CN110580941A - information processing method and device, electronic device and storage medium - Google Patents
information processing method and device, electronic device and storage medium Download PDFInfo
- Publication number
- CN110580941A CN110580941A CN201810582466.5A CN201810582466A CN110580941A CN 110580941 A CN110580941 A CN 110580941A CN 201810582466 A CN201810582466 A CN 201810582466A CN 110580941 A CN110580941 A CN 110580941A
- Authority
- CN
- China
- Prior art keywords
- data
- health
- prediction
- health prediction
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Abstract
The embodiment of the invention provides an information processing method and device, electronic equipment and a storage medium. The information processing method comprises the following steps: receiving physical sign data provided by terminal equipment; acquiring a visual avatar model by utilizing the physical sign data; receiving health data provided by the terminal equipment; and predicting health prediction data of the target user according to the health data, wherein the health prediction data is used for presenting health prediction results on the visual avatar model.
Description
Technical Field
The present invention relates to the field of information technologies, and in particular, to an information processing method and apparatus, an electronic device, and a storage medium.
background
at present, with the development of information technology, various artificial intelligence can be used for health prediction, but in the prior art, if the artificial intelligence device completes health prediction, a prediction report or a direct prediction result is generated and sent to a common user, and the prediction report or the prediction result is too professional for the common user to read and understand, and on the other hand, the prediction report is sent to the common user in a prediction report mode, so that readability is poor. In summary, the prior art human intelligence provides a health prediction report that is too obscure or difficult.
Disclosure of Invention
In view of the above, embodiments of the present invention are directed to an information processing method and apparatus, an electronic device, and a storage medium, which at least partially solve the above problems.
The technical scheme of the invention is realized as follows:
In a first aspect, an embodiment of the present invention provides an information processing method, including:
Receiving physical sign data provided by terminal equipment;
Acquiring a visual avatar model by utilizing the physical sign data;
receiving health data provided by the terminal equipment;
and predicting health prediction data of the target user according to the health data, wherein the health prediction data is used for presenting health prediction results on the visual avatar model.
Optionally, the obtaining a visual avatar model using the vital sign data includes:
and performing three-dimensional 3D modeling by using the sign information to obtain the visual avatar model.
optionally, the health data comprises at least one of:
dietary data;
living condition data;
sign data;
Physiological data.
optionally, the predicting health prediction data of the target user according to the health data includes:
carrying out data preprocessing on the health data to obtain characteristic data;
And obtaining the health prediction data according to the characteristic data.
optionally, the obtaining the health prediction data according to the feature data includes:
inputting the characteristic data into a health prediction model to obtain the health prediction data.
Optionally, the data preprocessing is performed on the health data to obtain feature data, and the feature data includes at least one of:
filtering the health data, and removing irrelevant interference data and/or abnormal data of health prediction;
classifying the health data according to preset dimensionality to obtain a crowd classification of a user target;
performing feature extraction on the health data according to the crowd classification;
the inputting the feature data into a health prediction model to obtain the health prediction data comprises:
And inputting the characteristic data into a corresponding health prediction model according to the crowd classification, and obtaining the health prediction data output by the health prediction model.
in a second aspect, an embodiment of the present invention provides an information processing method, including:
Sending the physical sign data of the target user to a cloud server;
Sending the health data of the target user to the cloud server;
Receiving a visual body model returned by the cloud server based on the sign data;
receiving health prediction data returned by the cloud server based on the health data;
Displaying the visualized body model and presenting a health prediction result on the visualized body model according to the health prediction data.
Optionally, the health data comprises at least one of:
dietary data;
Living condition data;
sign data;
Physiological data.
In a third aspect, an embodiment of the present invention provides an information processing apparatus, including:
the first receiving module is used for receiving the physical sign data provided by the terminal equipment;
The first acquisition module is used for acquiring the visual avatar model by utilizing the physical sign data;
The second receiving module is used for receiving the health data provided by the terminal equipment;
And the prediction module is used for predicting health prediction data of the target user according to the health data, wherein the health prediction data is used for presenting a health prediction result on the visual avatar model.
