Intelligent hospital logistics management platform

Abstract

The invention discloses an intelligent hospital logistics management platform, and relates to the technical field of logistics management. Comprising the following steps: establishing a hospital visual model through BIM, and adding a data acquisition device to a corresponding position of the visual model; performing type label setting on the data acquisition device according to the acquired data type, and then setting an attribute label according to the professional attribute of the target space where the data acquisition device is located; displaying corresponding equipment data according to the selected type tag and / or attribute tag; the method comprises the following steps: summarizing logistics information which comprises equipment data and repair data, identifying abnormal data in the equipment data, setting the corresponding equipment data as the abnormal data according to the content of the repair data, carrying out alarm processing on the abnormal data, processing according to position information, summarizing islanding logistics information, and sending the summarized islanding logistics information to a server; the service functions of logistics repair, alarm processing, energy analysis and the like of the whole hospital are undertaken, and the overall management level of the hospital is optimized.

Description

Technical Field

[0001] The present application relates to the field of logistics management technology, and specifically to a smart hospital logistics management platform. Background Art

[0002] With the continuous development of information technology, the intelligentization and digitization of hospital logistics management has become an important direction for the modern medical industry to improve management efficiency and reduce operating costs. Traditional hospital logistics management mainly relies on manual methods to perform tasks such as equipment maintenance, space planning and management, and energy consumption monitoring. Information collection and data processing are cumbersome and inefficient. This traditional method often has problems such as inaccurate data, long response time, and serious waste of resources. It cannot meet the needs of modern hospitals in terms of high efficiency, energy saving, and refined management in a timely manner.

[0003] At present, the technical means of hospital logistics management mostly rely on independent subsystems, and there is often a lack of effective integration between the systems, resulting in serious information islands. For example, the equipment management module, energy consumption monitoring module, maintenance management module, etc. are scattered and independent in actual applications, making it difficult to form a unified data flow and real-time monitoring system. At the same time, equipment failures and maintenance issues mostly rely on manual inspections and records, making it difficult to achieve real-time monitoring and efficient processing, delaying fault response and maintenance time, and thus affecting the normal operation of the hospital.

[0004] Especially in terms of equipment management, traditional methods often lack accurate equipment location and status information, and lack efficient positioning, monitoring and maintenance mechanisms. As the scale of hospitals and the number of equipment increase, the challenges faced by managers are also increasing. Problems such as long equipment failure response time, low maintenance efficiency, and inaccurate energy consumption monitoring have caused the hospital's logistics management to operate poorly, affecting the overall operational efficiency of the hospital. Summary of the invention

[0005] In response to the shortcomings of the existing technology, this application proposes a smart hospital logistics management platform, which aims to solve many pain points in traditional management methods through digital and intelligent means. The platform uses digital space modules to establish a visual space model of the hospital based on BIM technology, and obtains various information about equipment and space in real time through data acquisition devices to form a comprehensive and dynamic management system. At the same time, through the integrated design of multiple modules, it not only realizes automatic identification and alarm mechanisms to timely discover or obtain abnormal data, optimizes energy consumption management, and improves the overall efficiency of hospital logistics management. The specific technical solutions are as follows: Provide a smart hospital logistics management platform, including: The digital space module obtains the geometric information, professional attributes and status information of all target spaces in the hospital and establishes a visual model through BIM; the data acquisition device in the target space is added to the corresponding position of the visual model, the professional attributes include the department to which it belongs, and the status information includes whether it is in use or not in use; The device management module sets a type label for the data acquisition device according to the type of data collected, and then sets an attribute label according to the professional attribute of the target space where the data acquisition device is located; and displays the corresponding device data according to the selected type label and / or attribute label; The information processing module summarizes the logistics information of the entire hospital, wherein the logistics information includes the equipment data, automatically identifies abnormal data in the equipment data, performs alarm processing on the abnormal data, and processes the data according to the location of the data acquisition device corresponding to the abnormal data provided. The logistics information also includes repair data. According to the content of the repair data, the corresponding equipment data is set as abnormal data.

[0006] In one embodiment of the present application, an energy consumption management module is also included to obtain changes in the equipment data of different target spaces under different human flow rates, and changes in the equipment data of different target spaces under different outdoor temperatures, to obtain the correspondence between the human flow rate, outdoor temperature and the equipment data, and to obtain the normal energy consumption range of the current target space based on the current human flow rate and outdoor temperature. When the equipment data exceeds the current normal energy consumption range, it is regarded as the abnormal data.

[0007] In one embodiment of the present application, it also includes an energy consumption prediction module, which obtains the historical equipment data collected by the data acquisition device at each location, as well as the flow of people and the outdoor temperature at the corresponding time, and inputs them into the first neural network training to obtain the corresponding relationship between the flow of people and the outdoor temperature and the equipment data collected by the data acquisition device at each location; the first neural network monitors the equipment data in real time, obtains the future outdoor temperature through the Internet of Things, and predicts the future flow of people, and obtains the predicted data collected by the data acquisition device at each location at a future time through the first neural network.

[0008] In one embodiment of the present application, the future pedestrian flow is trained by inputting the pedestrian flow in each time period under different date attributes in historical data into the second neural network, so that the future pedestrian flow can be predicted based on the date attributes of the future time, and the date attributes include weekdays, holidays, and peak periods of specific diseases.

[0009] In one embodiment of the present application, the information processing module also includes an abnormality prediction unit, which obtains historical data, and uses the data within a preset time period before the abnormal data appears as predicted data. The predicted data is input into a third neural network for training. The third neural network monitors the device data in real time, and when the predicted data is identified, an abnormality warning notification is issued to the staff.

[0010] In one embodiment of the present application, the information processing module also includes a hierarchical processing unit, which classifies the abnormal data according to the severity of the incident that the abnormal data may cause, and dynamically schedules staff to handle the abnormal data with a high level; for the abnormal data of the same level, the more the abnormal data exceeds the normal data, the greater the probability that it may cause an incident, and the abnormal data with a high probability is processed first.

[0011] In one embodiment of the present application, the information processing module also includes a time estimation unit, which estimates the processing time of the current abnormal data by the processing time of various abnormal data in the historical data. When the estimated processing time of the target space is greater than a threshold, the target space whose current status information is unused is selected as the transition space; the professional attributes and status information of the data acquisition device in the target space are changed accordingly, and the transition time is set according to the processing time.

[0012] In one embodiment of the present application, the information processing module further includes a personnel management unit, and the personnel management unit includes a database subunit and an identification subunit: The database subunit establishes a skill information database, which includes portrait information and qualification information of the staff, and various processing standards of the abnormal data, wherein the processing standards include standard processing procedures and qualification information required by the current abnormal data processing personnel, and inputs the data in the skill information database into the fourth neural network for training; The identification subunit obtains the current processing standard of the abnormal data, collects personnel images through an image acquisition device, and collects the processing process of the abnormal data by the staff, and inputs them into the fourth neural network for comparative identification. When it is identified that the current staff does not have the qualifications required for the abnormal data processing personnel, or the current workflow is different from the standard processing process, an alarm prompt is issued.

[0013] In one embodiment of the present application, the standard processing flow divides the time according to the estimated processing time of the abnormal data to obtain the estimated time for each step. The fourth neural network identifies the abnormal data processing process collected by the image acquisition device. When the actual time used for the current processing process exceeds the estimated time, an alarm is given to the staff; and the transition time is extended according to the exceeded time.

[0014] In one embodiment of the present application, a line optimization module is also included to obtain the line design drawings corresponding to all the type labels, as well as the design loads of the bus and each branch; the data collected by the corresponding data acquisition device on the same branch is statistically compared with the corresponding design load, and the position of the target space on the branch that exceeds the design load is optimized, and the optimization method includes exchanging part of the target space on the branch with the target space with relatively low energy consumption on other branches, or increasing the design load of the branch. (The expected energy consumption is increased, and replacement or upgrading is carried out in advance.

[0015] This application has the following beneficial effects: 1. The platform uses digital space modules to establish a visual space model of the hospital based on BIM technology, and obtains various information about equipment and space in real time through data acquisition devices to form a comprehensive and dynamic management system. The integrated design of the equipment management module and the information processing module not only realizes real-time monitoring of equipment status, but also can detect abnormal data in a timely manner through automatic identification and alarm mechanisms, significantly improving the response speed and maintenance efficiency of equipment management. At the same time, the platform can also automatically receive repair data and effectively combine abnormal data. The automatically identified abnormal data and repair data are both abnormal data, and the same alarm processing is performed. Through the application of this intelligent platform, the hospital can accurately locate, quickly respond to and repair equipment failures, and can reduce manual operations through digital management, improve work efficiency, and reduce resource waste; at the same time, the platform displays equipment data of corresponding types and / or corresponding departments according to different type labels and / or attribute labels, and reminds the parts with higher energy consumption according to the energy consumption data of different departments; optimize energy consumption management, improve the comprehensive efficiency of hospital logistics management, summarize scattered and isolated logistics information, undertake logistics repair, alarm processing, energy analysis and other service functions of the whole hospital, and optimize the overall management level of the hospital.

[0016] 2. Considering that different human flows usually directly affect the number of equipment operations and operating power, but due to the different energy-consuming equipment and the different number of equipment in different target spaces, human flows have different effects on the equipment data in different target spaces; at the same time, due to the large temperature differences in different seasons, higher temperatures require more electricity for cooling, and lower temperatures require more gas and / or electricity for heating, so the room temperature will also affect the equipment data in the target space; take human flow and outdoor temperature as independent variables, and the equipment data as dependent variables to construct a multivariate regression model, such as linear regression, support vector machine, etc.; input the current The normal energy consumption range of the target space is obtained based on the previous pedestrian flow and outdoor temperature. When the equipment data exceeds the normal energy consumption range, it is regarded as the abnormal data, and the staff is notified to go for inspection and processing. For example, the air conditioner is not turned off after the outpatient clinic is off work, resulting in high power consumption in the target space with zero pedestrian flow, or a short circuit in the equipment causes an abnormal increase in power consumption. Furthermore, the sum of the equipment data collected by the data collection device with the same type label and attribute label is the department energy consumption, and the energy consumption of all departments is obtained. The number of times and the amount of excess of all departments exceeding the normal energy consumption range are counted, and department notifications are made to improve energy consumption management efficiency and effectively save energy.

[0017] 3. It also includes obtaining the equipment data in the historical data and the flow of people and outdoor temperature at the corresponding time, and the first neural network obtains the corresponding relationship between the flow of people, the outdoor temperature and the equipment data; that is, the equipment data predicted in the future time, that is, the predicted data, can be obtained by inputting the future outdoor temperature to the first neural network, which can be obtained by searching the future meteorological data through the Internet of Things, and inputting the future flow of people, and preparing energy in advance through the predicted data. For example, if the temperature rises in the future time, the power consumption of the air conditioner will increase, and the power will be reserved and / or the circuit load will be upgraded in advance. Further, when the energy is insufficient, the existing energy is allocated in advance according to the importance of different departments. Further, the future flow of people is trained by inputting the flow of people in each time period under different date attributes in the historical data to the second neural network, so that the future flow of people can be predicted according to the date attributes of the future time. The date attributes include working days, holidays, and the peak period of specific diseases; for example, respiratory diseases are prevalent during the transition between spring and summer, so the flow of people in the fever clinic and respiratory medicine department increases during the transition between spring and summer.

[0018] 4. The predicted data within a preset time period before the abnormal data appears is trained by the third neural network to realize real-time monitoring of the equipment data. When the predicted data is identified, an abnormal warning notification is issued to the staff, and the equipment is processed before the abnormality occurs to avoid the impact of the abnormality on the personnel. For example, the elevator fault can be maintained in advance to reduce the risk of people being trapped in the elevator, while reducing the number of abnormalities and effectively delaying the life of the equipment.

[0019] 5. Classify the abnormal data into levels, the higher the level, the higher the danger. For example, the danger of electric shock and casualties caused by equipment leakage is greater than the danger of dark roads caused by a broken light bulb. High-level abnormal data are processed first. Furthermore, the abnormal data of the same level are processed first with more serious abnormalities. For example, equipment short circuit causes increased current. The greater the current, the more likely it is to cause a fire. Therefore, the abnormal data with more serious abnormalities are processed first to ensure personnel safety and reduce resource waste.

[0020] 6. Estimate the processing time of the same abnormal data through the processing time of various abnormal data in the historical data. For situations with long processing time, such as painting a room, replacing a circuit, etc., the platform displays the target space that is currently unused, and gives priority to selecting the target space with the same professional attributes and the unused status attribute as the transition space. If no selection is available, select the target space with different professional attributes and the unused status attribute as the transition space, and provide the contact information of the corresponding department; automatically change the professional attributes and status information of the data acquisition device in the target space after transferring to the transition space, and set the transition time according to the processing time to facilitate the status change and subsequent use of the transition space; at the same time, the platform can actively change the professional attributes and status data of the target space, such as changes to geometric information that require new design drawings and reviews.

[0021] 7. The platform also includes the management of staff members. Specifically, the database subunit stores staff member information, including staff member portrait information and corresponding operating qualifications. Before processing the abnormal data, the qualifications required for processing are obtained. The identification subunit identifies the personnel who are processing the abnormal data through the fourth neural network. After the identification is completed, it is checked whether the staff member has the corresponding operating qualifications. If not, an alarm is issued to prevent staff members without operating qualifications or even non-staff members from processing abnormal data and causing safety accidents. At the same time, the working hours, operating hours, and workload of the staff can also be collected according to the image acquisition device, which is more convenient for the management of the staff, including the issuance of staff bonuses. , increase or decrease the number of staff with relevant qualifications; at the same time, the database sub-unit also stores standard processes for processing various abnormal data. When the staff processes the abnormal data, if the operating process is different from the standard process, an alarm will be issued to standardize the staff's operations. For operations completed according to the standard process, the process image data will be saved to verify whether it is executed as a new standard process; further, according to the completion time of the standard process in the historical data, the time for each step of the standard process is divided. When the staff processes the abnormal data, if the time progress is slower than the standard process, an alarm will be issued. If the target space uses a transition space, the transition time will be changed in real time according to the exceeded time.

[0022] 8. Obtain existing line design drawings, including circuit design drawings, water pipeline design drawings, and gas pipeline design drawings, and obtain the design load of each branch, and compare it with the sum of the equipment data on each branch. If it exceeds the design load, optimize it. The optimization method includes exchanging the target space with higher energy consumption on the branch that exceeds the design load with the target space with lower energy consumption on the branch that does not exceed the design load, reducing the load of the branch and reducing the risk of line use; in addition, the branch load capacity can be improved, such as replacing the circuit with a larger design load. Furthermore, the expected energy consumption changes are updated in real time. When the expected equipment data rises to exceed the design load, the target space or line is replaced in advance, so that the equipment data is always under the design load, improving the safety of line use. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0024] Figure 1 A schematic diagram of the electronic device structure of the hardware operating environment involved in an embodiment of the present application.

[0025] Figure 2It is a functional module diagram of a smart hospital logistics management platform provided in an embodiment of the present application.

[0026] Figure 3 It is a module construction diagram of a smart hospital logistics management platform provided in an embodiment of the present application.

[0027] Symbols in the figure: 1001 - processor, 1002 - communication bus, 1003 - user interface, 1004 - network interface, 1005 - memory. DETAILED DESCRIPTION

[0028] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0029] The solution of the present application is further described below in conjunction with the accompanying drawings.

[0030] like Figure 1 As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0031] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0032] like Figure 1As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module and a data storage module.

[0033] exist Figure 1 In the electronic device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in the electronic device, and the electronic device calls the corresponding system of a smart hospital logistics management platform stored in the data storage module in the memory 1005 through the processor 1001, and executes the smart hospital logistics management method.

[0034] Based on the aforementioned hardware operating environment and system architecture, refer to Figure 2 and Figure 3 As shown, a smart hospital logistics management platform is provided, including: The digital space module obtains the geometric information, professional attributes and status information of all target spaces in the hospital and establishes a visual model through BIM; the data acquisition device in the target space is added to the corresponding position of the visual model, the professional attributes include the department to which it belongs, and the status information includes whether it is in use or not in use; It should be noted that the target space of the hospital includes various treatment rooms, offices, wards, corridors and halls, etc. The visualization model of the hospital space is established through BIM to realize the visualization of the space management of all the target spaces of the hospital; the data collection device with corresponding functions is set according to specific needs, including but not limited to an electric meter for recording electric energy consumption, a water meter for recording water usage, a gas meter for recording gas usage, and a gas, temperature and humidity detection device; the professional attribute is the department to which the target space belongs, which can be specifically set according to the actual situation of each hospital, such as different departments and administrative departments; The device management module sets a type label for the data acquisition device according to the type of data collected, and then sets an attribute label according to the professional attribute of the target space where the data acquisition device is located; and displays the corresponding device data according to the selected type label and / or attribute label; It should be noted that the type label is set according to the type of the data acquisition device, such as a water meter or an electric meter; the attribute label is set according to the professional attribute of the target space, and the equipment data of the corresponding type is displayed by selecting the type label on the smart hospital logistics management platform; the equipment data of the corresponding department is displayed by selecting the attribute label; further, the department can be subdivided to flexibly display the equipment data of each area; the type label and the attribute label can also be selected to display the equipment data of the corresponding type in the corresponding department; the equipment data is classified according to the data collected by the data acquisition device, such as energy consumption data and environmental data; The information processing module summarizes the logistics information of the entire hospital, wherein the logistics information includes the equipment data, automatically identifies abnormal data in the equipment data, performs alarm processing on the abnormal data, and processes the data according to the location of the data acquisition device corresponding to the abnormal data provided. The logistics information also includes repair data. According to the content of the repair data, the corresponding equipment data is set as abnormal data.

