Hospital intelligent space management system and method

Abstract

The invention belongs to the technical field of hospital management, and discloses a hospital intelligent space management system and method, and the system comprises a space sensing module, a data processing and analysis module, an intelligent decision module, an execution module, and a user interaction module. The spatial sensing module is used for collecting hospital spatial data in real time and transmitting the hospital spatial data to the data processing and analyzing module through an Internet of Things communication protocol; the data processing and analyzing module is used for processing, classifying, storing and deeply analyzing the hospital spatial data and extracting key feature indexes; the intelligent decision module is used for generating a space management strategy by applying an artificial intelligence algorithm according to the key feature indexes and the management targets; the execution module is used for receiving the space management strategy and controlling automatic equipment and a system to adjust the hospital space; and the user interaction module is used for realizing bidirectional information transmission and supporting a user feedback optimization system. The invention aims to optimize the utilization and management of the hospital space through an intelligent means, and improve the operation efficiency and service quality of the hospital.

Description

Technical Field

[0001] The present invention belongs to the technical field of hospital management, and particularly relates to a hospital intelligent space management system and method. Background Art

[0002] With the continuous progress and development of medical technology levels and the increasing demand for medical services from people, the scale and complexity of hospitals are also increasing continuously. There are many deficiencies in traditional hospital space management methods, such as unreasonable allocation of space resources, low efficiency in equipment and material management, and cumbersome patient treatment processes, resulting in increased hospital operating costs and decreased patient satisfaction. Therefore, there is an urgent need for a system and method that can realize intelligent management of hospital space to improve the overall management level of the hospital. And the hospital space resources are limited, and it is difficult to grasp the space usage situation in real time with traditional management methods, resulting in unreasonable space allocation, such as uneven busyness of departments such as wards and consulting rooms, and congestion in public areas. At the same time, the distribution of hospital facilities and equipment is complex, making maintenance and management inconvenient, affecting the hospital operation efficiency and patient treatment experience. Summary of the Invention

[0003] To solve the problems existing in the prior art, the present invention provides a hospital intelligent space management system and method, aiming to optimize the utilization and management of hospital space through intelligent means and improve the hospital operation efficiency and service quality.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] A hospital intelligent space management system, the system includes: a space perception module, a data processing and analysis module, an intelligent decision-making module, an execution module, and a user interaction module;

[0006] The space perception module is used to collect hospital space data in real time and transmit it to the data processing and analysis module via the Internet of Things communication protocol;

[0007] The data processing and analysis module is used to process, classify, store, and deeply analyze hospital space data, and extract key characteristic indicators;

[0008] The intelligent decision-making module is used to generate space management strategies according to key characteristic indicators and management objectives by using artificial intelligence algorithms;

[0009] The execution module is used to receive space management strategies and control automation equipment and systems to adjust hospital space;

[0010] The user interaction module is used to realize two-way information transmission and support users to feedback and optimize the system.

[0011] Preferably, the space perception module includes: a personnel data unit, a device status data unit, and an environmental parameter data unit;

[0012] The personnel data unit is used to collect data for continuous positioning and event-triggered positioning when the personnel location changes, and obtain key information on personnel activities;

[0013] The equipment status data unit is used to set the collection frequency according to the importance of the equipment and the characteristics of its operation, and collect key equipment status data in real time;

[0014] The environmental parameter data unit is used to collect environmental data according to different environments, and provide data support for judging personnel flow and environmental comfort in the ward.

[0015] Preferably, the intelligent decision-making module includes: a personnel scheduling unit, an equipment allocation unit, and a ward allocation unit;

[0016] The personnel scheduling unit is used to intelligently allocate medical staff and adjust the work schedule when scheduling personnel;

[0017] The equipment allocation unit is used to arrange spare equipment and notify maintenance based on equipment usage rate, maintenance cycle, and performance parameters;

[0018] The ward allocation unit is used to allocate wards comprehensively considering the patient's condition, ward type, and usage status.

[0019] Preferably, the execution module includes: an automatic access control system, an intelligent lighting and air conditioning system, and an intelligent logistics system;

[0020] The automatic access control system is used to update permissions according to system instructions;

[0021] The intelligent lighting and air conditioning system is used to monitor real-time environmental data through sensors and automatically adjust according to system settings;

[0022] The intelligent logistics system is used to select the corresponding rail logistics, pneumatic logistics, or AGV transportation method according to the location of materials and equipment requirements, and transport materials and equipment.

[0023] The present invention also provides a hospital intelligent space management method, which is implemented by using any one of the hospital intelligent space management systems described above. The method includes the following steps:

[0024] Step 1: Initialize the system of the hospital intelligent space;

[0025] Step 2: Collect and transmit hospital intelligent space data in real time;

[0026] Step 3: Process and analyze hospital intelligent space data;

[0027] Step 4: Make management decisions for the hospital's intelligent space based on the processed and analyzed hospital intelligent space data;

[0028] Step 5: Execute and provide feedback on the management decisions for the hospital's intelligent space.

[0029] Preferably, in step 3, the processing and analysis of the hospital intelligent space data include:

[0030] Perform preprocessing operations such as processing, denoising, and verification on the hospital intelligent space data;

[0031] Input the preprocessed hospital intelligent space data into the big data processing framework for in-depth data analysis;

[0032] Among them, the in-depth data analysis includes: using the clustering analysis method to cluster areas with similar personnel flows to find the hot areas and time periods where people gather; using association rule mining to discover the potential association relationships between equipment usage rates and factors such as patient flow and department business volume; using time series analysis to predict ward turnover rates and equipment failure rates to discover potential problems in advance.

[0033] Preferably, in step 4, making management decisions for the hospital's intelligent space based on the processed and analyzed hospital intelligent space data includes:

[0034] In terms of personnel scheduling, when the patient flow in a certain department exceeds the threshold and continues to rise, an automatic scheduling plan for increasing the medical staff in that department is generated according to historical data and the personnel scheduling model;

[0035] In terms of equipment allocation, according to the equipment usage rate data and the equipment maintenance cycle, when the usage rate of a certain type of equipment is higher than the preset threshold, an equipment allocation plan is generated.

[0036] Preferably, in step 5, the execution and feedback of the management decisions for the hospital's intelligent space include:

[0037] When receiving an instruction to adjust the ward use, the automatic access control system updates the ward access permissions, prohibits unauthorized personnel from entering the adjusted ward, and at the same time, the intelligent lighting system and air conditioning system adjust the corresponding parameters according to the new ward use;

[0038] When medical supplies need to be delivered to a certain department, the intelligent logistics system transports the required supplies to the designated department according to the instruction.