In a fourth aspect, an embodiment of the present invention provides an information processing apparatus, including:
The first sending module is used for sending the physical sign data of the target user to the cloud server;
the second sending module is used for sending the health data of the target user to the cloud server;
the third receiving module is used for receiving the visual body model returned by the cloud server based on the sign data;
the fourth receiving module is used for receiving health prediction data returned by the cloud server based on the health data;
and the display module is used for displaying the visual body model and presenting a health prediction result on the visual body model according to the health prediction data.
in a fifth aspect, an embodiment of the present invention provides an electronic device, including:
a transceiver;
A memory;
and a processor, connected to the transceiver and the memory, respectively, for controlling the information transmission and reception of the transceiver and the information storage of the memory by executing the executable instructions stored in the memory, and implementing the information processing method according to any one of the claims of the first aspect or the second aspect.
in a sixth aspect, an embodiment of the present invention provides a computer storage medium, where the computer storage medium stores computer executable code; the computer executable code is capable of implementing the information processing method provided by any one of the claims of the first aspect or the second aspect when executed.
The information processing method and device, the electronic device and the storage medium provided by the embodiment of the invention can receive the physical sign data and the health data from the terminal device, obtain the visual body model through simulation and other modes according to the physical sign data, and obtain the health prediction data by using the health data; therefore, after the terminal equipment receives the visual avatar model and the health prediction data, the health prediction result corresponding to the health prediction data is displayed on the visual avatar model, so that the terminal equipment has the characteristics of intuition and clarity, the problems of difficult understanding and the like caused by the health prediction report in the form of text and/or table directly provided in the prior art are solved, and the user experience is improved.
drawings
fig. 1 is a schematic flowchart of a first information processing method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a second information processing method according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a first information processing apparatus according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating a second information processing apparatus according to an embodiment of the present invention;
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
Fig. 6 is a flowchart illustrating a third information processing method according to an embodiment of the present invention.
Detailed Description
the technical solution of the present invention is further described in detail with reference to the drawings and the specific embodiments of the specification.
As shown in fig. 1, the present embodiment provides an information processing method including:
step S110: receiving physical sign data provided by terminal equipment;
Step S120: acquiring a visual avatar model by utilizing the physical sign data;
step S130: receiving health data provided by the terminal equipment;
step S140: and predicting health prediction data of the target user according to the health data, wherein the health prediction data is used for presenting health prediction results on the visual avatar model.
The visual prediction method provided by the embodiment can be a method applied to a cloud server. In some embodiments, the method further comprises: and sending the visual avatar model and the health prediction data to a terminal device, wherein the terminal device can be a user terminal requesting health prediction.
the terminal equipment can be various types of terminal equipment such as mobile phones, tablet computers, health equipment, wearable equipment, cooking equipment and household appliances. The terminal device in the embodiment of the present invention may include: one or more than one. The terminal device may include: various intelligent household devices such as electric cookers, electric pressure cookers, automatic cooking machines, refrigerators, washing machines, water heaters and the like.
In step S110, the cloud end server receives sign data from the terminal device, where the sign data may be image data of a target user.
The physical sign data may be various data representing the physical condition of the target user, for example, data representing the physical form of the target user, data representing the appearance form of skin color, hair volume, and the like of the target user. In other embodiments, the vital sign data may further include: morphology of the target user's internal organs, etc. For example, various forms such as the size and color of internal organs of the body are also associated with the appearance of the target user.
In step S120, a visual body model is obtained according to the feature data, for example, a visual body model of the user is simulated by three-dimensional modeling, and the visual body model may include: a 3D body model.
In the embodiment of the invention, the cloud server also receives health data from the terminal equipment. The health data in embodiments of the present invention may be a variety of data that is capable of describing and/or characterizing the current health status of the target user.
For example, the health data includes at least one of:
Dietary data;
Living condition data;
Sign data;
physiological data.
different eating habits and/or eating preferences may have an impact on the health of the user, so in this embodiment, the health data comprises diet data of the target user.
The dietary data may include:
the name of the diet, the variety of the diet, the time of the diet, and the like of the target user in the recent period of time.
in some embodiments, the dietary data may further include:
Nutritional formula data, recipe data/recipe data, etc. of the diet of the target user.
the living condition data reflects the work and rest conditions of the user, such as work, life and entertainment, which also affect the health condition of the target user.
the characteristic data can comprise: appearance feature data of the user, and the like, for example, various data of the user's height, weight, skin color, and the like.
the physiological data may be various data other than the vital sign data, such as vital sign data collected by various physiological sensors, and various data such as a heartbeat value and a blood pressure value per unit time. In some embodiments, the physiological data further comprises: biometric data.
In general, the health data may be various types of data that characterize the current health state of the target user.
in the present embodiment, health prediction is performed based on the health data, and health prediction data is obtained. In this embodiment, the health prediction data may be presented on a visual health prediction model; and no longer in the form of a health prediction report. For example, in some embodiments, if some problem with the heart of the target user is detected, the health prediction of the heart is displayed next to the heart of the visual health prediction model, which facilitates the user to easily and intuitively see the current health prediction status.
In some embodiments, the method further comprises:
Converting the health prediction information into spoken health prediction information, for example, converting medical specific terms in the health prediction information into equivalent spoken health prediction information, and displaying the same on the periphery of the corresponding organ displayed by the visual body model. For example, a conversion mapping table is stored in the cloud server, and the medical special terms which are difficult to understand can be converted into the equivalent spoken health prediction information by inquiring the conversion mapping table.
in this way, if the cloud server sends the visual health prediction model and the health prediction information to the terminal device for display, only the spoken health prediction information may be sent. In other embodiments, the cloud server can simultaneously send the health prediction information before conversion and the health prediction information after conversion to the terminal device, so that the terminal device can meet different viewing requirements conveniently.
in still other embodiments, the method further comprises:
And according to the health prediction information, adjusting the color and/or morphological information of the corresponding part in the visual avatar model, and representing the health condition of the current corresponding organ or body part by visualizing the healthy body model.
optionally, the step S120 may include:
And performing three-dimensional (3D) modeling by using the physical sign information to obtain the visual avatar model.
In this embodiment, the visual body model is obtained by means of 3D modeling, and the visual body model may be sent to the terminal device, so that the terminal device may simulate the body model of the target user.
In this embodiment, the physical sign data may be image information such as a photograph of the target user, but is not limited to the image information.
Optionally, the step S130 may include:
carrying out data preprocessing on the health data to obtain characteristic data;
and obtaining the health prediction data according to the characteristic data.
In this embodiment, before the health prediction is performed, data preprocessing of the health data is performed, for example, data preprocessing is performed through data filtering, clustering, and the like; and extracting characteristic data representing the physical health state of the current user by extracting the characteristics of the preprocessed data. Health prediction data is obtained from the characteristic data.
optionally, the obtaining the health prediction data according to the feature data includes:
Inputting the characteristic data into a health prediction model to obtain the health prediction data.
The health prediction model can be various big data models, for example, various health prediction models with health prediction function obtained by training sample data, such as machine learning model, neural network model, binary tree model, multi-branch tree model, linear regression model, etc.
optionally, the data preprocessing is performed on the health data to obtain feature data, and the feature data includes at least one of:
filtering the health data, and removing irrelevant interference data and/or abnormal data of health prediction;
classifying the health data according to preset dimensionality to obtain a crowd classification of a user target;
performing feature extraction on the health data according to the crowd classification;
The obtaining the health prediction data from the feature data comprises:
And inputting the characteristic data into a corresponding health prediction model according to the crowd classification, and obtaining the health prediction data output by the health prediction model.
In this embodiment, the cloud server first filters the interference data and/or the abnormal data in the health data, for example, the heartbeat value is 300, which is obviously an abnormal heartbeat value and can be filtered out as the abnormal data. In some embodiments, as the error of information transmission and collection is introduced into other interference data, for example, data conflicting with an actual measurement value is introduced, the data needs to be filtered according to a preset filtering rule, and interference of the interference data and/or abnormal data on health prediction is reduced by removing the interference data and/or abnormal data, so that the accuracy of health prediction is improved.
In this embodiment, the health data may be classified according to preset dimensions, for example, the classification of the population based on dietary habits is performed according to the dietary habits, and the category of the population where the target user is located is determined. For example, the crowd classification is performed based on the sign similarity, and the crowd category of the target user is determined. And proportionally classifying the crowd according to living modes such as living conditions and the like to determine the crowd category of the target user.
and processing the characteristic data by using a health prediction model corresponding to the crowd classification of the target user according to the crowd classification to obtain health prediction data of the target user, so that accurate prediction of the health of the target user is realized.
when people are classified, people can be classified based on a clustering algorithm, and the clustering here can include: various types of clustering algorithms are available, such as k-means clustering, grid-based clustering, density-based clustering or hierarchical clustering, and the like, and the specific examples are not given here.
as shown in fig. 2, the present embodiment provides an information processing method, including:
step S210: sending the physical sign data of the target user to a cloud server;
Step S220: sending the health data of the target user to the cloud server;
Step S230: receiving a visual body model returned by the cloud server based on the sign data;
step S240: receiving health prediction data returned by the cloud server based on the health data;
step S250: displaying the visualized body model and presenting a health prediction result on the visualized body model according to the health prediction data.
the terminal device in this embodiment can be various terminal devices held by the user, and send the physical sign data and the health data to the cloud server, and the cloud server performs health prediction. In the embodiment of the invention, the terminal equipment not only receives the health prediction data, but also receives the visual avatar model, displays the visual avatar model after receiving the visual avatar model and the health prediction data, and presents the health prediction result on the visual avatar model according to the received health prediction data.
optionally, the health data comprises at least one of: dietary data; living condition data; sign data; physiological data.
