Artificial intelligence big data intelligent health management method and system

Abstract

The invention relates to the technical field of intelligent health management, and particularly discloses an artificial intelligence big data intelligent health management method and system, and the method comprises the steps: obtaining the body parameters of a user based on an intelligent device, and constructing a body portrait of the user according to the body parameters; obtaining behavior data containing a time span of the user, obtaining change information of the body portrait according to the time span, and training a mapping model from the behavior data to the change information; comparing the body portraits of different users at the latest moment with the latest mapping model, and clustering the users; for any type of users, when the physical examination data uploaded by any user is received, generating prompt information according to the physical examination data, and broadcasting the prompt information to the same type of users; according to the method, the users are clustered through the data acquired by the intelligent equipment, the highly similar users are classified into one class, and when any user in the same class of users is subjected to physical examination, the physical examination data are shared, so that the physical examination frequency of each user is improved in a disguised manner.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent health management, and specifically to an artificial intelligence big data intelligent health management method and system. Background Art

[0002] With the progress of society and the development of technology, more and more people will use various intelligent devices to collect their own body data, and then evaluate their physical states, so that they can know their own conditions and ensure their health.

[0003] The costs of existing household health management devices are relatively low, and their accuracies are not high enough. Although they can achieve certain effects, the effects are minimal. Most of them are used for weight monitoring and the like, and it is difficult to meet the health management requirements. Summary of the Invention

[0004] The purpose of the present invention is to provide an artificial intelligence big data intelligent health management method and system to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] An artificial intelligence big data intelligent health management method and system, the method comprising:

[0007] Obtaining the body parameters of a user based on an intelligent device, and constructing a body portrait of the user according to the body parameters;

[0008] Obtaining the behavior data of the user with a time span, obtaining the change information of the body portrait according to the time span, and training a mapping model from the behavior data to the change information;

[0009] Comparing the body portraits at the latest moment and the latest mapping models of different users, and clustering the users;

[0010] For any class of users, when receiving the physical examination data uploaded by any user, generating a prompt message according to the physical examination data and broadcasting it to the users of the same class.

[0011] As a further solution of the present invention: the step of obtaining the body parameters of the user based on the intelligent device and constructing the body portrait of the user according to the body parameters comprises:

[0012] Obtaining the basic parameters of the user based on an intelligent body fat scale;

[0013] Traversing and matching a body model in a preset body model library according to the basic parameters;

[0014] Obtaining the changing parameters of the user in real time based on an intelligent wearable device, and determining the display parameters of the body model according to the changing parameters;

[0015] Insert the display parameters into the body model to obtain the user's body portrait.

[0016] The variable parameters include heart rate, exercise amount, and blood oxygen saturation. Convert the heart rate, exercise amount, and blood oxygen saturation to the range of 0 to 255, and use them as the H value, S value, and V value respectively to obtain the display parameters.

[0017] As a further solution of the present invention: The steps of obtaining the behavior data of the user with a time span, obtaining the change information of the body portrait according to the time span, and training the mapping model from the behavior data to the change information include:

[0018] Based on the intelligent wearable device, obtain the variable parameters of the user in real time, identify the variable parameters, and determine the behavior type of the user at each moment;

[0019] Within a time period, merge the behavior types at each moment to obtain the behavior data of each time period;

[0020] Obtain the change information of the body portrait of each time period, use the behavior data of the same time period as features, and the change information of the body portrait as labels to construct samples;

[0021] Count a preset number of samples, construct a sample set, divide the sample set into a training set and a test set according to a preset ratio, and train the neural network model;

[0022] When the error rate of the neural network model is less than the preset error rate threshold, output the neural network model as the mapping model from the behavior data to the change information.

[0023] As a further solution of the present invention: The steps of comparing the body portraits and the latest mapping models of different users and clustering the users include:

[0024] Obtain the body portraits and mapping models of each user at the current moment;

[0025] Compare the body portraits and mapping models of different users, and calculate the portrait distance and the model distance;

[0026] Cluster the users according to the portrait distance and the model distance.

