CN113936335B - Intelligent sitting posture reminding method and device - Google Patents
Intelligent sitting posture reminding method and device Download PDFInfo
- Publication number
- CN113936335B CN113936335B CN202111181174.9A CN202111181174A CN113936335B CN 113936335 B CN113936335 B CN 113936335B CN 202111181174 A CN202111181174 A CN 202111181174A CN 113936335 B CN113936335 B CN 113936335B
- Authority
- CN
- China
- Prior art keywords
- sitting posture
- information
- obtaining
- model
- preset 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses an intelligent sitting posture reminding method and device, wherein the method comprises the following steps: training the neural network model by a federal learning method to obtain a third sitting posture preset model; obtaining height information and skeleton information of a first user; inputting the third sitting posture preset model to obtain standard sitting posture information of the first user; acquiring multi-angle images of the first user through the image acquisition device to obtain N pieces of first image information; constructing a three-dimensional sitting posture model of the first user; obtaining first sitting posture information of the first user; comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result; and determining whether first reminding information is obtained or not according to the first comparison result. The problem of among the prior art can't carry out real-time supervision, intelligence warning, timely correction to pupil's the not end position of sitting, and then influence the technique that the development of later stage skeleton was rectified is solved.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an intelligent sitting posture reminding method and device.
Background
A good sitting posture is important for learning and growth of children, the sitting postures of students in primary schools have a plurality of problems at present, and the cultivation of the good sitting postures of the pupils becomes important content of primary school health education and is also an important and urgent task.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
the technical problem that the development correction of later-stage bones is influenced by the fact that real-time monitoring, intelligent reminding and timely correction cannot be carried out on the out-of-position sitting posture of a pupil in the prior art.
Disclosure of Invention
Aiming at the defects in the prior art, the method and the device for reminding the pupil of the pupil sitting posture intelligently aim at solving the technical problem that the pupil of the pupil cannot be monitored, intelligently reminded and corrected in time in real time to influence the later-stage bone development correction in the prior art. Through federal study, generate pupil's standard position of sitting information, and then compare pupil's actual position of sitting information and standard position of sitting information, remind the position of sitting of nonstandard, reached and carried out intelligent image monitoring to pupil's position of sitting, in time remind and effectively adjust nonstandard position of sitting simultaneously for form good position of sitting custom, lay the technological effect of good basis for the bone growth and development of acquired and correction thereof.
In one aspect, an embodiment of the present application provides an intelligent sitting posture reminding method, where the method is applied to an intelligent sitting posture reminding system, the system includes an image acquisition device, and the method includes: training the neural network model through a federal learning method to obtain a third sitting posture preset model; obtaining height information and skeleton information of a first user; inputting the height information and the skeleton information into the third sitting posture preset model to obtain standard sitting posture information of the first user; acquiring multi-angle images of the first user through the image acquisition device to obtain N pieces of first image information, wherein the first image information comprises sitting posture image information of the first user; constructing a three-dimensional sitting posture model of the first user according to the N pieces of first image information; obtaining first sitting posture information of the first user according to the three-dimensional sitting posture model; comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result; and determining whether first reminding information is obtained or not according to the first comparison result, wherein the first reminding information is used for reminding the first user to adjust the sitting posture.
On the other hand, this application still provides an intelligence position of sitting reminder system, wherein, the system includes: a first obtaining unit: the first obtaining unit is used for training the neural network model through a federal learning method to obtain a third sitting posture preset model; a second obtaining unit: the second obtaining unit is used for obtaining height information and skeleton information of the first user; a first input unit: the first input unit is used for inputting the height information and the skeleton information into the third sitting posture preset model to obtain standard sitting posture information of the first user; a first acquisition unit: the first acquisition unit is used for acquiring multi-angle images of the first user through an image acquisition device to obtain N pieces of first image information, wherein the first image information comprises sitting posture image information of the first user; a first building unit: the first constructing unit is used for constructing a three-dimensional sitting posture model of the first user according to the N pieces of first image information; a third obtaining unit: the third obtaining unit is used for obtaining first sitting posture information of the first user according to the three-dimensional sitting posture model; a first comparison unit: the first comparison unit is used for comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result; a first determination unit: the first determining unit is used for determining whether first reminding information is obtained or not according to the first comparison result, and the first reminding information is used for reminding the first user to adjust the sitting posture.
