maintain a hospital digital twin model, which maps physical entities into digital objects with attributes, states, and relationships.

5. The visualized IoT integrated management platform according to claim 1, characterized in that: The visualization application layer provides views including a comprehensive view of the hospital's overall operations, a panoramic view of the patient's entire disease course, a doctor's performance analysis view, and a back-end management decision-making dashboard view.

6. The visualized IoT integrated management platform according to claim 1, characterized in that: The information management module provides unified full lifecycle management functions for devices, gateways, certificates, applications, and users within the platform.

Images