[0027] As a further solution of the present invention: The steps of clustering the users according to the portrait distance and the model distance include:

[0028] For any two users, read the body portraits of the two users, calibrate the origin points of the two body portraits, and calculate the portrait distance;

[0029] Read the mapping models of two users, randomly determine a preset number of test data, input the test data into the two mapping models to obtain outputs, and calculate the model distance based on the outputs;

[0030] Calculate the similarity of users based on the portrait distance and the model distance, and apply the optics clustering algorithm to cluster the users; the similarity is inversely proportional to both the portrait distance and the model distance;

[0031] Among them, the calculation process of the portrait distance is as follows:

[0032] d1 represents the portrait distance, N, M, and K respectively represent the dimensions of the space where the body model is located; A(i, j, k) and B(i, j, k) respectively represent the parameters at point (i, j, k) of the two body models, and A(i, j, k) and B(i, j, k) are both arrays used to represent display parameters. When a certain body model has no display parameter at point (i, j, k), an array with all elements being zero is used as a substitute array; dis{A(i, j, k), B(i, j, k)} represents the array distance between the two arrays; α is a preset adjustment coefficient.

[0033] As a further solution of the present invention: for any type of user, when receiving the physical examination data uploaded by any user, the steps of generating a prompt message based on the physical examination data and broadcasting it to the same type of users include:

[0034] Regularly send physical examination data acquisition requests to various types of users;

[0035] When receiving the physical examination data uploaded by any user, transcode the physical examination data to obtain digital physical examination data;

[0036] Locate abnormal data in the digital physical examination data and insert a prompt box in the abnormal data;

[0037] Broadcast the digital physical examination data containing the prompt box to the same type of users.

[0038] The technical solution of the present invention also provides an artificial intelligence big data intelligent health management system, and the system includes:

[0039] A body portrait construction module, which is used to obtain the body parameters of the user based on the intelligent device and construct the body portrait of the user according to the body parameters;

[0040] A mapping model training module, which is used to obtain the behavior data of the user with a time span, obtain the change information of the body portrait according to the time span, and train the mapping model from the behavior data to the change information;

[0041] A user clustering module, which is used to compare the body portraits and the latest mapping models of different users at the latest moment, and cluster the users;

[0042] A physical examination data sharing module, which is used for any type of user. When receiving the physical examination data uploaded by any user, it generates a prompt message according to the physical examination data and broadcasts it to the users of the same type.

[0043] As a further solution of the present invention: the body portrait construction module includes:

[0044] A basic parameter acquisition unit, which is used to acquire the basic parameters of the user based on an intelligent body fat scale;

[0045] A body model matching unit, which is used to traverse and match the body model in a preset body model library according to the basic parameters;

[0046] A variable parameter determination unit, which is used to acquire the variable parameters of the user in real time based on an intelligent wearable device, and determine the display parameters of the body model according to the variable parameters;

[0047] A display parameter application unit, which is used to insert the display parameters into the body model to obtain the body portrait of the user.

[0048] The variable parameters include heart rate, exercise amount, and blood oxygen saturation. The heart rate, exercise amount, and blood oxygen saturation are all converted to the range of 0 to 255, and are used as the H value, S value, and V value respectively to obtain the display parameters.

[0049] As a further solution of the present invention: the mapping model training module includes:

[0050] A variable parameter identification unit, which is used to acquire the variable parameters of the user in real time based on an intelligent wearable device, identify the variable parameters, and determine the behavior types of the user at each moment;

[0051] A behavior type merging unit, which is used to merge the behavior types at each moment within a time period to obtain the behavior data of each time period;

[0052] A sample creation unit, which is used to acquire the change information of the body portrait of each time period, and construct a sample with the behavior data of the same time period as the feature and the change information of the body portrait as the label;

[0053] A model training unit, which is used to count a preset number of samples, construct a sample set, divide the sample set into a training set and a test set according to a preset ratio, and train a neural network model;

[0054] A model output unit, which is used to output the neural network model as the mapping model of the behavior data to the change information when the error rate of the neural network model is less than a preset error rate threshold.

