Method and system for realizing portrayal construction of senile dementia based on big data

Abstract

The invention relates to a method for realizing portrayal construction of senile dementia based on big data, and belongs to the field of electrical digital data processing, and the method comprises the steps: carrying out the multiple learning of a feedforward neural network, so as to obtain an intelligent portrayal construction model; and intelligently constructing senile dementia portrait data of the target person at the set aged age by adopting an intelligent portrait construction model according to the resolution of the portrait, the various physiological associated data of the target person and the portrait data corresponding to the previous ages of the target person before the current age. The invention also relates to a system for realizing portrayal construction of senile dementia based on big data. Through the method, the technical problem that reliable associated reference data cannot be prepared in advance for future health monitoring of potential senile dementia people in the prior art is solved, and intelligent construction of senile dementia portrait data of the people at the set age can be completed by adopting the artificial intelligence model based on the screened big data; therefore, the technical problem is solved.

Description

Technical Field

[0001] The present invention relates to the field of electronic digital data processing, and in particular to a method and system for constructing a portrait of Alzheimer's disease based on big data. Background Art

[0002] Alzheimer's disease is a common, chronic, and progressive mental degeneration disorder in the elderly, occupying a significant position in the spectrum of illness and mortality among the elderly. Alzheimer's disease is a syndrome characterized by impairment of higher-level brain function due to chronic or progressive organic damage to brain structure. It presents as a persistent and comprehensive decline in intellectual function, manifested by decreased memory, calculation, judgment, attention, abstract thinking, language, emotional and behavioral disturbances, and the ability to live and work independently. Alzheimer's disease includes Alzheimer's disease (AD), vascular dementia (VD), and mixed dementia. Generally, patient profile data can often provide a targeted analysis of the type and status of a patient's Alzheimer's disease.

[0003] For example, Chinese invention patent publication CN116580832A proposes a video-based Alzheimer's disease auxiliary diagnosis system and method, specifically relating to the field of video analysis. The system includes a terminal, a network, a server, and a database. The terminal and the server are connected to each other via a network. The terminal is used to collect a video of the subject's tea-making task operation process, which is then uploaded to the server via the network. The server performs character interaction recognition and Alzheimer's disease health status diagnosis on the detected image, and saves the relevant data and original video data information to the database. The present invention is a new type of intelligent auxiliary diagnosis and early warning method for Alzheimer's disease, with high diagnostic accuracy, reducing the workload of doctors, and at the same time facilitating the early warning and diagnosis of cognitive abnormalities for users in the community or at home.

[0004] For example, Chinese invention patent publication CN 111899887A proposes a method for predicting Alzheimer's disease risk in the elderly. The method comprises the following steps: obtaining and preprocessing a dataset of brain test samples; extracting features from the preprocessed brain test sample data in multiple dimensions using a support vector machine (SVM) algorithm; training a neural network using the extracted features to obtain an Alzheimer's disease risk prediction model; and obtaining brain test data to be predicted, inputting the data into the Alzheimer's disease risk prediction model to achieve Alzheimer's disease risk prediction. This method can conveniently and accurately predict Alzheimer's disease risk.

[0005] However, although the above-mentioned technical solutions are all related technical solutions for Alzheimer's disease based on big data, their essential content is either Alzheimer's disease warning and diagnosis solutions based on visual big data, or Alzheimer's disease risk prediction based on brain detection sample big data. They all belong to Alzheimer's disease condition analysis based on the patient's current big data, and cannot intelligently predict the patient's future data. For example, it is impossible to intelligently predict the patient's future portrait data, resulting in the inability to conduct targeted analysis of the patient's Alzheimer's disease type and status in the future, and it is impossible to prepare reliable related reference data in advance for the patient's future health monitoring. Summary of the Invention

[0006] In order to solve the technical problems in the prior art, the present invention provides a method and system for constructing a portrait of Alzheimer's disease based on big data. By adopting an artificial intelligence model with a customized structure and based on fully and comprehensively screened big data including portrait data corresponding to each past age of the target person before the current age and various physiological related data of the target person, the intelligent construction of the Alzheimer's portrait data of the target person at the set old age is completed, thereby preparing reliable related reference data in advance for the future health monitoring of the target person and extending the medical monitoring period of the target person.

[0007] According to a first aspect of the present invention, a method for constructing a portrait of Alzheimer's disease based on big data is provided, the method comprising: Analyze various physiological data of the target person for whom the Alzheimer's disease portrait is to be constructed, wherein the physiological data of the target person include the target person's current age, gender identifier, height-to-weight ratio, and nationality code value; Analyze the portrait data corresponding to each age of the target person before the current age, wherein the resolution and clarity of each portrait are the same, and each portrait data includes the L component values, A component values, and B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait; Performing multiple learning on the feedforward neural network to obtain a feedforward neural network after completing multiple learning and outputting it as an intelligent portrait construction model; An intelligent portrait construction model is used to intelligently construct the target person's Alzheimer's portrait data at the set old age based on the portrait resolution, various physiological data of the target person, and the portrait data corresponding to each of the target person's past ages before the current age; Among them, the number of learning times performed by the feedforward neural network is positively correlated with the total number of nationalities; Among them, the number of past ages before the current age is positively correlated with the resolution of the portrait, and is also positively correlated with the clarity of the portrait.

