Multi-dimensional exercise prescription making system based on cloud computing

Abstract

The invention discloses a multi-dimensional exercise prescription making system based on cloud computing. And finding the sequence of a plurality of motion mode categories conforming to the user information to obtain a plurality of two-dimensional motion connected graphs. The motion connected graphs which are similar in motion mode category sequence and frequently appear are found out in the multiple motion connected graphs. A plurality of paths in a graph structure are represented by adopting a motion connected graph, so that a plurality of sequential connection modes of a plurality of motion mode categories are represented. And traversing the motion connected graph to obtain a plurality of motion mode routes after the user information is considered. And constructing a three-dimensional motion parameter point diagram by taking the motion mode category as an abscissa and taking the corresponding motion human body information before and after the motion of the user as an ordinate. And detecting the three-dimensional change characteristics of the motion parameter point diagram by using a 2 * 2 * 2 three-dimensional convolution kernel. And adopting the second motion convolutional network to detect the characteristics of the change of the motion human body information corresponding to one motion mode category.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a multi-dimensional exercise prescription formulation system based on cloud computing. Background Art

[0002] At present, the correct way of exercising can change the user's physical condition, making the human body healthier during exercise. However, the current method of specifying exercise prescriptions generally directly uses multi-dimensional information to divide users and build user portraits to give the corresponding exercise category ranking, or directly uses deep learning to make judgments. The user's heart rate data during exercise is collected through smart wearable devices, and the obtained GPS data is converted into the user's speed information. However, the data obtained are all unsupervised, multimodal time series data. It is very necessary to analyze the characteristics of the time series data to obtain the user's athletic ability and recommend exercise prescriptions suitable for the user's own ability. Summary of the invention

[0003] The purpose of the present invention is to provide a multi-dimensional exercise prescription formulation system based on cloud computing to solve the above-mentioned problems existing in the prior art.

[0004] The embodiment of the present invention provides a multi-dimensional exercise prescription formulation system based on cloud computing, including: A monitoring module, for obtaining multi-dimensional user information, exercise body information and exercise mode categories; the user information represents body information that does not change with exercise; the exercise body information includes a plurality of post-exercise body sign values ​​and corresponding pre-exercise body sign values; the post-exercise body sign values ​​represent the values ​​of body signs before exercise; the post-exercise body sign values ​​represent the values ​​of body signs after exercise; The processor is used to process the following method: Based on the user information and the exercise mode category, find the sequence that matches the user's exercise mode category to obtain an exercise connectivity graph; Based on the motion connectivity graph, a basic motion mode set is obtained by traversing; the basic motion mode set includes a plurality of motion mode routes; the motion mode routes represent the order of the motion mode categories that meet the user information; Through the movement mode prediction network, based on the moving human body information, the basic movement mode set and the movement mode category, the changes in the user's physical signs during exercise are judged to obtain an exercise prescription; the exercise prescription represents the order of the movement mode categories suitable for the user's physical signs.

[0005] Optionally, the step of determining changes in physical signs of the user during exercise based on the moving human body information, the basic movement pattern set and the movement pattern category through the movement pattern prediction network to obtain an exercise prescription includes: Based on the information of the moving human body and the categories of the movement mode, a relationship between multiple categories of movement mode is constructed to obtain a movement parameter point diagram; the movement parameter point diagram represents the changes in the physical signs of the human body before and after the movement corresponding to the movement mode category; Based on the motion parameter point graph, the relationship between the motion mode categories is judged through the motion mode prediction network to obtain multiple motion influence sequences; Find the exercise route corresponding to the order of exercise impact in the basic exercise method set and get the exercise prescription.

[0006] Optionally, the motion mode prediction network includes a first motion convolutional network, a second motion convolutional network and a third motion network.

[0007] Optionally, the determining the relationship between the movement mode categories based on the movement parameter point graph through a movement mode prediction network to obtain the movement influence order includes: Inputting the motion parameter point graph into a first motion convolutional network to determine the motion state of the user and obtain a first feature graph; The number of the movement mode categories is used as the number of movement mode categories; The segmentation length is obtained by dividing the horizontal coordinate corresponding to the lower right corner of the motion parameter point diagram by the number of motion mode categories; On the horizontal axis, the point with the distance to the division length is taken as the division point; According to the segmentation points, the motion parameter point map is segmented to obtain a plurality of first motion parameter segmentation maps; The plurality of first motion parameter segmentation images are kept unchanged in length and superimposed in width to obtain a superimposed image; Inputting the superimposed image into a second motion convolutional network to obtain a second feature map; The first feature map and the second feature map are input into a third motion network to obtain a motion influence sequence.

[0008] Optionally, the convolution kernel of the first motion convolution network is a three-dimensional convolution kernel of 2*2*2, and the convolution kernel of the second motion convolution network is a three-dimensional convolution kernel with a width equal to the length of the motion parameter point map, a height of 2, and a depth equal to the number of pages of the motion parameter point map.

[0009] Optionally, the finding, based on the user information and the exercise mode category, a sequence matching the user's exercise mode category to obtain an exercise connectivity graph includes: Based on the user information, a plurality of user motion connectivity graphs are obtained through a user prediction network; the user motion connectivity graphs use motion mode categories as vertices; Based on multiple user motion connectivity graphs, similarities are determined and a motion connectivity graph is obtained.

[0010] Optionally, the determining similarity based on multiple user motion connectivity graphs to obtain the motion connectivity graph includes: Input two user motion connectivity graphs into the similarity discrimination network to judge the similarity of the two user motion connectivity graphs and obtain motion similarity values; corresponding to p user motion connectivity graphs, (p-1)*p / 2 motion similarity values ​​are obtained; Obtaining a motion similarity value that is smaller than other motion similarity values ​​among (p-1)*p / 2 motion similarity values ​​as the first similarity cluster center; Obtaining a similarity gap value; the similarity gap value represents a fixed value from the first similarity cluster center; The sum of the first similar cluster center and the similarity gap value is used as the gap threshold; Constructing a motion similarity set from motion similarity values ​​that are smaller than a gap threshold among the multiple motion similarity values; The user motion connectivity graph corresponding to the motion similarity set is used as a similar motion connectivity graph; A similar motion connectivity graph is randomly obtained from multiple similar motion connectivity graphs as a motion connectivity graph.

[0011] Optionally, the basic motion mode set is obtained by traversing the motion connectivity graph, including: Obtaining m motion initial values; the motion initial values ​​represent m motion mode categories in the motion connectivity graph; According to the initial movement value, the movement order of the movement mode category is traversed to obtain n movement mode routes; m movement initial values ​​correspond to m*n movement mode routes; The m*n movement mode routes constitute a basic movement mode set.

[0012] Optionally, the relationship between multiple movement mode categories is constructed based on the moving human body information and the movement mode category to obtain a movement parameter point diagram, including: Acquire a blank image; the blank image is a binary image; The horizontal axis of the blank image represents multiple categories of motion patterns; the vertical axis of the blank image represents a value that can reflect the change value of all motion signs; According to the blank image, a coordinate axis is constructed; the lower left corner of the blank image is used as the origin, the length of the blank image is used as the horizontal coordinate, and the width of the blank image is used as the vertical coordinate; Subtract the value of the body sign before exercise from the value of the body sign after exercise to obtain the value of the change of the body sign; The sports sign change values ​​corresponding to the multiple sports mode categories are punctuated in the blank image to obtain a two-dimensional sports parameter point map; multiple post-exercise human body sign values ​​and the corresponding pre-exercise human body sign values ​​are correspondingly obtained to obtain multiple two-dimensional sports parameter point maps; Multiple two-dimensional motion parameter point maps are superimposed to construct a three-dimensional image and obtain a motion parameter point map.

[0013] Optionally, a method for training a user prediction network includes: Acquire multiple training user information and corresponding multiple annotated user motion connectivity graphs; one training user information corresponds to multiple annotated user motion connectivity graphs; Inputting the training user information into a user prediction network to obtain a predicted user motion connectivity graph; The loss is calculated by comparing the predicted user motion connectivity graph with the labeled user motion connectivity graph to obtain a trained user prediction network.

[0014] Compared with the prior art, the embodiments of the present invention achieve the following beneficial effects: The embodiment of the present invention also provides a multi-dimensional exercise prescription formulation system based on cloud computing.

[0015] In the present invention, because different user information has different movement mode categories and corresponding movement sequences of movement mode categories. Find the order of multiple movement mode categories that meet the user information, represent them in a graph structure, and obtain multiple two-dimensional movement connectivity graphs. Find a movement connectivity graph in which the order of movement mode categories is similar and frequently appears in multiple movement connectivity graphs. Use the movement connectivity graph to represent multiple paths in the graph structure, thereby representing the connection mode of multiple order of multiple movement mode categories. The connection mode of complex movement mode categories is embodied by a connectivity graph constructed by 0 and 1, which is convenient for storage and calculation. Traverse the movement connectivity graph to obtain multiple movement mode routes after considering user information. Use the movement mode category as the horizontal coordinate and the corresponding movement human body information of a user before and after movement as the vertical coordinate to construct a three-dimensional movement parameter point graph. And use a 2*2*2 three-dimensional convolution kernel to detect the three-dimensional change characteristics of the movement parameter point graph. The second movement convolution network is used to detect the characteristics of the change of the movement human body information corresponding to a movement mode category. The technical effect of being able to more accurately obtain the changes in the user's human body information before and after exercise, thereby more accurately finding an exercise prescription that suits the user's physique and can meet the user's human body information before and after exercise. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1It is a method flow chart of a multi-dimensional exercise prescription formulation system based on cloud computing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The present invention will be described in detail below in conjunction with the accompanying drawings. Example

[0018] like Figure 1 As shown, an embodiment of the present invention provides a multi-dimensional exercise prescription formulation system based on cloud computing, the system comprising a monitoring module and a processor: A monitoring module, used to obtain multi-dimensional user information, exercise body information and exercise mode categories; the user information represents body information that does not change with exercise; the exercise body information includes a plurality of post-exercise body sign values ​​and corresponding pre-exercise body sign values; the post-exercise body sign values ​​represent the values ​​of body signs before exercise; the post-exercise body sign values ​​represent the values ​​of body signs after exercise; The post-exercise body sign value and the corresponding pre-exercise body sign value are separated by a fixed time length.

[0019] In this embodiment, the key-value pair is constructed with the moving body category as the key and the moving body information as the value.

[0020] In this embodiment, the user information includes age and gender.

[0021] Among them, in this embodiment, the human body information includes blood pressure, body temperature, pulse-heart rate, cardiac output, blood sugar, body temperature, body fat percentage, and skeletal muscle content.

[0022] For example, if the user suffers from obesity, it means that the body fat percentage is too high, and the amount of aerobic exercise training needs to be increased to reduce fat accumulation. If the user's skeletal muscle mass is low, strength training needs to be increased to improve muscle strength and endurance.

[0023] The processor is used to process the following method: S101: Based on the user information, determine the order of the categories of exercise modes adapted by the user, and obtain a movement connectivity graph; The graph structure in the data structure is constructed by using a plurality of optional motion modes as points and the order of motion mode categories as edges through graph theory. The motion connectivity graph is used to represent the edges in the graph structure, i.e., the order of motion mode categories.

[0024] The sports mode categories represent the categories of sports that can be performed, including swimming, jogging and other sports mode categories in this embodiment.

[0025] S102: Performing an image based on the connection graph, and obtaining a basic movement mode set by traversal; the basic movement mode set includes multiple movement mode routes; the movement mode routes represent the order of movement mode categories that meet user information.

[0026] S103: Detecting the user's exercise state through an exercise mode prediction network based on the exercise user information and a basic exercise mode set to obtain an exercise prescription; the exercise prescription represents the order of exercise mode categories suitable for the user's physical signs.

[0027] Optionally, the detecting the user's motion state through the motion mode prediction network based on the motion human body information and the basic motion mode set to obtain the motion prescription includes: Based on the moving human body information and the movement mode category, the relationship between multiple movement mode categories is constructed to obtain a movement parameter point diagram; the movement parameter point diagram represents the changes in the physical signs of the human body before and after exercise corresponding to the movement mode category.

[0028] Based on the motion parameter point graph, the relationship between the motion mode categories is judged through the motion mode prediction network to obtain multiple motion influence sequences.

[0029] Find the exercise route corresponding to the order of exercise impact in the basic exercise method set and get the exercise prescription.

[0030] Optionally, the motion mode prediction network includes a first motion convolutional network, a second motion convolutional network and a third motion network.

[0031] In this embodiment, the first motion convolutional network is a yolov5 model, the second motion convolutional network is a convolutional neural network (CNN), and the third motion network is a fully-connected neural network (FCNN).

[0032] Optionally, the determining the relationship between the movement mode categories based on the movement parameter point graph through a movement mode prediction network to obtain the movement influence order includes: The motion parameter point map is input into a first motion convolutional network to determine the motion state of the user and obtain a first feature map.

[0033] Among them, the trained first motion convolutional network represents the ranking of the corresponding motion categories of the user under multiple historical data.

[0034] The number of the movement type categories is used as the number of movement type categories.

[0035] Among them, in this embodiment, the number of exercise type categories is 16 exercise type categories.

[0036] The segmentation length is obtained by dividing the horizontal coordinate corresponding to the lower right corner of the motion parameter point diagram by the number of motion mode categories; On the horizontal axis, the point with a distance of the division length is used as the division point.

[0037] In this embodiment, if the segmentation length is 32, the positions corresponding to 32, 64, 96, 128 ... 480, 512 in the horizontal coordinate are used as segmentation points.

[0038] The motion parameter point map is segmented according to the segmentation points to obtain a plurality of first motion parameter segmentation maps.

[0039] In this embodiment, the length of the first motion parameter segmentation map is 32, the width is equal to the width of the motion parameter point map, and the number of pages is equal to the number of pages of the motion parameter point map.

[0040] The plurality of first motion parameter segmentation images are kept unchanged in length and are superimposed in width to obtain a superimposed image.

[0041] The plurality of first motion parameter segmentation maps are superimposed in sequence from small to large segmentation points.

[0042] In this embodiment, the total number of the first motion parameter segmentation maps is used as the segmentation number. The length of the superimposed image is equal to 32, the width is equal to the product of the width of the first motion parameter segmentation map and the segmentation number, and the number of pages is equal to the number of pages of the first motion parameter segmentation map.

[0043] Inputting the superimposed image into a second motion convolutional network to obtain a second feature map; The first feature map and the second feature map are input into a third motion network to obtain a motion influence sequence.

[0044] Optionally, the convolution kernel of the first motion convolution network is a three-dimensional convolution kernel of 2*2*2, and the convolution kernel of the second motion convolution network is a three-dimensional convolution kernel with a width equal to the length of the motion parameter point map, a height of 2, and a depth equal to the number of pages of the motion parameter point map.

[0045] Among them, the first motion convolution network is used to detect the three-dimensional change characteristics of the motion parameter point map, and the second motion convolution network is used to detect the change characteristics of the moving human body information corresponding to a motion mode category.

[0046] Optionally, the finding, based on the user information and the exercise mode category, a sequence matching the user's exercise mode category to obtain an exercise connectivity graph includes: Based on the user information, a plurality of user motion connectivity graphs are obtained through a user prediction network; the user motion connectivity graphs use motion mode categories as vertices; The user movement connectivity graph is a representation of a graph structure.

[0047] Based on multiple user motion connectivity graphs, similarities are determined and a motion connectivity graph is obtained.

[0048] Optionally, the determining similarity based on multiple user motion connectivity graphs to obtain the motion connectivity graph includes: The two user motion connectivity graphs are input into the similarity discrimination network to judge the similarity of the two user motion connectivity graphs and obtain the motion similarity value; p user motion connectivity graphs correspond to (p-1)*p / 2 motion similarity values. In this embodiment, the motion similarity value has a value range of 0 to 1. p is a natural number greater than 0.

[0049] Obtaining a motion similarity value that is smaller than other motion similarity values ​​among (p-1)*p / 2 motion similarity values ​​as the first similarity cluster center; A similarity gap value is obtained; the similarity gap value represents a fixed value from the first similarity cluster center.

[0050] In this embodiment, the similarity gap value is 0.15.

[0051] The sum of the first similar cluster center and the similarity gap value is used as the gap threshold; A motion similarity set is constructed by using motion similarity values ​​that are smaller than a gap threshold among multiple motion similarity values.

[0052] The motion similarity set includes a plurality of motion similarity values ​​that are smaller than a gap threshold.

[0053] The user motion connectivity graph corresponding to the motion similarity set is used as a similar motion connectivity graph; A similar motion connectivity graph is randomly obtained from multiple similar motion connectivity graphs as a motion connectivity graph.

[0054] Optionally, the basic motion mode set is obtained by traversing the motion connectivity graph, including: Obtain m motion initial values; the motion initial values ​​represent m motion mode categories in the motion connectivity graph.

[0055] For example, the first row and the first column of the motion connectivity graph represent swimming, and the second row and the second column represent jogging. The first row and the second column are 1, indicating that the partial sorting of the sports mode categories is swimming as the first value and jogging as the second value.

[0056] According to the movement initial value, the movement sequence of the movement mode category is traversed to obtain n movement mode routes; m movement initial values ​​correspond to m*n movement mode routes.

[0057] Wherein, m and n are natural numbers greater than 0.

[0058] The m*n movement mode routes constitute a basic movement mode set.

[0059] Optionally, the relationship between multiple movement mode categories is constructed based on the moving human body information and the movement mode category to obtain a movement parameter point diagram, including: Acquire a blank image; the blank image is a binary image.

[0060] In this embodiment, the blank image is 512*512.

[0061] In this embodiment, all values ​​in the blank image are 255, indicating white.

[0062] The horizontal axis of the blank image represents multiple categories of motion patterns; the vertical axis of the blank image represents a numerical value that can reflect the change values ​​of all motion signs.

[0063] According to the blank image, a coordinate axis is constructed; the lower left corner of the blank image is used as the origin, the length of the blank image is used as the horizontal coordinate, and the width of the blank image is used as the vertical coordinate; Subtract the value of the body sign before exercise from the value of the body sign after exercise to obtain the value of the change of the body sign; The horizontal axis of the blank image represents a plurality of categories of motion modes; and the vertical axis of the blank image represents a numerical value that can reflect the change values ​​of all motion signs.

[0064] In this embodiment, the position with the horizontal coordinate equal to 16 is used as the first exercise mode category, and 16+32 is used as the second exercise mode category. For example, in the two-dimensional exercise parameter point diagram corresponding to body temperature, 512 / 32=16 is used, and the position with the vertical coordinate equal to 16 is used as the value corresponding to the body temperature of 15 degrees Celsius, and the position with the vertical coordinate equal to 32 is used as the value corresponding to the body temperature of 16 degrees Celsius, and so on, until the position with the vertical coordinate equal to 512 is used as the body temperature of 46 degrees Celsius.

[0065] The sports sign change values ​​corresponding to the multiple sports mode categories are punctuated in the blank image to obtain a two-dimensional sports parameter point map; multiple post-exercise human body sign values ​​and the corresponding pre-exercise human body sign values ​​are correspondingly obtained to obtain multiple two-dimensional sports parameter point maps; In this embodiment, a value of 0 is used for punctuation, that is, it is represented as a black dot in a blank image.

[0066] Multiple two-dimensional motion parameter point maps are superimposed to construct a three-dimensional image and obtain a motion parameter point map.

[0067] Among them, the length of the motion parameter point graph is equal to the length of the two-dimensional motion parameter point graph, the width of the motion parameter point graph is equal to the width of the two-dimensional motion parameter point graph, and the number of pages of the motion parameter point graph is equal to the number of post-exercise human body vital sign values ​​of the two-dimensional motion parameter point graph.

[0068] Optionally, a method for training a user prediction network includes: Acquire multiple training user information and corresponding multiple annotated user motion connectivity graphs; one training user information corresponds to multiple annotated user motion connectivity graphs; The training user information is input into a user prediction network to obtain a predicted user motion connectivity graph.

[0069] Among them, the training user information is 1-dimensional data, the user prediction network is a convolutional neural network that performs deconvolution, and the convolution kernel corresponding to the user prediction network is 2*2*2.

[0070] The loss is calculated by comparing the predicted user motion connectivity graph with the labeled user motion connectivity graph to obtain a trained user prediction network.

[0071] Among them, the cross entropy loss function is used to calculate the loss.

[0072] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0073] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0074] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the apparatus according to an embodiment of the present invention. The present invention may also be implemented as a device or device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

Claims

1. A multi-dimensional exercise prescription formulation system based on cloud computing, characterized in that: Including monitoring module and processor: A monitoring module, for obtaining multi-dimensional user information, exercise body information and exercise mode categories; the user information represents body information that does not change with exercise; the exercise body information includes a plurality of post-exercise body sign values ​​and corresponding pre-exercise body sign values; the post-exercise body sign values ​​represent the values ​​of body signs before exercise; the post-exercise body sign values ​​represent the values ​​of body signs after exercise; The processor is used to process the following method: Based on the user information and the exercise mode category, find the sequence that matches the user's exercise mode category to obtain an exercise connectivity graph; Based on the motion connectivity graph, a basic motion mode set is obtained by traversing; the basic motion mode set includes a plurality of motion mode routes; the motion mode routes represent the order of the motion mode categories that meet the user information; Through the movement mode prediction network, based on the moving human body information, the basic movement mode set and the movement mode category, the changes in the user's physical signs during exercise are judged to obtain an exercise prescription; the exercise prescription represents the order of the movement mode categories suitable for the user's physical signs.

2. The multi-dimensional exercise prescription formulation system based on cloud computing according to claim 1 is characterized in that: The method of using the movement mode prediction network to determine the changes in the user's physical signs during exercise based on the moving human body information, the basic movement mode set and the movement mode category, and obtaining an exercise prescription includes: Based on the information of the moving human body and the categories of the movement mode, a relationship between multiple categories of movement mode is constructed to obtain a movement parameter point diagram; the movement parameter point diagram represents the changes in the physical signs of the human body before and after the movement corresponding to the movement mode category; Based on the motion parameter point graph, the relationship between the motion mode categories is judged through a motion mode prediction network to obtain multiple motion influence sequences; Find the exercise route corresponding to the order of exercise impact in the basic exercise method set and get the exercise prescription.

3. The multi-dimensional exercise prescription formulation system based on cloud computing according to claim 2 is characterized in that: The motion mode prediction network includes a first motion convolutional network, a second motion convolutional network and a third motion network.

4. The multi-dimensional exercise prescription formulation system based on cloud computing according to claim 3 is characterized in that: The method of determining the relationship between the categories of motion modes based on the motion parameter point graph and obtaining the motion influence sequence through a motion mode prediction network includes: Inputting the motion parameter point graph into a first motion convolutional network to determine the motion state of the user and obtain a first feature graph; The number of the movement mode categories is used as the number of movement mode categories; The segmentation length is obtained by dividing the horizontal coordinate corresponding to the lower right corner of the motion parameter point diagram by the number of motion mode categories; On the horizontal axis, the point with the distance to the division length is taken as the division point; According to the segmentation points, the motion parameter point map is segmented to obtain a plurality of first motion parameter segmentation maps; The plurality of first motion parameter segmentation images are kept unchanged in length and superimposed in width to obtain a superimposed image; Inputting the superimposed image into a second motion convolutional network to obtain a second feature map; The first feature map and the second feature map are input into a third motion network to obtain a motion influence sequence.

5. The multi-dimensional exercise prescription formulation system based on cloud computing according to claim 4 is characterized in that: The convolution kernel of the first motion convolution network is a three-dimensional convolution kernel of 2*2*2, and the convolution kernel of the second motion convolution network is a three-dimensional convolution kernel with a width equal to the length of the motion parameter point map, a height of 2, and a depth equal to the number of pages of the motion parameter point map.

6. The multi-dimensional exercise prescription formulation system based on cloud computing according to claim 1, characterized in that: The step of finding a sequence of the user's exercise mode categories based on the user information and the exercise mode categories to obtain an exercise connectivity graph includes: Based on the user information, a plurality of user motion connectivity graphs are obtained through a user prediction network; the user motion connectivity graphs use motion mode categories as vertices; Based on multiple user motion connectivity graphs, similarities are determined and a motion connectivity graph is obtained.

7. The multi-dimensional exercise prescription formulation system based on cloud computing according to claim 6, characterized in that: The method of determining similarities based on multiple user motion connectivity graphs to obtain a motion connectivity graph includes: Input two user motion connectivity graphs into the similarity discrimination network to judge the similarity of the two user motion connectivity graphs and obtain motion similarity values; corresponding to p user motion connectivity graphs, (p-1)*p / 2 motion similarity values ​​are obtained; Obtaining a motion similarity value that is smaller than other motion similarity values ​​among (p-1)*p / 2 motion similarity values ​​as the first similarity cluster center; Obtaining a similarity gap value; the similarity gap value represents a fixed value from the first similarity cluster center; The sum of the first similar cluster center and the similarity gap value is used as the gap threshold; Constructing a motion similarity set from motion similarity values ​​that are smaller than a gap threshold among the multiple motion similarity values; The user motion connectivity graph corresponding to the motion similarity set is used as a similar motion connectivity graph; A similar motion connectivity graph is randomly obtained from multiple similar motion connectivity graphs as a motion connectivity graph.

8. The multi-dimensional exercise prescription formulation system based on cloud computing according to claim 1, characterized in that: The basic motion mode set is obtained by traversing the motion connectivity graph, including: Obtaining m motion initial values; the motion initial values ​​represent m motion mode categories in the motion connectivity graph; According to the initial movement value, the movement order of the movement mode category is traversed to obtain n movement mode routes; m movement initial values ​​correspond to m*n movement mode routes; The m*n movement mode routes constitute a basic movement mode set.

9. The multi-dimensional exercise prescription formulation system based on cloud computing according to claim 2, characterized in that: The relationship between multiple movement mode categories is constructed based on the moving human body information and the movement mode category to obtain a movement parameter point diagram, including: Acquire a blank image; the blank image is a binary image; The horizontal axis of the blank image represents multiple categories of motion patterns; the vertical axis of the blank image represents a value that can reflect the change value of all motion signs; According to the blank image, a coordinate axis is constructed; the lower left corner of the blank image is used as the origin, the length of the blank image is used as the horizontal coordinate, and the width of the blank image is used as the vertical coordinate; Subtract the value of the body sign before exercise from the value of the body sign after exercise to obtain the value of the change of the body sign; The sports sign change values ​​corresponding to the multiple sports mode categories are punctuated in the blank image to obtain a two-dimensional sports parameter point map; multiple post-exercise human body sign values ​​and the corresponding pre-exercise human body sign values ​​are correspondingly obtained to obtain multiple two-dimensional sports parameter point maps; Multiple two-dimensional motion parameter point maps are superimposed to construct a three-dimensional image and obtain a motion parameter point map.

10. The multi-dimensional exercise prescription formulation system based on cloud computing according to claim 2, characterized in that: Methods for training user prediction networks include: Acquire multiple training user information and corresponding multiple annotated user motion connectivity graphs; one training user information corresponds to multiple annotated user motion connectivity graphs; Inputting the training user information into a user prediction network to obtain a predicted user motion connectivity graph; The loss is calculated by comparing the predicted user motion connectivity graph with the labeled user motion connectivity graph to obtain a trained user prediction network.

Images