[0055] As a further solution of the present invention: the user clustering module includes:

[0056] A parameter acquisition unit for acquiring the body portraits and mapping models of each user at the current moment;

[0057] A user comparison unit for comparing the body portraits and mapping models of different users and calculating the portrait distance and model distance;

[0058] A clustering execution unit for clustering users according to the portrait distance and model distance.

[0059] Compared with the prior art, the beneficial effects of the present invention are: the present invention clusters users through the data obtained by intelligent devices, classifies highly similar users into one category, and when any user in the same category undergoes a physical examination, the physical examination data is shared. When the number of users is large, someone will undergo a physical examination almost every day, which virtually increases the physical examination frequency of each user and meets the health management needs of users. Brief Description of the Drawings

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0061] Figure 1 Shows the overall flowchart of the artificial intelligence big data intelligent health management method.

[0062] Figure 2 Shows the structure diagram of the artificial intelligence big data intelligent health management system. Detailed Embodiments

[0063] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer, the following further details the present invention with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0064] Figure 1 For the overall flowchart of the artificial intelligence big data intelligent health management method and system, in an embodiment of the present invention, an artificial intelligence big data intelligent health management method, the method includes:

[0065] Step S100: Based on intelligent devices, acquire the body parameters of users and construct body portraits of users according to the body parameters;

[0066] The intelligent devices in the technical solution of the present invention include an intelligent body fat scale and a wearable device. Existing intelligent body fat scales can measure many kinds of body parameters, and many enterprises also provide very affordable intelligent body fat scales, which are commonly used devices in many families. The data that the body fat scale can measure include: body weight, BMI, body fat percentage, muscle mass, water percentage, basal metabolic rate (BMR), visceral fat level, bone mass, and body age, etc. The principle of obtaining these parameters is BIA bioelectrical impedance technology (measuring body composition through foot electrodes), and its accuracy is not very high, but in the application scenario of this application, this accuracy is already sufficient. In addition, the wearable device refers to some intelligent bracelets that can monitor heart rate, steps, blood oxygen saturation, etc. The body fat scale generally detects once every period of time, such as every few days, and the wearable device can monitor in real time. The meaning of real-time monitoring is to monitor once every few minutes or even seconds. Combining the monitoring data of the body fat scale and the wearable device, it is collectively called body parameters. Analyzing and applying the body parameters can construct a user's body portrait. The body portrait is a three-dimensional model of the user containing display parameters.

[0067] Step S200: Obtain the behavior data of the user with a time span, obtain the change information of the body portrait according to the time span, and train the mapping model from the behavior data to the change information.

[0068] Behavior data is a superordinate concept used to characterize the user's behavior, such as walking, standing, sitting and lying, running, etc. Each behavior is a behavior within a period of time. For example, being in a sleep state from 0:00 to 8:00, the behavior data with a time span is the sleep behavior from 0:00 to 8:00. At the same time, obtaining the change situation of the body portrait from 0:00 to 8:00 is the change information in the above content. Taking the behavior data with a time span as the independent variable and the change situation of the body portrait as the dependent variable, training the neural network model from the independent variable to the dependent variable. After training, the mapping model from the behavior data to the change information is obtained.

[0069] Step S300: Compare the body portraits and the latest mapping models of different users at the latest moment, and cluster the users.

[0070] For any user, the body portrait at the latest moment represents the latest state of the user, and the latest mapping model represents the impact of the user's behavior on the body. These two can reflect the real state of the user and are very comprehensive. Comparing the body portraits and the latest mapping models of different users at the latest moment, calculating the differences between two users according to the comparison results, and then clustering the users, and classifying the same type of users into one category.