[0008] According to a second aspect of the present invention, a system for constructing a portrait of Alzheimer's disease based on big data is provided. The system includes a memory and multiple processors, the multiple processors being located at a wireless router of a target residential user and a remote omni-media content server. The memory stores a computer program, and the computer program is configured to be executed by the multiple processors to perform the following steps: Analyze various physiological data of the target person for whom the Alzheimer's disease portrait is to be constructed, wherein the physiological data of the target person include the target person's current age, gender identifier, height-to-weight ratio, and nationality code value; Analyze the portrait data corresponding to each age of the target person before the current age, wherein the resolution and clarity of each portrait are the same, and each portrait data includes the L component values, A component values, and B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait; Performing multiple learning on the feedforward neural network to obtain a feedforward neural network after completing multiple learning and outputting it as an intelligent portrait construction model; An intelligent portrait construction model is used to intelligently construct the target person's Alzheimer's portrait data at the set old age based on the portrait resolution, various physiological data of the target person, and the portrait data corresponding to each of the target person's past ages before the current age; Among them, the number of learning times performed by the feedforward neural network is positively correlated with the total number of nationalities; Among them, the number of past ages before the current age is positively correlated with the resolution of the portrait, and is also positively correlated with the clarity of the portrait.

[0009] According to a third aspect of the present invention, a system for constructing a portrait of Alzheimer's disease based on big data is provided, the system comprising: The first parsing unit is used to parse various physiological data of the target person for constructing the Alzheimer's disease portrait, wherein the physiological data of the target person are the current age, gender identifier, height-to-weight ratio, and nationality code value of the target person; The second parsing mechanism is used to parse the portrait data corresponding to each age of the target person before the current age, wherein the resolution and clarity of each portrait are the same, and each portrait data includes the L component values, A component values, and B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait; An object reshaping mechanism is used to perform multiple learning on the feedforward neural network to obtain a feedforward neural network after completing multiple learning and output it as an intelligent portrait construction model; an intelligent construction mechanism, connected to the first analysis mechanism, the second analysis mechanism, and the object reconstruction mechanism, respectively, for using an intelligent portrait construction model to intelligently construct Alzheimer's portrait data of the target person at a set old age based on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age; Among them, the number of learning times performed by the feedforward neural network is positively correlated with the total number of nationalities; Among them, the number of past ages before the current age is positively correlated with the resolution of the portrait, and is also positively correlated with the clarity of the portrait.

[0010] Compared with the prior art, the present invention has at least the following four outstanding substantive features: Firstly, an artificial intelligence model is used to intelligently predict the target person's Alzheimer's disease profile data at a set age based on the profile data corresponding to each age before the current age and the target person's various physiological correlation data. This allows the use of artificial intelligence mechanisms to intelligently construct Alzheimer's disease profiles for different individuals, preparing reliable correlation reference data in advance for their future health monitoring. Secondly, the artificial intelligence model used is a custom-designed intelligent portrait construction model, which is a feedforward neural network that has completed multiple learning cycles. In this intelligent portrait construction model, the number of learning cycles performed by the feedforward neural network is positively correlated with the total number of nationalities, and the number of previous ages before the current age is positively correlated with the resolution and clarity of the portrait, thereby ensuring the effectiveness and stability of the prediction results of the target person's Alzheimer's portrait data. Again: The target person's various physiological association data include the target person's current age, gender identifier, height-to-weight ratio, and nationality code value, as well as the portrait data corresponding to each of the target person's previous ages before the current age. The resolution and clarity of each portrait are the same, and each portrait data includes the L component values, A component values, and B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait. The full and comprehensive screening of the above big data further ensures the effectiveness and stability of the prediction results of the target person's Alzheimer's portrait data. Finally: In each learning execution of the feedforward neural network, the Alzheimer's portrait data of a certain person at a set old age is used as the output content of the feedforward neural network, and the resolution of the portrait, the various physiological related data of the certain person, and the portrait data corresponding to each past age of the certain person before the current age are used as the input content of the feedforward neural network to complete this learning, thereby ensuring the learning effect of each learning of the feedforward neural network. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The embodiments of the present invention will be described below with reference to the accompanying drawings, in which: Figure 1 This is a technical flow chart of the method and system for constructing a portrait of Alzheimer's disease based on big data according to the present invention.

[0012] Figure 2 The present invention is a flowchart showing the steps of a method for constructing a portrait of Alzheimer's disease based on big data according to Example 1 of the present invention.

[0013] Figure 3 The present invention is a flowchart showing the steps of a method for constructing a portrait of Alzheimer's disease based on big data according to Example 2 of the present invention.

[0014] Figure 4 The present invention is a flowchart showing the steps of a method for constructing a portrait of Alzheimer's disease based on big data according to Example 3 of the present invention.

[0015] Figure 5 The present invention is a flowchart showing the steps of a method for constructing a portrait of Alzheimer's disease based on big data according to Example 4 of the present invention.

[0016] Figure 6 This is a structural diagram of a system for constructing a portrait of Alzheimer's disease based on big data according to Example 5 of the present invention.

[0017] Figure 7 This is a structural diagram of a system for constructing a portrait of Alzheimer's disease based on big data according to Example 6 of the present invention. DETAILED DESCRIPTION

[0018] like Figure 1 As shown, a technical flow chart of the method and system for constructing a portrait of Alzheimer's disease based on big data according to the present invention is given.

