Intelligent management system for human health data

Abstract

The invention relates to a human health data intelligent management system, which comprises a data conversion device, the intelligent data conversion module is used for adopting an intelligent data conversion model to obtain diagnosis data of a target patient according to the diagnosis data corresponding to set time segments of the target patient in historical days and the blood vessel width and age of the pulse measurement position of the target patient. The pulse frequency, the pulse intensity and the pulse rhythm uniformity identifier of the target patient in the set time segment of the day are intelligently predicted according to the pulse frequency, the pulse intensity and the pulse rhythm uniformity identifier of the target patient according to the length of the arm where the pulse measurement position of the target patient is located; and the wireless transmission device is used for wirelessly transmitting the intelligent prediction result. The human health data intelligent management system is intelligent in design and has certain pertinence. Due to the fact that the intelligent data conversion model can be adopted to intelligently predict the pulse frequency, the pulse intensity and the pulse rhythm uniform identification of the patient in the future time segment based on the data of the target patient, the foreseeability of the treatment measures of the intelligent medical system is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart medical care, and more specifically, to a smart management system for human health data. Background Art

[0002] From a technical perspective, the conceptual framework of smart healthcare includes five aspects: basic environment, basic database group, software basic platform and data exchange platform, comprehensive application and service system, and guarantee system.

[0003] Basic environment: Through the construction of a public health dedicated network, interconnection with the information network is achieved; a health data center is built to provide security for basic health data and various application systems.

[0004] Basic databases: including six basic databases in the health field, including drug catalog database, resident health record database, PACS imaging database, LIS inspection database, medical personnel database, and medical equipment.

[0005] Software basic platform and data exchange platform: provide services at three levels: first, infrastructure services, providing virtual optimized servers, storage servers and network resources; second, platform services, providing optimized middleware, including application servers, database servers, portal servers, etc.; and finally, software services, including application, process and information services.

[0006] Comprehensive applications and their service systems: including three categories of comprehensive applications: smart hospital system, regional health platform and family health system.

[0007] Guarantee system: including security guarantee system, standard specification system and management guarantee system. Construct a security prevention system from the three aspects of technical security, operation security and management security to ensure the availability, confidentiality, integrity, non-repudiation, auditability and controllability of the basic platform and various application systems.

[0008] Even so, the current smart medical system is still unable to solve the problem of intelligent prediction of various physiological data of target patients in future time segments. For example, it is unable to effectively predict the pulse frequency, pulse strength and pulse rhythm uniformity of target patients in future time segments, resulting in delayed medical measures and monitoring methods, which cannot improve predictability. Summary of the invention

[0009] In order to solve technical problems in related fields, the present invention provides an intelligent management system for human health data, which can obtain the blood vessel width, age, gender identification of the target patient's pulse measurement position and the length of the arm where the pulse measurement position is located, as well as obtain the respective diagnostic data corresponding to the set time segments of the target patient on each historical day. The single diagnostic data corresponding to the set time segment of the target patient on a certain historical day is the pulse frequency, pulse strength and pulse rhythm uniformity identification of the target patient within the set time segment on a certain historical day. Then, an intelligent data conversion model is used to intelligently predict the pulse frequency, pulse strength and pulse rhythm uniformity identification of the target patient in future time segments based on the target patient's data, thereby improving the predictability of the treatment measures of the intelligent medical system.

[0010] According to the present invention, a human health data intelligent management system is provided, the system comprising: A target training mechanism, used for training each layer of the deconvolution neural network to obtain an intelligent data conversion model output, wherein training each layer of the deconvolution neural network is performing each training process on the deconvolution neural network; The content acquisition mechanism is used to acquire the diagnostic data corresponding to the set time segments of the target patient on each historical day. The single diagnostic data corresponding to the set time segment of the target patient on a certain historical day is the pulse frequency, pulse strength and pulse rhythm uniformity mark of the target patient within the set time segment of the certain historical day. An information collection mechanism for obtaining the blood vessel width, age, gender identification, and arm length of the target patient at the pulse measurement location; A data conversion device is connected to the target training mechanism, the content acquisition mechanism and the information collection mechanism, and is used to use an intelligent data conversion model to intelligently predict the target patient's pulse frequency, pulse strength and pulse rhythm uniformity mark within the set time segment of the day according to the target patient's respective diagnostic data corresponding to the set time segments on each historical day, the blood vessel width, age, gender mark of the target patient's pulse measurement position and the length of the arm where the target patient's pulse measurement position is located; A wireless transmission device, connected to the data conversion device, is used to transmit the pulse frequency, pulse strength and pulse rhythm uniformity mark of the target patient predicted intelligently within the set time segment of the day to the nearest medical care server through a wireless communication link; Among them, the diagnostic data corresponding to the set time segments of the target patient on each historical day are obtained, and the single diagnostic data corresponding to the set time segment of the target patient on a certain historical day are the pulse frequency, pulse strength and pulse rhythm uniformity mark of the target patient within the set time segment of a certain historical day, including: the pulse rhythm uniformity mark of the target patient within the set time segment of a certain historical day is used to indicate whether the pulse rhythm of the blood vessels in the pulse manifestation part of the target patient is uniform within the set time segment of a certain historical day.

[0011] Therefore, the present invention has at least the following three beneficial technical effects: Technical effect A: training each layer of the deconvolution neural network to obtain the output of the intelligent data conversion model, and performing training on each layer of the deconvolution neural network is performing each training process on the deconvolution neural network; Technical effect B: The number of training layers of each layer of the deconvolutional neural network is monotonically positively correlated with the blood vessel width at the pulse measurement position of the target patient, thereby customizing intelligent data conversion models with different structures for different patients; Technical effect C: Obtain the blood vessel width, age, gender identification, and arm length of the target patient's pulse measurement location at the pulse measurement location, as well as obtain the respective diagnostic data corresponding to the set time segments of the target patient on each historical day. The single diagnostic data corresponding to the set time segment of a certain historical day of the target patient is the pulse frequency, pulse strength, and pulse rhythm uniformity identification of the target patient within the set time segment of a certain historical day, thereby providing reliable and comprehensive basic information for the intelligent prediction of the pulse frequency, pulse strength, and pulse rhythm uniformity identification of the target patient in future time segments.

[0012] The human health data intelligent management system of the present invention is intelligently designed and has certain pertinence. Since it can use an intelligent data conversion model to intelligently predict the pulse frequency, pulse strength and pulse rhythm uniformity of the target patient in the future time segment based on the target patient's various data, the predictability of the treatment measures of the intelligent medical system is improved. BRIEF DESCRIPTION OF THE DRAWINGS Those skilled in the art may better understand the numerous advantages of the present invention by referring to the accompanying drawings, in which: Figure 1 It is a schematic diagram of the internal structure of the human health data intelligent management system according to the first embodiment of the present invention.

[0014] Figure 2 It is a schematic diagram of the internal structure of the human health data intelligent management system according to the second embodiment of the present invention.

[0015] Figure 3 It is a schematic diagram of the internal structure of the human health data intelligent management system according to the third embodiment of the present invention. DETAILED DESCRIPTION

[0016] The implementation scheme of the human health data intelligent management system of the present invention will be described in detail below with reference to the accompanying drawings.

[0017] Figure 1 1 is a schematic diagram of the internal structure of a human health data intelligent management system according to a first embodiment of the present invention, the system comprising: A target training mechanism, used for training each layer of the deconvolution neural network to obtain an intelligent data conversion model output, wherein training each layer of the deconvolution neural network is performing each training process on the deconvolution neural network; For example, an FPGA chip may be selected to implement the target training mechanism, which is used to train each layer of the deconvolution neural network to obtain an intelligent data conversion model output, and performing training on each layer of the deconvolution neural network is performing each training process on the deconvolution neural network; The content acquisition mechanism is used to acquire the diagnostic data corresponding to the set time segments of the target patient on each historical day. The single diagnostic data corresponding to the set time segment of the target patient on a certain historical day is the pulse frequency, pulse strength and pulse rhythm uniformity mark of the target patient within the set time segment of the certain historical day. An information collection mechanism for obtaining the blood vessel width, age, gender identification, and arm length of the target patient at the pulse measurement location; A data conversion device is connected to the target training mechanism, the content acquisition mechanism and the information collection mechanism, and is used to use an intelligent data conversion model to intelligently predict the target patient's pulse frequency, pulse strength and pulse rhythm uniformity mark within the set time segment of the day according to the target patient's respective diagnostic data corresponding to the set time segments on each historical day, the blood vessel width, age, gender mark of the target patient's pulse measurement position and the length of the arm where the target patient's pulse measurement position is located; A wireless transmission device, connected to the data conversion device, is used to transmit the pulse frequency, pulse strength and pulse rhythm uniformity mark of the target patient predicted intelligently within the set time segment of the day to the nearest medical care server through a wireless communication link; Among them, the diagnosis data corresponding to the target patient at the set time segments on each historical day are obtained, and the single diagnosis data corresponding to the target patient at the set time segment on a certain historical day is the pulse frequency, pulse strength and pulse rhythm uniformity mark of the target patient within the set time segment on a certain historical day, including: the pulse rhythm uniformity mark of the target patient within the set time segment on a certain historical day is used to indicate whether the pulse rhythm of the blood vessels at the pulse manifestation site of the target patient is uniform within the set time segment on a certain historical day; The target training mechanism is used to train each layer of the deconvolution neural network to obtain the output of the intelligent data conversion model, and the training of each layer of the deconvolution neural network is to perform each training process on the deconvolution neural network, including: the number of training layers of each layer of the deconvolution neural network is monotonically positively correlated with the blood vessel width at the pulse measurement position of the target patient; The number of training layers of each layer of training performed by the deconvolution neural network is monotonically positively correlated with the width of the blood vessel at the pulse measurement position of the target patient, including: using a signal mapping function to represent a signal mapping relationship of monotonically positively correlated number of training layers of each layer of training performed by the deconvolution neural network and the width of the blood vessel at the pulse measurement position of the target patient; And wherein, the signal mapping relationship in which the number of training layers of each layer of training performed by the deconvolution neural network is monotonically positively correlated with the blood vessel width at the pulse measurement position of the target patient using a signal mapping function includes: in the signal mapping function, the blood vessel width at the pulse measurement position of the target patient is the input content, and the number of training layers of each layer of training performed by the deconvolution neural network is the output content.

[0018] Figure 2 It is a schematic diagram of the internal structure of the human health data intelligent management system according to the second embodiment of the present invention.

[0019] and Figure 1 different, Figure 2 The human health data intelligent management system can also include the following components: A content analysis mechanism is connected to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, respectively, and is used to provide the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism with respective real-time positioning data; Wherein, the content analysis mechanism is respectively connected with the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, and is used to provide the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism with their respective real-time positioning data, including: the content analysis mechanism includes a plurality of positioning execution components, which are respectively connected with the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, so as to complete the respective supply of real-time positioning data to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism; Wherein, the content analysis mechanism includes a plurality of positioning execution components, which are used to respectively connect with the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism to complete the respective supply of real-time positioning data to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, including: the plurality of positioning execution components are a plurality of positioning sensors, which are used to respectively connect with the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism to complete the respective supply of real-time positioning data to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism; Wherein, the plurality of positioning execution components are a plurality of positioning sensors, which are used to be connected to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism respectively, so as to complete the supply of the respective instant positioning data of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism respectively, including: the structures of the plurality of positioning execution components are the same; Among them, the multiple positioning execution components are multiple positioning sensors, which are used to connect with the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism respectively, so as to complete the separate supply of real-time positioning data to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism respectively, and also include: the multiple positioning sensors have the same positioning range.

[0020] Figure 3 It is a schematic diagram of the internal structure of the human health data intelligent management system according to the third embodiment of the present invention.

[0021] and Figure 1 different, Figure 3 The human health data intelligent management system can also include the following components: An access processing interface, connected to the plurality of positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information acquisition mechanism, respectively, for synchronously controlling the current working mode of the respective positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information acquisition mechanism; Wherein, the access processing interface is respectively connected to a plurality of positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information acquisition mechanism, and is used to synchronously control the current working mode of the respective positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information acquisition mechanism, including: the current working mode of the respective positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information acquisition mechanism is a sleep working mode or a running working mode; And wherein, the access processing interface is respectively connected to multiple positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, and is used to synchronously control the current working mode of the respective positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, including: the multiple positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism are all based on the Beidou positioning mechanism.

[0022] In addition, in the human health data intelligent management system, the target patient's pulse rhythm uniformity mark within the set time segment on a certain historical day is used to indicate whether the pulse rhythm of the target patient's pulse manifestation site is uniform within the set time segment on a certain historical day. The mark includes: when the target patient's pulse rhythm uniformity mark within the set time segment on a certain historical day is 0B01, it indicates that the pulse rhythm of the target patient's pulse manifestation site is uniform within the set time segment on a certain historical day; And wherein, the pulse rhythm uniformity mark of the target patient within the set time segment on a certain historical day is used to indicate whether the pulse rhythm of the blood vessels in the pulse manifestation part of the target patient within the set time segment on a certain historical day is uniform, and also includes: when the pulse rhythm uniformity mark of the target patient within the set time segment on a certain historical day takes a value of 0B11, it indicates that the pulse rhythm of the blood vessels in the pulse manifestation part of the target patient within the set time segment on a certain historical day is uneven.

[0023] While the invention has been particularly shown and described with reference to exemplary embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the claims.

Claims

1. A human health data intelligent management system, characterized in that: The system comprises: A target training mechanism, used for training each layer of the deconvolution neural network to obtain an intelligent data conversion model output, wherein training each layer of the deconvolution neural network is performing each training process on the deconvolution neural network; The content acquisition mechanism is used to acquire the diagnostic data corresponding to the set time segments of the target patient on each historical day. The single diagnostic data corresponding to the set time segment of the target patient on a certain historical day is the pulse frequency, pulse strength and pulse rhythm uniformity mark of the target patient within the set time segment of the certain historical day. An information collection mechanism for obtaining the blood vessel width, age, gender identification, and arm length of the target patient at the pulse measurement location; A data conversion device is connected to the target training mechanism, the content acquisition mechanism and the information collection mechanism, and is used to use an intelligent data conversion model to intelligently predict the target patient's pulse frequency, pulse strength and pulse rhythm uniformity mark within the set time segment of the day according to the target patient's respective diagnostic data corresponding to the set time segments on each historical day, the blood vessel width, age, gender mark of the target patient's pulse measurement position and the length of the arm where the target patient's pulse measurement position is located; A wireless transmission device, connected to the data conversion device, is used to transmit the pulse frequency, pulse strength and pulse rhythm uniformity mark of the target patient predicted intelligently within the set time segment of the day to the nearest medical care server through a wireless communication link; Among them, the diagnostic data corresponding to the set time segments of the target patient on each historical day are obtained, and the single diagnostic data corresponding to the set time segment of the target patient on a certain historical day are the pulse frequency, pulse strength and pulse rhythm uniformity mark of the target patient within the set time segment of a certain historical day, including: the pulse rhythm uniformity mark of the target patient within the set time segment of a certain historical day is used to indicate whether the pulse rhythm of the blood vessels in the pulse manifestation part of the target patient is uniform within the set time segment of a certain historical day.

2. The human health data intelligent management system according to claim 1, characterized in that: The target training mechanism is used to train each layer of the deconvolution neural network to obtain the output of the intelligent data conversion model, and the training of each layer of the deconvolution neural network is to perform each training process on the deconvolution neural network, including: the number of training layers of each layer of the training performed by the deconvolution neural network is monotonically positively correlated with the blood vessel width at the pulse measurement position of the target patient; The number of training layers of each layer of training performed by the deconvolution neural network is monotonically positively correlated with the width of the blood vessel at the pulse measurement position of the target patient, including: using a signal mapping function to represent a signal mapping relationship of monotonically positively correlated number of training layers of each layer of training performed by the deconvolution neural network and the width of the blood vessel at the pulse measurement position of the target patient; Among them, the signal mapping relationship in which the number of training layers of each layer of training performed by the deconvolution neural network is monotonically positively correlated with the blood vessel width at the pulse measurement position of the target patient using a signal mapping function includes: in the signal mapping function, the blood vessel width at the pulse measurement position of the target patient is the input content, and the number of training layers of each layer of training performed by the deconvolution neural network is the output content.

3. The human health data intelligent management system as claimed in claim 2, characterized in that: The system further comprises: A content analysis mechanism is connected to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, respectively, and is used to provide the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism with respective real-time positioning data; Among them, the content analysis mechanism is respectively connected to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, and is used to provide the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism with their own real-time positioning data, including: the content analysis mechanism includes multiple positioning execution components, which are respectively connected to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism to complete the respective supply of real-time positioning data to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism.

4. The human health data intelligent management system according to claim 3, characterized in that: The content analysis mechanism includes a plurality of positioning execution components, which are used to respectively connect with the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism to complete the respective supply of real-time positioning data to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, including: the plurality of positioning execution components are a plurality of positioning sensors, which are used to respectively connect with the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism to complete the respective supply of real-time positioning data to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism.

5. The human health data intelligent management system according to claim 4, characterized in that: The multiple positioning execution components are multiple positioning sensors, which are used to connect to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism respectively, so as to complete the separate supply of real-time positioning data to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism respectively, including: the structures of the multiple positioning execution components are the same.

6. The human health data intelligent management system according to claim 5, characterized in that: The multiple positioning execution components are multiple positioning sensors, which are used to connect with the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism respectively, so as to complete the separate supply of real-time positioning data to the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism respectively, and also include: the multiple positioning sensors have the same positioning range.

7. The human health data intelligent management system as claimed in claim 3, characterized in that: The system further comprises: An access processing interface is respectively connected to multiple positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, and is used to synchronously control the current working mode of the respective positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism.

8. The human health data intelligent management system according to claim 7, characterized in that: An access processing interface is respectively connected to multiple positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, and is used to synchronously control the current working mode of the respective positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, including: the current working mode of the respective positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism is a sleep working mode or a running working mode.

9. The human health data intelligent management system according to claim 7, characterized in that: An access processing interface is respectively connected to multiple positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, and is used to synchronously control the current working mode of the respective positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism, including: the multiple positioning execution components of the data conversion device, the target training mechanism, the content acquisition mechanism and the information collection mechanism are all based on the Beidou positioning mechanism.

Images