In a third aspect, an embodiment of the present application provides an intelligent sitting posture reminding device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
training the neural network model by a federal learning method to obtain a third sitting posture preset model; obtaining height information and skeleton information of a first user; inputting the height information and the skeleton information into the third sitting posture preset model to obtain standard sitting posture information of the first user; acquiring multi-angle images of the first user through the image acquisition device to obtain N pieces of first image information; constructing a three-dimensional sitting posture model of the first user; obtaining first sitting posture information of the first user; comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result; and determining whether first reminding information is obtained or not according to the first comparison result. Through federal study, generate pupil's standard position of sitting information, and then compare pupil's actual position of sitting information and standard position of sitting information, remind the position of sitting of nonstandard, reached and carried out intelligent image monitoring to pupil's position of sitting, in time remind and effectively adjust nonstandard position of sitting simultaneously for form good position of sitting custom, lay the technological effect of good basis for the bone growth and development of acquired and correction thereof.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
fig. 1 is a schematic flow chart of an intelligent sitting posture reminding method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a process of training a neural network model by a federal learning method according to an intelligent sitting posture reminding method in an embodiment of the present application;
fig. 3 is a schematic flowchart of a process of training the initial sitting posture preset model through the first training data set in the intelligent sitting posture reminding method according to the embodiment of the present application;
fig. 4 is a schematic flowchart of a classification of the first training data set according to an intelligent sitting posture reminding method in an embodiment of the present application;
fig. 5 is a schematic structural diagram of an intelligent sitting posture reminding system according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides an intelligent sitting posture reminding method and device, and solves the technical problems that in the prior art, the non-end sitting posture of a pupil cannot be monitored in real time, intelligently reminded and timely corrected, and further the later skeleton development correction is influenced. Through federal study, generate pupil's standard position of sitting information, and then compare pupil's actual position of sitting information and standard position of sitting information, remind the position of sitting of non-standard, reached and carried out intelligent image monitoring to pupil's position of sitting, in time remind and effectively adjust the position of sitting of non-standard simultaneously for form good position of sitting custom, lay the technological effect of good basis for the skeleton growth and development of the future generations and correction thereof.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
A good sitting posture is important for the learning and the growth of children, the sitting posture of students in primary schools still has a plurality of problems, and the cultivation of the good sitting posture of the pupils becomes an important content of primary school health education and is an important and urgent task. The technical problem that the development correction of later-stage bones is influenced by the fact that real-time monitoring, intelligent reminding and timely correction cannot be carried out on the out-of-position sitting posture of a pupil in the prior art.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides an intelligent sitting posture reminding method, wherein the method is applied to an intelligent sitting posture reminding system, the system comprises an image acquisition device, and the method comprises the following steps: training the neural network model by a federal learning method to obtain a third sitting posture preset model; obtaining height information and skeleton information of a first user; inputting the height information and the skeleton information into the third sitting posture preset model to obtain standard sitting posture information of the first user; acquiring multi-angle images of the first user through the image acquisition device to obtain N pieces of first image information, wherein the first image information comprises sitting posture image information of the first user; constructing a three-dimensional sitting posture model of the first user according to the N pieces of first image information; obtaining first sitting posture information of the first user according to the three-dimensional sitting posture model; comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result; and determining whether first reminding information is obtained or not according to the first comparison result, wherein the first reminding information is used for reminding the first user to adjust the sitting posture.
For better understanding of the above technical solutions, the following detailed descriptions will be provided in conjunction with the drawings and the detailed description of the embodiments.
Example one
As shown in fig. 1, the present application provides an intelligent sitting posture reminding method, wherein the method is applied to a dialysis room treatment matching system, and the method includes:
step S100: training the neural network model by a federal learning method to obtain a third sitting posture preset model;
specifically, a good sitting posture is important for the learning and the growth of children, the sitting posture of students in primary schools still has a plurality of problems at present, and the cultivation of the good sitting posture of the pupils becomes an important content of primary school health education and is also an important and urgent task. In order to solve the problem that the later-stage bone development correction is influenced by the improper sitting posture of the pupils, the embodiment of the application provides the intelligent sitting posture reminding method which can remind the improper sitting posture of the pupils, so that the problems are avoided. The neural network model agent can be trained based on federal learning, wherein the federal learning is essentially a distributed machine learning technology or a machine learning framework, the aim is to realize common modeling on the basis of ensuring data privacy safety and legal compliance, the effect of the AI model is improved, the neural network model can be trained by adopting horizontal federal learning based on similar performance characteristics of users in different areas, the essence of the horizontal federal learning is sample combination, and the neural network model is suitable for scenes that participants have the same state but different clients are touched, namely, the characteristics are overlapped more and the users are overlapped less, and the obtained third sitting posture preset model is a preset model downloaded from a third-party server, and the sitting posture of the users can be preset through the third preset model.
Step S200: obtaining height information and skeleton information of a first user;
step S300: inputting the height information and the skeleton information into the third sitting posture preset model to obtain standard sitting posture information of the first user;
specifically, since the height and the bone growth state of the user affect the sitting posture of the user, the height information and the bone information of the first user can be obtained, wherein the first user is described here by taking a pupil as an example, and then the height information and the bone information are input into the third sitting posture preset model for prediction training, and the standard sitting posture information of the first user can be obtained, wherein the standard sitting posture information is obtained through scientific and accurate prediction training of the model based on the existing height information and the bone growth information of the pupil.
Step S400: acquiring multi-angle images of the first user through the image acquisition device to obtain N pieces of first image information, wherein the first image information comprises sitting posture image information of the first user;
step S500: constructing a three-dimensional sitting posture model of the first user according to the N pieces of first image information;
specifically, in order to perform multi-angle acquisition on the sitting posture of the pupils, the image acquisition device may further be used to perform multi-angle image acquisition on the first user, that is, perform image acquisition on each angle of the sitting posture of the pupils, for example, it may be determined whether the back of the pupils stops through image acquisition on the back, and it is determined whether the elbows of the pupils support the head, etc. through image acquisition on the front, where the N pieces of first image information are N image sets obtained by performing multi-angle acquisition on the pupils, and then a three-dimensional sitting posture model of the first user is constructed according to the N pieces of first image information, where the three-dimensional sitting posture model includes as many sitting postures of the pupils as possible.
Step S600: obtaining first sitting posture information of the first user according to the three-dimensional sitting posture model;
step S700: comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result;
step S800: and determining whether first reminding information is obtained or not according to the first comparison result, wherein the first reminding information is used for reminding the first user to adjust the sitting posture.
