Intelligent medical health management system

Abstract

The invention relates to an intelligent medical health management system which comprises a multi-learning device, a density extraction device, an information capture device, a numerical value mapping mechanism and a resource allocation mechanism. According to the invention, effective and dynamic allocation of medical resources can be realized, and reliable treatment and treatment of patients are ensured.

Description

Technical Field

[0001] This invention relates to the field of smart healthcare, and more particularly to a smart healthcare management system. Background Technology

[0002] The controllability of smart healthcare rests on the following preconditions:

[0003] First, interconnected collaboration: Through a professional wireless information platform, patients, medical staff, healthcare service providers, insurance companies, etc. are seamlessly and intelligently interconnected, allowing patients to experience one-stop medical, nursing and insurance services.

[0004] Second, resource application and sharing: Through the sharing and interconnection of medical information and records, a highly developed comprehensive medical network will be integrated. This will enable unified planning among medical institutions at all levels and among operational departments, achieving complementary advantages in medical resources and harmonious unity in supervision, evaluation, and decision-making.

[0005] However, existing smart healthcare systems still have many gaps that need to be filled. For example, they cannot effectively predict the cardiovascular disease population density of a given city on a given day, which makes it impossible to send network allocation instructions for insufficient cardiovascular doctors to the health management servers of surrounding cities. Naturally, this makes it impossible to achieve effective and dynamic allocation of relatively limited cardiovascular doctor resources among cities. Summary of the Invention

[0006] To address the aforementioned problems in the prior art, this invention provides a smart healthcare management system. This system intelligently analyzes the cardiovascular disease population density of a given city on a given day based on a density analysis model. When the cardiovascular disease population density of the given city on that day exceeds a set density threshold, a network allocation instruction for cardiovascular physicians is sent to the healthcare management servers of surrounding cities. Conversely, when the cardiovascular disease population density of the given city on that day does not exceed the set density threshold, a network allocation instruction for sufficient cardiovascular physicians is sent to the healthcare management servers of surrounding cities. This enables the effective and dynamic allocation of relatively limited cardiovascular physician resources among cities, ensuring reliable access to medical care and treatment for cardiovascular patients in each city every day.

[0007] According to the present invention, a smart medical and health management system is provided, the system comprising: A multi-learning device is used to output a density analytical model of a deep neural network after multiple learning processes. The deep neural network is learned multiple times to obtain a deep neural network after multiple learning processes. The number of times the deep neural network is learned is positively correlated with the distribution area of ​​a set city and also positively correlated with the number of permanent residents of the set city. The density extraction device is used to obtain the cardiovascular disease population density of a set city on each day in history. The number of days in history is positively correlated with the distribution area of ​​the set city. The single cardiovascular disease population density corresponding to each day in history is the ratio of the number of cardiovascular diseases in the set city on that day in history to the total population of the set city on that day in history. An information capture device is used to acquire various city-related information for a designated city, including the number of permanent residents of the designated city, the number of blocks in the designated city, and the number of hospitals with cardiovascular departments in the designated city. The numerical mapping mechanism is connected to the multiple learning device, the density extraction device, and the information capture device, respectively, and is used to analyze the cardiovascular disease population density of the set city on the current day using a density analysis model based on the cardiovascular disease population density of the set city on each day in history, the city association information of the set city, and the number of registered cardiovascular doctors in the set city. The resource allocation agency, connected to the numerical mapping agency, is used to send a network allocation instruction for cardiovascular doctors to the medical and health management servers of the surrounding cities when the cardiovascular disease population density of the set city on a given day exceeds a set density threshold. The resource allocation agency is also used to send a network allocation instruction for sufficient cardiovascular doctors to the medical and health management servers of the cities surrounding the set city when the cardiovascular disease population density of the set city on the set day does not exceed the set density threshold. The density analysis model is used to analyze the cardiovascular disease population density of a given city on a given day based on the cardiovascular disease population density of the given city on each day in history, the city association information of the given city, and the number of registered cardiovascular doctors in the given city. This includes performing numerical normalization on the cardiovascular disease population density of the given city on each day in history, the city association information of the given city, and the number of registered cardiovascular doctors in the given city, and then inputting them in parallel into the density analysis model.

[0008] Therefore, it can be seen that the present invention has at least the following important inventive concepts: Firstly, a multi-learning device is introduced to output a density analysis model as a deep neural network after multiple learning iterations. The deep neural network is trained multiple times to obtain a multi-learning deep neural network. The number of times the deep neural network is trained is positively correlated with the distribution area of ​​a set city and the number of permanent residents of the set city, thereby completing the targeted design of different density analysis models for different cities. Secondly: Obtain the cardiovascular disease population density of the designated city for each historical day. The number of historical days is positively correlated with the distribution area of ​​the designated city. The single cardiovascular disease population density for each historical day is the ratio of the number of cardiovascular diseases in the designated city on that historical day to the total population of the designated city on that historical day. Also, obtain the city association information of the designated city, which includes the number of permanent residents of the designated city, the number of blocks in the designated city, and the number of hospitals with cardiovascular departments in the designated city. This provides a number of basic information for the intelligent analysis of the cardiovascular disease population density of the designated city on a given day based on the density analysis model. Furthermore, when the cardiovascular disease population density of a set city on a given day exceeds a set density threshold, a network allocation instruction for cardiovascular physicians is sent to the healthcare management servers of surrounding cities. Conversely, when the cardiovascular disease population density of a set city on a given day does not exceed the set density threshold, a network allocation instruction for sufficient cardiovascular physicians is sent to the healthcare management servers of surrounding cities. This enables the effective and dynamic allocation of relatively limited cardiovascular physician resources among cities, ensuring reliable access to medical care and treatment for cardiovascular patients in each city every day. Detailed Implementation

[0009] The embodiments of the intelligent medical and health management system of the present invention will be described in detail below.

[0010] The intelligent medical and health management system shown in the first embodiment of the present invention includes: A multi-learning device is used to output a density analytical model of a deep neural network after multiple learning processes. The deep neural network is learned multiple times to obtain a deep neural network after multiple learning processes. The number of times the deep neural network is learned is positively correlated with the distribution area of ​​a set city and also positively correlated with the number of permanent residents of the set city. The density extraction device is used to obtain the cardiovascular disease population density of a set city on each day in history. The number of days in history is positively correlated with the distribution area of ​​the set city. The single cardiovascular disease population density corresponding to each day in history is the ratio of the number of cardiovascular diseases in the set city on that day in history to the total population of the set city on that day in history. For example, a density extraction device is used to obtain the cardiovascular disease population density of a set city on each historical day. The number of historical days is positively correlated with the distribution area of ​​the set city. The single cardiovascular disease population density corresponding to each historical day is the ratio of the number of cardiovascular diseases in the set city on that historical day to the total population of the set city on that historical day. The device is implemented using a DSP chip to obtain the cardiovascular disease population density of a set city on each historical day. The number of historical days is positively correlated with the distribution area of ​​the set city. The single cardiovascular disease population density corresponding to each historical day is the ratio of the number of cardiovascular diseases in the set city on that historical day to the total population of the set city on that historical day. An information capture device is used to acquire various city-related information for a designated city, including the number of permanent residents of the designated city, the number of blocks in the designated city, and the number of hospitals with cardiovascular departments in the designated city. The numerical mapping mechanism is connected to the multiple learning device, the density extraction device, and the information capture device, respectively, and is used to analyze the cardiovascular disease population density of the set city on the current day using a density analysis model based on the cardiovascular disease population density of the set city on each day in history, the city association information of the set city, and the number of registered cardiovascular doctors in the set city. The resource allocation agency, connected to the numerical mapping agency, is used to send a network allocation instruction for cardiovascular doctors to the medical and health management servers of the surrounding cities when the cardiovascular disease population density of the set city on a given day exceeds a set density threshold. For example, a resource allocation agency, connected to the numerical mapping agency, is used to send a network allocation instruction for cardiovascular physician requisition to the medical and health management server of the surrounding cities when the cardiovascular disease population density of a set city on a given day exceeds a set density threshold. This instruction includes: the resource allocation agency having a built-in network transmission interface. The resource allocation agency is also used to send a network allocation instruction for sufficient cardiovascular doctors to the medical and health management servers of the cities surrounding the set city when the cardiovascular disease population density of the set city on the set day does not exceed the set density threshold. The density analysis model is used to analyze the cardiovascular disease population density of a set city on a given day based on the cardiovascular disease population density of the set city on each day in history, the city association information of the set city, and the number of registered cardiovascular doctors in the set city. This includes performing numerical normalization on the cardiovascular disease population density of the set city on each day in history, the city association information of the set city, and the number of registered cardiovascular doctors in the set city, and then inputting them in parallel into the density analysis model. The method of using a density analysis model to analyze the cardiovascular disease population density of a set city on a given day based on the cardiovascular disease population density of the set city on each day in history, the city association information of the set city, and the number of registered cardiovascular doctors in the set city also includes: the cardiovascular disease population density of the set city on a given day output by the density analysis model is a numerical representation after numerical normalization. The process of performing numerical normalization on the cardiovascular disease population density corresponding to each day in history for the set city, the city association information of the set city, and the number of registered cardiovascular doctors in the set city before inputting them into the density analysis model in parallel includes: performing octal numerical conversion on the cardiovascular disease population density corresponding to each day in history for the set city, the city association information of the set city, and the number of registered cardiovascular doctors in the set city before inputting them into the density analysis model in parallel.

[0011] Unlike the first embodiment of the present invention, the intelligent medical and health management system shown in the second embodiment of the present invention may further include the following components: The cloud-based monitoring network element includes multiple network cameras facing the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device, respectively, for time-division monitoring of the real-time status of the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device; The cloud monitoring network element includes multiple network cameras facing the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device, respectively, for time-division monitoring of the real-time status of the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device. The numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device are connected to the cloud monitoring network element using different CSI interfaces. The cloud monitoring network element includes multiple network cameras facing the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device, respectively, for time-division monitoring of the real-time status of the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device. It also includes multiple network cameras with identical structures facing the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device, respectively. The cloud monitoring network element includes multiple network cameras facing the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device, respectively, for time-division monitoring of the real-time status of the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device. It also includes multiple network cameras facing the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device, each with a built-in different photoelectric sensor. Among them, multiple network camera devices, each facing the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device, have different built-in photoelectric sensors: the photoelectric sensors are CMOS sensing units or CCD sensing units.

[0012] Unlike the first embodiment of the present invention, the intelligent medical and health management system shown in the third embodiment of the present invention may further include the following components: A waveform generating mechanism is connected to the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capturing device, respectively, and is used to simultaneously provide the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capturing device with their respective required reference waveform data; The waveform generating mechanism is connected to the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capturing device, respectively, and is used to simultaneously provide the reference waveform data required by the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capturing device. The waveform generating mechanism has a built-in waveform generating circuit. The waveform generation mechanism, which is connected to the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device, and is used to simultaneously provide the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device with their respective required reference waveform data, further includes: the reference waveform data provided to the numerical mapping mechanism, the multiple learning device, the density extraction device, and the information capture device are all toothed waveforms with different frequencies.

[0013] In addition, in the smart healthcare management system, the process of performing numerical normalization on the cardiovascular disease population density of a given city for each historical day, the city association information of the given city, and the number of registered cardiovascular doctors in the given city before inputting them in parallel into the density analysis model also includes: using a programmable logic device to input the cardiovascular disease population density of a given city for each historical day, the city association information of the given city, and the number of registered cardiovascular doctors in the given city, after performing numerical normalization on each historical day, into the density analysis model in parallel.

[0014] The intelligent medical and health management system of this invention addresses the technical problem in existing technologies where a limited number of cardiovascular physicians cannot be dynamically allocated across cities in advance. By introducing a density analysis model to intelligently analyze and set the cardiovascular disease population density of a city for a given day, and when the cardiovascular disease population density of the set city exceeds the limit, a network allocation instruction for cardiovascular physicians is sent to the medical and health management servers of surrounding cities. This enables the effective and dynamic allocation of relatively limited cardiovascular physician resources among cities, ensuring reliable access to medical care and treatment for cardiovascular patients in each city every day, thus solving the aforementioned technical problem.

[0015] Although the invention has been described and illustrated in detail with reference to exemplary embodiments, those skilled in the art will understand that various changes in form and detail may be made without departing from the spirit and scope of the invention as defined in the claims.

Claims

1. A smart medical health management system, characterized in that: The system comprises: A multiple learning device, used for outputting a deep neural network after multiple learning as a density analysis model, wherein the deep neural network is learned multiple times to obtain a deep neural network after multiple learning, and the number of times the deep neural network is learned is positively correlated with the distribution area of ​​a set city and the number of permanent residents in the set city; A density extraction device is used to obtain the population density of cardiovascular diseases corresponding to each day in history of a set city. The number of days in history is positively correlated with the distribution area of ​​the set city. The population density of cardiovascular diseases corresponding to each day in history is the ratio of the number of cardiovascular diseases in the set city on that day in history divided by the total population of the set city on that day in history. An information capturing device, used for acquiring each piece of city-related information of a set city, wherein each piece of city-related information of the set city is the number of permanent residents of the set city, the number of blocks of the set city, and the number of hospitals with cardiovascular departments in the set city; a numerical mapping mechanism, connected to the multiple learning device, the density extraction device and the information capture device, respectively, for analyzing the cardiovascular disease population density corresponding to the set city on the day of the set city by using a density analysis model based on the respective cardiovascular disease population densities corresponding to the set city on the respective days in history, the respective city association information of the set city and the number of cardiovascular doctors registered in the set city; A resource allocation mechanism, connected to the value mapping mechanism, is used to send a network allocation instruction for recruiting cardiovascular doctors to the medical health management servers in the cities around the set city when the cardiovascular disease population density corresponding to the set city on that day exceeds the set density threshold; The resource allocation mechanism is further used to send a network allocation instruction for sufficient cardiovascular doctors to the medical health management servers in the cities around the set city when the cardiovascular disease population density corresponding to the set city on that day does not exceed the set density threshold; Among them, the density analysis model is used to analyze the cardiovascular disease population density corresponding to the set city on the day based on the cardiovascular disease population density corresponding to each day in history of the set city, the city-related information of the set city and the number of cardiovascular doctors registered in the set city, including: performing numerical normalization processing on the cardiovascular disease population density corresponding to each day in history of the set city, the city-related information of the set city and the number of cardiovascular doctors registered in the set city, and then inputting them into the density analysis model in parallel.

2. The smart medical health management system according to claim 1, characterized in that: The method of using a density analysis model to analyze the cardiovascular disease population density corresponding to the set city on the day of the set city based on the respective cardiovascular disease population densities corresponding to the set city on the respective days in history, the respective city association information of the set city, and the number of cardiovascular doctors registered in the set city further includes: the cardiovascular disease population density corresponding to the set city on the day of the set city output by the density analysis model is in the form of a numerical representation after numerical normalization processing; Among them, the various cardiovascular disease population densities corresponding to each day in history of the set city, the various city-related information of the set city, and the number of cardiovascular doctors registered in the set city are respectively numerically normalized and then input in parallel to the density analysis model, including: the various cardiovascular disease population densities corresponding to each day in history of the set city, the various city-related information of the set city, and the number of cardiovascular doctors registered in the set city are respectively numerically converted into octal values ​​and then input in parallel to the density analysis model.

3. The smart medical health management system according to claim 2, characterized in that: The system further comprises: A cloud monitoring network element, comprising a plurality of network camera devices facing the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device respectively, for monitoring the real-time status of the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device in time sharing; Among them, the cloud-based monitoring network element includes multiple network camera devices respectively facing the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device, and is used for time-sharing monitoring of the real-time status of the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device. The real-time status includes: the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device are respectively connected to the cloud-based monitoring network element using different CSI interfaces.

4. The smart medical health management system according to claim 3, characterized in that: The cloud-based monitoring network element includes a plurality of network camera devices respectively facing the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device, and is used for time-sharing monitoring of the real-time status of the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device. It also includes: the structures of the plurality of network camera devices respectively facing the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device are the same.

5. The smart medical health management system according to claim 4, characterized in that: The cloud-based monitoring network element includes a plurality of network camera devices respectively facing the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device, and is used for time-sharing monitoring of the real-time status of the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device. The cloud-based monitoring network element also includes: a plurality of network camera devices respectively facing the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device, each having a built-in different photoelectric sensor device.

6. The smart medical health management system according to claim 5, characterized in that: A plurality of network camera devices respectively facing the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device each have a built-in different photoelectric sensor device: the photoelectric sensor device is a CMOS sensor unit or a CCD sensor unit.

7. The smart medical health management system according to claim 2, characterized in that: The system further comprises: The waveform generating mechanism is respectively connected to the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device, and is used to simultaneously provide the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device with the reference waveform data they need.

8. The smart medical health management system according to claim 7, characterized in that: The waveform generating mechanism is respectively connected to the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device, and is used to simultaneously provide the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device with the reference waveform data they need respectively, including: the waveform generating mechanism has a built-in waveform generating circuit.

9. The smart medical health management system according to claim 8, characterized in that: A waveform generating mechanism is respectively connected to the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device, and is used to simultaneously provide the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device with the reference waveform data they each need. The reference waveform data they each need provided to the numerical mapping mechanism, the multiple learning device, the density extraction device and the information capture device are all tooth-shaped waveforms and have different frequencies.