[0071] It should be noted that the user mentioned in this application refers to a user who has registered in the execution entity of this method. During the registration stage, the execution entity of this method will send a permission acquisition request to obtain the permissions granted by the user. Only in this way can the execution entity of this method query which category the user belongs to, and only then can it send the physical examination data to the corresponding user in the subsequent physical examination data sharing session.

[0072] Step S400: For any category of users, when receiving the physical examination data uploaded by any user, generate a prompt message according to the physical examination data and broadcast it to users of the same category;

[0073] The physical states of each user in the same category of users are extremely similar, and their implicit response capabilities to behaviors are also similar. When any user in any category of users undergoes a physical examination and uploads the physical examination data to the execution entity of this method, the execution entity of this method can share the physical examination data with users of the same category; at that time, this process requires the user to explicitly grant permissions. In actual applications, authorization can be obtained uniformly once during the registration stage, and subsequent direct sharing can be done. Although this method is convenient, after all, the physical examination data is the user's personal data. Therefore, this application adopts the method of multiple inquiries. Before each sharing, a permission granting request needs to be sent to the user again. This method has very low convenience, and even users may find it very troublesome, but it can obtain very clear authorization, which is essentially for the consideration of users.

[0074] In an example of the technical solution of the present invention, after a user completes registration on the execution entity of this method, the detection data is uploaded in real time. The detection data is obtained by an intelligent device. The execution entity of this method classifies the user according to the detection data, and classifies users with highly similar characteristics into one category. At this time, when this user undergoes a very accurate physical examination, the physical examination report will be shared with users of the same category; for a certain user, the physical examination may be once a year, but for a category of users, when the number of users is large, the probability that no one undergoes a physical examination on a certain day is actually very low. This also means that any user in the same category of users can almost get a physical examination report every day, and the physical examination report obtained is the physical examination report of a user who is very similar to himself, enabling the user to have a more accurate understanding of his own state.

[0075] As a preferred embodiment of the technical solution of the present invention, the step of obtaining the user's body parameters based on the intelligent device and constructing the user's body portrait according to the body parameters includes:

[0076] Obtain the user's basic parameters based on an intelligent body fat scale;

[0077] Traverse and match the body model in the preset body model library according to the basic parameters;

[0078] Based on the intelligent wearable device, the changing parameters of the user are obtained in real time, and the display parameters of the body model are determined according to the changing parameters;

[0079] The display parameters are inserted into the body model to obtain the user's body portrait.

[0080] Based on the intelligent body fat scale, the basic parameters of the user are obtained. The basic parameters include body weight, height, body fat percentage, muscle mass and bone mass. Of course, fewer parameters can also be obtained. According to these parameters, the body model can be determined. After determining the body model, based on the intelligent wearable device, the changing parameters of the user are obtained in real time. The changing parameters include heart rate, exercise amount and blood oxygen saturation. The exercise amount is determined by the instantaneous number of steps, and the exercise amount is proportional to the instantaneous number of steps. According to the changing parameters, the display parameters of the body model are determined, and the display parameters are inserted into the body model to obtain the user's body portrait.

[0081] In the technical solution of the present invention, regarding the determination process of the body model, the present application adopts the method of matching and reading, and no longer introduces the modeling process. This method is very fast, but it requires the staff to pre-construct a body model library. First, the user determines some basic parameters, and models these basic parameters to obtain the body model corresponding to each basic parameter. When modeling each user, according to the basic parameters of the user, the closest body model in the body model library is queried as the body model of the user; the closest body model is the model with the smallest difference in basic parameters; in this architecture, the body model library contains basic parameter items and body model items. The more data items, the higher the accuracy, and the more accurate the matched body model.

[0082] The changing parameters include heart rate, exercise amount and blood oxygen saturation. The heart rate, exercise amount and blood oxygen saturation are all converted to the range of 0 to 255, and are used as the H value, S value and V value respectively to obtain the display parameters; the HSV space is a conventional color mode and belongs to the commonly used color value space in the computer display process.

[0083] As a preferred embodiment of the technical solution of the present invention, the steps of obtaining the behavior data of the user with a time span and obtaining the change information of the body portrait according to the time span and training the mapping model from the behavior data to the change information include:

[0084] Based on the intelligent wearable device, the changing parameters of the user are obtained in real time, and the changing parameters are identified to determine the behavior type of the user at each moment;

[0085] Within a time period, the behavior types at each moment are merged to obtain the behavior data of each time period;

[0086] Obtain the change information of the body image for each time period, use the behavior data in the same time period as features, and the change information of the body image as labels to construct samples;

[0087] Count a preset number of samples to construct a sample set, split the sample set into a training set and a test set according to a preset ratio, and train a neural network model;

[0088] When the error rate of the neural network model is less than a preset error rate threshold, output the neural network model as a mapping model from behavior data to change information.

[0089] In an example of the technical solution of the present invention, the acquisition process and application process of the change information are described. Based on the intelligent wearable device, the change parameters of the user are obtained in real time, and the change parameters are identified to determine the behavior type of the user at each moment. The corresponding relationship between the change parameters and the behavior type is known. In the prior art, there are already solutions for determining whether the user is sleeping, walking, or sitting / lying based on the change parameters, which will not be elaborated in this application.

[0090] Within a time period, merge the behavior types at each moment. Generally, a time period is a whole, that is, from 0:00 to 24:00. The process of merging the behavior types at each moment is as follows: Compare the behavior types at adjacent moments in sequence. When the behavior types are the same, merge the two adjacent moments. When the behavior types are different, mark the two adjacent moments as abnormal moments. After performing the merging process of adjacent moments, for the abnormal moments, obtain the behavior type after merging that is closest to the abnormal moment, and merge the abnormal moment into the behavior type after merging that is closest. Thus, the merging process is considered to be truly completed.

[0091] As a preferred embodiment of the technical solution of the present invention, the steps of clustering users by comparing the latest body images and the latest mapping models of different users include:

[0092] Obtain the body images and mapping models of each user at the current moment;

[0093] Compare the body images and mapping models of different users, and calculate the image distance and model distance;

[0094] Cluster users according to the image distance and model distance.

[0095] In an example of the technical solution of the present invention, the clustering process of users is described. Obtain the body images and mapping models of each user at the current moment. The current moment means the latest moment. Compare the body images and mapping models of different users, calculate the image distance and model distance, and use the image distance and model distance as parameters in the clustering process to perform the clustering process.

[0096] In an example of the technical solution of the present invention, the step of clustering users according to the portrait distance and the model distance includes:

[0097] For any two users, read the body portraits of the two users, calibrate the origin points of the two body portraits, and calculate the portrait distance;

[0098] Read the mapping models of the two users, randomly determine a preset number of test data, input the test data into the two mapping models to obtain outputs, and calculate the model distance according to the outputs;

[0099] Calculate the similarity of the users according to the portrait distance and the model distance, apply the optics clustering algorithm to cluster the users; the similarity is inversely proportional to both the portrait distance and the model distance;

[0100] Among them, the calculation process of the portrait distance is:

[0101] d1 represents the portrait distance, N, M, and K respectively represent the dimensions of the space where the body model is located; A(i, j, k) and B(i, j, k) respectively represent the parameters at the point (i, j, k) of the two body models, and A(i, j, k) and B(i, j, k) are both arrays used to represent the display parameters. When a certain body model has no display parameters at the point (i, j, k), an array with all elements being zero is used as a substitute array; dis{A(i, j, k), B(i, j, k)} represents the array distance between the two arrays; α is a preset adjustment coefficient.

[0102] The above content describes the clustering process. The clustering process adopts an unsupervised clustering scheme without restricting the number of classes. Applying the optics clustering algorithm requires determining the similarity first, and the similarity is determined by the portrait distance and the model distance. It is worth mentioning that the influence degree of the portrait distance and the model distance on the similarity can be determined by a preset weight.