[0039] Compared with the prior art, the beneficial effects of the present invention are:

[0040] The present invention creates a hospital intelligent space management system and method, which scientifically allocates and efficiently utilizes modern hospital space resources, improves the management efficiency of equipment and materials, optimizes the patient medical experience, and enhances the hospital's emergency response ability. Specifically:

[0041] Optimize the allocation of space resources: By collecting the space information of each area in the hospital in real time, using big data analysis and artificial intelligence algorithms, deeply mining the space usage rules, and accurately formulating space allocation strategies, such as adjusting the use arrangements of wards and consulting rooms, optimizing the flow guidance of public areas, improving the space utilization rate, and reducing resource idle and waste.

[0042] Improve the management level of equipment and materials: Monitor the equipment status in real time, combine the equipment usage rate and maintenance cycle, and use intelligent algorithms to achieve precise allocation and preventive maintenance of equipment. At the same time, with the help of an intelligent logistics system, realize the efficient transportation and management of medical supplies, reduce the equipment failure rate, extend the service life of equipment, and ensure the continuity and stability of hospital medical services.

[0043] Improve the patient medical experience: According to the distribution of patient flow, intelligently adjust the distribution and process of links such as registration, consultation, and examination, and reduce the patient's queuing waiting time. Through the user interaction module, provide convenient information query services for patients, such as information on adjusted consultation processes, waiting times, and examination reports, improve the patient's medical autonomy and convenience, and enhance the patient's satisfaction.

[0044] Enhance the hospital's emergency response ability: In the event of an emergency, the system quickly responds to integrate and analyze relevant data, providing comprehensive and accurate decision-making basis for hospital management personnel. The intelligent decision-making module quickly formulates emergency treatment plans, and the execution module quickly allocates personnel, materials, and equipment, improving the hospital's emergency response speed and handling ability, and ensuring the safety of patients and medical staff. Brief Description of the Drawings

[0045] In order to more clearly illustrate the technical solutions of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0046] Figure 1 It is a schematic structural diagram of a hospital intelligent space management system according to an embodiment of the present invention;

[0047] Figure 2 It is a schematic data flow diagram of a hospital intelligent space management method according to an embodiment of the present invention;

[0048] Figure 3 It is a schematic flowchart of a hospital intelligent space management method according to an embodiment of the present invention. Detailed implementation manners

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0050] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0051] Embodiment 1

[0052] As can be seen from the background technology:

[0053] With the gradual development of medical technology levels and the growth of people's requirements for medical services, as well as the increasing complexity of hospital scale, the traditional hospital space management method can no longer meet the current needs:

[0054] 1. Uneven distribution of space resources: The hospital space resources are limited, but the traditional hospital management mode can no longer accurately and timely master the usage situation of each area in real time, resulting in uneven busyness and idleness of departments such as wards and consulting rooms, congestion in public areas, low space utilization rate, and waste of resources.

[0055] 2. Low efficiency in equipment and material management: The distribution of hospital facilities and equipment is complex. Under the traditional hospital management mode, the equipment status cannot be monitored in a timely manner, and maintenance and management are inconvenient. At the same time, equipment failures are difficult to predict and handle in advance, affecting the normal operation of the hospital, increasing the operating cost, and also having a negative impact on the patient's medical experience.

[0056] 3. Complicated operations for patients in the medical treatment process: In the traditional medical treatment process, patients need to queue up for a long time in links such as registration, medical treatment, examination, and medicine collection. The medical treatment process lacks flexibility and high efficiency, resulting in low medical treatment efficiency and a decrease in patient satisfaction.

[0057] 4. Lack of emergency response ability: In the face of emergencies such as public health events and sudden equipment failures, the traditional management method cannot quickly obtain comprehensive and accurate information, resulting in decision-making lag, making it difficult to quickly formulate effective emergency response plans and unable to guarantee the lives of patients and medical staff.

[0058] Such as Figure 1As shown in the figure, the present invention provides a hospital intelligent space management system, which is jointly composed of a space perception module, a data processing and analysis module, an intelligent decision-making module, an execution module, and a user interaction module. In the overall hospital management process, each module has a clear division of labor. Through data collection, processing, analysis, decision-making, execution, and user interaction feedback, a closed-loop intelligent space management system is formed to comprehensively improve the efficiency and service quality of hospital space management.

[0059] When the system starts to work, the space perception module collects hospital space data in real time and transmits it to the data processing and analysis module via the Internet of Things communication protocol. This module processes, classifies, stores, and deeply analyzes the data to extract key characteristic indicators. The intelligent decision-making module generates space management strategies using artificial intelligence algorithms based on this information and management objectives. The execution module receives instructions and controls automated devices and systems to adjust the hospital space. At the same time, the user interaction module realizes two-way information transmission and supports users to provide feedback to optimize the system.

[0060] In this embodiment, the space perception module, as the basis for data collection, is responsible for comprehensively, real-time, and accurately collecting space information in various areas of the hospital, providing a solid data foundation for subsequent data analysis and decision-making modules. It constructs an integrated sensor network including Internet of Things sensors and cameras. The Internet of Things sensors are small in size, low in power consumption, and high in sensitivity, and are widely deployed throughout the hospital. For example, infrared sensors in the ward can monitor the entry and exit of personnel, and temperature and humidity sensors collect environmental data according to different environments, providing data support for judging the personnel flow and environmental comfort in the ward. High-precision device status sensors are used for equipment monitoring in key areas to ensure the stable operation of infrastructure. The positioning device adopts a fusion scheme of ultra-wideband (UWB), Bluetooth, and Wi-Fi positioning technologies. UWB is used for high-precision positioning of important facilities and special patients, Bluetooth tracks medical staff, and Wi-Fi enables large-scale positioning to meet the needs of different scenarios. Cameras can provide intuitive image information to assist in real-time monitoring of the status of personnel and equipment. Its data collection strategy is that when the position of a person changes, continuous positioning and event-triggered positioning data collection will occur. Normally, interval collection is performed every 10 seconds, and accurate data is immediately uploaded when entering a specific area or when the behavior is abnormal to ensure the acquisition of key information on personnel activities. The collection frequency of device status data is set according to the importance of the device and the characteristics of its operation. Key devices will be collected in real time, and ordinary devices will be collected once every 30 minutes to ensure the pertinence and efficiency of device operation monitoring. Among the environmental parameter data, the temperature and humidity sensors are collected once every 5 minutes, and the air quality sensors will adjust the frequency according to the environmental dynamics to timely grasp environmental changes.