Specifically, the first sitting posture information is any sitting posture information of the first user selected from the three-dimensional sitting posture model, and the first sitting posture information is compared with the standard sitting posture information, that is, any sitting posture information of the pupils is compared with the standard sitting posture information, and the standard sitting posture of the pupils is as follows: the upper body has the same posture as a standing posture, and is upright on the head, flat on the shoulders, straight on the body, standing on the waist and straightening the chest. The lower body should be a chair or stool with the buttocks sitting on the chair or stool and the upper legs (i.e., thigh) lying naturally upright from the lower leg below the knees. Two feet are naturally placed on the ground, two arms are naturally stretched, the two arms are placed on the table top, and the right arm is placed on the table top. The first comparison result comprises two conditions, namely the sitting posture of the pupils is in accordance with the standard sitting posture, and the sitting posture of the pupils is not in accordance with the standard sitting posture, whether first reminding information is obtained or not is further determined according to the first comparison result, if the sitting posture of the pupils is not in accordance with the standard sitting posture, the pupils can be reminded to adjust the own sitting posture, a good sitting posture habit is formed, and a good foundation is laid for the growth and development of acquired bones and the correction of the acquired bones.
Further, as shown in fig. 2, the step S100 of training the neural network model by the federal learning method to obtain a third sitting posture preset model includes:
step S110: obtaining first base data of a first set of users of a first area, the first base data comprising first height information, first skeletal information;
step S120: constructing a first training data set according to the first height information and the first skeleton information;
step S130: obtaining second base data of a second set of users of a second area, the second base data comprising second height information, second skeletal information;
step S140: constructing a second training data set according to the second height information and the second skeleton information;
step S150: obtaining an initial sitting posture preset model from a third party platform;
step S160: training the initial sitting posture preset model through the first training data set to obtain a first sitting posture preset model;
step S170: training the initial sitting posture preset model through the second training data set to obtain a second sitting posture preset model;
step S180: obtaining a first model parameter according to the first sitting posture preset model, and obtaining a second model parameter according to the second sitting posture preset model;
step S190: and updating the initial sitting posture preset model according to the first model parameter and the second model parameter to obtain a third sitting posture preset model.
Specifically, when the neural network model is trained by the federal learning method, user data of different areas may be further collected, where the first area and the second area are two areas at different positions, the first user set may be understood as a set of pupils in the first area, the second user set may be understood as a set of pupils in the second area, the first basic data includes height information and bone growth and development information of the set of pupils in the first area, the second basic data includes height information and bone growth and development information of the set of pupils in the second area, the basic training data of the first training data set is constructed by the first basic data, the basic training data of the second training data set is constructed by the second basic data, and an initial sitting posture preset model is obtained from a third-party platform, the third-party platform may be understood as a virtual third party, the initial sitting posture preset model may be understood as a model inherent to the third-party platform, and then the initial sitting posture preset model is trained based on the first training data set and the second training data set, respectively, that is, the model is actually trained through actual basic training data, so that a first sitting posture preset model and a second sitting posture preset model may be obtained in sequence, wherein the first sitting posture preset model corresponds to the first user set, the second sitting posture preset model corresponds to the second user set, and further, based on the first sitting posture preset model, a gradient update model parameter of the first user set, that is, the first model parameter, and similarly, the second model parameter is a gradient update model parameter of the second user set, and finally, according to the first model parameter and the second model parameter, the initial sitting posture preset model is updated to obtain a third sitting posture preset model, and by adopting a transverse federal learning mode, height information and skeleton information of pupils in different areas are subjected to data acquisition and interactive updating, so that the obtained third sitting posture preset model is more accurate and comprehensive and has certain persuasiveness.
Further, as shown in fig. 3, the training of the initial sitting posture preset model through the first training data set is performed to obtain a first sitting posture preset model, and step S160 includes:
step S161: classifying the first training data set to obtain different classes of sub-training data sets;
step S162: respectively training the initial sitting posture preset model by utilizing the sub-training data sets of different categories to obtain a plurality of sub-initial sitting posture preset models;
step S163: obtaining a plurality of sub-model parameters according to the plurality of sub-initial sitting posture preset models;
step S164: and updating the initial sitting posture preset model through the plurality of sub-model parameters to obtain the first sitting posture preset model.
Specifically, when the initial sitting posture preset model is trained by the first training data set, more specifically, the first training data set may be classified to obtain sub-training data sets of different categories, and the first training data set is constructed by the first height information and the first skeleton information, so that the data in the first training data set may be classified, for example, according to the difference in height and the difference in skeleton development posture, the sub-training data sets may include classified data sets of different categories, may be a sub-training data set with a short height and a slow skeleton development, may be a sub-training data set with a moderate height and a normal skeleton development, may be a sub-training data set with a high height and a advanced skeleton development, and the initial sitting posture preset model may be trained by using the sub-training data sets of different categories, obtaining a plurality of sub-initial sitting posture preset models, wherein the plurality of sub-initial sitting posture preset models correspond to the sub-training data sets of different types one by one, further obtaining gradient updating model parameters corresponding to the plurality of sub-initial sitting posture preset models, namely the plurality of sub-model parameters, further updating the initial sitting posture preset models through the plurality of sub-model parameters, obtaining the first sitting posture preset model, and achieving the purpose of training the initial sitting posture preset models through the first training data set.