[0019] exist Figure 1 The specific technical process of the present invention is as follows: Technical Process 1: Build the Alzheimer's disease portrait data of the target person at the set age for intelligent construction, and design the artificial intelligence model in a targeted manner; Specifically, the artificial intelligence model is a customized intelligent portrait construction model. The structural customization of the intelligent portrait construction model is mainly reflected in the following aspects: First: the intelligent portrait construction model is a feedforward neural network that has completed multiple learning cycles; Second: In the intelligent portrait construction model, the number of learning times performed by the feedforward neural network is positively correlated with the total number of nationalities; Third: In the intelligent portrait construction model, the number of past ages before the current age in the filtered big data is positively correlated with the resolution of the portrait and also with the clarity of the portrait; Fourth: In each learning process of the feedforward neural network, the known Alzheimer's portrait data of a certain person at a set old age is used as the output content of the feedforward neural network, and the resolution of the portrait, various physiological data of the certain person, and the portrait data corresponding to each age of the certain person before the current age are used as the input content of the feedforward neural network to complete the learning process, thereby ensuring the learning effect of each learning process of the feedforward neural network; In this way, the above-mentioned customized model structure design ensures the effectiveness and stability of the prediction results of the target person's Alzheimer's portrait data Technical process 2: To intelligently construct the Alzheimer's portrait data of the target person at the set age, comprehensive and sufficient big data is selected as the basic data; Specifically, the big data screened includes the resolution of the portrait, various physiological data of the target person, and the portrait data corresponding to each age of the target person before the current age; More specifically, the target person's physiological related data include the target person's current age, gender identifier, height-to-weight ratio, and nationality code value; More specifically, in each set of portrait data corresponding to each past age of the target person before the current age, the resolution and clarity of each portrait are the same, and each set of portrait data includes each set of L component values, each set of A component values, and each set of B component values ​​corresponding to each pixel point of the portrait, as well as multiple sets of grayscale gradient information corresponding to multiple edge pixels of the portrait; In this way, the comprehensive and sufficient screening of the above big data further ensures the validity and stability of the prediction results of the target person's Alzheimer's portrait data; Technical Process 3: Using the intelligent portrait construction model with customized structure design from Technical Process 1 and the big data fully screened from Technical Process 2, intelligently construct the Alzheimer's portrait data of the target person at the set age; Specifically, the intelligently constructed Alzheimer's portrait data of the target person when the old age is set includes each L component value, each A component value, and each B component value corresponding to each pixel point of the Alzheimer's portrait, and multiple grayscale gradient information corresponding to multiple edge pixels of the Alzheimer's portrait; Specifically, each pixel of the Alzheimer's disease portrait has an L component value, an A component value, and a B component value in the LAB color space; Specifically, the L component value, the A component value, and the B component value of each pixel of the Alzheimer's disease portrait are all between 0 and 255. Technical process four: Use the Alzheimer's portrait data of the target person at the set old age intelligently constructed in technical process three to create an Alzheimer's portrait of the target person at the set old age; Specifically, the Alzheimer's disease portrait is constructed according to the respective L component values, the respective A component values, and the respective B component values ​​corresponding to the respective pixel points of the Alzheimer's disease portrait in the Alzheimer's disease portrait data; In this way, the intelligent prediction of the target person's Alzheimer's portrait at the set old age is completed based on the portrait data corresponding to the known ages of the target person and the target person's various physiological correlation data, thereby helping to analyze the type and status of the target person's Alzheimer's disease at the set old age, and preparing reliable correlation reference data in advance for the target person's future health monitoring, making the management of Alzheimer's disease more predictable.

[0020] The key points of the present invention are: multiple customized structural designs of artificial intelligence models for intelligently constructing Alzheimer's portrait data, comprehensive and sufficient big data screening for intelligently constructing Alzheimer's portrait data, intelligent prediction of Alzheimer's portraits, and more predictive management of Alzheimer's disease.

[0021] Below, the method and system for constructing a portrait of Alzheimer's disease based on big data of the present invention will be specifically described in the form of an embodiment. Example 1

[0022] Figure 2 The present invention is a flowchart showing the steps of a method for constructing a portrait of Alzheimer's disease based on big data according to Example 1 of the present invention.

[0023] like Figure 2 As shown, the method for constructing a portrait of Alzheimer's disease based on big data includes the following specific steps: Step S101: parsing various physiological data of a target person for constructing a portrait of Alzheimer's disease, wherein the physiological data of the target person include the target person's current age, gender identifier, height-to-weight ratio, and nationality code value; For example, parsing various physiological data of a target person for constructing an Alzheimer's disease portrait, wherein the various physiological data of the target person are the target person's current age, gender identifier, height-to-weight ratio, and nationality code value, includes: selectively using multiple parameter parsing components for respectively parsing the target person's current age, gender identifier, height-to-weight ratio, and nationality code value; Step S102: Parsing portrait data corresponding to each age of the target person before the current age, wherein each portrait has the same resolution and clarity, and each portrait data includes L component values, A component values, and B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait; Specifically, analyzing each set of portrait data corresponding to each past age of the target person before the current age, wherein each set of portrait data has the same resolution and clarity, and each set of portrait data includes each set of L component values, each set of A component values, and each set of B component values ​​corresponding to each pixel point of the portrait, as well as multiple sets of grayscale gradient information corresponding to multiple edge pixels of the portrait, including: the value range of any component value among the L component value, the A component value, and the B component value corresponding to each pixel point is between 0 and 255; Here, by obtaining the L component value, A component value, and B component value of each pixel point of a frame image, the frame image can be assembled and displayed; Step S103: performing multiple learning on the feedforward neural network to obtain a feedforward neural network after completing multiple learning and outputting it as an intelligent portrait construction model; For example, performing multiple learning on a feedforward neural network to obtain a feedforward neural network after the multiple learning and outputting the feedforward neural network as an intelligent portrait construction model includes: the feedforward neural network includes an input layer, a hidden layer, and an output layer, wherein the hidden layer is located between the input layer and the output layer; Step S104: Using an intelligent portrait construction model to intelligently construct Alzheimer's portrait data of the target person at the set old age based on the resolution of the portrait, various physiological related data of the target person, and various portrait data corresponding to each of the target person's past ages before the current age; For example, the intelligent portrait construction model is used to intelligently construct the target person's Alzheimer's portrait data at a set old age based on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age, including: a numerical simulation mode can be selected to complete the testing and simulation of the data processing process of the intelligent portrait construction model being used to intelligently construct the target person's Alzheimer's portrait data at a set old age based on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age; Among them, the number of learning times performed by the feedforward neural network is positively correlated with the total number of nationalities; For example, the positive correlation between the number of learning times performed by the feedforward neural network and the total number of nationalities includes: when the number of nationalities involved in the processing is 50, the number of learning times performed by the feedforward neural network is 600; when the number of nationalities involved in the processing is 70, the number of learning times performed by the feedforward neural network is 800; and when the number of nationalities involved in the processing is 100, the number of learning times performed by the feedforward neural network is 1000, and so on; Among them, the number of past ages before the current age is positively correlated with the resolution of the portrait, and is also positively correlated with the clarity of the portrait; For example, the number of past ages before the current age is positively correlated with the resolution of the portrait and is also positively correlated with the clarity of the portrait. When the clarity of the portrait is fixed, the number of past ages before the current age is 5 years, 6 years, 7 years, and 8 years when the resolution of the portrait is SD, HD, UHD, and 4K, respectively. Specifically, when the clarity of the portrait is fixed, when the resolution of the portrait is standard definition, high definition, ultra-high definition, and 4K, the number of each past age before the current age is 5 years, 6 years, 7 years, and 8 years, respectively, including: each past age before the current age includes the current age; In each learning process of the feedforward neural network, the known Alzheimer's portrait data of a certain person at a set old age is used as the output of the feedforward neural network, and the resolution of the portrait, various physiological data of the certain person, and the portrait data corresponding to each age of the certain person before the current age are used as the input of the feedforward neural network to complete the learning process; For each edge pixel, the corresponding grayscale gradient information is calculated based on the grayscale values ​​of the surrounding pixels and its own grayscale value; And wherein, for each edge pixel point, calculating its corresponding grayscale gradient information based on the grayscale values ​​of each pixel point around it and its own grayscale value includes: placing the grayscale values ​​of each pixel point around it and its own grayscale value into the same grayscale value set, and taking the standard deviation of each grayscale value in the grayscale value set as its corresponding grayscale gradient information Specifically, the grayscale values ​​of each pixel point around it and its own grayscale value are placed in the same grayscale value set, and the standard deviation of each grayscale value in the grayscale value set is used as its corresponding grayscale gradient information, including: determining the pixel point window corresponding to a certain edge pixel point by the middle pixel point of a pixel point window that is a square with a certain edge pixel point, and taking each pixel point covered by the pixel point window corresponding to the edge pixel point as each pixel point around the certain edge pixel point and the certain edge pixel point.

[0024] Example 2 Figure 3 The present invention is a flowchart showing the steps of a method for constructing a portrait of Alzheimer's disease based on big data according to Example 2 of the present invention.

[0025] like Figure 3 As shown, Figure 2 Unlike the embodiment in , after using the intelligent portrait construction model to intelligently construct Alzheimer's portrait data of the target person at the set old age based on the portrait resolution, various physiological association data of the target person, and various portrait data corresponding to each past age of the target person before the current age, that is, after step S104, the method further includes: Step S105: constructing an Alzheimer's disease portrait according to the respective L component values, the respective A component values, and the respective B component values ​​corresponding to the respective pixel points of the Alzheimer's disease portrait in the Alzheimer's disease portrait data; Specifically, constructing an Alzheimer's portrait based on the L component values, A component values ​​and B component values ​​corresponding to each pixel point of the Alzheimer's portrait in the Alzheimer's portrait data includes: the constructed Alzheimer's portrait can help analyze the type and status of Alzheimer's disease of the target person at a set age, prepare reliable related reference data in advance for the future health monitoring of the target person, and make the management of Alzheimer's disease more predictable.

[0026] Example 3 Figure 4 The present invention is a flowchart showing the steps of a method for constructing a portrait of Alzheimer's disease based on big data according to Example 3 of the present invention.

[0027] like Figure 4 As shown, Figure 2Unlike the embodiment in , after using the intelligent portrait construction model to intelligently construct Alzheimer's portrait data of the target person at the set old age based on the resolution of the portrait, various physiological association data of the target person, and various portrait data corresponding to various past ages of the target person before the current age, after step S104, the method further includes: Step S106: receiving the Alzheimer's portrait and displaying the content of the Alzheimer's portrait; For example, an LCD display array, a liquid crystal display screen, or an LED display array may be selected to receive the Alzheimer's portrait and to display the content of the Alzheimer's portrait; Step S107: receiving the Alzheimer's portrait, packaging the Alzheimer's portrait and the target person's identification information into a network data packet, and wirelessly sending the network data packet to a remote medical monitoring server via a wireless communication network; For example, the remote medical monitoring server is a big data server, a blockchain server, or a cloud computing server.

[0028] Example 4 Figure 5 The present invention is a flowchart showing the steps of a method for constructing a portrait of Alzheimer's disease based on big data according to Example 4 of the present invention.

[0029] like Figure 5 As shown, Figure 2 Unlike the embodiment in , after performing multiple learning on the feedforward neural network to obtain the feedforward neural network after the multiple learning is completed and output as the intelligent portrait construction model, that is, after step S103, the method further includes: Step S108: receiving the intelligent portrait construction model, and completing the model storage of the intelligent portrait construction model by storing various model parameters of the intelligent portrait construction model; Specifically, a FLASH flash memory or an MMC memory card may be selected to receive the intelligent portrait construction model, and the model storage of the intelligent portrait construction model is completed by storing various model parameters of the intelligent portrait construction model.

[0030] Next, various method embodiments of the present invention will be described in detail.

[0031] In the method for constructing a portrait of Alzheimer's disease based on big data according to various method embodiments of the present invention: parsing respective portrait data corresponding to each past age of the target person before the current age, wherein each portrait has the same resolution and clarity, and each portrait data comprises respective L component values, respective A component values, and respective B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait, including: the respective portrait data corresponding to each past age before the current age were obtained by photographing the target person in the same month of each past age; wherein, parsing respective portrait data corresponding to respective past ages of the target person before the current age, wherein the respective portraits have the same resolution and clarity, and each portrait data comprises respective L component values, respective A component values, and respective B component values ​​corresponding to respective pixels of the portrait, and multiple grayscale gradient information corresponding to multiple edge pixels of the portrait, further comprising: each pixel having its corresponding L component value, A component value, and B component value in the LAB color space; Specifically, the L component value, A component value, and B component value of each pixel in the LAB color space are all between 0 and 255. Among them, the intelligent portrait construction model is used to intelligently construct the Alzheimer's portrait data of the target person at the set old age according to the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to each past age of the target person before the current age, including: the resolution and clarity of the Alzheimer's portrait of the target person at the set old age are respectively the same as the resolution and clarity of the portrait corresponding to any of the past ages of the target person before the current age; And wherein, an intelligent portrait construction model is used to intelligently construct the target person's Alzheimer's portrait data when the old age is set according to the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to the target person's past ages before the current age, and the Alzheimer's portrait data of the target person when the old age is set also includes: the Alzheimer's portrait data of the target person when the old age is set is each L component value, each A component value and each B component value corresponding to each pixel point of the Alzheimer's portrait data, and multiple grayscale gradient information corresponding to multiple edge pixel points of the Alzheimer's portrait data.

[0032] And in the method for constructing a portrait of Alzheimer's disease based on big data according to various method embodiments of the present invention: Adopting an intelligent portrait construction model to intelligently construct Alzheimer's portrait data of the target person at a set old age based on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age, further includes: inputting the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age into the intelligent portrait construction model in parallel, and executing the intelligent portrait construction model to obtain the Alzheimer's portrait data of the target person at the set old age output by the intelligent portrait construction model; The process includes inputting the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age into the intelligent portrait construction model in parallel, and executing the intelligent portrait construction model to obtain the Alzheimer's disease portrait data of the target person at the set old age output by the intelligent portrait construction model, including: performing binary value conversion processing on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age, respectively, before inputting the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age into the intelligent portrait construction model in parallel; For example, a programmable logic device may be selected to convert the resolution of the portrait, various physiological data of the target person, and various portrait data corresponding to each age of the target person before the current age into binary values; And wherein, the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to the target person's past ages before the current age are input into the intelligent portrait construction model in parallel, and the intelligent portrait construction model is executed to obtain the output of the intelligent portrait construction model. The Alzheimer's portrait data of the target person at the set old age also includes: the Alzheimer's portrait data of the target person at the set old age is represented in the form of binary values.

[0033] Example 5 Figure 6 This is a structural diagram of a system for constructing a portrait of Alzheimer's disease based on big data according to Example 5 of the present invention.

[0034] like Figure 6 As shown, the system for constructing a portrait of Alzheimer's disease based on big data includes a memory and multiple processors, wherein the multiple processors are located at a wireless routing end of a target residential user and a remote omni-media content server. The memory stores a computer program, and the computer program is configured to be executed by the multiple processors to complete the following steps: Step S101: parsing various physiological data of a target person for constructing a portrait of Alzheimer's disease, wherein the physiological data of the target person include the target person's current age, gender identifier, height-to-weight ratio, and nationality code value; For example, parsing various physiological data of a target person for constructing an Alzheimer's disease portrait, wherein the various physiological data of the target person are the target person's current age, gender identifier, height-to-weight ratio, and nationality code value, includes: selectively using multiple parameter parsing components for respectively parsing the target person's current age, gender identifier, height-to-weight ratio, and nationality code value; Step S102: Parsing portrait data corresponding to each age of the target person before the current age, wherein each portrait has the same resolution and clarity, and each portrait data includes L component values, A component values, and B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait; Specifically, analyzing each set of portrait data corresponding to each past age of the target person before the current age, wherein each set of portrait data has the same resolution and clarity, and each set of portrait data includes each set of L component values, each set of A component values, and each set of B component values ​​corresponding to each pixel point of the portrait, as well as multiple sets of grayscale gradient information corresponding to multiple edge pixels of the portrait, including: the value range of any component value among the L component value, the A component value, and the B component value corresponding to each pixel point is between 0 and 255; Here, by obtaining the L component value, A component value, and B component value of each pixel point of a frame image, the frame image can be assembled and displayed; Step S103: performing multiple learning on the feedforward neural network to obtain a feedforward neural network after completing multiple learning and outputting it as an intelligent portrait construction model; For example, performing multiple learning on a feedforward neural network to obtain a feedforward neural network after the multiple learning and outputting the feedforward neural network as an intelligent portrait construction model includes: the feedforward neural network includes an input layer, a hidden layer, and an output layer, wherein the hidden layer is located between the input layer and the output layer; Step S104: Using an intelligent portrait construction model to intelligently construct Alzheimer's portrait data of the target person at the set old age based on the resolution of the portrait, various physiological related data of the target person, and various portrait data corresponding to each of the target person's past ages before the current age; For example, the intelligent portrait construction model is used to intelligently construct the target person's Alzheimer's portrait data at a set old age based on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age, including: a numerical simulation mode can be selected to complete the testing and simulation of the data processing process of the intelligent portrait construction model being used to intelligently construct the target person's Alzheimer's portrait data at a set old age based on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age; Among them, the number of learning times performed by the feedforward neural network is positively correlated with the total number of nationalities; For example, the positive correlation between the number of learning times performed by the feedforward neural network and the total number of nationalities includes: when the number of nationalities involved in the processing is 50, the number of learning times performed by the feedforward neural network is 600; when the number of nationalities involved in the processing is 70, the number of learning times performed by the feedforward neural network is 800; and when the number of nationalities involved in the processing is 100, the number of learning times performed by the feedforward neural network is 1000, and so on; Among them, the number of past ages before the current age is positively correlated with the resolution of the portrait, and is also positively correlated with the clarity of the portrait; For example, the number of past ages before the current age is positively correlated with the resolution of the portrait and is also positively correlated with the clarity of the portrait. When the clarity of the portrait is fixed, the number of past ages before the current age is 5 years, 6 years, 7 years, and 8 years when the resolution of the portrait is SD, HD, UHD, and 4K, respectively. Specifically, when the clarity of the portrait is fixed, when the resolution of the portrait is standard definition, high definition, ultra-high definition, and 4K, the number of each past age before the current age is 5 years, 6 years, 7 years, and 8 years, respectively, including: each past age before the current age includes the current age; In each learning process of the feedforward neural network, the known Alzheimer's portrait data of a certain person at a set old age is used as the output of the feedforward neural network, and the resolution of the portrait, various physiological data of the certain person, and the portrait data corresponding to each age of the certain person before the current age are used as the input of the feedforward neural network to complete the learning process; For each edge pixel, the corresponding grayscale gradient information is calculated based on the grayscale values ​​of the surrounding pixels and its own grayscale value; And wherein, for each edge pixel point, calculating its corresponding grayscale gradient information based on the grayscale values ​​of each pixel point around it and its own grayscale value includes: placing the grayscale values ​​of each pixel point around it and its own grayscale value into the same grayscale value set, and taking the standard deviation of each grayscale value in the grayscale value set as its corresponding grayscale gradient information Specifically, placing the grayscale values ​​of surrounding pixels and the grayscale value of the pixel itself into the same grayscale value set, and using the standard deviation of each grayscale value in the grayscale value set as the corresponding grayscale gradient information includes: determining a pixel window corresponding to a certain edge pixel point by taking the middle pixel of a square pixel window as the edge pixel point, and using each pixel covered by the pixel window corresponding to the edge pixel point as each pixel around the certain edge pixel point and the certain edge pixel point; like Figure 6 As shown, illustratively, S processors are provided, and the S processors are located at the wireless routing end of the target residential user and the remote full-media content server, where S is a natural number greater than or equal to 1.