[0103] Furthermore, regarding the portrait distance, the portrait distance is the difference between the two body portraits. In practical applications, a cylindrical space will be created starting from the origin point, such as 2m * 2m * 3m. This space is large enough to include most human bodies. Scale the cylindrical space according to the scale of the body portrait. At this time, query the positions in the cylindrical space in sequence to determine whether the position belongs to the body portrait. If it belongs, what are the corresponding display parameters? Compare the display parameters of the two body portraits at this position to obtain the distance at this position. Since the display parameters are arrays, the distance is the array distance. After all the array distances are calculated, calculate the average value of the array distances, and then introduce a correction coefficient to obtain the final portrait distance.

[0104] In addition, regarding the model distance, the model distance is a test architecture. Some test data are randomly determined, input into the mapping model, and after obtaining the output, comparison is carried out, the difference is calculated, and the average value of the differences corresponding to each test data is calculated to obtain the final model distance. Since the output of the mapping model is the change information of the body portrait and its data structure is the same as that of the body portrait, the calculation formula of the portrait distance can also be applied.

[0105] As a preferred embodiment of the technical solution of the present invention, the step of generating a prompt message according to the physical examination data and broadcasting it to users of the same type when receiving the physical examination data uploaded by any user includes:

[0106] Regularly send requests for obtaining physical examination data to users of various types;

[0107] When receiving the physical examination data uploaded by any user, transcode the physical examination data to obtain digital physical examination data;

[0108] Locate abnormal data in the digital physical examination data and insert a prompt box into the abnormal data;

[0109] Broadcast the digital physical examination data containing the prompt box to users of the same type.

[0110] In the original technical solution, the physical examination data is completely uploaded by users. In actual situations, users may not remember to upload the physical examination data after the physical examination. Therefore, this application regularly sends requests for obtaining physical examination data to users of various types to prompt users. When receiving the physical examination data uploaded by any user, transcode the physical examination data to obtain digital physical examination data. The purpose of this process is to unify the format of the physical examination data because the physical examination reports issued by different physical examination parties may be different, some are in the form of tables, some are paper reports, and some are directly digital reports. This application unifies all formats of physical examination data, and the unified physical examination data is called digital physical examination data.

[0111] Locate abnormal data in the digital physical examination data. The location process is to compare each index in the physical examination data with a preset range. If the physical examination data exceeds the threshold, it is considered abnormal data, and a prompt box is inserted into the abnormal data as a prompt message. Finally, broadcast the digital physical examination data containing the prompt box to users of the same type.

[0112] Figure 2 The structure diagram of the artificial intelligence big data intelligent health management system is shown. In a preferred embodiment of the technical solution of the present invention, an artificial intelligence big data intelligent health management system is also provided. The system 10 includes:

[0113] A body portrait construction module 11, configured to obtain the body parameters of a user based on an intelligent device and construct a body portrait of the user according to the body parameters;

[0114] The mapping model training module 12 is configured to obtain the behavior data of the user with a time span, obtain the change information of the body portrait according to the time span, and train the mapping model from the behavior data to the change information;

[0115] The user clustering module 13 is configured to compare the body portraits and the latest mapping models of different users at the latest moment, and cluster the users;

[0116] The physical examination data sharing module 14 is configured to, for any type of user, when receiving the physical examination data uploaded by any user, generate a prompt message according to the physical examination data and broadcast it to the users of the same type.

[0117] Furthermore, the body portrait construction module 11 includes:

[0118] The basic parameter acquisition unit is configured to acquire the basic parameters of the user based on the intelligent body fat scale;

[0119] The body model matching unit is configured to traverse and match the body model in the preset body model library according to the basic parameters;

[0120] The variable parameter determination unit is configured to acquire the variable parameters of the user in real time based on the intelligent wearable device, and determine the display parameters of the body model according to the variable parameters;

[0121] The display parameter application unit is configured to insert the display parameters into the body model to obtain the body portrait of the user.