Further, as shown in fig. 4, the classifying the first training data set to obtain sub-training data sets of different categories, where the step S161 includes:
step S1611: obtaining an age characteristic and an interest characteristic of the first training data set;
step S1612: constructing a rectangular coordinate system, taking the age characteristics as horizontal coordinates, and taking the interest characteristics as vertical coordinates;
step S1613: performing regional labeling classification on the rectangular coordinate system to obtain a first label classification result;
step S1614: inputting the age characteristics and the interest characteristics of the first user set into the rectangular coordinate system to obtain a first vector set;
step S1615: performing distance calculation on the first vector set to obtain an Euclidean distance data set;
step S1616: obtaining a first classification data set according to the Euclidean distance data set, wherein the first classification data set is the shortest k distances in the Euclidean distance data set;
step S1617: mapping and matching are carried out according to the first classification data set and the first label classification result, and a first classification result is obtained;
step S1618: and obtaining the sub-training data sets of different categories according to the first classification result.
Specifically, when the first training data set is classified, more specifically, the age characteristics and interest characteristics of the first training data set can be obtained, and the bone development situation of the pupils can be influenced to a certain extent due to the age characteristics and interest characteristics of the pupils, so that the sitting posture of the pupils can be influenced. And performing regional labeling classification on the rectangular coordinate system, wherein different regions correspond to different label classification results, and for example, different regions correspond to different sitting postures of pupils. Inputting the age characteristics and the interest characteristics of the first user set into the rectangular coordinate system to obtain a first vector set, and performing mapping matching on the first label classification result according to the first vector set to obtain the sitting posture information of the pupils matched with the first vector set.
The Euclidean distance data set is an Euclidean distance measurement data set, namely a straight-line distance between two points in a coordinate system, and the distance of the first vector set is calculated to obtain the Euclidean distance data set. The first classification data set is the shortest k distances in the Euclidean distance data set, and the k value is a part of the Euclidean distance data set and can be set by self. And performing mapping matching according to the first classification data set and the first label classification result to obtain a first classification result, and obtaining the sub-training data sets of different classes according to the first classification result. The method for performing vector mapping by constructing the rectangular coordinate system is achieved, so that scheme classification results are more accurate, and the technical effect that classification of the sub-training data sets of different types is more definite is ensured.
Further, the step S300 of inputting the height information and the bone information into the third sitting posture preset model to obtain the standard sitting posture information of the first user further includes:
step S310: inputting the height information and the skeleton information as input information into the third sitting posture preset model;
step S320: the third sitting posture preset model is obtained by training a plurality of groups of training data until convergence, wherein each group of data in the plurality of groups of training data comprises the height information, the skeleton information and identification information for identifying a standard sitting posture;
step S330: and obtaining output information of the third sitting posture preset model, wherein the output information comprises standard sitting posture information of the first user.
Specifically, in order to input the height information and the skeletal information into the third sitting posture preset model, more specifically, the third sitting posture preset model is a Neural network model in machine learning, a Neural Network (NN) is a complex Neural network system formed by widely connecting a large number of simple processing units (called neurons), which reflects many basic features of human brain functions, and is a highly complex nonlinear dynamical learning system. Neural network models are described based on mathematical models of neurons. Artificial Neural Networks (ANN), is a description of the first-order properties of the human brain system. Briefly, it is a mathematical model. And through training of a large amount of training data, inputting the height information and the bone information as input information into the third sitting posture preset model, and outputting the standard sitting posture information of the first user.
Furthermore, the training process is essentially a supervised learning process, each group of supervised data comprises the height information, the bone information and identification information for identifying a standard sitting posture, the height information and the bone information are input into the third sitting posture preset model as input information, the neural network model is continuously self-corrected and adjusted according to the identification information for identifying the standard sitting posture, and the group of supervised learning is ended and the next group of data supervised learning is carried out until the obtained output information is consistent with the identification information; and when the output information of the neural network model reaches the preset accuracy rate/reaches the convergence state, finishing the supervised learning process. Through the supervised learning of the neural network model, the neural network model can process the input information more accurately, the output standard sitting posture information of the first user is more reasonable and accurate, and the technical effect of correcting the sitting posture of the pupils based on the standard sitting posture information is achieved.
Further, the comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result, and step S700 includes:
step S710: obtaining a predetermined error threshold;
step S720: obtaining the error amount of the first sitting posture information and the standard sitting posture information according to the first sitting posture information and the standard sitting posture information;
step S730: and judging whether the error amount is within the preset error threshold value or not, and obtaining the first comparison result.
Specifically, when the first sitting posture information is compared with the standard sitting posture information, more specifically, a predetermined error threshold may be obtained, where the predetermined error threshold is acceptable error information between an actual sitting posture of the pupils and a standard sitting posture set by the system, and further, an error amount between the first sitting posture information and the standard sitting posture information is obtained according to the first sitting posture information and the standard sitting posture information, where the error amount is actual error information between the actual sitting posture of the pupils and the standard sitting posture, and whether the sitting posture of the pupils is standard is determined by determining whether the error amount is within the predetermined error threshold, that is, the first comparison result includes two cases, one case is that the error amount is within the predetermined error threshold, indicates that the sitting posture of the pupils is more standard, and the other case is not standard, for example, the arm of the pupil can be placed flat on a desk, and is suitable for listening to and speaking in class, and can also be slightly lifted for reading aloud, so that the arm can be placed flat on a desktop, and can also be slightly lifted, the change is included in the preset error threshold, and the standard sitting posture of the pupil is further defined by comparing the actual error with the preset error threshold.
Further, the embodiment of the present application further includes:
step S711: obtaining learning duration historical data of the first user;
step S712: predicting a first learning duration of the first user according to a Markov characteristic;
step S713: obtaining a first sitting posture error adjustment parameter according to the first learning duration;
step S714: and adjusting the preset error threshold value according to the first sitting posture error adjusting parameter.