[0035] Example 6 Figure 7 This is a structural diagram of a system for constructing a portrait of Alzheimer's disease based on big data according to Example 6 of the present invention.

[0036] like Figure 7 As shown, the big data-based Alzheimer's disease portrait construction system includes the following components: The first parsing unit is used to parse various physiological data of the target person for constructing the Alzheimer's disease portrait, wherein the physiological data of the target person are the current age, gender identifier, height-to-weight ratio, and nationality code value of the target person; For example, parsing various physiological data of a target person for constructing an Alzheimer's disease portrait, wherein the various physiological data of the target person are the target person's current age, gender identifier, height-to-weight ratio, and nationality code value, includes: selectively using multiple parameter parsing components for respectively parsing the target person's current age, gender identifier, height-to-weight ratio, and nationality code value; The second parsing mechanism is used to parse the portrait data corresponding to each age of the target person before the current age, wherein the resolution and clarity of each portrait are the same, and each portrait data includes the L component values, A component values, and B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait; Specifically, analyzing each set of portrait data corresponding to each past age of the target person before the current age, wherein each set of portrait data has the same resolution and clarity, and each set of portrait data includes each set of L component values, each set of A component values, and each set of B component values ​​corresponding to each pixel point of the portrait, as well as multiple sets of grayscale gradient information corresponding to multiple edge pixels of the portrait, including: the value range of any component value among the L component value, the A component value, and the B component value corresponding to each pixel point is between 0 and 255; Here, by obtaining the L component value, A component value, and B component value of each pixel point of a frame image, the frame image can be assembled and displayed; An object reshaping mechanism is used to perform multiple learning on the feedforward neural network to obtain a feedforward neural network after completing multiple learning and output it as an intelligent portrait construction model; For example, performing multiple learning on a feedforward neural network to obtain a feedforward neural network after the multiple learning and outputting the feedforward neural network as an intelligent portrait construction model includes: the feedforward neural network includes an input layer, a hidden layer, and an output layer, wherein the hidden layer is located between the input layer and the output layer; an intelligent construction mechanism, connected to the first analysis mechanism, the second analysis mechanism, and the object reconstruction mechanism, respectively, for using an intelligent portrait construction model to intelligently construct Alzheimer's portrait data of the target person at a set old age based on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age; For example, the intelligent portrait construction model is used to intelligently construct the target person's Alzheimer's portrait data at a set old age based on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age, including: a numerical simulation mode can be selected to complete the testing and simulation of the data processing process of the intelligent portrait construction model being used to intelligently construct the target person's Alzheimer's portrait data at a set old age based on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age; Among them, the number of learning times performed by the feedforward neural network is positively correlated with the total number of nationalities; For example, the positive correlation between the number of learning times performed by the feedforward neural network and the total number of nationalities includes: when the number of nationalities involved in the processing is 50, the number of learning times performed by the feedforward neural network is 600; when the number of nationalities involved in the processing is 70, the number of learning times performed by the feedforward neural network is 800; and when the number of nationalities involved in the processing is 100, the number of learning times performed by the feedforward neural network is 1000, and so on; Among them, the number of past ages before the current age is positively correlated with the resolution of the portrait, and is also positively correlated with the clarity of the portrait; For example, the number of past ages before the current age is positively correlated with the resolution of the portrait and is also positively correlated with the clarity of the portrait. When the clarity of the portrait is fixed, the number of past ages before the current age is 5 years, 6 years, 7 years, and 8 years when the resolution of the portrait is SD, HD, UHD, and 4K, respectively. Specifically, when the clarity of the portrait is fixed, when the resolution of the portrait is standard definition, high definition, ultra-high definition, and 4K, the number of each past age before the current age is 5 years, 6 years, 7 years, and 8 years, respectively, including: each past age before the current age includes the current age; In each learning process of the feedforward neural network, the known Alzheimer's portrait data of a certain person at a set old age is used as the output of the feedforward neural network, and the resolution of the portrait, various physiological data of the certain person, and the portrait data corresponding to each age of the certain person before the current age are used as the input of the feedforward neural network to complete the learning process; For each edge pixel, the corresponding grayscale gradient information is calculated based on the grayscale values ​​of the surrounding pixels and its own grayscale value; And wherein, for each edge pixel point, calculating its corresponding grayscale gradient information based on the grayscale values ​​of each pixel point around it and its own grayscale value includes: placing the grayscale values ​​of each pixel point around it and its own grayscale value into the same grayscale value set, and taking the standard deviation of each grayscale value in the grayscale value set as its corresponding grayscale gradient information Specifically, the grayscale values ​​of each pixel point around it and its own grayscale value are placed in the same grayscale value set, and the standard deviation of each grayscale value in the grayscale value set is used as its corresponding grayscale gradient information, including: determining the pixel point window corresponding to a certain edge pixel point by the middle pixel point of a pixel point window that is a square with a certain edge pixel point, and taking each pixel point covered by the pixel point window corresponding to the edge pixel point as each pixel point around the certain edge pixel point and the certain edge pixel point.

[0037] In addition, the present invention may also cite the following technical contents to further demonstrate the outstanding substantial progress of the present invention: The number of past ages before the current age is positively correlated with the resolution of the portrait, and is also positively correlated with the clarity of the portrait, including: using a double-input single-output numerical mapping formula to express the numerical mapping relationship between the resolution of the portrait and the clarity of the portrait and the number of past ages before the current age; For example, the number of past ages before the current age is positively correlated with the resolution of the portrait and is also positively correlated with the clarity of the portrait. Furthermore, a numerical simulation mode can be selected to complete the testing and simulation of the double-input single-output numerical mapping formula; The method of using a dual-input, single-output numerical mapping formula to express the numerical mapping relationship between the image resolution and the image clarity and the number of past ages before the current age includes: in the dual-input, single-output numerical mapping formula, the image resolution and the image clarity are two input values ​​of the numerical mapping formula; And wherein, the use of a dual-input single-output numerical mapping formula to represent the numerical mapping relationship between the resolution and clarity of the portrait and the number of past ages before the current age also includes: in the dual-input single-output numerical mapping formula, the number of past ages before the current age is the single output value of the numerical mapping formula.

[0038] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0039] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device / electronic device / computer-readable storage medium / computer program product embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The above is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are included in the scope of protection of the present invention.

Claims

1. A method for constructing a portrait of Alzheimer's disease based on big data, characterized in that: The method comprises: Analyze various physiological data of the target person for whom the Alzheimer's disease portrait is to be constructed, wherein the physiological data of the target person include the target person's current age, gender identifier, height-to-weight ratio, and nationality code value; Analyze the portrait data corresponding to each age of the target person before the current age, wherein the resolution and clarity of each portrait are the same, and each portrait data includes the L component values, A component values, and B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait; Performing multiple learning on the feedforward neural network to obtain a feedforward neural network after completing multiple learning and outputting it as an intelligent portrait construction model; An intelligent portrait construction model is used to intelligently construct the target person's Alzheimer's portrait data at the set old age based on the portrait resolution, various physiological data of the target person, and the portrait data corresponding to each of the target person's past ages before the current age; Among them, the number of learning times performed by the feedforward neural network is positively correlated with the total number of nationalities; Among them, the number of past ages before the current age is positively correlated with the resolution of the portrait, and is also positively correlated with the clarity of the portrait.

2. The method for constructing a portrait of Alzheimer's disease based on big data according to claim 1, characterized in that: In each learning process performed on the feedforward neural network, the Alzheimer's portrait data of a known person at a set old age is used as the output content of the feedforward neural network, and the resolution of the portrait, the various physiological related data of the person, and the portrait data corresponding to each past age of the person before the current age are used as the input content of the feedforward neural network to complete this learning.

3. The method for constructing a portrait of Alzheimer's disease based on big data according to claim 2, characterized in that: For each edge pixel, the corresponding grayscale gradient information is calculated based on the grayscale values ​​of the surrounding pixels and its own grayscale value; Among them, for each edge pixel point, the corresponding grayscale gradient information is calculated based on the grayscale values ​​of the surrounding pixel points and its own grayscale value, including: placing the grayscale values ​​of the surrounding pixel points and its own grayscale value into the same grayscale value set, and taking the standard deviation of each grayscale value in the grayscale value set as its corresponding grayscale gradient information.

4. The method for constructing a portrait of Alzheimer's disease based on big data according to claim 3, wherein: After intelligently constructing Alzheimer's disease portrait data of the target person at a set old age using the intelligent portrait construction model based on the resolution of the portrait, various physiological association data of the target person, and various portrait data corresponding to each of the target person's past ages before the current age, the method further includes: An Alzheimer's portrait is constructed according to the L component values, A component values ​​and B component values ​​corresponding to each pixel point of the Alzheimer's portrait in the Alzheimer's portrait data.

5. The method for constructing a portrait of Alzheimer's disease based on big data according to claim 3, wherein: After intelligently constructing Alzheimer's disease portrait data of the target person at a set old age using the intelligent portrait construction model based on the resolution of the portrait, various physiological association data of the target person, and various portrait data corresponding to each of the target person's past ages before the current age, the method further includes: receiving a portrait of an elderly person with dementia, and displaying the content of the portrait of an elderly person with dementia; Receive the Alzheimer's portrait, package the Alzheimer's portrait and the target person's identification information into a network data packet, and wirelessly send the network data packet to a remote medical monitoring server through a wireless communication network.

6. The method for constructing a portrait of Alzheimer's disease based on big data according to claim 3, wherein: After performing multiple learning on the feedforward neural network to obtain a feedforward neural network after the multiple learning is completed and output as an intelligent portrait construction model, the method further includes: Receive the intelligent portrait construction model and complete the model storage of the intelligent portrait construction model by storing various model parameters of the intelligent portrait construction model.

7. The method for constructing a portrait of Alzheimer's disease based on big data according to any one of claims 3 to 6, characterized in that: parsing respective portrait data corresponding to each past age of the target person before the current age, wherein each portrait has the same resolution and clarity, and each portrait data comprises respective L component values, respective A component values, and respective B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait, including: the respective portrait data corresponding to each past age before the current age were obtained by photographing the target person in the same month of each past age; wherein, parsing respective portrait data corresponding to respective past ages of the target person before the current age, wherein the respective portraits have the same resolution and clarity, and each portrait data comprises respective L component values, respective A component values, and respective B component values ​​corresponding to respective pixels of the portrait, and multiple grayscale gradient information corresponding to multiple edge pixels of the portrait, further comprising: each pixel having its corresponding L component value, A component value, and B component value in the LAB color space; Among them, the intelligent portrait construction model is used to intelligently construct the Alzheimer's portrait data of the target person at the set old age according to the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to each past age of the target person before the current age, including: the resolution and clarity of the Alzheimer's portrait of the target person at the set old age are respectively the same as the resolution and clarity of the portrait corresponding to any of the past ages of the target person before the current age; Among them, the intelligent portrait construction model is used to intelligently construct the target person's Alzheimer's portrait data when the old age is set according to the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to the target person's past ages before the current age. The data also includes: the target person's Alzheimer's portrait data when the old age is set is the various L component values, various A component values ​​and various B component values ​​corresponding to each pixel point of the Alzheimer's portrait data, and multiple grayscale gradient information corresponding to multiple edge pixel points of the Alzheimer's portrait data.

8. The method for constructing a portrait of Alzheimer's disease based on big data according to any one of claims 3 to 6, characterized in that: Adopting an intelligent portrait construction model to intelligently construct Alzheimer's portrait data of the target person at a set old age based on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age, further includes: inputting the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age into the intelligent portrait construction model in parallel, and executing the intelligent portrait construction model to obtain the Alzheimer's portrait data of the target person at the set old age output by the intelligent portrait construction model; The process includes inputting the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age into the intelligent portrait construction model in parallel, and executing the intelligent portrait construction model to obtain the Alzheimer's disease portrait data of the target person at the set old age output by the intelligent portrait construction model, including: performing binary value conversion processing on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age, respectively, before inputting the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age into the intelligent portrait construction model in parallel; Among them, the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to the target person's past ages before the current age are input into the intelligent portrait construction model in parallel, and the intelligent portrait construction model is executed to obtain the output of the intelligent portrait construction model. The Alzheimer's portrait data of the target person at the set old age also includes: the Alzheimer's portrait data of the target person at the set old age is represented in the form of binary values.

9. A system for constructing a portrait of Alzheimer's disease based on big data, characterized in that: The system includes a memory and multiple processors, wherein the multiple processors are respectively located at a wireless routing end of a target residential user and a remote all-media content server. The memory stores a computer program, and the computer program is configured to be executed by the multiple processors to complete the following steps: Analyze various physiological data of the target person for whom the Alzheimer's disease portrait is to be constructed, wherein the physiological data of the target person include the target person's current age, gender identifier, height-to-weight ratio, and nationality code value; Analyze the portrait data corresponding to each age of the target person before the current age, wherein the resolution and clarity of each portrait are the same, and each portrait data includes the L component values, A component values, and B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait; Performing multiple learning on the feedforward neural network to obtain a feedforward neural network after completing multiple learning and outputting it as an intelligent portrait construction model; An intelligent portrait construction model is used to intelligently construct the target person's Alzheimer's portrait data at the set old age based on the portrait resolution, various physiological data of the target person, and the portrait data corresponding to each of the target person's past ages before the current age; Among them, the number of learning times performed by the feedforward neural network is positively correlated with the total number of nationalities; Among them, the number of past ages before the current age is positively correlated with the resolution of the portrait, and is also positively correlated with the clarity of the portrait.

10. A system for constructing a portrait of Alzheimer's disease based on big data, characterized in that: The system comprises: The first parsing unit is used to parse various physiological data of the target person for constructing the Alzheimer's disease portrait, wherein the physiological data of the target person are the current age, gender identifier, height-to-weight ratio, and nationality code value of the target person; The second parsing mechanism is used to parse the portrait data corresponding to each age of the target person before the current age, wherein the resolution and clarity of each portrait are the same, and each portrait data includes the L component values, A component values, and B component values ​​corresponding to each pixel point of the portrait, as well as multiple grayscale gradient information corresponding to multiple edge pixels of the portrait; An object reshaping mechanism is used to perform multiple learning on the feedforward neural network to obtain a feedforward neural network after completing multiple learning and output it as an intelligent portrait construction model; an intelligent construction mechanism, connected to the first analysis mechanism, the second analysis mechanism, and the object reconstruction mechanism, respectively, for using an intelligent portrait construction model to intelligently construct Alzheimer's portrait data of the target person at a set old age based on the resolution of the portrait, various physiological correlation data of the target person, and various portrait data corresponding to various past ages of the target person before the current age; Among them, the number of learning times performed by the feedforward neural network is positively correlated with the total number of nationalities; Among them, the number of past ages before the current age is positively correlated with the resolution of the portrait, and is also positively correlated with the clarity of the portrait.

Images