[0122] The body model library includes:; The traversal and matching process is: different weights.

[0123] Specifically, the mapping model training module 12 includes:

[0124] The variable parameter identification unit is configured to acquire the variable parameters of the user in real time based on the intelligent wearable device, identify the variable parameters, and determine the behavior types of the user at each moment;

[0125] The behavior type merging unit is configured to merge the behavior types at each moment within a time period to obtain the behavior data of each time period;

[0126] The sample creation unit is configured to obtain the change information of the body portrait of each time period, and construct a sample with the behavior data of the same time period as the feature and the change information of the body portrait as the label;

[0127] The model training unit is configured to count a preset number of samples, construct a sample set, divide the sample set into a training set and a test set according to a preset ratio, and train the neural network model;

[0128] A model output unit, configured to output the neural network model as a mapping model of behavioral data to change information when the error rate of the neural network model is less than a preset error rate threshold.

[0129] Further, the user clustering module 13 includes:

[0130] A parameter acquisition unit, configured to acquire the body portraits and mapping models of each user at the current moment;

[0131] A user comparison unit, configured to compare the body portraits and mapping models of different users, and calculate the portrait distance and model distance;

[0132] A clustering execution unit, configured to cluster users according to the portrait distance and model distance.

[0133] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. An artificial intelligence big data intelligent health management method, characterized in that, The method includes: Obtaining the user's body parameters based on an intelligent device, and constructing a body portrait of the user according to the body parameters; Obtaining the user's behavior data with a time span, obtaining the change information of the body portrait according to the time span, and training a mapping model from the behavior data to the change information; Comparing the body portraits and the latest mapping models of different users at the latest moment, and clustering the users; For any category of users, when receiving the physical examination data uploaded by any user, generating a prompt message according to the physical examination data and broadcasting it to the users of the same category.

2. The artificial intelligence big data intelligent health management method according to claim 1, wherein, The step of obtaining the user's body parameters based on an intelligent device and constructing a body portrait of the user according to the body parameters includes: Obtaining the basic parameters of the user based on an intelligent body fat scale; Traversing and matching the body models in a preset body model library according to the basic parameters; Obtaining the changing parameters of the user in real time based on an intelligent wearable device, and determining the display parameters of the body model according to the changing parameters; Inserting the display parameters into the body model to obtain the user's body portrait; The changing parameters include heart rate, exercise amount, and blood oxygen saturation. The heart rate, exercise amount, and blood oxygen saturation are all converted to the range of 0 to 255, and are used as the H value, S value, and V value respectively to obtain the display parameters.

3. The artificial intelligence big data intelligent health management method according to claim 2, characterized in that The step of obtaining the user's behavior data with a time span, obtaining the change information of the body portrait according to the time span, and training a mapping model from the behavior data to the change information includes: Obtaining the changing parameters of the user in real time based on an intelligent wearable device, identifying the changing parameters, and determining the behavior types of the user at each moment; Within a time period, merging the behavior types at each moment to obtain the behavior data of each time period; Obtaining the change information of the body portrait of each time period, using the behavior data of the same time period as features, and the change information of the body portrait as labels to construct samples; Counting a preset number of samples, constructing a sample set, splitting the sample set into a training set and a test set according to a preset ratio, and training a neural network model; When the error rate of the neural network model is less than a preset error rate threshold, outputting the neural network model as a mapping model from the behavior data to the change information.

4. The artificial intelligence big data intelligent health management method according to claim 1, wherein, The step of comparing the body portraits and the latest mapping models of different users at the latest moment and clustering the users includes: Obtaining the body portraits and mapping models of each user at the current moment; Comparing the body portraits and mapping models of different users, and calculating the portrait distance and the model distance; Clustering the users according to the portrait distance and the model distance.

5. The artificial intelligence big data intelligent health management method according to claim 1, characterized in that The step of clustering the users according to the portrait distance and the model distance includes: For any two users, reading the body portraits of the two users, calibrating the origin points of the two body portraits, and calculating the portrait distance; Reading the mapping models of the two users, randomly determining a preset number of test data, inputting the test data into the two mapping models to obtain outputs, and calculating the model distance according to the outputs; Calculating the similarity of the users according to the portrait distance and the model distance, and applying the optics clustering algorithm to cluster the users; the similarity is inversely proportional to both the portrait distance and the model distance; Among them, the calculation process of the portrait distance is: Let d1 denote the image distance, and let N, M, and K respectively denote the dimensions of the space where the body model is located; let A(i, j, k) and B(i, j, k) respectively denote the parameters at point (i, j, k) of the two body models. Both A(i, j, k) and B(i, j, k) are arrays used to represent display parameters. When a certain body model has no display parameter at point (i, j, k), an array with all elements being zero is used as a substitute array; dis{A(i, j, k), B(i, j, k)} represents the array distance between the two arrays; and α is a preset adjustment coefficient.

6. The artificial intelligence big data intelligent health management method according to claim 5, wherein, For any type of user, when receiving the physical examination data uploaded by any user, the steps of generating a prompt message based on the physical examination data and broadcasting it to users of the same type include: Regularly send requests for obtaining physical examination data to various types of users; When receiving the physical examination data uploaded by any user, transcode the physical examination data to obtain digital physical examination data; Locate abnormal data in the digital physical examination data and insert a prompt box into the abnormal data; Broadcast the digital physical examination data containing the prompt box to users of the same type.

7. An artificial intelligence big data intelligent health management system, characterized in that, The system includes: A body portrait construction module for obtaining the user's body parameters based on an intelligent device and constructing the user's body portrait according to the body parameters; A mapping model training module for obtaining the user's behavior data with a time span, obtaining the change information of the body portrait according to the time span, and training the mapping model from the behavior data to the change information; A user clustering module for comparing the body portraits and the latest mapping models of different users and clustering the users; A physical examination data sharing module for, for any type of user, when receiving the physical examination data uploaded by any user, generating a prompt message based on the physical examination data and broadcasting it to users of the same type.

8. The artificial intelligence big data intelligent health management system according to claim 7, wherein, The body portrait construction module includes: A basic parameter acquisition unit for obtaining the user's basic parameters based on an intelligent body fat scale; A body model matching unit for traversing and matching the body model in a preset body model library according to the basic parameters; A variable parameter determination unit for obtaining the user's variable parameters in real time based on an intelligent wearable device and determining the display parameters of the body model according to the variable parameters; A display parameter application unit for inserting the display parameters into the body model to obtain the user's body portrait. The variable parameters include heart rate, exercise amount, and blood oxygen saturation, and the heart rate, exercise amount, and blood oxygen saturation are all converted to the range of 0 to 255, and are used as the H value, S value, and V value respectively to obtain the display parameters.

9. The artificial intelligence big data intelligent health management system according to claim 8, characterized in that The mapping model training module includes: A variable parameter identification unit for obtaining the user's variable parameters in real time based on an intelligent wearable device, identifying the variable parameters, and determining the behavior types of the user at each moment; A behavior type merging unit for merging the behavior types at each moment within a time period to obtain the behavior data of each time period; A sample creation unit for obtaining the change information of the body portrait of each time period, using the behavior data of the same time period as features, and the change information of the body portrait as labels to construct samples; A model training unit for counting a preset number of samples, constructing a sample set, splitting the sample set into a training set and a test set according to a preset ratio, and training a neural network model; A model output unit for outputting the neural network model as the mapping model from the behavior data to the change information when the error rate of the neural network model is less than a preset error rate threshold.

10. The artificial intelligence big data intelligent health management system according to claim 9, wherein The user clustering module includes: A parameter acquisition unit for obtaining the body portraits and mapping models of each user at the current moment; A user comparison unit for comparing the body portraits and mapping models of different users and calculating the portrait distance and model distance; A clustering execution unit, configured to cluster users according to the portrait distance and the model distance.

Images