Specifically, upon obtaining the predetermined error threshold, further, learning duration history data of the first user may be obtained, the learning duration history data being accumulated from different learning duration distribution data of pupils, and at the same time, the first learning duration of the first user is predicted based on a markov characteristic, wherein the markov characteristic is understood that, given a present state and all past states of a random process, a conditional probability distribution of a future state thereof depends only on the present state; in other words, given a present state, which is conditionally independent from a past state (i.e., a historical path of the process), based on the markov characteristic, a mapping relationship between the current sitting posture information of the pupils and the learning duration at the previous time can be obtained, and therefore, based on the learning duration history data, the learning duration of the most recent pupils can be obtained, and further based on this, a first learning duration of the first user can be predicted, which can be understood as the learning duration of the pupils at a future time, and further based on the mapping relationship that has been determined, preset sitting posture information of the pupils corresponding to the first learning duration can be obtained in reverse, and the first sitting posture error adjustment parameter is an adjustable sitting posture error parameter between the current sitting posture information of the pupils and the preset sitting posture information, and further based on the first sitting posture error adjustment parameter, and the preset error threshold is adjusted, so that the adjusted preset error threshold is more scientific, and the sitting posture information of the pupils can be further grasped and corrected.
Compared with the prior art, the invention has the following beneficial effects:
1. training the neural network model by a federal learning method to obtain a third sitting posture preset model; obtaining height information and skeleton information of a first user; inputting the height information and the skeleton information into the third sitting posture preset model to obtain standard sitting posture information of the first user; acquiring multi-angle images of the first user through the image acquisition device to obtain N pieces of first image information; constructing a three-dimensional sitting posture model of the first user; obtaining first sitting posture information of the first user; comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result; and determining whether first reminding information is obtained or not according to the first comparison result. Through federal study, generate pupil's standard position of sitting information, and then compare pupil's actual position of sitting information and standard position of sitting information, remind the position of sitting of nonstandard, reached and carried out intelligent image monitoring to pupil's position of sitting, in time remind and effectively adjust nonstandard position of sitting simultaneously for form good position of sitting custom, lay the technological effect of good basis for the bone growth and development of acquired and correction thereof.
2. Based on Markov characteristics, the sitting posture error of the pupils can be scientifically adjusted, so that the adjustment parameters have certain scientificity and persuasiveness.
Example two
Based on the same inventive concept as the intelligent sitting posture reminding method in the foregoing embodiment, the present invention further provides an intelligent sitting posture reminding system, as shown in fig. 5, the system includes:
the first obtaining unit 11: the first obtaining unit 11 is configured to train a neural network model through a federal learning method to obtain a third sitting posture preset model;
the second obtaining unit 12: the second obtaining unit 12 is configured to obtain height information and bone information of the first user;
first input unit 13: the first input unit 13 is configured to input the height information and the bone information into the third sitting posture preset model, so as to obtain standard sitting posture information of the first user;
the first acquisition unit 14: the first collecting unit 14 is configured to perform multi-angle image collection on the first user through an image collecting device to obtain N pieces of first image information, where the first image information includes sitting posture image information of the first user;
the first building element 15: the first constructing unit 15 is configured to construct a three-dimensional sitting posture model of the first user according to the N pieces of first image information;
the third obtaining unit 16: the third obtaining unit 16 is configured to obtain first sitting posture information of the first user according to the three-dimensional sitting posture model;
first comparison unit 17: the first comparison unit 17 is configured to compare the first sitting posture information with the standard sitting posture information to obtain a first comparison result;
the first determination unit 18: the first determining unit 18 is configured to determine whether to obtain first reminding information according to the first comparison result, where the first reminding information is used to remind the first user of adjusting the sitting posture.
Further, the system further comprises:
a fourth obtaining unit: the fourth obtaining unit is configured to obtain first basic data of a first user set of a first area, where the first basic data includes first height information and first skeleton information;
a second building element: the second construction unit is used for constructing a first training data set according to the first height information and the first skeleton information;
a fifth obtaining unit: the fifth obtaining unit is configured to obtain second basic data of a second user set of a second area, where the second basic data includes second height information and second bone information;
a third construction unit: the third construction unit is used for constructing a second training data set according to the second height information and the second skeleton information;
a sixth obtaining unit: the sixth obtaining unit is used for obtaining an initial sitting posture preset model from a third-party platform;
a seventh obtaining unit: the seventh obtaining unit is configured to train the initial sitting posture preset model through the first training data set to obtain a first sitting posture preset model;
an eighth obtaining unit: the eighth obtaining unit is configured to train the initial sitting posture preset model through the second training data set to obtain a second sitting posture preset model;
a ninth obtaining unit: the ninth obtaining unit is used for obtaining a first model parameter according to the first sitting posture preset model;
a tenth obtaining unit: the tenth obtaining unit is used for obtaining a second model parameter according to the second sitting posture preset model;
a first update unit: the first updating unit is used for updating the initial sitting posture preset model according to the first model parameter and the second model parameter to obtain a third sitting posture preset model.
Further, the system further comprises:
a first classification unit: the first classification unit is used for classifying the first training data set to obtain sub-training data sets of different classes;
an eleventh obtaining unit: the eleventh obtaining unit is configured to train the initial sitting posture preset model by using the sub-training data sets of different categories, respectively, to obtain a plurality of sub-initial sitting posture preset models;
a twelfth obtaining unit: the twelfth obtaining unit is used for obtaining a plurality of sub-model parameters according to the plurality of sub-initial sitting posture preset models;
a second updating unit: the second updating unit is used for updating the initial sitting posture preset model through the plurality of sub-model parameters to obtain the first sitting posture preset model.