[0035] It should be noted that the neural network can be trained by using the existing abnormal data to realize automatic identification of abnormal data in the device data; In this implementation, the platform uses digital space modules to build a visual space model of the hospital based on BIM technology, and obtains various information about equipment and space in real time through data acquisition devices to form a comprehensive and dynamic management system. The integrated design of the equipment management module and the information processing module not only realizes real-time monitoring of equipment status, but also can detect abnormal data in a timely manner through automatic identification and alarm mechanisms, significantly improving the response speed and maintenance efficiency of equipment management. At the same time, the platform can also automatically receive repair data and effectively combine abnormal data. The automatically identified abnormal data and repair data are both abnormal data, and the same alarm processing is performed. Through the application of this intelligent platform, the hospital can accurately locate, quickly respond to and repair equipment failures, and can reduce manual operations through digital management, improve work efficiency, and reduce resource waste; at the same time, the platform displays equipment data of corresponding types and / or corresponding departments according to different type labels and / or attribute labels, and reminds the parts with higher energy consumption according to the energy consumption data of different departments; optimize energy consumption management, improve the comprehensive efficiency of hospital logistics management, summarize scattered and isolated logistics information, undertake logistics repair, alarm processing, energy analysis and other service functions of the whole hospital, and optimize the overall management level of the hospital.

[0036] In one embodiment of the present application, an energy consumption management module is also included to obtain changes in the equipment data of different target spaces under different human flow rates, and changes in the equipment data of different target spaces under different outdoor temperatures, to obtain the correspondence between the human flow rate, outdoor temperature and the equipment data, and to obtain the normal energy consumption range of the current target space based on the current human flow rate and outdoor temperature. When the equipment data exceeds the current normal energy consumption range, it is regarded as the abnormal data.

[0037] In this embodiment, it is considered that different human flows usually directly affect the number of times and the operating power of the equipment. However, due to the different energy-consuming devices and the different numbers of devices in different target spaces, the human flow has different effects on the equipment data in different target spaces. At the same time, due to the large temperature differences in different seasons, higher temperatures require more electricity for cooling, and lower temperatures require more gas and / or electricity for heating. Therefore, the room temperature will also affect the equipment data in the target space. The human flow and outdoor temperature are used as independent variables, and the equipment data are used as dependent variables to construct a multivariate regression model, such as linear regression, support vector machine, etc. The current flow of people and outdoor temperature are input to obtain the normal energy consumption range of the current target space. When the equipment data exceeds the normal energy consumption range, it is regarded as the abnormal data, and the staff is notified to check and handle it. For example, the air conditioner is not turned off after the outpatient clinic is off work, resulting in high power consumption in the target space with zero flow, or a short circuit in the equipment causes an abnormal increase in power consumption. Furthermore, the sum of the equipment data collected by the data acquisition device with the same type label and attribute label is the department energy consumption, and the energy consumption of all departments is obtained. The number of times and the amount of excess of all departments exceeding the normal energy consumption range are counted, and department notifications are made to improve energy consumption management efficiency and effectively save energy.

[0038] In one embodiment of the present application, it also includes an energy consumption prediction module, which obtains the historical equipment data collected by the data acquisition device at each location, as well as the flow of people and the outdoor temperature at the corresponding time, and inputs them into the first neural network training to obtain the corresponding relationship between the flow of people and the outdoor temperature and the equipment data collected by the data acquisition device at each location; the first neural network monitors the equipment data in real time, obtains the future outdoor temperature through the Internet of Things, and predicts the future flow of people, and obtains the predicted data collected by the data acquisition device at each location at a future time through the first neural network.

[0039] In one embodiment of the present application, the future pedestrian flow is trained by inputting the pedestrian flow in each time period under different date attributes in historical data into the second neural network, so that the future pedestrian flow can be predicted based on the date attributes of the future time, and the date attributes include weekdays, holidays, and peak periods of specific diseases.

[0040] In this embodiment, it also includes obtaining the equipment data in the historical data and the flow of people and outdoor temperature at the corresponding time, and the first neural network obtains the corresponding relationship between the flow of people and the outdoor temperature and the equipment data; that is, the equipment data predicted in the future time, that is, the predicted data, can be obtained by inputting the future outdoor temperature to the first neural network, which can be obtained by searching the future meteorological data through the Internet of Things, and inputting the future flow of people, and preparing energy in advance through the predicted data. For example, if the temperature rises in the future time, the power consumption of the air conditioner will increase, and the power will be reserved and / or the circuit load will be upgraded in advance. Further, when energy is insufficient, the existing energy is allocated in advance according to the importance of different departments. Further, the future flow of people is trained by inputting the flow of people in each time period under different date attributes in the historical data to the second neural network, so that the future flow of people can be predicted according to the date attributes of the future time. The date attributes include working days, holidays, and the peak period of specific diseases; for example, respiratory diseases are prevalent during the transition between spring and summer, so the flow of people in the fever clinic and respiratory medicine department increases during the transition between spring and summer.

[0041] In one embodiment of the present application, the information processing module also includes an abnormality prediction unit, which obtains historical data, and uses the data within a preset time period before the abnormal data appears as predicted data. The predicted data is input into a third neural network for training. The third neural network monitors the device data in real time, and when the predicted data is identified, an abnormality warning notification is issued to the staff.

[0042] In this embodiment, the predicted data within a preset time period before the abnormal data appears is trained by the third neural network to realize real-time monitoring of the equipment data. When the predicted data is identified, an abnormal warning notification is issued to the staff, and the equipment is processed before the abnormality occurs to avoid the impact of the equipment abnormality on personnel. For example, elevator faults can be maintained in advance to reduce the risk of people being trapped in the elevator, while reducing the number of abnormalities and effectively delaying the life of the equipment.

[0043] In one embodiment of the present application, the information processing module also includes a hierarchical processing unit, which classifies the abnormal data according to the severity of the incident that the abnormal data may cause, and dynamically schedules staff to handle the abnormal data with a high level; for the abnormal data of the same level, the more the abnormal data exceeds the normal data, the greater the probability that it may cause an incident, and the abnormal data with a high probability is processed first.

[0044] In this embodiment, the abnormal data is classified into levels, and the higher the level, the higher the danger. For example, the danger of electric shock and casualties caused by equipment leakage is greater than the danger of a broken light bulb causing a dark road. High-level abnormal data are processed first. Furthermore, abnormal data of the same level are processed first with more serious abnormalities. For example, a short circuit in equipment causes an increase in current. The greater the current, the more likely it is to cause a fire. Therefore, the abnormal data with more serious abnormalities are processed first to ensure personnel safety and reduce waste of resources.

[0045] In one embodiment of the present application, the information processing module also includes a time estimation unit, which estimates the processing time of the current abnormal data by the processing time of various abnormal data in the historical data. When the estimated processing time of the target space is greater than a threshold, the target space whose current status information is unused is selected as the transition space; the professional attributes and status information of the data acquisition device in the target space are changed accordingly, and the transition time is set according to the processing time.

[0046] In this embodiment, the processing time of the same abnormal data is estimated by the processing time of various abnormal data in the historical data. For situations where the processing time is long, such as painting a room, replacing a circuit, etc., the target space that is currently unused is displayed through the platform, and the target space with the same professional attributes and the unused status attribute is preferentially selected as the transition space. If no selection is made, the target space with different professional attributes and the unused status attribute is selected as the transition space, and the contact information of the corresponding department is provided; after transferring to the transition space, the professional attributes and status information of the data acquisition device in the target space are automatically changed, and the transition time is set according to the processing time to facilitate the status change and subsequent use of the transition space; at the same time, the professional attributes and status data of the target space can be actively changed through the platform, such as changes to geometric information that require new design drawings and reviews.

[0047] In one embodiment of the present application, the information processing module further includes a personnel management unit, and the personnel management unit includes a database subunit and an identification subunit: The database subunit establishes a skill information database, which includes portrait information and qualification information of the staff, and various processing standards of the abnormal data, wherein the processing standards include standard processing procedures and qualification information required by the current abnormal data processing personnel, and inputs the data in the skill information database into the fourth neural network for training; The identification subunit obtains the current processing standard of the abnormal data, collects personnel images through an image acquisition device, and collects the processing process of the abnormal data by the staff, and inputs them into the fourth neural network for comparative identification. When it is identified that the current staff does not have the qualifications required for the abnormal data processing personnel, or the current workflow is different from the standard processing process, an alarm prompt is issued.

[0048] It should be noted that different qualifications are required to handle different abnormal data. For example, the staff who handle circuit failures need to hold an electrician certificate, and the staff who handle elevator failures need a special equipment operator certificate (elevator type), etc. In one embodiment of the present application, the standard processing flow divides the time according to the estimated processing time of the abnormal data to obtain the estimated time for each step. The fourth neural network identifies the abnormal data processing process collected by the image acquisition device. When the actual time used for the current processing process exceeds the estimated time, an alarm is given to the staff; and the transition time is extended according to the exceeded time.

[0049] In this embodiment, the platform also includes the management of staff members, specifically, the staff member information is stored through the database subunit, including the staff member's portrait information and corresponding operating qualifications; before processing the abnormal data, the qualifications required for processing are obtained, and the identification subunit identifies the personnel who are processing the abnormal data through the fourth neural network. After the identification is completed, it is checked whether the staff member has the corresponding operating qualifications. If not, an alarm is issued to avoid staff members without operating qualifications or even non-staff members from processing abnormal data and causing safety accidents; at the same time, the working hours, operating hours, and workload of the staff member can also be collected according to the image acquisition device, which is more convenient for the management of the staff, including personnel rewards and bonuses. Funds are issued, and the number of staff with relevant qualifications is increased or decreased; at the same time, the database subunit also stores standard processes for processing various abnormal data. When the staff processes the abnormal data, if the operating process is different from the standard process, an alarm is issued to standardize the staff's operation. For operations completed according to the standard process, the process image data is saved to verify whether it is executed as a new standard process; further, according to the completion time of the standard process in the historical data, the time of each step of the standard process is divided. When the staff processes the abnormal data, if the time progress is slower than the standard process, an alarm is issued. If the target space uses a transition space, the transition time is changed in real time according to the exceeded time.

[0050] In one embodiment of the present application, it also includes a line optimization module, which obtains the line design drawings corresponding to all the type labels, as well as the design loads of the bus and each branch; statistically compares the data collected by the corresponding data acquisition device on the same branch with the corresponding design load, and optimizes the position of the target space on the branch that exceeds the design load. The optimization method includes exchanging part of the target space on the branch with the relatively low energy consumption target space on other branches, or increasing the design load of the branch.

[0051] In this embodiment, the existing line design drawings are obtained, including circuit design drawings, water pipeline design drawings, and gas pipeline design drawings, and the design load of each branch is obtained, and compared with the sum of the equipment data on each branch. If the design load is exceeded, optimization is performed. The optimization method includes exchanging the target space with higher energy consumption on the branch that exceeds the design load with the target space with lower energy consumption on the branch that does not exceed the design load, thereby reducing the load of the branch and reducing the risk of line use; in addition, the branch load capacity can be improved, such as replacing a circuit with a larger design load. Furthermore, the expected energy consumption changes are updated in real time. When the expected equipment data rises to exceed the design load, the target space or line is replaced in advance, so that the equipment data is always under the design load, thereby improving the safety of line use.

[0052] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that an article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such article or device. In the absence of more restrictions, the elements defined by the sentence "includes..." do not exclude the existence of other identical elements in the article or device including the elements.

[0053] The above is a detailed introduction to the provided intelligent hospital logistics management platform. This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the intelligent hospital logistics management platform and its core idea of ​​this application; at the same time, for general technical personnel in this field, according to the idea of ​​this application, there will be changes in the specific implementation method and scope of application. In summary, the content of this specification should not be understood as a limitation on this application.

Claims

1. A smart hospital logistics management platform, characterized by: include: The digital space module obtains the geometric information, professional attributes and status information of all target spaces in the hospital and builds a visual model through BIM; The data acquisition device in the target space is added to the corresponding position of the visualization model, the professional attributes include the department to which it belongs, and the status information includes being in use and not in use; The device management module sets a type label for the data acquisition device according to the type of data collected, and then sets an attribute label according to the professional attribute of the target space where the data acquisition device is located; and displays the corresponding device data according to the selected type label and / or attribute label; The information processing module summarizes the logistics information of the entire hospital, wherein the logistics information includes the equipment data, automatically identifies abnormal data in the equipment data, performs alarm processing on the abnormal data, and processes the data according to the location of the data acquisition device corresponding to the abnormal data provided. The logistics information also includes repair data. According to the content of the repair data, the corresponding equipment data is set as abnormal data.

2. According to claim 1, a smart hospital logistics management platform is characterized in that: It also includes an energy consumption management module, which obtains the changes in the equipment data of different target spaces under different human flow rates, and the changes in the equipment data of different target spaces under different outdoor temperatures, and obtains the corresponding relationship between the human flow rate, outdoor temperature and the equipment data. According to the current human flow rate and outdoor temperature, the normal energy consumption range of the current target space is obtained. When the equipment data exceeds the current normal energy consumption range, it is regarded as the abnormal data.

3. According to claim 1, a smart hospital logistics management platform is characterized in that: It also includes an energy consumption prediction module, which obtains the historical equipment data collected by the data collection device at each location, as well as the human flow and outdoor temperature at the corresponding time, inputs them into the first neural network training, and obtains the corresponding relationship between the human flow and the outdoor temperature and the equipment data collected by the data collection device at each location; The first neural network monitors the device data in real time, obtains the future outdoor temperature through the Internet of Things, and predicts the future flow of people. The first neural network obtains the predicted data collected by the data acquisition device at each location in the future time.

4. The intelligent hospital logistics management platform according to claim 3 is characterized in that: The future pedestrian flow is trained by inputting the pedestrian flow in each time period under different date attributes in the historical data into the second neural network, so that the future pedestrian flow can be predicted according to the date attributes of the future time, and the date attributes include working days, holidays, and the peak period of specific diseases.

5. The intelligent hospital logistics management platform according to claim 1 is characterized in that: The information processing module also includes an abnormality prediction unit, which obtains historical data and uses the data within a preset time period before the abnormal data appears as prediction data. The prediction data is input into a third neural network for training. The third neural network monitors the device data in real time and issues an abnormality warning notification to the staff when the prediction data is identified.

6. The intelligent hospital logistics management platform according to claim 1 is characterized in that: The information processing module also includes a hierarchical processing unit, which classifies the abnormal data according to the severity of the incident that the abnormal data may cause, and dynamically dispatches staff to handle the abnormal data with a high level; for the abnormal data of the same level, the more the abnormal data exceeds the normal data, the greater the probability that it may cause an incident, and the abnormal data with a high probability is processed first.

7. The intelligent hospital logistics management platform according to claim 6 is characterized in that: The information processing module also includes a time estimation unit, which estimates the processing time of the current abnormal data based on the processing time of various abnormal data in the historical data. When the estimated processing time of the target space is greater than a threshold, the target space whose current status information is unused is selected as the transition space; the professional attributes and status information of the data acquisition device in the target space are changed accordingly, and the transition time is set according to the processing time.

8. The intelligent hospital logistics management platform according to claim 7 is characterized in that: The information processing module further includes a personnel management unit, which includes a database subunit and an identification subunit: The database subunit establishes a skill information database, which includes portrait information and qualification information of the staff, and various processing standards of the abnormal data, wherein the processing standards include standard processing procedures and qualification information required by the current abnormal data processing personnel, and inputs the data in the skill information database into the fourth neural network for training; The identification subunit obtains the current processing standard of the abnormal data, collects personnel images through an image acquisition device, and collects the processing process of the abnormal data by the staff, and inputs them into the fourth neural network for comparative identification. When it is identified that the current staff does not have the qualifications required for the abnormal data processing personnel, or the current workflow is different from the standard processing process, an alarm prompt is issued.

9. The intelligent hospital logistics management platform according to claim 8, characterized in that: The standard processing flow divides the processing time according to the estimated processing time of the abnormal data to obtain the estimated time of each step, and the fourth neural network identifies the abnormal data processing process collected by the image acquisition device, and when the actual time used for the current processing process exceeds the estimated time, an alarm is given to the staff; The transition time is extended according to the exceeded time.

10. A smart hospital logistics management platform according to any one of claims 2-8, characterized in that: It also includes a line optimization module, which obtains the line design drawings corresponding to all the types of labels, as well as the design loads of the bus and each branch; statistically compares the data collected by the corresponding data acquisition device on the same branch with the corresponding design load, and optimizes the position of the target space on the branch that exceeds the design load. The optimization method includes exchanging part of the target space on the branch with the relatively low energy consumption target space on other branches, or increasing the design load of the branch.

Images