[0061] In this embodiment, the data processing and analysis module serves as the core data processing center of the system, responsible for processing and analyzing the massive data collected by the spatial perception module, mining the data value, and providing a reliable basis for intelligent decision-making. It uses the big data processing frameworks Hadoop and Spark. The Hadoop Distributed File System (HDFS) dispersedly stores the massive data on multiple nodes to achieve redundant backup and efficient storage, ensuring the security and reliability of the data. Spark is based on in-memory computing, significantly improving the data processing speed and being suitable for real-time data analysis.

[0062] Special processing algorithms are adopted to remove abnormal data, such as filtering unreasonable data from temperature sensors; filtering algorithms such as Kalman filtering and wavelet filtering are used for denoising; the improved algorithm: Adaptive Weighted Moving Average Filter (AWMAF) is utilized. The traditional moving average filter assigns the same weight to all data points and cannot effectively process abrupt data. The improved Adaptive Weighted Moving Average Filter (AWMAF) dynamically adjusts the weight according to the local changes of data points, and the formula is as follows:

[0063]

[0064] Where y t is the filtered data point, x i is the original data point, w i is the weight, and k is the size of the sliding window. The calculation formula for the weight w i is:

[0065]

[0066] Where α is the adjustment parameter used to control the sensitivity of the weight to data changes. When the data changes significantly, the weight decreases to reduce the impact of abnormal data.

[0067] Verification is performed by checking the data format and integrity. The clustering analysis algorithm is used to classify areas with similar personnel flow to find hotspots of personnel gathering; through the improved algorithm: Context-Aware Data Verification (CADV), traditional data verification methods are usually based on fixed rules and cannot adapt to the complex data context. The improved Context-Aware Data Verification (CADV) combines context information and dynamically adjusts the verification rules. The formula is as follows:

[0068]

[0069] Where C(x) is the verification result of the data point x, f(x,context) is the context-aware function, and θ is the threshold. The calculation formula for the context-aware function f(x,context) is:

[0070]

[0071] Among them, β i is the weight, and g(x, c i ) is the similarity function between the data point x and the context c i .

[0072] The association rule mining algorithm discovers the potential relationships among factors such as device utilization rate and patient flow; by improving the algorithm: Time-Weighted Association Rule Mining (TWARM). Traditional association rule mining ignores the time factor, and the improved Time-Weighted Association Rule Mining (TWARM) introduces time weights, and the formula is as follows:

[0073]

[0074] Among them, ω(t) is the time weight, t0 is the current time, and τ is the time decay parameter. Time weights are added to the calculation of the support and confidence of association rules, and the formula is:

[0075]

[0076] The time series analysis algorithm predicts the ward turnover rate, equipment failure rate, etc., and detects potential problems in advance. By improving the algorithm: Multi-Scale Time Series Prediction (MSTSP). Traditional time series analysis is usually based on a single scale, and the improved Multi-Scale Time Series Prediction (MSTSP) combines multi-scale information, and the formula is as follows:

[0077]

[0078] Among them, is the predicted value, γ S is the weight of scale s, f S is the prediction function of scale s, and L is the time window size. The formula for calculating the weight γ S is:

[0079]

[0080] Among them, α s is the importance parameter of scale S, which is learned from the training data.

[0081] In this embodiment, the intelligent decision-making module serves as the core of the system's wisdom. Based on the data analysis results and the hospital management rule objectives, it formulates the optimal space management strategy to achieve the rational allocation and efficient utilization of hospital resources. It is trained and optimized by applying machine learning and deep learning algorithms and combining a large amount of historical and real-time data. When scheduling personnel, it comprehensively considers factors such as patient flow, department business volume, professional skills and work efficiency of medical staff. For example, when the number of patients in the fever clinic increases during the flu season, it intelligently allocates medical staff and adjusts the work schedule. For equipment allocation, it considers equipment utilization rate, maintenance cycle, performance parameters, etc. For example, when the utilization rate of the CT equipment is high and it is approaching the maintenance period, it arranges for standby equipment and notifies for maintenance. For ward allocation, it comprehensively considers the patient's condition, ward type and usage status to improve the ward utilization efficiency.

[0082] (1) Data preprocessing and feature extraction

[0083] First, preprocess the historical and real-time data, including data processing, normalization and feature extraction. Suppose we have a dataset D = {(x1,y1),(x2,y2),…,(x n ,y n ),} where x i is the feature vector and y i is the target variable (such as ward utilization rate, equipment utilization rate, etc.). Introduce the Adaptive Feature Selection (AFS) algorithm, and by dynamically adjusting the feature weights, select the most relevant features. The formula is as follows:

[0084]

[0085] Where, w j is the weight of the feature x j , α is the adjustment parameter, and Relevance(x j ) is the relevance between the feature x j and the target variable.

[0086] (2) Generation of space management strategy

[0087] Based on the preprocessed data, use the improved Enhanced Reinforcement Learning (ERL) algorithm to generate the space management strategy. ERL combines the Deep Q-Network (DQN) and the policy gradient method, and can converge quickly in complex environments. Introduce an adaptive learning rate adjustment mechanism to dynamically adjust the learning rate according to the convergence speed of the policy and environmental changes. The formula is as follows:

[0088]

[0089] Where, η tis the learning rate at time step t, η0 is the initial learning rate, β is the decay coefficient, and T is the total number of time steps.

[0090] (3) Policy Optimization and Evaluation

[0091] The generated policy is optimized using the Enhanced Genetic Algorithm (EGA). EGA introduces an individual diversity preservation mechanism to avoid premature convergence. Dynamic crossover and mutation probabilities are introduced, and the crossover and mutation probabilities are adjusted according to the population diversity. The formulas are as follows:

[0092]

[0093] Among them, P c and P m are the crossover and mutation probabilities respectively, P c0 and P m0 are the initial probabilities, D is the population diversity, and D max is the maximum diversity.

[0094] (4) Policy Execution and Feedback

[0095] The optimized policy is applied to the actual hospital space management, and the policy is continuously adjusted through real-time data feedback. The Enhanced Online Learning (EOL) algorithm is used for real-time update. An adaptive forgetting factor is introduced, and the forgetting factor is dynamically adjusted according to the stability of the policy and environmental changes. The formula is as follows:

[0096]

[0097] Among them, λ t is the forgetting factor at time step t, λ0 is the initial forgetting factor, γ is the decay coefficient, and T is the total number of time steps.

[0098] (5) Comprehensive Evaluation and Adjustment

[0099] The policy is comprehensively evaluated through comprehensive evaluation indicators (such as ward utilization rate, equipment utilization rate, medical staff satisfaction, etc.), and further adjusted according to the evaluation results. The Multi-Objective Optimization (MOO) algorithm is introduced to comprehensively consider multiple evaluation indicators and generate the optimal policy. The formula is as follows:

[0100]

[0101] Among them, θ is the policy parameter, f i (θ) is the i-th evaluation indicator, and w i is the weight.

[0102] In this embodiment, the execution module converts the instructions of the intelligent decision-making module into actual actions, dynamically adjusts and manages the hospital space, and ensures the effective implementation of decisions. It integrates automated equipment systems such as intelligent logistics, automatic access control, and intelligent lighting.

[0103] The automatic access control system will update the permissions according to the system instructions to ensure the safety and privacy of the wards.

[0104] The automatic access control system needs to dynamically adjust permissions according to the space usage and security requirements of the hospital. Traditional permission control is usually static and cannot cope with emergencies or dynamic requirements. We propose a permission update algorithm based on fuzzy control and dynamic programming.

[0105] Improved algorithm formula: Let P(t) be the permission matrix at time t, S(t) be the current security state (such as ward occupancy, emergency events, etc.), and U(t) be the user demand matrix (such as medical staff, patient families, etc.). The permission update formula is:

[0106] where α is the learning rate, is the permission adjustment function based on fuzzy control, defined as:

[0107]

[0108] Here, μ i (S(t)) is the fuzzy membership function of the security state, and φ i (U(t)) is the fuzzy rule function of user demand. By dynamically adjusting α and fuzzy rules, the system can adaptively update permissions to ensure security and flexibility.

[0109] The intelligent lighting and air conditioning systems monitor real-time environmental data through sensors and automatically adjust according to system settings to achieve reasonable utilization of energy and create a comfortable environment.

[0110] The intelligent lighting and air conditioning systems monitor environmental data (such as light intensity, temperature, humidity, etc.) through sensors and automatically adjust according to system settings. We propose an environmental regulation algorithm based on reinforcement learning that can dynamically optimize energy use in different time periods and spatial regions.

[0111] Improved algorithm formula: Let E(t) be the environmental state at time t (such as temperature, humidity, light, etc.), and A(t) be the actions taken by the system (such as adjusting the light brightness, air conditioning temperature, etc.). The goal is to maximize the comfort C(t) and minimize the energy consumption W(t). We define the reward function R(t) as:

[0112] R(t) = β·C(t) - (1 - β)·W(t)

[0113] Among them, β is the weight coefficient of comfort and energy consumption.

[0114] The intelligent logistics system adopts advanced logistics regulation algorithms and navigation technologies. According to the demand positions of materials and equipment, it selects corresponding rail logistics, pneumatic logistics or AGV transportation methods to quickly and accurately transport materials and equipment. When transporting large equipment, it automatically plans a reasonable route.

[0115] The intelligent logistics system needs to select the optimal transportation method (such as rail logistics, pneumatic logistics or AGV transportation) according to the demand positions of materials and equipment. We propose a path planning algorithm based on the improved A* algorithm, which combines dynamic obstacle avoidance and multi-objective optimization.

[0116] Improved algorithm formula: Let G be the spatial map of the hospital, S be the starting point, T be the ending point, and O(t) be the set of dynamic obstacles at time t. The goal of path planning is to minimize the path length L and the transportation time T. We define the cost function F(t) as:

[0117]

[0118] Among them, λ is the weight coefficient of path length and time, is the avoidance cost function of dynamic obstacles. Through the improved A* algorithm, the system can plan the optimal path in real time:

[0119]

[0120] Here, g(n) is the actual cost from the starting point to node n, and h(n) is the heuristic estimated cost. By dynamically updating O t and ψ(o), the system can handle sudden obstacles and select the optimal path.

[0121] In this embodiment, the user interaction module connects the system with hospital personnel, provides an operation interface and an information feedback channel, promotes the participation of all parties in space management, and improves the service quality of the system. It provides data for managers through the Web interface, facilitating the viewing of the implementation status of space management strategies and real-time data for decision-making adjustment. The mobile application can facilitate medical staff to receive work arrangements and real-time patient information updates, improving work efficiency; it can also facilitate patients to query medical treatment information and arrange medical treatment time in a timely and reasonable manner. It has a perfect information feedback and processing mechanism to process user feedback in a timely manner and optimize the system function services.

[0122] Furthermore, alternative positioning technologies:

[0123] In some cost-sensitive scenarios with lower accuracy requirements, radio frequency identification (RFID)-based positioning technology can be used to replace some positioning methods. RFID tags are low-cost and can be attached to equipment or personnel. The location is determined by identifying the tag signal through the reader deployed in the hospital. However, RFID positioning accuracy is relatively low, and it is suitable for general equipment management and personnel approximate location tracking scenarios that do not require high location accuracy.

[0124] Further, alternatives to big data processing frameworks:

[0125] If the hospital has a relatively small amount of data and does not require real-time processing, it can consider using a traditional relational database combined with lightweight data analysis tools to replace Hadoop and Spark. For example, the MySQL database combined with Python's data analysis library (such as Pandas and Scikit-learn) can complete data storage, processing and simple analysis tasks, reducing system deployment and operation and maintenance costs, but the performance is relatively weak when processing large-scale complex data.

[0126] Further, AI algorithm alternatives:

[0127] In personnel scheduling and equipment deployment decisions, if machine learning and deep learning algorithms are difficult to implement, simple rule-based decision algorithms can be used as an alternative. For example, set fixed personnel deployment thresholds and rules. When the patient flow in a department reaches a certain value, deploy personnel from other departments at a fixed ratio. This method is easy to understand and implement, but it has poor flexibility and adaptability, and cannot fully utilize complex data information to make accurate decisions.

[0128] In summary, the technical effects of the present invention are as follows: Improve space utilization: Through real-time monitoring and dynamic management of hospital space, space resources can be allocated more reasonably, space utilization can be improved, and resource waste can be reduced. Optimize medical treatment process: According to the patient flow and distribution, the layout and process of registration, medical treatment, examination and other links are intelligently adjusted to reduce the waiting time of patients in queues, improve medical treatment efficiency and patient satisfaction. Improve equipment management efficiency: Real-time grasp of the use status and location information of the equipment, realize accurate deployment and maintenance management of the equipment, extend the service life of the equipment, reduce the equipment failure rate, and improve the hospital's medical service capabilities. Reduce operating costs: By optimizing space management and resource allocation, reduce unnecessary manpower, material and financial resources, reduce the operating costs of the hospital, and improve economic benefits. Enhance emergency response capabilities: In the event of an emergency, relevant information can be quickly obtained, emergency response plans can be formulated, the hospital's emergency response speed and processing capabilities can be improved, and the life safety of patients and medical staff can be guaranteed.

[0129] Embodiment 2

[0130] like Figure 2 ,Figure 3 As shown, the present invention provides an optimization method for hospital intelligent space management, which is implemented by applying any of the described hospital intelligent space management systems. This method includes the following parts:

[0131] System initialization, data collection and transmission, data processing and analysis, intelligent decision-making, execution and feedback;

[0132] Step 1: System initialization of the hospital intelligent space:

[0133] System initialization is the basis for the normal operation of the entire hospital intelligent space management system, and various preparatory work needs to be carried out. In various areas of the hospital, such as wards, consulting rooms, corridors, examination rooms, pharmacies, logistics areas, etc., sensors and positioning devices are installed comprehensively. Infrared sensors, temperature sensors, humidity sensors, and high-definition cameras are installed in the wards. The infrared sensors are used to monitor the entry and exit of patients and medical staff, helping to count the frequency of personnel flow in the wards; the temperature and humidity sensors collect real-time temperature and humidity data in the wards to ensure the comfort of the patients' hospitalization environment; the high-definition cameras can be used to observe the real-time status of patients and detect abnormalities in a timely manner in case of emergencies. In equipment-intensive areas, such as operating rooms and intensive care units, high-precision equipment status sensors are equipped to monitor real-time information such as the operating parameters and usage duration of the equipment. In terms of positioning devices, a combination of ultra-wideband (UWB) positioning technology, Bluetooth positioning technology, and Wi-Fi positioning technology is adopted. UWB positioning technology is used for high-precision positioning of important medical equipment and special patients (such as critically ill patients and psychiatric patients), with an accuracy of up to sub-meter level; Bluetooth positioning technology is used for tracking the positions of medical staff, facilitating contact and scheduling at any time; Wi-Fi positioning technology realizes large-scale positioning of personnel and equipment in the hospital to meet the needs of daily management.

[0134] Step 2: Data collection and transmission of the hospital intelligent space:

[0135] After the system initialization is completed, it enters the data collection and transmission stage. The sensor network in the space perception module starts to function, and each sensor collects hospital space data in real time according to the preset time interval and trigger conditions. Taking the collection of personnel location data as an example, the positioning devices installed in each area continuously send and receive signals to accurately obtain personnel location information. When a person moves from one area to another, the location data will be updated in a timely manner. When collecting device status data, device status sensors continuously monitor the operating status of devices, such as the on / off status, operating parameters, and fault alarms of medical devices. Regarding environmental parameter data, temperature, humidity, and air quality sensors collect data at regular intervals. Once the environmental parameters exceed the set comfortable range or safety standards, data collection will be immediately triggered and uploaded. The collected data is transmitted to the data processing and analysis server through Internet of Things communication protocols. Currently, commonly used Internet of Things communication protocols include ZigBee, NB-IoT, LoRa, etc. In a hospital scenario, the ZigBee protocol is suitable for short-distance and low-power sensor data transmission, such as sensor data in a ward; the NB-IoT protocol is suitable for long-distance and low-rate data transmission and can be used to transmit sensor data distributed in various corners of the hospital to the server; for high-definition camera video data with a large amount of data, a high-speed wired network or 5G wireless network is used for transmission to ensure the real-time and stability of the data.

[0136] Step 3: Process and analyze the hospital intelligent space data:

[0137] Data processing and analysis is one of the core links of the system. After the data processing and analysis server receives the data transmitted from the space perception module, it first performs preprocessing operations such as processing, denoising, and verification. During the data processing process, data processing algorithms are used to remove abnormal data caused by sensor failures, signal interference, etc. For example, data collected by a temperature sensor outside the reasonable range (such as outside -50°C to 100°C). Data denoising uses filtering algorithms to eliminate noise signals in the data, making the data smoother and more accurate. The verification link ensures the accuracy and reliability of the data by checking the data format and data integrity. The preprocessed massive data enters big data processing frameworks such as Hadoop and Spark. The data is stored in the Hadoop Distributed File System (HDFS), and the in-memory computing power of Spark is used to quickly process the data. Through data mining algorithms such as clustering analysis, association rule mining, and time series analysis, in-depth analysis of the data is carried out. Clustering analysis can cluster areas with similar personnel flow to find hot spots and time periods of personnel gathering; association rule mining is used to discover potential association relationships between factors such as device usage rate, patient flow, and department business volume; time series analysis predicts data such as ward turnover rate and device failure rate to discover potential problems in advance.

[0138] Step 4: Intelligent decision-making for the hospital's intelligent space:

[0139] Based on the key indicators and analysis results output by the data processing and analysis module, combined with the pre-set management objectives, the intelligent decision-making module generates space management strategies using machine learning algorithms. In terms of personnel scheduling, when the patient flow in a certain department exceeds the threshold and continues to rise, the intelligent decision-making module automatically generates a scheduling plan to increase the medical staff in that department according to historical data and the personnel scheduling model. For example, during the peak flu season, the patient flow in the fever clinic surges, and the system predicts that the number of patients will continue to rise in the next few hours. At this time, the intelligent decision-making module transfers medical staff from other relatively idle departments to the fever clinic and adjusts the work schedules of the medical staff to ensure that there is sufficient manpower in the fever clinic to meet the patient treatment needs. In terms of equipment allocation, according to the equipment usage rate data and the equipment maintenance cycle, when the usage rate of a certain type of equipment is too high and approaching the maintenance deadline, the intelligent decision-making module generates an equipment allocation plan. For example, if the usage rate of the CT examination equipment has exceeded 80% for a consecutive week and is approaching the specified cycle since the last maintenance, the system will arrange for a spare CT equipment to be put into use and notify the equipment maintenance personnel to maintain the CT equipment with high load operation to ensure the normal operation of the equipment and avoid affecting the patient examination progress due to equipment failure.

[0140] Step 5: Execution and feedback for the hospital's intelligent space:

[0141] The execution module is responsible for converting the instructions generated by the intelligent decision-making module into actual actions, and dynamically adjusts and manages the hospital space by controlling Internet of Things devices and systems. When receiving the instruction to adjust the ward use, the automatic access control system updates the permission settings of the ward, prohibits unauthorized personnel from entering the ward with adjusted use, and at the same time, the intelligent lighting system and air conditioning system adjust the corresponding parameters according to the new ward use. For example, when an idle ward is adjusted to a temporary isolation ward, the intelligent lighting system increases the brightness, and the air conditioning system adjusts to a specific ventilation mode to ensure the use requirements of the isolation ward. The intelligent logistics system plays an important role in material allocation and equipment transportation. When medical supplies need to be delivered to a certain department, the intelligent logistics system quickly and accurately transports the required supplies to the designated department according to the instruction through methods such as rail logistics, pneumatic logistics, or AGV (Automated Guided Vehicle).

[0142] In a specific embodiment, the process of executing Step 1 may specifically include the following steps:

[0143] (1) Installation of sensors and positioning devices

[0144] (2) Construction of the Internet of Things network

[0145] (3) Configuration of the data processing and analysis server

[0146] (4) Establishment of Hospital Space Management Database and Information Entry

[0147] Specifically, first of all, the installation work of sensors and positioning devices is carried out in an orderly manner in various areas of the hospital. Taking the ward as an example, in order to achieve precise monitoring of the activities of patients and medical staff, multiple infrared sensors are carefully arranged in each ward. The sensors installed at the door can keenly capture the entry and exit movements of people; the sensors beside the hospital beds mainly monitor whether the patients leave the beds, etc., providing a basis for medical staff to promptly know the dynamics of patients. Temperature sensors and humidity sensors are also reasonably placed in the ward, and their high-precision characteristics can collect temperature and humidity data in real time to ensure that patients are always in a comfortable environment.

[0148] In key areas such as operating rooms and intensive care units, the monitoring of equipment status is crucial. Therefore, a large number of equipment status sensors are installed, and these sensors closely monitor information such as the operating parameters and usage duration of the equipment. For example, once the operating status of surgical equipment shows abnormalities, the sensors can quickly capture and transmit relevant data to ensure the smooth progress of the operation.

[0149] In terms of positioning devices, the positioning technologies of ultra-wideband (UWB), Bluetooth, and Wi-Fi are comprehensively used. With the advantage of high precision, UWB positioning technology is mainly used for precise positioning of important medical equipment and special patients (such as critically ill patients and psychiatric patients), and the accuracy can reach the sub-meter level, allowing medical staff to conveniently and quickly find the required equipment or patients. The advantage of Bluetooth positioning is that the technical cost is low and the power consumption is small, which is suitable for tracking the positions of medical staff and can be used to contact and dispatch more quickly when needed. Wi-Fi positioning technology can utilize the existing network infrastructure in the hospital to achieve large-scale positioning of patients, medical staff, and equipment in the hospital, meeting the basic needs of daily system management.

[0150] Building an Internet of Things network covering the whole hospital is the key support for the entire system. In each floor and area of the hospital building, the Internet of Things gateways are reasonably arranged. In the ward area, one gateway is set for every few wards to ensure stable signal coverage; in open areas such as corridors and lobbies, according to the space size and signal attenuation situation, the gateway positions are scientifically set to ensure no dead spots in the signal.

[0151] For areas where the signal is easily interfered with, such as equipment machine rooms and basements, special signal enhancement measures are taken. By installing signal amplifiers and optimizing the positions of gateway antennas, etc., the signal strength is effectively enhanced to ensure the stability of data transmission.

[0152] Establishing a hospital space management database is an important foundation for realizing the system functions. The database structure design covers all aspects of information in the hospital, including department information, ward information, equipment information, personnel information, and management rules, etc. The department information details the location, functions, medical staff allocation, etc. of each department, so that the system can allocate resources according to the characteristics of the departments. The ward information includes ward numbers, bed numbers, ward types (general wards, intensive care units, etc.), usage status, etc., providing a basis for the reasonable allocation of ward resources. The equipment information records the equipment name, model, location, purchase time, maintenance cycle, etc., which helps to achieve precise management of the equipment.

[0153] When entering the basic information of the hospital, a strict data review mechanism is established. Special data entry personnel are responsible for entering the information into the database. After the entry is completed, it goes through at least two rounds of review to ensure the accuracy and integrity of the data. For the entry of management rules, the personnel permissions are clearly set, such as the operation permissions of different roles like doctors, nurses, and managers for the system functions; detailed equipment maintenance rules are formulated, stipulating the maintenance cycle, maintenance standards, and maintenance processes for various types of equipment; scientific space allocation rules are set, determining the allocation principles of wards and consulting rooms according to factors such as department business volume and patient flow.

[0154] In a specific embodiment, the process of executing step 2 may specifically include the following steps:

[0155] (I) Spatial data collection strategy

[0156] (II) Data transmission guarantee measures

[0157] Specifically, first, the sensor network in the space perception module collects the spatial data of the hospital in real time according to the required collection strategy. The collection of personnel location data adopts a combination of continuous positioning and event-triggered positioning. When personnel are moving normally, the positioning device collects location data at 10-second intervals to form a rough activity trajectory of the personnel. When personnel enter specific areas (such as restricted areas like operating rooms and intensive care units) or abnormal behaviors occur (such as staying in a certain area for a long time without moving), event-driven collection is triggered, and accurate location data is immediately uploaded.

[0158] The real-time status collection data of the equipment will be set at different frequencies according to the importance and operating characteristics of the equipment. Key medical equipment (such as CT machines, magnetic resonance imaging devices, etc.) will adopt a real-time collection mode to continuously monitor operating parameters and working status; general equipment (such as office computers, printers, etc.) will collect status data at 30-minute intervals.

[0159] In terms of environmental parameter data collection, the temperature and humidity sensors collect data every 5 minutes. The air quality sensor adjusts the system collection frequency according to the real-time environmental quality status of the hospital, and speeds up the collection frequency when the air quality is poor so that the environmental changes can be grasped in a timely manner.

[0160] In order to ensure the accuracy and timely transmission of data to the data processing and analysis system, a variety of safeguards will be taken. In terms of communication link selection, a combination of wired and wireless networks is adopted. The amount of video data collected by high-definition cameras is large and has high real-time requirements. It is preferentially transmitted through wired networks, and the high bandwidth and stability of optical fibers are used to ensure data quality. Sensor data distributed throughout the hospital and difficult to wire are transmitted using wireless networks, such as Wi-Fi, Bluetooth, ZigBee, NB-IoT, etc.

[0161] In order to prevent data transmission loss and errors, a data verification and re-upload mechanism is adopted. At the data sending end, a checksum is added to each data packet, and the receiving end verifies the integrity of the data through the checksum of the data. If data errors or loss are found, the receiving end will send a re-upload request to the sending end. At the same time, the transmitted data is encrypted and the AES encryption algorithm is used to ensure the absolute security of the data, prevent the leakage of patient privacy information and the loss of sensitive hospital data.

[0162] In a specific embodiment, the process of executing step 3 may specifically include the following steps:

[0163] (I) Data preprocessing operations

[0164] 2. Application of Big Data Analysis Technology

[0165] 3. Application of artificial intelligence algorithms

[0166] After receiving the collected data, the data processing and analysis system first performs a series of preprocessing operations such as data processing, denoising, and verification. Data processing identifies and removes abnormal erroneous data caused by sensor failure or signal interference by writing a special processing algorithm. Data collected by the temperature sensor that exceeds the reasonable demand range (such as -50°C to 100°C) is marked and removed. Data denoising processing will use filtering algorithms such as Kalman filtering and wavelet filtering to eliminate noise signals in the data and make the data smoother and more accurate. The verification link ensures the accuracy and reliability of the data by checking the data format and data integrity. For example, check whether the data contains complete timestamps, sensor numbers and other information, and if there are missing errors, perform corresponding processing.

[0167] The preprocessed data will be deeply analyzed through the big data processing framework. In the Hadoop Distributed File System (HDFS), the data will be distributedly stored on each node to achieve data backup and storage. The MapReduce computing model is used to perform distributed processing on the data. For example, when statistically analyzing the personnel flow data, the data is processed in chunks, computed in parallel on multiple nodes, and finally the results are aggregated, greatly improving the processing efficiency.

[0168] During the data analysis process, a variety of data mining algorithms are applied. The clustering analysis algorithm clusters the areas with similar personnel flows to find the hot spots and time periods of personnel gathering, providing a basis for the hospital to reasonably arrange guiding personnel and adjust the space layout. The association rule mining algorithm is used to discover the potential association relationships between factors such as equipment utilization rate, patient flow, and department business volume. For example, when it is found that the patient flow in a certain department increases, the utilization rate of specific equipment in that department also rises accordingly, thus providing a reference for equipment allocation. Time series analysis predicts data such as ward turnover rate and equipment failure rate, and discovers potential problems in advance. For example, it predicts that a certain type of equipment may malfunction in the future and arranges a maintenance plan in advance.

[0169] Artificial intelligence algorithms such as machine learning and deep learning are used to model and solve complex problems in hospital space management. In terms of personnel scheduling, a machine learning algorithm is used to establish a personnel scheduling model. This model uses historical patient flow data, department business volume data, and medical staff work efficiency data as training samples. Through continuous training and optimization, it learns the relationship between personnel requirements and various factors. When the patient flow in a certain department exceeds the threshold and continues to rise, the model automatically generates a scheduling plan to increase the medical staff in that department according to the learned pattern and reasonably adjusts the work schedule of the medical staff.

[0170] In terms of equipment management, deep learning algorithms play an important role. By performing deep learning on the equipment operation data, an equipment failure prediction model is established. For example, a convolutional neural network (CNN) is used to extract and analyze the feature of the equipment operation parameter data, and learn the feature differences between the normal operation state and the failure state. When the model monitors that the equipment operation data shows abnormal features, it timely predicts the possible failure of the equipment and gives corresponding maintenance suggestions, effectively reducing the equipment failure rate and ensuring the normal operation of the hospital.

[0171] In a specific embodiment, the process of executing step 4 may specifically include the following steps:

[0172] (1) Strategy generation based on data analysis

[0173] (2) Optimization and evaluation of decisions

[0174] Based on the key indicators and analysis results output by the data processing and analysis module, combined with the pre-set management objectives, the intelligent decision-making module generates a space management strategy using machine learning algorithms. In terms of personnel scheduling, when the patient flow in a certain department exceeds the threshold and continues to rise, the intelligent decision-making module automatically generates a scheduling plan to increase the medical staff in that department according to historical data and the personnel scheduling model. For example, during the flu high-incidence season, the patient flow in the fever clinic surges, and the system predicts that the number of patients will continue to rise in the next few hours. At this time, the intelligent decision-making module transfers medical staff from other relatively idle departments to the fever clinic and adjusts the work schedules of the medical staff to ensure that there is sufficient manpower in the fever clinic to meet the patient treatment needs.

[0175] In terms of equipment allocation, according to the equipment utilization rate data and the equipment maintenance cycle, when the utilization rate of a certain type of equipment is too high and approaching the maintenance deadline, the intelligent decision-making module generates an equipment allocation plan. For example, if the utilization rate of the CT examination equipment has exceeded 80% for a consecutive week and is close to the specified cycle since the last maintenance, the system will arrange for a spare CT equipment to be put into use and notify the equipment maintenance personnel to maintain the CT equipment with high load operation to ensure the normal operation of the equipment and avoid affecting the patient examination progress due to equipment failure.

[0176] The generated space management strategy is not static, but is continuously improved through the optimization and evaluation process. During the optimization process, the constraint conditions of various factors are considered, such as the resource limitations of the hospital, the matching of personnel skills, and the compatibility of equipment. For example, during personnel scheduling, not only the allocation of the number of personnel should be considered, but also it is necessary to ensure that the allocated medical staff have the corresponding professional skills and are competent for the work of the new positions. During equipment allocation, the compatibility and substitutability between equipment should be considered to avoid affecting the quality of medical services due to improper equipment allocation.

[0177] Decision evaluation is achieved by establishing an evaluation index system, which includes multiple indexes such as patient satisfaction, equipment utilization rate, and hospital operation cost. After implementing the space management strategy, relevant data is collected and quantitative evaluation is carried out on each index. If the patient satisfaction is improved, the equipment utilization rate is increased, and the operation cost is reduced after a certain strategy is implemented, it indicates that the strategy is effective; otherwise, the strategy needs to be adjusted and optimized, and re-evaluated until the expected management objectives are achieved.

[0178] In a specific embodiment, the process of executing step 5 may specifically include the following steps:

[0179] (1) Instruction execution and space adjustment

[0180] (2) Information feedback and system optimization

[0181] The execution module is responsible for converting the instructions generated by the intelligent decision-making module into actual actions, and dynamically adjusts and manages the hospital space by controlling Internet of Things devices and systems. When receiving an instruction to adjust the use of a ward, the automatic access control system quickly updates the access settings of the ward and prohibits unauthorized personnel from entering the ward with adjusted use. At the same time, the intelligent lighting system and air conditioning system adjust the corresponding parameters according to the new ward use. For example, when an idle ward is adjusted to a temporary isolation ward, the intelligent lighting system enhances the brightness to meet the lighting requirements for medical operations; the air conditioning system is adjusted to a specific ventilation mode to ensure the air quality of the isolation ward and prevent virus transmission.

[0182] The intelligent logistics system plays an important role in material allocation and equipment transportation. When medical supplies need to be delivered to a certain department, the intelligent logistics system, according to the instruction, transports the required supplies quickly and accurately to the designated department through methods such as track logistics, pneumatic logistics, or AGV (Automated Guided Vehicle). In terms of equipment transportation, for the handling of large medical equipment, the intelligent logistics system will plan a reasonable transportation route to avoid crowded areas and ensure the safety and efficiency of the transportation process.

[0183] The user interaction module timely feeds back relevant information on space management to hospital administrators, medical staff, and patients. Hospital administrators can view the implementation of space management strategies and real-time data reports through the Web interface, such as information on the patient flow, equipment utilization rate, and ward occupancy rate in each department, so as to promptly discover problems and make adjustments. Medical staff can receive work arrangements and patient information updates through the mobile application, understand their scheduling plans, the conditions of the patients they are responsible for, and the material requirements of the department, etc., to improve work efficiency. Patients can view the adjusted information on the medical treatment process, waiting time, and inspection reports through the hospital's self-service query terminal or mobile application, reasonably arrange their time, and reduce waiting time.

[0184] At the same time, the system is optimized according to the information fed back by users. If a patient feedbacks that the navigation instructions in a certain area are not clear, the system will optimize the navigation information in that area to provide more accurate and intuitive navigation guidance. If a medical staff feedbacks that the operation of a certain device is inconvenient or its functions are not perfect, the system will promptly notify the device supplier for improvement, or adjust the device management strategy to improve the work experience and work efficiency of medical staff. Through continuous information feedback and system optimization, the performance and service quality of the hospital intelligent space management system are continuously improved, providing strong guarantee for the efficient operation of the hospital and the high-quality medical experience of patients.

[0185] The embodiments described above are only descriptions of the preferred embodiments of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A hospital smart space management system, characterized in that: The system includes: a space perception module, a data processing and analysis module, an intelligent decision-making module, an execution module and a user interaction module; The spatial perception module is used to collect hospital spatial data in real time and transmit it to the data processing and analysis module via the Internet of Things communication protocol; The data processing and analysis module is used to process, classify, store and deeply analyze hospital space data and extract key feature indicators; The intelligent decision-making module is used to generate space management strategies using artificial intelligence algorithms based on key feature indicators and management objectives; The execution module is used to receive the space management strategy and control the automation equipment and system to adjust the hospital space; The user interaction module is used to realize two-way information transmission and support user feedback optimization system.

2. The system according to claim 1, characterized in that The space perception module includes: a personnel data unit, a device status data unit, and an environmental parameter data unit; The personnel data unit is used to collect data of continuous positioning and event-triggered positioning when the position of a person changes, so as to obtain key information of the person's activities; The equipment status data unit is used to set the collection frequency according to the importance of the equipment and the characteristics of its operation, and to collect key equipment status data in real time; The environmental parameter data unit is used to collect environmental data according to different environments and provide data support for judging the flow of ward personnel and environmental comfort.

3. The system according to claim 1, characterized in that The intelligent decision-making module includes: a personnel dispatching unit, an equipment deployment unit, and a ward allocation unit; The personnel dispatching unit is used to intelligently deploy medical staff and adjust the shift schedule during personnel dispatching; The equipment allocation unit is used to arrange spare equipment and notify maintenance based on equipment utilization, maintenance cycle, and performance parameters; The ward allocation unit is used to allocate wards based on the patient's condition, ward type and usage status.

4. The system according to claim 1, characterized in that The execution modules include: automatic access control system, intelligent lighting and air conditioning system, and intelligent logistics system; The automatic access control system is used to update permissions according to system instructions; The intelligent lighting and air conditioning system is used to monitor real-time environmental data through sensors and automatically adjust according to system settings; The intelligent logistics system is used to select corresponding rail logistics, pneumatic logistics or AGV transportation methods to transport materials and equipment according to the location of material and equipment requirements.

5. A hospital smart space management method, characterized in that: The hospital smart space management system according to any one of claims 1 to 4 is implemented, and the method comprises the following steps: Step 1: Initialize the system of hospital smart space; Step 2: Real-time collection and transmission of hospital smart space data; Step 3: Process and analyze hospital smart space data; Step 4: Make management decisions for the hospital smart space based on the processed and analyzed hospital smart space data; Step 5: Execution and feedback of management decisions on hospital smart space.

6. The method according to claim 5, characterized in that In step 3, the processing and analysis of hospital smart space data includes: Process, denoise, and verify pre-processing operations on hospital smart space data; Input the pre-processed hospital smart space data into the big data processing framework and conduct in-depth analysis of the data; Among them, in-depth analysis of the data includes: using cluster analysis methods to cluster areas with similar personnel flow to find out hot areas and time periods where people gather; using association rule mining to discover potential correlations between equipment utilization rate and patient flow and department business volume factors; using time series analysis to predict ward turnover rate and equipment failure rate data to discover potential problems in advance.

7. The method according to claim 5, characterized in that In step 4, based on the processed and analyzed hospital smart space data, making management decisions for the hospital smart space includes: In terms of personnel scheduling, when the patient flow in a department exceeds the threshold and continues to rise, a scheduling plan for increasing the number of medical staff in the department is automatically generated based on historical data and the personnel scheduling model; In terms of equipment allocation, based on equipment utilization data and equipment maintenance cycle, when the utilization rate of a certain type of equipment is higher than the preset threshold, an equipment allocation plan is generated.

8. The method according to claim 5, characterized in that In step 5, the management decision execution and feedback of the hospital smart space include: When receiving the instruction to adjust the use of the ward, the automatic access control system updates the permission settings of the ward, prohibiting irrelevant personnel from entering the ward with the adjusted use. At the same time, the intelligent lighting system and air conditioning system adjust the corresponding parameters according to the new use of the ward; When medical supplies need to be delivered to a certain department, the intelligent logistics system will transport the required supplies to the designated department according to the instructions.

Images