Further, the system further comprises:
a thirteenth obtaining unit: the thirteenth obtaining unit is configured to obtain an age feature and an interest feature of the first training data set;
a fourth construction unit: the fourth construction unit is used for constructing a rectangular coordinate system, the age characteristic is used as an abscissa, and the interest characteristic is used as an ordinate;
a second classification unit: the second classification unit is used for performing regional labeling classification on the rectangular coordinate system to obtain a first label classification result;
a second input unit: the second input unit is used for inputting the age characteristics and the interest characteristics of the first user set into the rectangular coordinate system to obtain a first vector set;
a fourteenth obtaining unit: the fourteenth obtaining unit is configured to perform distance calculation on the first vector set to obtain a euclidean distance data set;
a fifteenth obtaining unit: the fifteenth obtaining unit is configured to obtain a first classified data set according to the euclidean distance data set, where the first classified data set is the shortest k distances in the euclidean distance data set;
a sixteenth obtaining unit: the sixteenth obtaining unit is configured to perform mapping matching according to the first classification data set and the first label classification result to obtain a first classification result;
a seventeenth obtaining unit: the seventeenth obtaining unit is configured to obtain the sub-training data sets of different categories according to the first classification result.
Further, the system further comprises:
a third input unit: the third input unit is used for inputting the height information and the skeleton information as input information into the third sitting posture preset model;
a first training unit: the first training unit is used for training the third sitting posture preset model to convergence through multiple groups of training data to obtain the third sitting posture preset model, wherein each group of data in the multiple groups of training data comprises the height information, the bone information and identification information for identifying a standard sitting posture;
an eighteenth obtaining unit: the eighteenth obtaining unit is configured to obtain output information of the third sitting posture preset model, where the output information includes standard sitting posture information of the first user.
Further, the system further comprises:
a nineteenth obtaining unit: the nineteenth obtaining unit is used for obtaining a predetermined error threshold value;
a twentieth obtaining unit: the twentieth obtaining unit is used for obtaining the error amount of the first sitting posture information and the standard sitting posture information according to the first sitting posture information and the standard sitting posture information;
a first judgment unit: the first judging unit is used for judging whether the error amount is within the preset error threshold value or not and obtaining the first comparison result.
Further, the system further comprises:
a twenty-first obtaining unit: the twenty-first obtaining unit is configured to obtain learning duration history data of the first user;
a first prediction unit: the first prediction unit is used for predicting a first learning duration of the first user according to Markov characteristics;
a twenty-second obtaining unit: the twenty-second obtaining unit is used for obtaining a first sitting posture error adjusting parameter according to the first learning duration;
a first adjustment unit: the first adjusting unit is used for adjusting the preset error threshold according to the first sitting posture error adjusting parameter.
Various changes and specific examples of the intelligent sitting posture reminding method in the first embodiment of fig. 1 are also applicable to the intelligent sitting posture reminding system in the present embodiment, and through the foregoing detailed description of the intelligent sitting posture reminding method, those skilled in the art can clearly know the implementation method of the intelligent sitting posture reminding system in the present embodiment, so for the sake of brevity of the description, detailed description is not repeated again.
EXAMPLE III
The electronic apparatus of the embodiment of the present application is described below with reference to fig. 6.
Fig. 6 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the intelligent sitting posture reminding method in the embodiment, the invention also provides an intelligent sitting posture reminding system, wherein a computer program is stored on the intelligent sitting posture reminding system, and the computer program is used for realizing the steps of any method of the intelligent sitting posture reminding system when being executed by a processor.
Where in fig. 6 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium. The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The embodiment of the application provides an intelligent sitting posture reminding method, wherein the method is applied to an intelligent sitting posture reminding system, the system comprises an image acquisition device, and the method comprises the following steps: training the neural network model by a federal learning method to obtain a third sitting posture preset model; obtaining height information and skeleton information of a first user; inputting the height information and the skeleton information into the third sitting posture preset model to obtain standard sitting posture information of the first user; acquiring multi-angle images of the first user through the image acquisition device to obtain N pieces of first image information, wherein the first image information comprises sitting posture image information of the first user; constructing a three-dimensional sitting posture model of the first user according to the N pieces of first image information; obtaining first sitting posture information of the first user according to the three-dimensional sitting posture model; comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result; and determining whether first reminding information is obtained or not according to the first comparison result, wherein the first reminding information is used for reminding the first user to adjust the sitting posture.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (7)
1. An intelligent sitting posture reminding method is applied to an intelligent sitting posture reminding system, the system comprises an image acquisition device, and the method comprises the following steps:
training the neural network model through a federal learning method to obtain a third sitting posture preset model;
obtaining height information and skeleton information of a first user;
inputting the height information and the skeleton information into the third sitting posture preset model to obtain standard sitting posture information of the first user;
acquiring multi-angle images of the first user through the image acquisition device to obtain N pieces of first image information, wherein the first image information comprises sitting posture image information of the first user;
constructing a three-dimensional sitting posture model of the first user according to the N pieces of first image information;
obtaining first sitting posture information of the first user according to the three-dimensional sitting posture model;
comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result;
determining whether first reminding information is obtained or not according to the first comparison result, wherein the first reminding information is used for reminding the first user to adjust the sitting posture;
the method comprises the following steps of training a neural network model through a federal learning method to obtain a third sitting posture preset model, and comprises the following steps:
obtaining first base data of a first set of users of a first area, the first base data comprising first height information, first skeletal information;
constructing a first training data set according to the first height information and the first skeleton information;
obtaining second base data of a second set of users of a second area, the second base data comprising second height information and second bone information;
constructing a second training data set according to the second height information and the second skeleton information;
obtaining an initial sitting posture preset model from a third party platform;
training the initial sitting posture preset model through the first training data set to obtain a first sitting posture preset model;
training the initial sitting posture preset model through the second training data set to obtain a second sitting posture preset model;
obtaining a first model parameter according to the first sitting posture preset model, and obtaining a second model parameter according to the second sitting posture preset model;
updating the initial sitting posture preset model according to the first model parameter and the second model parameter to obtain a third sitting posture preset model;
through the first training data set is right initial position of sitting preset model trains, obtains first position of sitting preset model, includes:
classifying the first training data set to obtain different classes of sub-training data sets;
respectively training the initial sitting posture preset model by utilizing the sub-training data sets of different categories to obtain a plurality of sub-initial sitting posture preset models;
obtaining a plurality of sub-model parameters according to the plurality of sub-initial sitting posture preset models;
and updating the initial sitting posture preset model through the plurality of sub-model parameters to obtain the first sitting posture preset model.
2. The method of claim 1, wherein said classifying the first training data set to obtain different classes of sub-training data sets comprises:
obtaining an age characteristic and an interest characteristic of the first training data set;
constructing a rectangular coordinate system, taking the age characteristics as horizontal coordinates, and taking the interest characteristics as vertical coordinates;
performing regional labeling classification on the rectangular coordinate system to obtain a first label classification result;
inputting the age characteristics and the interest characteristics of the first user set into the rectangular coordinate system to obtain a first vector set;
performing distance calculation on the first vector set to obtain an Euclidean distance data set;
obtaining a first classification data set according to the Euclidean distance data set, wherein the first classification data set is the shortest k distances in the Euclidean distance data set;
mapping and matching are carried out according to the first classification data set and the first label classification result, and a first classification result is obtained;
and obtaining the sub-training data sets of different categories according to the first classification result.
3. The method of claim 1, wherein said entering said height information and said skeletal information into said third sitting position preset model, obtaining standard sitting position information for said first user, comprises:
inputting the height information and the skeleton information as input information into the third sitting posture preset model;
the third sitting posture preset model is obtained by training a plurality of groups of training data to convergence, wherein each group of data in the plurality of groups of training data comprises the height information, the skeleton information and identification information for identifying a standard sitting posture;
and obtaining output information of the third sitting posture preset model, wherein the output information comprises standard sitting posture information of the first user.
4. The method of claim 1, wherein the comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result comprises:
obtaining a predetermined error threshold;
obtaining the error amount of the first sitting posture information and the standard sitting posture information according to the first sitting posture information and the standard sitting posture information;
and judging whether the error amount is within the preset error threshold value or not, and obtaining the first comparison result.
5. The method of claim 4, wherein the method further comprises:
obtaining learning duration historical data of the first user;
predicting a first learning duration of the first user according to a Markov characteristic;
obtaining a first sitting posture error adjustment parameter according to the first learning duration;
and adjusting the preset error threshold value according to the first sitting posture error adjusting parameter.
6. An intelligent sitting posture reminding system, wherein the system comprises:
a first obtaining unit: the first obtaining unit is used for training the neural network model through a federal learning method to obtain a third sitting posture preset model;
a second obtaining unit: the second obtaining unit is used for obtaining height information and skeleton information of the first user;
a first input unit: the first input unit is used for inputting the height information and the skeleton information into the third sitting posture preset model to obtain standard sitting posture information of the first user;
a first acquisition unit: the first acquisition unit is used for acquiring multi-angle images of the first user through an image acquisition device to obtain N pieces of first image information, wherein the first image information comprises sitting posture image information of the first user;
a first building element: the first construction unit is used for constructing a three-dimensional sitting posture model of the first user according to the N pieces of first image information;
a third obtaining unit: the third obtaining unit is used for obtaining first sitting posture information of the first user according to the three-dimensional sitting posture model;
a first comparison unit: the first comparison unit is used for comparing the first sitting posture information with the standard sitting posture information to obtain a first comparison result;
a first determination unit: the first determining unit is used for determining whether first reminding information is obtained or not according to the first comparison result, wherein the first reminding information is used for reminding the first user to adjust the sitting posture;
the first obtaining unit is used for training a neural network model through a federal learning method to obtain a third sitting posture preset model, and the obtaining method comprises the following steps:
a fourth obtaining unit: the fourth obtaining unit is configured to obtain first basic data of a first user set of a first area, where the first basic data includes first height information and first skeleton information;
a second building element: the second construction unit is used for constructing a first training data set according to the first height information and the first skeleton information;
a fifth obtaining unit: the fifth obtaining unit is configured to obtain second basic data of a second user set of a second area, where the second basic data includes second height information and second skeleton information;
a third building element: the third construction unit is used for constructing a second training data set according to the second height information and the second skeleton information;
a sixth obtaining unit: the sixth obtaining unit is used for obtaining an initial sitting posture preset model from a third-party platform;
a seventh obtaining unit: the seventh obtaining unit is configured to train the initial sitting posture preset model through the first training data set to obtain a first sitting posture preset model;
an eighth obtaining unit: the eighth obtaining unit is configured to train the initial sitting posture preset model through the second training data set to obtain a second sitting posture preset model;
a ninth obtaining unit: the ninth obtaining unit is used for obtaining a first model parameter according to the first sitting posture preset model;
a tenth obtaining unit: the tenth obtaining unit is used for obtaining a second model parameter according to the second sitting posture preset model;
a first update unit: the first updating unit is used for updating the initial sitting posture preset model according to the first model parameter and the second model parameter to obtain a third sitting posture preset model;
the seventh obtaining unit is configured to train the initial sitting posture preset model through the first training data set, obtain a first sitting posture preset model, and includes:
a first classification unit: the first classification unit is used for classifying the first training data set to obtain sub-training data sets of different classes;
an eleventh obtaining unit: the eleventh obtaining unit is configured to train the initial sitting posture preset model by using the different types of sub-training data sets, respectively, to obtain a plurality of sub-initial sitting posture preset models;
a twelfth obtaining unit: the twelfth obtaining unit is used for obtaining a plurality of sub-model parameters according to the plurality of sub-initial sitting posture preset models;
a second updating unit: the second updating unit is used for updating the initial sitting posture preset model through the plurality of sub-model parameters to obtain the first sitting posture preset model.
7. An intelligent sitting posture reminder system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1-5 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111181174.9A CN113936335B (en) | 2021-10-11 | 2021-10-11 | Intelligent sitting posture reminding method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111181174.9A CN113936335B (en) | 2021-10-11 | 2021-10-11 | Intelligent sitting posture reminding method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113936335A CN113936335A (en) | 2022-01-14 |
| CN113936335B true CN113936335B (en) | 2022-08-23 |
Family
ID=79278165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111181174.9A Active CN113936335B (en) | 2021-10-11 | 2021-10-11 | Intelligent sitting posture reminding method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113936335B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114572068A (en) * | 2022-01-28 | 2022-06-03 | 中国第一汽车股份有限公司 | Electric seat adjusting method and device based on convolutional neural network and vehicle |
| CN117441190A (en) * | 2022-05-17 | 2024-01-23 | 华为技术有限公司 | Position positioning method and device |
| CN116092129B (en) * | 2023-04-06 | 2023-06-16 | 合肥工业大学 | Intelligent bookshelf and control method thereof |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5820366B2 (en) * | 2010-10-08 | 2015-11-24 | パナソニック株式会社 | Posture estimation apparatus and posture estimation method |
| KR102575147B1 (en) * | 2018-04-25 | 2023-09-06 | 현대자동차주식회사 | Apparatus and Method for notifying correction of posture |
| CN111881886A (en) * | 2020-08-21 | 2020-11-03 | 董秀园 | Intelligent seat control method and device based on posture recognition |
| CN112016497A (en) * | 2020-09-04 | 2020-12-01 | 王海 | Single-view Taijiquan action analysis and assessment system based on artificial intelligence |
| CN113128031A (en) * | 2021-03-27 | 2021-07-16 | 南京林业大学 | Measuring device and evaluation method for comfort level of seat |
| CN113052097A (en) * | 2021-03-31 | 2021-06-29 | 开放智能机器（上海）有限公司 | Human body sitting posture real-time monitoring system and monitoring method |
-
2021
- 2021-10-11 CN CN202111181174.9A patent/CN113936335B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113936335A (en) | 2022-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113936335B (en) | Intelligent sitting posture reminding method and device | |
| CN109102857B (en) | Intelligent limb rehabilitation training system and method | |
| Cang et al. | An intelligent pig weights estimate method based on deep learning in sow stall environments | |
| CN105069423A (en) | Human body posture detection method and device | |
| WO2021217848A1 (en) | Human body falling detection method and apparatus, and computer device and storage medium | |
| CN111341450B (en) | Artificial intelligence-based spine deformity correction prediction method, device and terminal | |
| US20220262036A1 (en) | Computer-implemented method, data processing apparatus, and computer program for generating three-dimensional pose-estimation data | |
| CN109829971B (en) | Method and device for creating human body virtual model | |
| CN109145868A (en) | A kind of Activity recognition method and apparatus assisting running training | |
| CN114098284B (en) | Height adjusting method for infrared induction height and learning table | |
| Ebrahimi et al. | Effects of anthropomorphic fidelity of self-avatars on reach boundary estimation in immersive virtual environments | |
| JP2019191974A (en) | Information processing device, information processing program, and information processing method | |
| CN110838179B (en) | Human body modeling method and device based on body measurement data and electronic equipment | |
| CN108426349B (en) | Air conditioner personalized health management method based on complex network and image recognition | |
| CN110222734B (en) | Bayesian network learning method, intelligent device and storage device | |
| CN112148758A (en) | Community diet health management method and system based on big data | |
| CN109948569B (en) | Three-dimensional mixed expression recognition method using particle filter framework | |
| Guo et al. | System identification approaches for energy intake estimation: Enhancing interventions for managing gestational weight gain | |
| CN111695614A (en) | Dynamic monitoring sensor layout and multi-source information fusion method and system | |
| CN117224115A (en) | Method and system for measuring ratio of long bones of limbs to height of human body based on image | |
| Chen et al. | Media adaptation framework in biofeedback system for stroke patient rehabilitation | |
| US20220023717A1 (en) | Matching system, matching method, and matching program | |
| CN105354665A (en) | Physician performance evaluation method in better accordance with patient demands in mobile medical system | |
| Zhu et al. | Research and Implementation of Intelligent Learning Desk Based on Visio Sensor in AI IoT Environments for Smart Education. | |
| CN113505637A (en) | Real-time virtual anchor motion capture method and system for live streaming |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |