CN114649096A - Body type data determination method, device, equipment, storage medium and product - Google Patents
Body type data determination method, device, equipment, storage medium and product Download PDFInfo
- Publication number
- CN114649096A CN114649096A CN202011499160.7A CN202011499160A CN114649096A CN 114649096 A CN114649096 A CN 114649096A CN 202011499160 A CN202011499160 A CN 202011499160A CN 114649096 A CN114649096 A CN 114649096A
- Authority
- CN
- China
- Prior art keywords
- user
- body type
- daily
- type data
- whole
- 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
Images
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
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1079—Measuring physical dimensions, e.g. size of the entire body or parts thereof using optical or photographic means
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1118—Determining activity level
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- Data Mining & Analysis (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- General Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Dentistry (AREA)
- Epidemiology (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Cardiology (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Geometry (AREA)
- Physical Education & Sports Medicine (AREA)
- Computer Graphics (AREA)
- Pulmonology (AREA)
- Databases & Information Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the invention provides a body type data determining method, a body type data determining device, body type data determining equipment, a body type data determining storage medium and a body type data determining product, wherein the method comprises the following steps: receiving a body type prediction request triggered by a user; acquiring current body type data, daily caloric intake and daily energy consumption of a user according to the body type prediction request; inputting and training current body type data, daily caloric intake and daily energy consumption of a user into a converged bidirectional cyclic neural network model to determine predicted body type data; and outputting the predicted body type data. According to the body type data determining method provided by the embodiment of the invention, the user can obtain the comparison condition between the current body type data and the predicted body type data by adopting the bidirectional circulation neural network model. And moreover, the predicted body type data of the user after the body type change is obtained by combining the daily calorie intake and the daily energy consumption, so that the predicted body type data is closer to the actual body type change of the user, and the accuracy is higher.
Description
Technical Field
The embodiment of the invention relates to the technical field of data processing, in particular to a body type data determining method, device, equipment, storage medium and product.
Background
Along with the development of socio-economy, people pay more and more attention to health, and in daily life, people maintain physical health through fitness exercise, such as increasing the number of steps of walking to increase daily physical consumption, or performing fitness exercise through a fitness room. In the process of body building, the body shape of people can be changed continuously, and good body shape usually represents the health of the body. Therefore, the change of body shape becomes a major concern in body building.
Currently, in order to clearly identify the change of the receptor type, various methods for predicting the change of the body type have been developed. At present, the main method for predicting the body type change of people is to build a function through big data to predict the body type change of an individual. Such a body type prediction method is far from the actual body type variation.
Therefore, the difference between the current mode for predicting the body type change of people and the actual body type change is large, and the accuracy is low.
Disclosure of Invention
The invention provides a body type data determining method, a body type data determining device, body type data determining equipment, a body type data determining storage medium and a body type data determining product, which are used for solving the problems that the difference between the current body type change predicting method and the actual body type change is large and the accuracy is low.
A first aspect of an embodiment of the present invention provides a body type data determining method, including:
receiving a body type prediction request triggered by a user;
acquiring current body type data, daily caloric intake and daily energy consumption of the user according to the body type prediction request;
inputting the current body type data, daily caloric intake and daily energy consumption of the user into a converged bidirectional recurrent neural network model for training to determine predicted body type data;
and outputting the predicted body type data.
Further, the method as described above, the obtaining the daily energy consumption amount of the user, includes:
acquiring the daily exercise steps of a user, and calculating the daily exercise consumption according to the daily exercise steps;
acquiring daily electrocardio-activity data of a user, and calculating daily resting heart rate according to the daily electrocardio-activity data of the user;
calculating a daily energy consumption based on the daily exercise consumption and the daily resting heart rate.
Further, the method as described above, the obtaining daily caloric intake of the user, comprising:
acquiring daily food intake images of a user, and inputting the daily food intake images of the user into a converged calorie recognition model for training to determine standard daily food calories;
calculating daily caloric intake based on the daily food standard calorie.
Further, the method as described above, before the inputting the current body type data, daily caloric intake and daily energy consumption of the user into the training to the converged bi-directional recurrent neural network model, further comprising:
obtaining a training sample, wherein the training sample comprises: historical body type data of the user, future actual body type data of the user, corresponding actual daily calorie intake and actual daily energy consumption;
inputting the training sample into a preset bidirectional cyclic neural network model to train the preset bidirectional cyclic neural network model;
judging whether the preset bidirectional recurrent neural network model meets a convergence condition or not by adopting a preset error formula;
and if the preset bidirectional cyclic neural network model meets the convergence condition, determining the preset bidirectional cyclic neural network model meeting the convergence condition as a bidirectional cyclic neural network model trained to be converged.
Further, the method as described above, before obtaining the current body type data, daily caloric intake and daily energy consumption of the user, further comprising:
acquiring a whole body image and user height data of a user, and inputting the whole body image into a preset characteristic point determination model to determine a plurality of characteristic points of a human body of the user;
determining a three-dimensional area block of each characteristic point according to the user height data and the plurality of characteristic points;
splicing the three-dimensional region blocks of the characteristic points to generate a three-dimensional human body model of the user;
after the outputting the predicted body type data, the method further comprises:
and updating the three-dimensional human body model according to the predicted body type data to obtain an updated three-dimensional human body model.
Further, as described above, the whole-body image includes a frontal whole-body image, a reverse whole-body image, and a lateral whole-body image;
the method for acquiring the whole-body image and the height data of the user and inputting the whole-body image into a preset feature point determination model to determine a plurality of feature points of the human body of the user comprises the following steps:
the method comprises the steps of obtaining a front whole-body image, a back whole-body image, a side whole-body image and user height data of a user, inputting the front whole-body image, the back whole-body image and the side whole-body image into a preset feature point determination model, and determining a plurality of feature points corresponding to the front, the side and the back of a human body of the user.
A second aspect of an embodiment of the present invention provides a body type data determining apparatus, including:
the receiving module is used for receiving a body type prediction request triggered by a user;
the obtaining module is used for obtaining the current body type data, the daily calorie intake and the daily energy consumption of the user according to the body type prediction request;
the determining module is used for inputting and training the current body type data, the daily calorie intake and the daily energy consumption of the user into a converged bidirectional circulation neural network model so as to determine predicted body type data;
and the output module is used for outputting the predicted body type data.
Further, in the apparatus as described above, the obtaining module, when obtaining the daily energy consumption of the user, is specifically configured to:
acquiring the daily exercise steps of a user, and calculating the daily exercise consumption according to the daily exercise steps; acquiring daily electrocardio-activity data of a user, and calculating daily resting heart rate according to the daily electrocardio-activity data of the user; calculating a daily energy consumption based on the daily exercise consumption and the daily resting heart rate.
Further, in the apparatus as described above, the obtaining module, when obtaining the daily caloric intake of the user, is specifically configured to:
acquiring daily food intake images of a user, and inputting the daily food intake images of the user into a converged calorie recognition model for training to determine standard daily food calories; calculating daily caloric intake based on the daily food standard calorie.
Further, the apparatus as described above, further comprising:
a training module, configured to obtain a training sample, where the training sample includes: historical body type data of the user, future actual body type data of the user, corresponding actual daily calorie intake and actual daily energy consumption; inputting the training sample into a preset bidirectional circulation neural network model to train the preset bidirectional circulation neural network model; judging whether the preset bidirectional recurrent neural network model meets a convergence condition or not by adopting a preset error formula; and if the preset bidirectional cyclic neural network model meets the convergence condition, determining the preset bidirectional cyclic neural network model meeting the convergence condition as a bidirectional cyclic neural network model trained to be converged.
Further, the apparatus as described above, further comprising:
the three-dimensional model generation module is used for acquiring a whole-body image and user height data of a user, and inputting the whole-body image into a preset characteristic point determination model so as to determine a plurality of characteristic points of the human body of the user; determining a three-dimensional area block of each characteristic point according to the user height data and the plurality of characteristic points; splicing the three-dimensional region blocks of the characteristic points to generate a three-dimensional human body model of the user;
the device further comprises:
and the updating module is used for updating the three-dimensional human body model according to the predicted body type data so as to obtain an updated three-dimensional human body model.
Further, the apparatus as described above, the whole-body image includes a front whole-body image, a back whole-body image, and a side whole-body image;
the three-dimensional model generation module is used for acquiring a whole-body image and height data of a user, inputting the whole-body image into a preset characteristic point determination model, and specifically used for:
the method comprises the steps of obtaining a front whole-body image, a back whole-body image, a side whole-body image and user height data of a user, inputting the front whole-body image, the back whole-body image and the side whole-body image into a preset feature point determination model, and determining a plurality of feature points corresponding to the front, the side and the back of a human body of the user.
A third aspect of embodiments of the present invention provides an electronic device, including: a memory, a processor;
a memory; a memory for storing the processor-executable instructions;
wherein the processor is configured to perform the body type data determination method of any one of the first aspect by the processor.
A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-readable storage medium is configured to implement the body shape data determination method according to any one of the first aspect.
A fifth aspect of the embodiments of the present invention provides a computer program product, which includes a computer program that, when executed by a processor, implements the body shape data determination method according to any one of the first aspects.
The embodiment of the invention provides a method, a device, equipment, a storage medium and a product for determining body type data, wherein the method comprises the following steps: receiving a body type prediction request triggered by a user; acquiring current body type data, daily caloric intake and daily energy consumption of the user according to the body type prediction request; inputting the current body type data, daily caloric intake and daily energy consumption of the user into a converged bidirectional recurrent neural network model for training to determine predicted body type data; and outputting the predicted body type data. According to the body type data determining method, when the user has a body type prediction demand, the current body type data, daily caloric intake and daily energy consumption of the user are obtained by receiving the body type prediction request triggered by the user, and the daily caloric intake and the daily energy consumption are related to the body type change of the user. The current body type data, the daily calorie intake and the daily energy consumption of the user are input into a converged bidirectional circulation neural network model for training, and the predicted body type data of the user after body type change can be obtained. Meanwhile, by adopting the bidirectional circulation neural network model, the user can obtain the comparison condition between the current body type data and the predicted body type data. And moreover, the predicted body type data of the user after the body type change is obtained by combining the daily calorie intake and the daily energy consumption, so that the predicted body type data is closer to the actual body type change of the user, and the accuracy is higher.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a scene diagram of a body type data determination method that can implement an embodiment of the present invention;
fig. 2 is a schematic flowchart of a body type data determining method according to a first embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for determining body type data according to a second embodiment of the present invention;
FIG. 4 is a schematic flowchart of a bi-directional recurrent neural network model training in the body type data determination method according to a third embodiment of the present invention;
FIG. 5 is a schematic diagram of a user interface of a body type data determination method according to a fourth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a body type data determining apparatus according to a fifth embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present invention.
With the above figures, certain embodiments of the invention have been illustrated and described in more detail below. The drawings and the description are not intended to limit the scope of the inventive concept in any way, but rather to illustrate it by those skilled in the art with reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
For a clear understanding of the technical solutions of the present application, a detailed description of the prior art solutions is first provided. With the development of socio-economic, people pay more attention to health and body type. Currently, in order to clearly identify the change of the receptor type, various methods for predicting the change of the body type have been developed. At present, the main way of predicting the body shape change of a person is to predict the body shape change of the person by establishing a function through big data, for example, by obtaining the body mass index, the body fat rate index and the muscle density index of the user within several weeks, so as to construct a corresponding body index function according to the body mass index, the body fat rate index and the muscle density index of the user. Because the body type prediction mode is only established on the rule of big data, the difference with the actual body type change is large.
Therefore, in order to solve the technical problems that the difference between the mode for predicting the body type change of the person and the actual body type change is large and the accuracy is low in the prior art, the inventor finds that the daily calorie intake and the daily energy consumption of the user can be obtained in order to solve the problems that the difference between the current mode for predicting the body type change of the person and the actual body type change is large and the accuracy is low. Firstly, a bidirectional recurrent neural network model is constructed and trained through training samples. When the user has a body type prediction demand, receiving a body type prediction request triggered by the user. And acquiring the current body type data, daily calorie intake and daily energy consumption of the user according to the body type prediction request. The acquisition mode can be manual input by a user, measurement by a measuring device or acquisition by a database, and the like. Then, the user's current body conformation data, daily caloric intake, and daily energy consumption are input into a converged bi-directional recurrent neural network model trained to determine predicted body conformation data. By adopting the bidirectional circulation neural network model, the user can obtain the comparison condition between the current body type data and the predicted body type data. And finally, outputting the predicted body type data so that the user can see the predicted result. The technical scheme of this application is because combined daily calorie intake and daily energy consumption to obtain the prediction size data after the user's size changes, compares the mode through big data structure function, and the size that more closely is close to the user reality changes, and the accuracy is higher.
The inventor provides the technical scheme of the application based on the creative discovery.
An application scenario of the body type data determination method provided by the embodiment of the present invention is described below. As shown in fig. 1, 1 is a first electronic device, and 2 is a second electronic device. The network architecture of the application scene corresponding to the body type data determining method provided by the embodiment of the invention comprises the following steps: a first electronic device 1 and a second electronic device 2. The second electronic device 2 stores data relating to the user's body type, such as the user's historical body type data, current body type data, daily caloric intake and daily energy consumption. The first electronic device 1 acquires the current body type data, daily calorie intake and daily energy consumption of the user from the second electronic device 2 upon receiving a user-triggered request. The user's current body conformation data, daily caloric intake, and daily energy consumption are then input into a converged bi-directional recurrent neural network model trained to determine predicted body conformation data. After the predicted body type data are determined, the predicted body type data can be output to a display interface to be displayed, or output to other electronic equipment to be correspondingly processed.
According to the body type data determining method provided by the embodiment of the invention, the daily calorie intake and the daily energy consumption are related to the body type change of the user. The current body type data, the daily calorie intake and the daily energy consumption of the user are input into a converged bidirectional circulation neural network model for training, and the predicted body type data of the user after body type change can be obtained. Meanwhile, by adopting the bidirectional circulation neural network model, the user can obtain the comparison condition between the current body type data and the predicted body type data. And moreover, the predicted body type data of the user after the body type change is obtained by combining the daily calorie intake and the daily energy consumption, so that the predicted body type data is closer to the actual body type change of the user, and the accuracy is higher.
The embodiments of the present invention will be described with reference to the accompanying drawings.
Fig. 2 is a schematic flow chart of a body type data determining method according to a first embodiment of the present invention, and as shown in fig. 2, in this embodiment, an execution subject of the embodiment of the present invention is a body type data determining apparatus, and the body type data determining apparatus may be integrated in an electronic device. The body type data determining method provided by the embodiment includes the following steps:
step S101, receiving a body type prediction request triggered by a user.
In this embodiment, the user may trigger the body shape prediction request by touching with a finger or may trigger the body shape prediction request by using a tool, which is not limited in this embodiment.
And step S102, acquiring current body type data, daily calorie intake and daily energy consumption of the user according to the body type prediction request.
In this embodiment, the current body type data, daily calorie intake and daily energy consumption of the user may be obtained by inputting relevant data by the user, obtained by a measurement device externally connected to the electronic device, or obtained by a preset database storing the current body type data, daily calorie intake and daily energy consumption of the user. The external measuring device may be a shooting device, a sports watch for measuring daily energy consumption, a weight meter, or the like, which is not limited in this embodiment.
In this embodiment, the current body type data of the user may include one or more of the following: body fat rate, muscle content, bone mass, moisture content, visceral fat, subcutaneous fat, lean body weight, skeletal muscle rate, weight, height, chest circumference, waist circumference, hip circumference, etc. The current body type data can be set according to actual requirements, and the types of the current body type data are increased. Generally, the user is more concerned about the chest circumference, waist circumference, and hip circumference, and these three data may be mainly used in daily use.
In this embodiment, the daily calorie intake refers to the daily calorie intake of the user, and mainly refers to the calorie taken by the user from the food. The daily energy consumption amount refers to the daily energy consumption amount of a user, and the daily energy consumption amount mainly refers to the energy consumption amount generated when the user stands still and moves because the human body generates energy consumption when standing still and moving.
Step S103, inputting the current body type data, daily calorie intake and daily energy consumption of the user into a converged bidirectional circulation neural network model for training so as to determine predicted body type data.
In this embodiment, the bidirectional recurrent neural network model is formed by superimposing two recurrent neural network models one on another, and the output is determined by the states of the two recurrent neural network models. Therefore, the bidirectional cyclic neural network model not only has the function of unidirectional cyclic neural network model prediction, but also can provide the function of a historical data end. The current body type data, the daily calorie intake and the daily energy consumption of the user are input into a converged bidirectional circulation neural network model for training, the predicted body type data can be determined, and meanwhile, the user can check the current body type data and the predicted body type data at the same time to obtain more intuitive comparison.
In this embodiment, the predicted body type data corresponds to the current body type data of the user, and similarly includes one or more of the following: body fat rate, muscle content, bone mass, moisture content, visceral fat, subcutaneous fat, lean body weight, skeletal muscle rate, weight, height, chest circumference, waist circumference, hip circumference, etc. The current body type data can be set according to actual requirements, and the types of the current body type data are increased. Generally, the user is more concerned about the chest circumference, waist circumference, and hip circumference, and these three data may be mainly used in daily use.
Step S104, outputting the predicted body type data.
In this embodiment, after the predicted body type data is determined, the predicted body type data may be output to a display interface for display, or output to other electronic devices for corresponding processing, for example, the predicted body type data may be output to other electronic devices to construct a three-dimensional human body model of the user, or may be output to other electronic devices to construct a body type data change curve of the user, and the like.
The embodiment of the invention provides a body type data determining method, which comprises the following steps: and receiving a body type prediction request triggered by a user. And acquiring the current body type data, daily calorie intake and daily energy consumption of the user according to the body type prediction request. Current body type data, daily caloric intake, and daily energy consumption of the user are input into a converged bi-directional recurrent neural network model trained to determine predicted body type data. And outputting the predicted body type data. According to the body type data determining method, when the user has a body type prediction demand, the current body type data, daily caloric intake and daily energy consumption of the user are obtained by receiving the body type prediction request triggered by the user, and the daily caloric intake and the daily energy consumption are related to the body type change of the user. The current body type data, the daily calorie intake and the daily energy consumption of the user are input into a converged bidirectional circulation neural network model for training, and the predicted body type data of the user after body type change can be obtained. Meanwhile, by adopting the bidirectional circulation neural network model, the user can obtain the comparison condition between the current body type data and the predicted body type data. In addition, the predicted body type data after the body type of the user is changed are obtained by combining the daily calorie intake and the daily energy consumption, so that the predicted body type data are closer to the actual body type change of the user, and the accuracy is higher.
Fig. 3 is a schematic flow chart of a body type data determining method according to a second embodiment of the present invention, and as shown in fig. 3, the body type data determining method according to the present embodiment is further refined in each step based on the body type data determining method according to the previous embodiment of the present invention. The body type data determination method provided by the present embodiment includes the following steps.
Step S201, a body type prediction request triggered by a user is received.
In this embodiment, the implementation manner of step 201 is similar to that of step 101 in the previous embodiment of the present invention, and is not described in detail here.
Step S202, a whole body image and user height data of the user are obtained according to the body type prediction request, and the whole body image is input into a preset feature point determination model to determine a plurality of feature points of the human body of the user.
In this embodiment, the whole body image of the user needs to include the whole body of the user, and a background with distinct colors, such as white and blue, may be preferably used.
In this embodiment, the preset feature point determination model may adopt a neural network model, so that the plurality of determined feature points are more accurate. The plurality of feature points of the user's body may include head feature points, torso feature points, and extremity feature points. In the head feature points, 66 feature points are defined on the front face and the side face of the human face, 10 points are defined on the contour, and 3 points are defined on the forehead. 3 points for each of the left and right eyebrows, 8 points for each of the left and right eyes, 8 points for the nose, 9 points for the mouth, 5 points for each of the left and right ears, and 2 points for each of the cheek and cheek. Similarly, a plurality of characteristic points are arranged on the trunk characteristic points and the limb characteristic points. Therefore, the structural characteristics of the human body of the user can be preliminarily constructed through a plurality of characteristic points of the human body of the user.
And S203, determining the three-dimensional region block of each characteristic point according to the height data of the user and the plurality of characteristic points, and splicing the three-dimensional region blocks of each characteristic point to generate the three-dimensional human body model of the user.
In this embodiment, a search center point of the plurality of feature points is selected according to the height ratio of the user height data, and the search center points are moved upward and downward by the same height to determine the search range. Thereby determining the three-dimensional region blocks of the respective feature points. When the three-dimensional region blocks of each characteristic point are spliced, smooth filtering processing can be carried out to obtain a more accurate three-dimensional human body model.
In this embodiment, the human body model corresponding to the user can be visually displayed by constructing the three-dimensional human body model.
Optionally, in this embodiment, the whole-body image includes a front whole-body image, a back whole-body image, and a side whole-body image.
The method comprises the steps of acquiring a whole body image and height data of a user, inputting the whole body image into a preset characteristic point determination model to determine a plurality of characteristic points of a human body of the user, and comprises the following steps:
the method comprises the steps of obtaining a front whole-body image, a back whole-body image, a side whole-body image and user height data of a user, inputting the front whole-body image, the back whole-body image and the side whole-body image into a preset feature point determination model, and determining a plurality of feature points corresponding to the front, the side and the back of a human body of the user.
In this embodiment, since a plurality of head feature points, trunk feature points, and four-limb feature points are required for constructing the three-dimensional human body model, it is necessary to acquire a front whole-body image, a back whole-body image, and a side whole-body image of the user, so that a three-dimensional human body model closer to the human body of the user can be constructed.
It should be noted that the steps 204-208 are further detailed for the step 102.
And S204, acquiring the daily exercise steps of the user, calculating the daily exercise consumption according to the daily exercise steps, acquiring the daily electrocardio-activity data of the user, and calculating the daily resting heart rate according to the daily electrocardio-activity data of the user.
In this embodiment, the number of exercise steps per day of the user may be obtained through user input, a preset database, or through a measurement device. The measuring device can be a portable measuring tool, such as a sports watch, a mobile phone and the like, so that the daily exercise steps of the user can be measured and acquired through the measuring device. Since the daily exercise step count is correlated with the user's daily exercise amount, the daily exercise consumption amount can be calculated from the daily exercise step count.
In this embodiment, the obtaining of the daily cardiac electrical activity data of the user may be obtained through user input, a preset database, or through a measurement device, which is not limited in this embodiment. The measuring equipment can obtain the data of the electrocardio-activity of the user by measuring the change of the potential difference between two points on the surface of the human body.
In step S205, a daily energy consumption amount is calculated from the daily exercise consumption amount and the daily resting heart rate.
In this embodiment, since the daily resting heart rate of the user is related to the energy consumed by the user in a resting state, the daily energy consumption amount can be calculated from the daily exercise consumption amount and the daily resting heart rate.
And step S206, acquiring daily food intake images of the user, and inputting the daily food intake images of the user into a converged calorie recognition model for training so as to determine standard daily food calories.
In this embodiment, the image of the food taken by the user every day may be obtained by user input, a preset database, or by a camera. The shooting device may be a mobile phone, a video camera, etc., which is not limited in this embodiment. The user ingests an image of the food daily, preferably with a well-defined background color, for example white, to highlight the food image.
In this embodiment, the calorie identification model generally adopts a neural network model, and through continuous training, the daily food standard calorie is determined more and more accurately.
In step S207, the daily calorie intake is calculated based on the standard calorie of the daily food.
In this embodiment, the standard daily food calorie has different retention rates when entering the human body, and the retained calorie becomes the intake absorbed by the human body, so that the daily calorie intake can be calculated according to the standard daily food calorie.
Step S208, the current body type data of the user is obtained.
In this embodiment, the implementation manner of step 208 is similar to that of step 102 in the previous embodiment of the present invention, and is not described herein again.
Step S209, inputting the current body type data, daily caloric intake and daily energy consumption of the user into a converged bidirectional recurrent neural network model for training to determine predicted body type data.
In this embodiment, the implementation manner of step 209 is similar to that of step 103 in the previous embodiment of the present invention, and is not described in detail here.
Step S210 outputs the predicted body type data.
In this embodiment, the implementation manner of step 210 is similar to that of step 104 in the previous embodiment of the present invention, and is not described in detail here.
And step S211, updating the three-dimensional human body model according to the predicted body type data to obtain an updated three-dimensional human body model.
In this embodiment, after the three-dimensional human body model is updated according to the predicted body type data, the updated three-dimensional human body model can be obtained, and the three-dimensional human body model corresponds to the predicted body type data, so that the user can more intuitively check out what body type the user corresponds to at a future moment through the three-dimensional human body model, and the user can be encouraged to keep further fitness and keep a healthier body.
According to the body type data determining method provided by the embodiment of the invention, when a user has a body type prediction demand, a three-dimensional human body model corresponding to the user is firstly constructed by receiving a body type prediction request triggered by the user, and then the current body type data, daily calorie intake and daily energy consumption of the user are obtained, and the daily calorie intake and the daily energy consumption are related to the body type change of the user. The current body type data, the daily calorie intake and the daily energy consumption of the user are input into a converged bidirectional circulation neural network model for training, and the predicted body type data of the user after body type change can be obtained. Meanwhile, by adopting the bidirectional circulation neural network model, the user can obtain the comparison condition between the current body type data and the predicted body type data. And moreover, the predicted body type data of the user after the body type change is obtained by combining the daily calorie intake and the daily energy consumption, so that the predicted body type data is closer to the actual body type change of the user, and the accuracy is higher. And the updated three-dimensional human body model can be obtained by updating the three-dimensional human body model according to the predicted body type data, and the three-dimensional human body model corresponds to the predicted body type data, so that the user can more intuitively check out what body type the user corresponds to at the future time through the three-dimensional human body model, and the user can be stimulated to keep further fitness and keep a healthier body.
Fig. 4 is a schematic flow chart of bidirectional recurrent neural network model training in the body type data determination method according to the third embodiment of the present invention. As shown in fig. 4, the body type data determining method provided in this embodiment is based on the body type data determining method provided in the previous embodiment of the present invention, and adds a procedure of bidirectional recurrent neural network model training. The body type data determination method provided by the present embodiment includes the following steps.
Step S301, obtaining a training sample, wherein the training sample comprises: the method comprises the steps of obtaining historical body type data of a user, actual future body type data of the user and corresponding actual daily calorie intake and actual daily energy consumption.
In this embodiment, the training samples may include historical body type data of the user, future actual body type data of the user, and corresponding actual daily caloric intake and actual daily energy consumption. For example, all user body type data of the user in one week are acquired, the user body type data in one week is used as the user history body type data, and the user body type data in friday is used as the future actual body type data.
Step S302, inputting the training sample into a preset bidirectional cyclic neural network model so as to train the preset bidirectional cyclic neural network model.
In this embodiment, the user body type data corresponding to monday time is used as the historical user body type data and the user body type data corresponding to friday time is used as the future actual user type data, and the user body type data and the future actual user type data are simultaneously input into the preset bidirectional recurrent neural network model, so that the prediction accuracy of the preset bidirectional recurrent neural network model can be determined by comparing the output predicted body type data with the future actual user type data.
Step S303, judging whether the preset bidirectional recurrent neural network model meets a convergence condition by adopting a preset error formula.
In this embodiment, the preset error formula may be set according to actual requirements, which is not limited in this embodiment.
Step S304, if the preset bidirectional cyclic neural network model meets the convergence condition, determining the preset bidirectional cyclic neural network model meeting the convergence condition as the bidirectional cyclic neural network model trained to converge.
In this embodiment, when the preset bidirectional recurrent neural network model satisfies the convergence condition, that is, the prediction accuracy of the preset bidirectional recurrent neural network model at this time is high, and the preset bidirectional recurrent neural network model can be used as a bidirectional recurrent neural network model trained to converge for actual prediction.
Fig. 5 is a schematic view of a user interface of a body type data determining method according to a fourth embodiment of the present invention, and as shown in fig. 5, the body type data determining method according to this embodiment is based on the body type data determining method according to the above embodiment of the present invention, and a flow of the user interface when the user performs a body type prediction operation is described with reference to fig. 5.
This embodiment describes a scenario in which the current body type data, daily calorie intake amount, and daily energy consumption amount of the user are acquired by the user inputting the relevant data. As shown in fig. 5, when the user needs to perform body type prediction, the user may click on a body type prediction button on the application client operation interface and then input current body type data, daily caloric intake, and daily energy consumption amount as guided. Then, after the user clicks the determination button, the predicted body type data can be obtained. As shown in the figure, after the user inputs the current chest circumference and waist circumference, the predicted chest circumference is a and the predicted waist circumference is B.
Fig. 6 is a schematic structural diagram of a body type data determining apparatus according to a fifth embodiment of the present invention, and as shown in fig. 6, in this embodiment, the body type data determining apparatus 400 includes:
a receiving module 401, configured to receive a body type prediction request triggered by a user.
An obtaining module 402, configured to obtain current body type data, daily calorie intake and daily energy consumption of the user according to the body type prediction request.
A determining module 403, configured to input the current body type data, daily caloric intake and daily energy consumption of the user into a converged bidirectional recurrent neural network model for training to determine predicted body type data.
And an output module 404, configured to output the predicted body type data.
The body type data determining apparatus provided in this embodiment may implement the technical solution of the method embodiment shown in fig. 2, and the implementation principle and technical effect thereof are similar to those of the method embodiment shown in fig. 2, and are not described in detail herein.
Meanwhile, another embodiment of the body type data determining apparatus provided by the present invention further refines the body type data determining apparatus 400 on the basis of the body type data determining apparatus provided by the previous embodiment.
Optionally, in this embodiment, when obtaining the daily energy consumption of the user, the obtaining module 402 is specifically configured to:
and acquiring the daily exercise steps of the user, and calculating the daily exercise consumption according to the daily exercise steps. Acquiring daily electrocardio-activity data of the user, and calculating daily resting heart rate according to the daily electrocardio-activity data of the user. Daily energy expenditure is calculated from daily exercise expenditure and daily resting heart rate.
Optionally, in this embodiment, when acquiring the daily calorie intake of the user, the acquiring module 402 is specifically configured to:
an image of the daily food intake of the user is acquired and input into a converged calorie recognition model to determine a standard daily food calorie. Daily caloric intake was calculated from daily food standard calories.
Optionally, in this embodiment, the method further includes:
the training module is used for obtaining training samples, and the training samples comprise: historical body type data of the user, future actual body type data of the user and corresponding actual daily calorie intake and actual daily energy consumption. And inputting the training samples into a preset bidirectional cyclic neural network model so as to train the preset bidirectional cyclic neural network model. And judging whether the preset bidirectional cyclic neural network model meets the convergence condition or not by adopting a preset error formula. And if the preset bidirectional cyclic neural network model meets the convergence condition, determining the preset bidirectional cyclic neural network model meeting the convergence condition as the bidirectional cyclic neural network model trained to be converged.
Optionally, in this embodiment, the body type data determining apparatus 400 further includes:
and the three-dimensional model generation module is used for acquiring a whole-body image and height data of the user, and inputting the whole-body image into a preset characteristic point determination model so as to determine a plurality of characteristic points of the human body of the user. And determining the three-dimensional area block of each characteristic point according to the user height data and the plurality of characteristic points. And splicing the three-dimensional region blocks of the characteristic points to generate a three-dimensional human body model of the user.
The body type data determination apparatus 400 further includes:
and the updating module is used for updating the three-dimensional human body model according to the predicted body type data so as to obtain the updated three-dimensional human body model.
Optionally, in this embodiment, the whole-body image includes a front whole-body image, a back whole-body image, and a side whole-body image.
The three-dimensional model generation module is used for inputting the whole-body image into the preset characteristic point determination model when acquiring the whole-body image and the height data of the user so as to determine a plurality of characteristic points of the human body of the user, and is specifically used for:
the method comprises the steps of obtaining a front whole-body image, a back whole-body image, a side whole-body image and user height data of a user, inputting the front whole-body image, the back whole-body image and the side whole-body image into a preset feature point determination model, and determining a plurality of feature points corresponding to the front, the side and the back of a human body of the user.
The body type data determining apparatus provided in this embodiment may implement the technical solutions of the method embodiments shown in fig. 2 to 4, and the implementation principles and technical effects thereof are similar to those of the method embodiments shown in fig. 2 to 4, and are not described in detail here.
The invention also provides an electronic device, a computer readable storage medium and a computer program product according to the embodiments of the invention.
As shown in fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present invention. Electronic devices are intended for various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 7, the electronic apparatus includes: a processor 501 and a memory 502. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device.
The memory 502 is a non-transitory computer readable storage medium provided by the present invention. The memory stores instructions executable by the at least one processor, so that the at least one processor executes the body type data determination method provided by the invention. The non-transitory computer-readable storage medium of the present invention stores computer instructions for causing a computer to execute the body shape data determination method provided by the present invention.
The memory 502, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the body type data determination method in the embodiment of the present invention (for example, the receiving module 401, the obtaining module 402, the determining module 403, and the threat and output module 404 shown in fig. 6). The processor 501 executes various functional applications of the server and data processing by running non-transitory software programs, instructions, and modules stored in the memory 502, that is, implements the body type data determination method in the above-described method embodiments.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the embodiments of the invention following, in general, the principles of the embodiments of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the embodiments of the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of embodiments of the invention being indicated by the following claims.
It is to be understood that the embodiments of the present invention are not limited to the precise arrangements described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of embodiments of the invention is limited only by the appended claims.
Claims (10)
1. A method for determining body type data, comprising:
receiving a body type prediction request triggered by a user;
according to the body type prediction request, obtaining current body type data, daily calorie intake and daily energy consumption of a user;
inputting the current body type data, daily caloric intake and daily energy consumption of the user into a converged bidirectional recurrent neural network model for training to determine predicted body type data;
and outputting the predicted body type data.
2. The method of claim 1, wherein obtaining the daily energy consumption of the user comprises:
acquiring the daily exercise steps of a user, and calculating the daily exercise consumption according to the daily exercise steps;
acquiring daily electrocardio-activity data of a user, and calculating daily resting heart rate according to the daily electrocardio-activity data of the user;
calculating a daily energy consumption based on the daily exercise consumption and the daily resting heart rate.
3. The method of claim 2, wherein the obtaining the daily caloric intake of the user comprises:
acquiring daily food intake images of a user, and inputting the daily food intake images of the user into a converged calorie recognition model for training to determine standard daily food calories;
calculating daily caloric intake based on the daily food standard calories.
4. The method of any one of claims 1 to 3, wherein before inputting the current body conformation data, daily caloric intake, and daily energy consumption of the user into the training of the converged bi-directional recurrent neural network model, further comprising:
obtaining a training sample, wherein the training sample comprises: historical body type data of the user, future actual body type data of the user, corresponding actual daily calorie intake and actual daily energy consumption;
inputting the training sample into a preset bidirectional circulation neural network model to train the preset bidirectional circulation neural network model;
judging whether the preset bidirectional recurrent neural network model meets a convergence condition or not by adopting a preset error formula;
and if the preset bidirectional cyclic neural network model meets the convergence condition, determining the preset bidirectional cyclic neural network model meeting the convergence condition as a bidirectional cyclic neural network model trained to be converged.
5. The method of any one of claims 1 to 3, wherein prior to obtaining the current body conformation data, daily caloric intake and daily energy consumption of the user, further comprising:
acquiring a whole-body image and height data of a user, and inputting the whole-body image into a preset feature point determination model to determine a plurality of feature points of a human body of the user;
determining a three-dimensional area block of each characteristic point according to the user height data and the plurality of characteristic points;
splicing the three-dimensional region blocks of the characteristic points to generate a three-dimensional human body model of the user;
after the outputting the predicted body type data, the method further comprises:
and updating the three-dimensional human body model according to the predicted body type data to obtain an updated three-dimensional human body model.
6. The method of claim 5, wherein the whole-body images include a frontal whole-body image, a reverse whole-body image, and a lateral whole-body image;
the method for acquiring the whole-body image and the height data of the user and inputting the whole-body image into a preset feature point determination model to determine a plurality of feature points of the human body of the user comprises the following steps:
the method comprises the steps of obtaining a front whole-body image, a back whole-body image, a side whole-body image and user height data of a user, inputting the front whole-body image, the back whole-body image and the side whole-body image into a preset feature point determination model, and determining a plurality of feature points corresponding to the front, the side and the back of a human body of the user.
7. A body type data determination apparatus, comprising:
the receiving module is used for receiving a body type prediction request triggered by a user;
the obtaining module is used for obtaining the current body type data, the daily calorie intake and the daily energy consumption of the user according to the body type prediction request;
a determining module, configured to input the current body type data, daily caloric intake, and daily energy consumption of the user into a converged bidirectional recurrent neural network model for training, so as to determine predicted body type data;
and the output module is used for outputting the predicted body type data.
8. An electronic device, comprising: a memory, a processor;
a memory; a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the body type data determination method of any one of claims 1 to 6 by the processor.
9. A computer-readable storage medium having stored thereon computer-executable instructions for implementing the method of determining body shape data according to any one of claims 1 to 6 when executed by a processor.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the body shape data determination method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011499160.7A CN114649096A (en) | 2020-12-17 | 2020-12-17 | Body type data determination method, device, equipment, storage medium and product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011499160.7A CN114649096A (en) | 2020-12-17 | 2020-12-17 | Body type data determination method, device, equipment, storage medium and product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114649096A true CN114649096A (en) | 2022-06-21 |
Family
ID=81989738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011499160.7A Pending CN114649096A (en) | 2020-12-17 | 2020-12-17 | Body type data determination method, device, equipment, storage medium and product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114649096A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117224080A (en) * | 2023-09-04 | 2023-12-15 | 深圳市维康致远科技有限公司 | Human body data monitoring method and device for big data |
-
2020
- 2020-12-17 CN CN202011499160.7A patent/CN114649096A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117224080A (en) * | 2023-09-04 | 2023-12-15 | 深圳市维康致远科技有限公司 | Human body data monitoring method and device for big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102097190B1 (en) | Method for analyzing and displaying a realtime exercise motion using a smart mirror and smart mirror for the same | |
| US9195304B2 (en) | Image processing device, image processing method, and program | |
| JP2020516353A (en) | Data method and apparatus, and fitness robot | |
| CN108633249B (en) | Physiological signal quality judgment method and device | |
| KR20190113265A (en) | Augmented reality display apparatus for health care and health care system using the same | |
| CN107249441A (en) | Electronic installation and method for measuring biological information | |
| KR102453304B1 (en) | A system that provides virtual reality content for dementia prevention and self-diagnosis | |
| CN111178298A (en) | Human body key point detection method and device, electronic equipment and storage medium | |
| CN112288766A (en) | Motion evaluation method, device, system and storage medium | |
| KR102425481B1 (en) | Virtual reality communication system for rehabilitation treatment | |
| KR102429630B1 (en) | A system that creates communication NPC avatars for healthcare | |
| US20200193858A1 (en) | Unobtrusive motivation estimation | |
| CN110706784A (en) | Calorie intake amount calculation method, device, system, apparatus, and storage medium | |
| CN109710371A (en) | Font adjusting method, apparatus and system | |
| CN107729144B (en) | Application control method and device, storage medium and electronic equipment | |
| CN109243562A (en) | A kind of image makings method for improving based on Elman artificial neural network and genetic algorithms | |
| CN110314344A (en) | Move based reminding method, apparatus and system | |
| CN117392746A (en) | Rehabilitation training evaluation assisting method, device, computer equipment and storage medium | |
| CN114649096A (en) | Body type data determination method, device, equipment, storage medium and product | |
| CN116712048A (en) | Blood pressure measurement method and device and related equipment | |
| Masullo et al. | CaloriNet: From silhouettes to calorie estimation in private environments | |
| KR102012804B1 (en) | Method, apparatus and computer program for recognition of a user activity | |
| KR102429627B1 (en) | The System that Generates Avatars in Virtual Reality and Provides Multiple Contents | |
| WO2024082912A1 (en) | Body shape measurement method and electronic device | |
| KR102432251B1 (en) | Virtual reality rehabilitation system performed on social servers |
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 |