The detailed descriptions of the dietary data, daily life data, physical signs data, and physiological data can be found in the previous examples and will not be repeated here.
As shown in fig. 3, the present embodiment provides an information processing apparatus, which can be applied in a cloud server, including:
A first receiving module 110, configured to receive sign data provided by a terminal device;
A first obtaining module 120, configured to obtain a visual avatar model using the physical sign data;
A second receiving module 130, configured to receive health data provided by the terminal device;
A prediction module 140 configured to predict health prediction data of the target user according to the health data, wherein the health prediction data is used to present a health prediction result on the visual avatar model.
The first receiving module 110, the first obtaining module 120, the second receiving module 130, and the predicting module 140 may be program modules, and the program modules may be executed by a processor, so as to receive physical sign data and health data, and perform operations such as forming a visual avatar model and generating health predicting data.
optionally, the first obtaining module 120 is specifically configured to perform three-dimensional 3D modeling by using the sign information to obtain the visual avatar model.
in some embodiments, the health data includes at least one of: dietary data; living condition data; sign data; physiological data.
optionally, the prediction module 140 includes:
The preprocessing submodule is used for preprocessing the health data to obtain characteristic data;
and the prediction submodule is used for obtaining the health prediction data according to the characteristic data.
In still other embodiments, the prediction module 140 is specifically configured to input the feature data into a health prediction model to obtain the health prediction data.
the preprocessing submodule is specifically configured to execute at least one of: filtering the health data, and removing irrelevant interference data and/or abnormal data of health prediction; classifying the health data according to preset dimensionality to obtain a crowd classification of a user target; and according to the crowd classification, carrying out feature extraction on the health data.
The prediction submodule is specifically configured to input the feature data into a corresponding health prediction model according to the crowd classification and obtain the health prediction data output by the health prediction model.
As shown in fig. 4, the present embodiment provides an information processing apparatus including:
the first sending module 210 is configured to send the physical sign data of the target user to the cloud server;
A second sending module 220, configured to send the health data of the target user to the cloud server;
a third receiving module 230, configured to receive a visual body model returned by the cloud server based on the sign data;
a fourth receiving module 240, configured to receive health prediction data returned by the cloud server based on the health data;
A display module 250 configured to display the visualized body model and present a health prediction result on the visualized body model according to the health prediction data.
the information processing apparatus is applicable to a terminal device.
the first sending module 210, the second sending module 220, the third receiving module 230, the fourth receiving module 240 and the display module 250 may be program modules, and the processor may implement operations of one or more of the modules by executing the program modules, for example, interacting sign data, health data, visual avatar model and health prediction data with the cloud server.
the execution hardware of the display module 250 can be a display screen and the like, can display the visual body model, and presents the health prediction result on the visual body model according to the health prediction data, so that the health prediction result is presented, the display module has the characteristics of intuition, clearness and the like, various difficulties of the target user in viewing the health prediction report are reduced, and the user experience is improved.
Optionally, the health data comprises at least one of: dietary data; living condition data; sign data; physiological data.
as shown in fig. 5, the present embodiment further provides an electronic device, including:
a transceiver;
A memory;
And the processor is respectively connected with the transceiver and the memory, controls the information transceiving of the transceiver and the information storage of the memory by executing the executable instructions stored in the memory, and realizes the information processing method applied to the cloud server and/or the terminal equipment.
the transceiver may correspond to a communication interface, and may be used for information interaction between different electronic devices.
the memory may include: a storage medium that can be used for information storage.
The processor may be a central processing unit, a microprocessor, a digital signal processor, an application processor, a programmable array, or the like, may be connected to the transceiver and the memory through an integrated circuit bus (IIC), or the like, and may be configured to execute codes through a computer program or the like, control the operation of the transceiver and the memory, and implement the information processing method provided by one or more of the foregoing technical solutions.
In some embodiments, the electronic device may further include: a communication interface, which may include: a network interface, e.g., a local area network interface, a transceiver antenna, etc. The communication interface is also connected with the processor and can be used for information transceiving.
In some embodiments, the electronic device also includes a human interaction interface, which may include various input and output devices, such as a keyboard, a touch screen, and the like, for example.
if the electronic device is the cloud server, the electronic device may execute one or more of the information processing methods in the cloud server.
If the electronic device is the terminal device, the electronic device may execute one or more of the information processing methods in the terminal device.
the embodiment of the invention also provides a computer storage medium, wherein the computer storage medium stores computer executable codes; after being executed, the computer executable code can realize the information processing method applied to the cloud server and/or the terminal equipment.
optionally, the computer storage medium comprises: various media capable of storing program codes, such as a removable storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk; alternatively, the computer storage medium may be a non-transitory storage medium.
Several specific examples are provided below in connection with any of the embodiments described above:
Example 1:
the example provides a 3D reconstruction visualization health prediction system based on big data, the prediction result can be displayed in a 3D form while the future health prediction report can be predicted, the health trend report and model biological feature display of a future user can be simulated through data input of a 3D model, and the system is more visual, clear, rapid to edit and vivid and interesting.
the component 1 is used for acquiring data, and can be used for acquiring data through product integrated equipment, Application programs (apps) of mobile terminals, data mined from various large malls, and terminal software integrated with 3D model reconstruction and provided by the system scheme. Through the methods, the data of the human nutrition formula, the data of the human diet/menu, the data of the daily life of the human, the data of the motion state of the human, the data of the current physical signs of the human and other biological characteristics are obtained.
the component 2 is used for shooting images of different angles of the body of the user, the image data are uploaded through the terminal, the server can rebuild the 3D model according to the materials, the 3D model (visible avatar model) of the body of the user is simulated, and the visual presentation is carried out on the component 8 (terminal display).
The component 3 can be a big data processing center, is integrated with a classification algorithm, a clustering algorithm, a filtering algorithm and the like, classifies users according to crowd and physical sign similarity, classifies according to living systems, dietary preferences and other modes, extracts features and stores the features.
the component 4 can be a health prediction model such as a model based on a deep neural network algorithm, inputs health data processed by big data, and outputs a crowd classification health model.
Component 7 is a simulated model presentation of nutritional health predictions and data, such as: and the skin color change and the health index of the user in the next day are estimated according to the diet, the exercise amount and the sleep quality of the current user and are expressed through the 3D model image. And pushed to the component 8 (terminal display).
the clustering algorithm is exemplified below.
sample data acquisition requirements, for example: each user who thinks himself is good: counting data such as normal diet daily life, walking number, recent diet condition (whether a certain type of food is preferred or not), current physical sign condition and the like; thus forming positive sample data of model training; the same principle is that: and collecting data with the same attribute of the user with poor physical condition, thus forming negative sample data of model training. The sample data needs to be sufficiently large, for example 5000 thousand samples may be taken as an example.
Body well can be represented by data for the positive half axis, e.g., 1, body difference can be represented by data for the negative half axis; the same principle is that: the data statistics can be better classified in a positive and negative semi-axis mode according to the preference of certain food and the like.
in some cases, a clustering algorithm may be used to obtain the centroid (reference standard of data) of the data, and when actual user data enters, the distance between the center point of the actual user data in the multidimensional space and the centroid of each cluster may be used to determine the category to which the user belongs. One point represents one sample in this example and corresponds to one user.
the mass center is a process of continuous adjustment, and points (data) close to the mass center are divided into the same category; through iteration, a new centroid point is calculated, and the data of the distance is divided into the same category, and so on.
Clustering samples into k clusters (cluster), wherein k is given by a user, the solving process is very intuitive and simple, and the specific algorithm is described as follows:
randomly selecting k clustering centroid points, and giving a clustering number in advance;
the centroid is initially randomly given an initial value
2) the following process is repeated until convergence for each sample i, the class to which it should belong is calculated (by determining the respective distance of each point from a given centroid, those c that are the smallest in distance(i)the same class is classified),
for each class j, the centroid of the class is recalculated:
Convergence, distortion function is as follows:
judging whether the value of J (c, u) tends to a stable value after the mass center is readjusted, and judging the reference standard and the judgment reference of the mass center adjustment: the J (c, u) function represents the sum of the squares of the distances of each sample point to its centroid, and the algorithm is to adjust J (c, u) to a minimum. Assuming that the current J (c, u) does not reach a minimum, then the centroid μ for each class can be fixed firstjAdjust the class C to which each sample belongs(i)to let the J (C, u) function decrease, and likewise, to fix C(i)Adjusting the centroid μ of each classjj may also be reduced. These two processes are the processes of monotonically decreasing J in the inner loop. When J is decremented to a minimum, u and c also converge simultaneously.
Description of parameters and distance of application: wherein: argmin represents when the objective function takes the minimum value, C(i)representing convergence values, data convergence in a data range, C(i)representing the class of sample i that is closest to the K classes, the hidden variable, i.e., the best class.
Represents the mean of the ith sample.
x(i)sample data input value representing the ith sample, training sample { x }(1),...,x(i)each x(i)are all in a broad collection.
μjRepresenting the centroid of class j, representing a guess of the center point of the sample belonging to the same class, e.g. all users with similar preferences grouped into k data clusters (class k), first randomly choosing kpoints in the cliques are used as centroids of k cliques, then the distance from each point to the k centroids is calculated in the first step, and then the category with the closest distance is selected as the centroid; second step for each cluster, recalculate its centroid μj(average the parameter coordinates of all the classes inside), and repeat the first step and the second step until the centroid is unchanged or slightly changed.
Its pseudo code is as follows:
K points are created as initial centroid points (randomly selected).
And when the cluster distribution result of any one point changes, calculating the distance between the centroid and the data point for each centroid of each data point in the data set, distributing the data point to each cluster of the closest cluster pair, calculating the average value of all the points in the clusters, and taking the average value as the centroid.
The component 5 is used for calculating and pushing 3D model data to a client side through a cloud side, and the client side displays OpenGl to display a 3D model file; therefore, the pressure of a large amount of operations of the client is reduced, and the 3D model can be flexibly, quickly and smoothly displayed. In addition, the user can input health-related data into the model input interface through customization, and then the health prediction result is obtained.
The following provides a neural network training method to obtain a neural network model with a health prediction function.
network initialization:
The weight value is initialized by using a smaller random value, and the input vector and the weight value are normalized
X’＝X/||X||
ω’i＝ωi/||ωi||，
Wherein:
the value range is 1 ═ i ═ m;
the euclidean norm of the sample vector input by | X |;
the euclidean norm of the | ω i | weight vector.
Input of samples into the network: and (2) performing dot product on the samples and the weight vectors, and recording the competition won by the output neuron with the maximum dot product value (or calculating the Euclidean distance between the samples and the weight vectors and the competition won by the neuron with the minimum distance) as the winning neuron, thereby realizing the initialization of the neural network. Updating the weight:
and updating the neurons in the topological neighborhood of the winning neuron, and normalizing the learned weight again.
The neural network may be represented by the function ω (t +1) ═ ω (t) + η (t, n) × (x- ω (t)), where: the learning rate is a functional representation with respect to the training time t and the topological distance n from the winning neuron:
η(t，n):η
η(t，n)＝η(t)*e^(-n)
And updating the learning rate eta and the topological neighborhood N, wherein the distance is reduced as the time is increased.
and judging whether convergence occurs or not, and if the learning rate eta is less than eta min or reaches the preset iteration times, ending the algorithm.
Example 2
as shown in fig. 6, the present example provides a visual health prediction method, comprising:
step 1: acquiring crowd nutrition formula data, crowd recipe/menu data, crowd living condition data, crowd motion state data, crowd current physical sign data and other biological characteristic data;
step 2: the big data processing center carries out classification, clustering, filtering and other processing;
And step 3: training a data interface model to obtain a health prediction model;
And 4, step 4: human body 3D model reconstruction;
and 5: acquiring human body sign scanning data and user identity data (such as an identification number, a passport number or a name and the like);
step 6: a crowd classification health data model;
and 7: health prediction and 3D display;
and 8: the terminal displays, for example, a visual body model obtained by 3D modeling, and displays the health prediction result on the visual body model.
in the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
in addition, all the functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may be separately used as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments.
the above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (12)
1. An information processing method characterized by comprising:
Receiving physical sign data provided by terminal equipment;
Acquiring a visual avatar model by utilizing the physical sign data;
receiving health data provided by the terminal equipment;
And predicting health prediction data of the target user according to the health data, wherein the health prediction data is used for presenting health prediction results on the visual avatar model.
2. The method of claim 1,
the acquiring of the visual avatar model by using the physical sign data comprises:
And performing three-dimensional 3D modeling by using the sign information to obtain the visual avatar model.
3. The method according to claim 1 or 2,
the health data includes at least one of:
dietary data;
living condition data;
Sign data;
Physiological data.
4. The method according to claim 1 or 2,
the predicting health prediction data of the target user according to the health data comprises:
Carrying out data preprocessing on the health data to obtain characteristic data;
and obtaining the health prediction data according to the characteristic data.
5. the method of claim 4,
the obtaining the health prediction data from the feature data comprises:
inputting the characteristic data into a health prediction model to obtain the health prediction data.
6. The method of claim 5,
The health data is subjected to data preprocessing to obtain characteristic data, wherein the characteristic data comprises at least one of the following data:
filtering the health data, and removing irrelevant interference data and/or abnormal data of health prediction;
Classifying the health data according to preset dimensionality to obtain a crowd classification of a user target;
Performing feature extraction on the health data according to the crowd classification;
The inputting the feature data into a health prediction model to obtain the health prediction data comprises:
And inputting the characteristic data into a corresponding health prediction model according to the crowd classification, and obtaining the health prediction data output by the health prediction model.
7. an information processing method characterized by comprising:
Sending the physical sign data of the target user to a cloud server;
Sending the health data of the target user to the cloud server;
Receiving a visual body model returned by the cloud server based on the sign data;
receiving health prediction data returned by the cloud server based on the health data;
Displaying the visualized body model and presenting a health prediction result on the visualized body model according to the health prediction data.
8. the method of claim 7,
the health data includes at least one of:
Dietary data;
Living condition data;
Sign data;
Physiological data.
9. an information processing apparatus characterized by comprising:
The first receiving module is used for receiving the physical sign data provided by the terminal equipment;
The first acquisition module is used for acquiring the visual avatar model by utilizing the physical sign data;
the second receiving module is used for receiving the health data provided by the terminal equipment;
and the prediction module is used for predicting health prediction data of the target user according to the health data, wherein the health prediction data is used for presenting a health prediction result on the visual avatar model.
10. an information processing apparatus characterized by comprising:
The first sending module is used for sending the physical sign data of the target user to the cloud server;
the second sending module is used for sending the health data of the target user to the cloud server;
The third receiving module is used for receiving the visual body model returned by the cloud server based on the sign data;
The fourth receiving module is used for receiving health prediction data returned by the cloud server based on the health data;
and the display module is used for displaying the visual body model and presenting a health prediction result on the visual body model according to the health prediction data.
11. an electronic device, comprising:
a transceiver;
a memory;
And the processor is respectively connected with the transceiver and the memory, controls the information transmission and reception of the transceiver and the information storage of the memory by executing the executable instructions stored in the memory, and realizes the information processing method provided by any one of claims 1 to 6 or 7 to 8.
12. A computer storage medium having computer executable code stored thereon; the computer executable code, when executed, is capable of implementing the information processing method as provided in any one of claims 1 to 6 or 7 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810582466.5A CN110580941A (en) | 2018-06-07 | 2018-06-07 | information processing method and device, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810582466.5A CN110580941A (en) | 2018-06-07 | 2018-06-07 | information processing method and device, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110580941A true CN110580941A (en) | 2019-12-17 |
Family
ID=68810132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810582466.5A Pending CN110580941A (en) | 2018-06-07 | 2018-06-07 | information processing method and device, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110580941A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192686A (en) * | 2020-03-20 | 2020-05-22 | 京东方科技集团股份有限公司 | Human body three-dimensional model prediction method, device, equipment and storage medium |
| CN111627557A (en) * | 2020-05-26 | 2020-09-04 | 闻泰通讯股份有限公司 | Health condition feedback method, device, equipment and storage medium |
| CN114564264A (en) * | 2022-02-22 | 2022-05-31 | 国人康乐医学研究院(北京)有限公司 | Data analysis method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599106A (en) * | 2008-06-05 | 2009-12-09 | 英业达股份有限公司 | Health data image display system and method |
| US20130325493A1 (en) * | 2012-05-29 | 2013-12-05 | Medical Avatar Llc | System and method for managing past, present, and future states of health using personalized 3-d anatomical models |
| CN104857692A (en) * | 2015-05-25 | 2015-08-26 | 惠州Tcl移动通信有限公司 | User motion state processing method and system and mobile device |
| US20160180024A1 (en) * | 2014-12-22 | 2016-06-23 | Durgada V BASAVARAJ | System and method for personalizing a three-dimensiional medical/health record |
| CN106250685A (en) * | 2016-07-26 | 2016-12-21 | 广东小天才科技有限公司 | A kind of method and device showing user health parameter |
| CN107506602A (en) * | 2017-09-07 | 2017-12-22 | 北京海融兴通信息安全技术有限公司 | A kind of big data health forecast system |
| CN107680167A (en) * | 2017-09-08 | 2018-02-09 | 郭睿 | A kind of three-dimensional (3 D) manikin creation method and system based on user image |
-
2018
- 2018-06-07 CN CN201810582466.5A patent/CN110580941A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599106A (en) * | 2008-06-05 | 2009-12-09 | 英业达股份有限公司 | Health data image display system and method |
| US20130325493A1 (en) * | 2012-05-29 | 2013-12-05 | Medical Avatar Llc | System and method for managing past, present, and future states of health using personalized 3-d anatomical models |
| US20160180024A1 (en) * | 2014-12-22 | 2016-06-23 | Durgada V BASAVARAJ | System and method for personalizing a three-dimensiional medical/health record |
| CN104857692A (en) * | 2015-05-25 | 2015-08-26 | 惠州Tcl移动通信有限公司 | User motion state processing method and system and mobile device |
| CN106250685A (en) * | 2016-07-26 | 2016-12-21 | 广东小天才科技有限公司 | A kind of method and device showing user health parameter |
| CN107506602A (en) * | 2017-09-07 | 2017-12-22 | 北京海融兴通信息安全技术有限公司 | A kind of big data health forecast system |
| CN107680167A (en) * | 2017-09-08 | 2018-02-09 | 郭睿 | A kind of three-dimensional (3 D) manikin creation method and system based on user image |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192686A (en) * | 2020-03-20 | 2020-05-22 | 京东方科技集团股份有限公司 | Human body three-dimensional model prediction method, device, equipment and storage medium |
| CN111192686B (en) * | 2020-03-20 | 2024-03-05 | 京东方科技集团股份有限公司 | Human body three-dimensional model prediction method, device, equipment and storage medium |
| CN111627557A (en) * | 2020-05-26 | 2020-09-04 | 闻泰通讯股份有限公司 | Health condition feedback method, device, equipment and storage medium |
| CN114564264A (en) * | 2022-02-22 | 2022-05-31 | 国人康乐医学研究院(北京)有限公司 | Data analysis method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109117864B (en) | Coronary heart disease risk prediction method, model and system based on heterogeneous feature fusion | |
| CN114514562B (en) | Predictive personalized three-dimensional body model | |
| CN109147890B (en) | Method and equipment for generating medical report | |
| US9734426B2 (en) | Automated food recognition and nutritional estimation with a personal mobile electronic device | |
| US10803315B2 (en) | Electronic device and method for processing information associated with food | |
| CN109146856A (en) | Picture quality assessment method, device, computer equipment and storage medium | |
| CN110580941A (en) | information processing method and device, electronic device and storage medium | |
| EP3647992A1 (en) | Face image processing method and apparatus, storage medium, and electronic device | |
| US20210319585A1 (en) | Method and system for gaze estimation | |
| CN110349147A (en) | Training method, the lesion recognition methods of fundus flavimaculatus area, device and the equipment of model | |
| CN111582342B (en) | Image identification method, device, equipment and readable storage medium | |
| CN110100253A (en) | Electronic equipment and its operating method | |
| CN112365423A (en) | Image data enhancement method, device, medium and equipment | |
| Qi et al. | Learning complex spatio-temporal configurations of body joints for online activity recognition | |
| CN116311539B (en) | Sleep motion capturing method, device, equipment and storage medium based on millimeter waves | |
| CN109215131A (en) | The driving method and device of conjecture face | |
| CN114612960A (en) | Method and device for traditional Chinese medicine health management through facial image | |
| CN109726713B (en) | User region-of-interest detection system and method based on consumption-level sight tracker | |
| CN116226655A (en) | Smart home environment sensing method and device, storage medium and electronic equipment | |
| CN114203300A (en) | Health state evaluation method and system, server and storage medium | |
| CN110473176A (en) | Image processing method and device, method for processing fundus images, electronic equipment | |
| CN112906730B (en) | Information processing method, device and computer readable storage medium | |
| CN114842972A (en) | Method, device, electronic equipment and medium for determining user state | |
| Ding et al. | Segmentation algorithm of medical exercise rehabilitation image based on HFCNN and IoT | |
| KR102351169B1 (en) | Big data and AI-based color recognition measurement platform and method using the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |