Personalized exercise prescription recommendation system based on big data analysis

Abstract

The present invention discloses a personalized exercise prescription recommendation system based on big data analysis. User information is used to find an exercise method that suits the user. Because under gravity, pressure is downward, and the human body is supported by the feet. This pressure is related to the body's posture. Therefore, during training, multiple training segmented images can be obtained through historical user movement footprint images. A relationship is thus established between the segmented images and the pressure exerted by the user's posture on the footprints. Therefore, the multiple segmented images can not only represent the user's movement posture, but also the force applied to each body part when the user makes the gesture. This allows the user to determine whether the user's movements are standard. This allows the user to recommend an exercise prescription that enables the user to make movement postures more smoothly and accurately apply force to each body part.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a personalized exercise prescription recommendation system based on big data analysis. Background Art

[0002] Currently, recommendations are primarily based on user information. Furthermore, personalized recommendations are made by adding information about different symptoms, scenarios, and energy consumption. However, the user's posture is not considered to determine exercise accuracy. Because improper posture during exercise can hinder the user's ability to achieve the desired result, and some movements are difficult for the user to correct, it is important to provide users with postures that are easier to perform. Summary of the Invention

[0003] The purpose of the present invention is to provide a personalized exercise prescription recommendation system based on big data analysis to solve the above-mentioned problems existing in the prior art, including a monitoring module and a processor.

[0004] The monitoring module is used to obtain user information; the user information includes the user's age, gender and symptoms;

[0005] The processor is used to process the following method:

[0006] Inputting the user information into an exercise mode discrimination network to obtain a plurality of exercise modes; the exercise modes represent exercise categories suitable for the user;

[0007] According to the motion mode, a user motion footprint image and a corresponding user motion posture image are obtained; the user motion footprint image represents a two-dimensional grayscale image including footprints left by the user during motion; the user motion posture image represents an image including the corresponding user motion posture when recording the user motion footprint image;

[0008] Based on the user motion posture image and the user motion footprint image, a footprint support vector is obtained; the footprint support vector represents the pressure of the user's posture contained in the two-dimensional user motion posture image on the footprint;

[0009] Using a segmentation discriminant network, based on the user's motion posture image, the pressure corresponding to the posture applied to each part of the user's motion footprint image is found, thereby obtaining multiple segmentation angles;

[0010] Based on the cutting angle and the user motion posture image, the user motion posture image is segmented at different angles to obtain a plurality of segmented images; the segmented images are images including the user motion footprint images;

[0011] Through the posture discrimination network, based on the segmented image, it is judged whether the movement posture is correct and a recommended movement prescription is obtained.

[0012] Optionally, the segmentation discriminant network is used to find the pressure corresponding to each part of the user's motion footprint image caused by the posture based on the user's motion posture image, and obtain multiple segmentation angles, including:

[0013] Inputting the user motion posture image into an edge detection network to detect the user posture to obtain a first posture image; the first posture image represents the user's body posture;

[0014] Inputting the first posture image into a body part discrimination network to obtain a user body part position image; the user body part position image is an image on which the positions of multiple body parts of the user are marked;

[0015] The user's part position image is input into the segmentation discriminant network to obtain multiple cutting angles.

[0016] Optionally, the training method of the segmentation discriminant network includes:

[0017] Acquire a plurality of training images; the training images are historical user body position images;

[0018] Obtaining a footprint support vector corresponding to the training image as annotation data;

[0019] Inputting the training image into a segmentation discriminant network to obtain a training cutting angle;

[0020] Based on the training cutting angle and the annotation data, the training image is cut to obtain a plurality of training segmented images and corresponding second marking points; the training segmented image is an image cut according to the training cutting angle; the second marking point represents the midpoint of an edge of the first segmented image on the annotated basic straight line;

[0021] Based on the training segmented image and the second marked point, the degree of force is determined with the midline as a reference, and a plurality of training segmented grayscale total values ​​and corresponding training segmented distances are obtained; the training segmented distance represents a distance from the ground in the training segmented image; and the training segmented grayscale total value represents the pressure of each posture in the training segmented image at the training segmented distance;

[0022] Based on the total grayscale values ​​of the multiple training segments and the corresponding training segment distances, a training pressure value is obtained; the multiple total grayscale values ​​of the training segments correspond to one training pressure value; the multiple training segment images correspond to multiple training pressure values; the training pressure value represents the pressure exerted on the ground by the footprints of the entire training segment image;

[0023] Dividing each of the multiple training pressure values ​​by the sum of the multiple training pressure values ​​to obtain a training pressure ratio; the training pressure ratio represents the ratio of the pressures exerted on the ground by the footprints of the multiple training segmented images;

[0024] The loss is calculated based on the training pressure ratio and the footprint support vector, and the segmentation discriminant network is trained.

[0025] Optionally, obtaining a footprint support vector based on the user motion posture image and the user motion footprint image includes:

[0026] A straight line where the user motion posture image and the user motion footprint image intersect is used as a base straight line;

[0027] Segmenting the user's motion footprint image in a direction perpendicular to the base straight line to obtain a plurality of first segmented images;

[0028] Adding the grayscale values ​​in the first segmented image to obtain a footprint pressure value; obtaining a plurality of footprint pressure values ​​corresponding to the plurality of first segmented images;

[0029] According to the positions of the plurality of first segmented images in the user's motion footprint image, the plurality of footprint pressure values ​​are arranged in sequence to obtain a footprint support vector.

[0030] Optionally, the step of cutting the training image based on the training cutting angle and the annotation data to obtain a plurality of training segmented images and corresponding second marking points includes:

[0031] The first segmented image corresponding to the user running footprint image corresponding to the annotated data is used as the annotated first segmented image;

[0032] Using the basic straight line corresponding to the annotated first segmented image as the annotated basic straight line;

[0033] Marking the first segmented image at positions corresponding to the training image on the marking base straight line to obtain a plurality of first marking points;

[0034] The midpoint of two connected first marking points is used as the second marking point;

[0035] Find the angle difference from the marked base line to train the cutting angle, and use the line passing through the second marked point as the cutting line;

[0036] The training image is segmented using segmentation lines to obtain a training segmented image.

[0037] Optionally, the step of determining the degree of force based on the training segmentation image and the second marking point and taking the midline as a reference to obtain a plurality of training segmentation grayscale total values ​​and corresponding training segmentation distances includes:

[0038] According to the training segmentation image and the second marking point, finding the midline of the training segmentation image as the training segmentation midline;

[0039] Based on the training segmentation image and the training segmentation centerline, projecting the pressure of the user's posture onto the training segmentation centerline to obtain a plurality of training segmentation grayscale total values; each value on the training segmentation centerline corresponds to one training segmentation grayscale total value;

[0040] Get the position of the value on the training segmentation midline on the training image as the training segmentation position;

[0041] According to the training segmentation position and the position of the second marking point, the distance to the second marking point is calculated by the Pythagorean theorem to obtain the training segmentation distance;

[0042] The total grayscale value of the training segment is associated with the corresponding training segment distance.

[0043] Optionally, based on the training segmentation image and the training segmentation centerline, projecting the pressure of the user's posture onto the training segmentation centerline to obtain a plurality of training segmentation grayscale total values ​​includes:

[0044] Get the points on the training split midline as split points; multiple points on the training split midline correspond to multiple split points;

[0045] Obtain a straight line passing through the split point and perpendicular to the training split midline as the split bisector; multiple split points correspond to multiple split bisectors;

[0046] In the training segmentation image, the grayscale values ​​on the segmentation bisector are added to obtain a total grayscale value of the training segmentation; and a plurality of training segmentation total grayscale values ​​are obtained corresponding to a plurality of segmentation bisectors.

[0047] Optionally, obtaining a training pressure value based on a plurality of training segmentation grayscale total values ​​and corresponding training segmentation distances includes:

[0048] Add up multiple training segmentation distances to get the total predicted distance value;

[0049] Dividing the training segmentation distance by the total value of the predicted distance to obtain a predicted distance pressure value; multiple training segmentation distances correspond to multiple predicted distance pressure values;

[0050] Multiplying the total grayscale value of the training segmentation by the corresponding predicted distance pressure value to obtain a training segmentation pressure value; multiple training segmentation total grayscale values ​​correspond to multiple training segmentation pressure values;

[0051] Add up the multiple training segmentation pressure values ​​to obtain a training pressure value; the total grayscale values ​​of the multiple training segmentations correspond to one training pressure value;

[0052] Multiple training segmentation images correspond to multiple training pressure values.

[0053] Optionally, finding the midline of the training segmentation image as the training segmentation midline based on the training segmentation image and the second marking point includes:

[0054] If the training segmented image is a quadrilateral, four quadrilateral vertices are obtained;

[0055] Connect two non-adjacent four-sided vertices to obtain two four-sided line segments;

[0056] The point where two four-sided line segments intersect is taken as the first focal point;

[0057] The second marked point corresponding to the training segmentation image is connected to the first key point to obtain the training segmentation centerline.

[0058] Optionally, finding the midline of the training segmentation image as the training segmentation midline based on the training segmentation image and the second marking point includes:

[0059] If the training segmented image is a triangle, three triangle vertices are obtained;

[0060] The angle containing the second marked point is taken as the second marked angle;

[0061] The side corresponding to the second marked angle is used as the second marked side;

[0062] Take the midpoint of the second marked side as the first midpoint;

[0063] Connect the first midpoint with the second marked point to obtain the training segmentation midline.

[0064] Compared with the prior art, the embodiments of the present invention achieve the following beneficial effects:

[0065] The present invention also provides a personalized exercise prescription recommendation system based on big data analysis:

[0066] Using user information, a user-friendly exercise pattern is found. This improves the personalization of exercise prescription recommendations. This is achieved by correlating the user's posture with the pressure exerted by the body on the ground, as represented by their footprints. Because gravity exerts downward pressure, the body is supported by the feet. This pressure is related to the body's posture. Therefore, during training, multiple training segmented images can be obtained from historical user footprint images. A training segmented midline is found within the training segmented images. The training segmented midline divides the training segmented image into two equal parts while preserving the positional information corresponding to the posture. The value on the training segmented midline represents the pressure exerted by a point in the posture. The training segmented midline and training segmented images are visualized using a segmentation discriminant network. This establishes a relationship between the segmented images and the pressure exerted by the user's posture on the footprints. Consequently, the multiple segmented images not only represent the user's exercise posture but also the force applied to each body part during the gesture. This allows for accurate assessment of the user's movements. This results in recommended exercise prescriptions that help users more smoothly perform exercise postures and accurately apply force to each body part. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a method flow chart corresponding to a processor in a personalized exercise prescription recommendation system based on big data analysis provided by an embodiment of the present invention.

[0068] Figure 2 This is a schematic diagram of the installation positions of a footprint detection device and a posture camera device in a personalized exercise prescription recommendation system based on big data analysis provided by an embodiment of the present invention.

[0069] Figure 3 This is a schematic diagram of a method for obtaining footprint support vectors corresponding to a processor in a personalized exercise prescription recommendation system based on big data analysis provided by an embodiment of the present invention.

[0070] Figure 4 This is a schematic diagram of a method for acquiring training segmented images corresponding to a processor in a personalized exercise prescription recommendation system based on big data analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0071] The present invention will be described in detail below with reference to the accompanying drawings. Example

[0072] like Figure 1 As shown, an embodiment of the present invention provides a personalized exercise prescription recommendation system based on big data analysis, the system including a monitoring module and a processor:

[0073] The monitoring module is used to obtain a user's movement footprint image and a user's movement posture image. The user's movement footprint image represents a two-dimensional footprint image left by the user during movement.

[0074] The footprint image is a grayscale image, and grayscale values ​​are used to represent the force applied to the foot.

[0075] The monitoring module is used to obtain user information; the user information includes the user's age, gender and symptoms;

[0076] The processor is used to process the following method:

[0077] S101: Inputting the user information into an exercise mode discrimination network to obtain multiple exercise modes; the exercise modes represent exercise categories suitable for the user.

[0078] The movement mode discrimination network is a fully connected neural network (Fully Connected Neural Network).

[0079] The sports category represents a set of pre-set sports movements.

[0080] S102: According to the movement mode, obtain a user movement footprint image and a corresponding user movement posture image; the user movement footprint image represents a two-dimensional grayscale image containing footprints left by the user when exercising; the user movement posture image represents an image containing the corresponding user movement posture when recording the user movement footprint image.

[0081] The user's motion footprint image can be captured using a footprint detection device placed under the user's feet, or using a posture camera that captures images perpendicular to a horizontal plane. In this embodiment, the footprint detection device can employ a gravity sensor, or a footprint can be printed by smearing the sole of the foot with paint and then scanning it. The value is converted to a 0-255 value by calculating its proportion in the total value and multiplying it by 256. Finally, the gravity or printed footprint is converted into a grayscale image that reflects the pressure of the footprint.

[0082] Among them, in the user motion posture image, raising a hand is a user posture.

[0083] The installation positions of the footprint detection equipment and the posture camera equipment are as follows: Figure 2 In this embodiment, the footprint detection device is placed on the ground, and the posture camera device is placed on a wall perpendicular to the ground.

[0084] S103: Obtaining a footprint support vector based on the user motion posture image and the user motion footprint image; the footprint support vector represents the pressure of the user's posture contained in the two-dimensional user motion posture image on the footprint.

[0085] S104: Using a segmentation discriminant network, based on the user's motion posture image, finding the pressure corresponding to each part of the user's motion footprint image caused by the posture, and obtaining multiple segmentation angles;

[0086] S105: Based on the cutting angle and the user motion posture image, the user motion posture image is segmented at different angles to obtain a plurality of segmented images; the segmented images are images including the user motion footprint images.

[0087] S106: Using a posture discrimination network, based on the segmented image, determine whether the exercise posture is correct, and obtain a recommended exercise prescription.

[0088] The posture discrimination network is a LetNet network. The posture discrimination network is used to determine whether the user's exercise posture is correct. If the accuracy of each segmented image is low, an exercise prescription with a higher accuracy rate is recommended to the user.

[0089] Optionally, the segmentation discriminant network is used to find the pressure corresponding to each part of the user's motion footprint image caused by the posture based on the user's motion posture image, and obtain multiple segmentation angles, including:

[0090] The user motion posture image is input into an edge detection network to detect the user posture to obtain a first posture image; the first posture image represents the user's body posture.

[0091] Among them, the canny operator is used as the edge detection network to extract the edges of the user's posture.

[0092] The first posture image is input into a part discrimination network to obtain a user part position image; the user part position image is an image that marks the positions of multiple parts of the user's body.

[0093] The part discrimination network is a yolov5 model. The part discrimination network is a network that uses multiple labeled positions of user parts such as the user's arms, legs, head, and torso.

[0094] The user's part position image is input into the segmentation discriminant network to obtain multiple cutting angles.

[0095] Optionally, the training method of the segmentation discriminant network includes:

[0096] A plurality of training images are obtained; the training images are historical user body position images.

[0097] Obtain the footprint support vector corresponding to the training image as annotation data.

[0098] Among them, multiple training images correspond to multiple footprint support vectors and multiple annotation data.

[0099] The training image is input into a segmentation discriminant network to obtain a training cutting angle.

[0100] The segmentation discriminant network can visualize the values ​​on the subsequent training segmentation midline.

[0101] Based on the training cutting angle and the annotation data, the training image is cut to obtain a plurality of training segmented images and corresponding second marking points; the training segmented image is an image cut according to the training cutting angle; the second marking point represents the midpoint of an edge of the first segmented image on the annotated basic straight line;

[0102] The training segmented image is segmented according to the force conditions of the footprints.

[0103] Based on the training segmented image and the second marking point, the degree of force is determined with the midline as a reference to obtain multiple training segmented grayscale total values ​​and corresponding training segmented distances; the training segmented distance represents a distance from the ground in the training segmented image; the training segmented grayscale total value represents the pressure of each posture in the training segmented image at the training segmented distance.

[0104] Based on multiple training segmentation grayscale total values ​​and corresponding training segmentation distances, a training pressure value is obtained; multiple training segmentation grayscale total values ​​correspond to one training pressure value; multiple training segmentation images correspond to multiple training pressure values; the training pressure value represents the pressure generated by the entire training segmentation image on the ground through the footprints.

[0105] The multiple training pressure values ​​are divided by the sum of the multiple training pressure values ​​to obtain multiple training pressure ratios; the training pressure ratios represent the ratios of the pressures exerted on the ground by the footprints of the multiple training segmented images.

[0106] Among them, one training pressure value corresponds to one training pressure ratio value.

[0107] Among them, if the training pressure values ​​are 23, 34, 53, and 21 respectively. 23+34+53+21=131, then the training pressure ratios are 23 / 131, 34 / 131, 53 / 131, and 21 / 131 respectively.

[0108] The loss is calculated based on the training pressure ratio and the footprint support vector, and the segmentation discriminant network is trained.

[0109] The values ​​in the footprint support vectors are added together to obtain a total footprint support vector value. The value corresponding to an element in the footprint support vector is divided by the total footprint support vector value to obtain a footprint support vector ratio.

[0110] The loss is calculated by comparing the footprint support vector ratio with the corresponding training pressure ratio. The correlation between the footprint support vector ratio and the corresponding training pressure ratio is constructed by the positional order of the multiple training segmented images and the subscripts of the elements of the multiple footprint support vectors. For example, if the subscripts of the multiple training segmented images are labeled 0, 1, 2, and 3 from left to right, then the training segmented image with subscript 0 corresponds to the element of the footprint support vector with subscript 0.

[0111] Among them, the cross entropy loss function is used to calculate the loss.

[0112] Optionally, obtaining a footprint support vector based on the user motion posture image and the user motion footprint image includes:

[0113] The straight line where the user motion posture image and the user motion footprint image intersect is used as the basic straight line.

[0114] Wherein, the basic straight line is as follows Figure 3 .

[0115] The user movement footprint image is segmented in a direction perpendicular to the basic straight line to obtain a plurality of first segmented images.

[0116] The first segmented image and the user movement footprint image are on the same horizontal plane.

[0117] The plurality of first segmented images only have one segmentation direction which is a direction perpendicular to the base straight line.

[0118] In this embodiment, the direction of the user's footprint image parallel to the base line is used as the horizontal coordinate, the direction perpendicular to the base line is used as the vertical coordinate, and the lower left corner of the user's footprint image is used as the origin. The width of the first segmented image is equal to the width of the user's footprint image. The lengths of the multiple first segmented images are equal, and the sum of the lengths of the multiple first segmented images is equal to the length of the user's footprint image.

[0119] The segmentation direction of the first segmented image is as follows: Figure 3 shown.

[0120] Adding the grayscale values ​​in the first segmented image to obtain a footprint pressure value; obtaining a plurality of footprint pressure values ​​corresponding to the plurality of first segmented images;

[0121] According to the positions of the plurality of first segmented images in the user's motion footprint image, the plurality of footprint pressure values ​​are arranged in sequence to obtain a footprint support vector.

[0122] Among them, if the user motion footprint image is 64*64, the lower corner of the user motion footprint image is taken as the origin, the length is the horizontal coordinate, and the width is the vertical coordinate. Divide it into 4 first segmented images, each of which is 16 long and 64 wide. Place the footprint pressure value corresponding to the first segmented image corresponding to the horizontal coordinate 0-15 at the position with subscript 0 in the footprint support vector. Place the footprint pressure value corresponding to the first segmented image corresponding to the horizontal coordinate 16-31 at the position with subscript 1 in the footprint support vector. Place the footprint pressure value corresponding to the first segmented image corresponding to the horizontal coordinate 32-47 at the position with subscript 2 in the footprint support vector. Place the footprint pressure value corresponding to the first segmented image corresponding to the horizontal coordinate 48-64 at the position with subscript 3 in the footprint support vector.

[0123] Optionally, the step of cutting the training image based on the training cutting angle and the annotation data to obtain a plurality of training segmented images and corresponding second marking points includes:

[0124] The first segmented image corresponding to the user's running footprint image corresponding to the annotated data is used as the annotated first segmented image; and a plurality of annotated first segmented images are obtained corresponding to the plurality of first segmented images;

[0125] Using the basic straight line corresponding to the annotated first segmented image as the annotated basic straight line;

[0126] The first segmented image is marked by marking positions on the marking basic straight line corresponding to positions on the training image to obtain a plurality of first marking points.

[0127] The midpoint of two connected first marking points is used as the second marking point.

[0128] Wherein, the first marking point and the second marking point are as follows Figure 4 shown.

[0129] The angle difference from the marked base straight line is found to train the cutting angle, and the straight line passing through the second marked point is used as the cutting line.

[0130] In this embodiment, the angle from right to left of the labeled basic straight line is 0 degrees, and the angle from left to right is 180 degrees. If the following is marked as 0, the training cutting angle corresponding to the first training cutting angle of the first labeled first segmented image is 45 degrees.

[0131] Among them, the dividing line is as follows Figure 4 shown.

[0132] The training image is segmented using segmentation lines to obtain a training segmented image.

[0133] Optionally, the step of determining the degree of force based on the training segmentation image and the second marking point and taking the midline as a reference to obtain a plurality of training segmentation grayscale total values ​​and corresponding training segmentation distances includes:

[0134] According to the training segmentation image and the second marking point, a midline of the training segmentation image is found as a training segmentation midline.

[0135] Wherein, multiple vertices in the training segmented image are obtained. If the training segmented image is a triangle, then there are three vertices.

[0136] Using this method, because gravity exerts downward pressure, the body is supported by footprints. Since pressure is related to the body's posture, the training segmented images can be distributed based on the pressure supported by the footprints. The training segmented midline representation can be used to divide the training segmented image into two equal parts, bisecting the area while preserving the positional information corresponding to the posture.

[0137] Based on the training segmentation image and the training segmentation centerline, the pressure of the user posture is projected onto the training segmentation centerline to obtain a plurality of training segmentation grayscale total values; a value on the training segmentation centerline corresponds to a training segmentation grayscale total value.

[0138] Get the position of the value on the training segmentation midline on the training image as the training segmentation position;

[0139] According to the training segmentation position and the position of the second marking point, the distance to the second marking point is calculated by the Pythagorean theorem to obtain the training segmentation distance.

[0140] The coordinate axes are established with the lower left corner of the training image as the origin, the length as the horizontal coordinate, and the width as the vertical coordinate. The absolute value of the horizontal coordinate of the second marked point is subtracted from the horizontal coordinate of the training segmentation position as the first Pythagorean value, and the horizontal coordinate of the training segmentation position is used as the second Pythagorean value. The square root of the first Pythagorean value is added to the square root of the second Pythagorean value to obtain the training segmentation distance.

[0141] The total grayscale value of the training segment is associated with the corresponding training segment distance.

[0142] Optionally, based on the training segmentation image and the training segmentation centerline, projecting the pressure of the user's posture onto the training segmentation centerline to obtain a plurality of training segmentation grayscale total values ​​includes:

[0143] Get the points on the training split midline as split points; multiple points on the training split midline correspond to multiple split points;

[0144] A straight line passing through the split point and perpendicular to the training split midline is obtained as the split bisector; multiple split points correspond to multiple split bisectors.

[0145] Through the above method, the value on the training segmentation line represents the pressure exerted on the posture as a point.

[0146] In the training segmentation image, the grayscale values ​​on the segmentation bisector are added to obtain a total grayscale value of the training segmentation; and a plurality of training segmentation total grayscale values ​​are obtained corresponding to a plurality of segmentation bisectors.

[0147] Optionally, obtaining a training pressure value based on a plurality of training segmentation grayscale total values ​​and corresponding training segmentation distances includes:

[0148] Add up multiple training segmentation distances to get the total predicted distance value;

[0149] Dividing the training segmentation distance by the total value of the predicted distance to obtain a predicted distance pressure value; multiple training segmentation distances correspond to multiple predicted distance pressure values;

[0150] Multiplying the total grayscale value of the training segmentation by the corresponding predicted distance pressure value to obtain a training segmentation pressure value; multiple training segmentation total grayscale values ​​correspond to multiple training segmentation pressure values;

[0151] Add up the multiple training segmentation pressure values ​​to obtain a training pressure value; the total grayscale values ​​of the multiple training segmentations correspond to one training pressure value;

[0152] Multiple training segmentation images correspond to multiple training pressure values.

[0153] Optionally, finding the midline of the training segmentation image as the training segmentation midline based on the training segmentation image and the second marking point includes:

[0154] If the training segmented image is a quadrilateral, four quadrilateral vertices are obtained;

[0155] Connect two non-adjacent four-sided vertices to obtain two four-sided line segments;

[0156] The point where two four-sided line segments intersect is taken as the first focal point;

[0157] The second marked point corresponding to the training segmentation image is connected to the first key point to obtain the training segmentation centerline.

[0158] Optionally, the personalized exercise prescription recommendation system based on big data analysis according to claim 6 is characterized in that finding the midline of the training segmented image as the training segmented midline based on the training segmented image and the second marked point comprises:

[0159] If the training segmented image is a triangle, three triangle vertices are obtained;

[0160] The angle containing the second marked point is taken as the second marked angle;

[0161] The side corresponding to the second marked angle is used as the second marked side.

[0162] The two edges that construct the split angle are regarded as connected edges, and the edges other than the adjacent edges are regarded as edges corresponding to the split angle, namely, split edges.

[0163] Take the midpoint of the second marked side as the first midpoint;

[0164] Connect the first midpoint with the second marked point to obtain the training segmentation midline.

[0165] 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 this type of system. In addition, the present invention is not directed to any specific programming language. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0166] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Accordingly, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the invention.

Claims

1. A personalized exercise prescription recommendation system based on big data analysis, characterized by: Including monitoring module and processor: The monitoring module is used to obtain user information; the user information includes the user's age, gender and symptoms; The processor is used to process the following method: Inputting the user information into an exercise mode discrimination network to obtain a plurality of exercise modes; the exercise modes represent exercise categories suitable for the user; According to the motion mode, a user motion footprint image and a corresponding user motion posture image are obtained; the user motion footprint image represents a two-dimensional grayscale image including footprints left by the user during motion; the user motion posture image represents an image including the corresponding user motion posture when recording the user motion footprint image; Based on the user motion posture image and the user motion footprint image, a footprint support vector is obtained; the footprint support vector represents the pressure of the user's posture contained in the two-dimensional user motion posture image on the footprint; Using a segmentation discriminant network, based on the user's motion posture image, the pressure corresponding to the posture applied to each part of the user's motion footprint image is found, thereby obtaining multiple segmentation angles; Based on the multiple cutting angles and the user motion posture image, segmenting the user motion posture image at the multiple cutting angles to obtain multiple segmented images; The segmented image is an image containing the user's movement footprints; Through the posture discrimination network, based on the segmented image, it is judged whether the movement posture is correct and a recommended movement prescription is obtained.

2. The personalized exercise prescription recommendation system based on big data analysis according to claim 1 is characterized in that: The segmentation discriminant network is used to find the pressure corresponding to each part of the user's motion footprint image caused by the posture based on the user's motion posture image, and obtain multiple segmentation angles, including: Inputting the user motion posture image into an edge detection network to detect the user posture to obtain a first posture image; the first posture image represents the user's body posture; Inputting the first posture image into a body part discrimination network to obtain a user body part position image; the user body part position image is an image on which the positions of multiple body parts of the user are marked; The user's part position image is input into the segmentation discriminant network to obtain multiple cutting angles.

3. The personalized exercise prescription recommendation system based on big data analysis according to claim 2 is characterized in that: The training method of the segmentation discriminant network includes: Acquire a plurality of training images; the training images are historical user body position images; Obtaining a footprint support vector corresponding to the training image as annotation data; Inputting the training image into a segmentation discriminant network to obtain a training cutting angle; Based on the training cutting angle and the annotation data, the training image is cut to obtain a plurality of training segmented images and corresponding second marking points; the training segmented image is an image cut according to the training cutting angle; the second marking point represents the midpoint of an edge of the first segmented image on the annotated basic straight line; Based on the training segmented image and the second marked point, the degree of force is determined with the midline as a reference, and a plurality of training segmented grayscale total values ​​and corresponding training segmented distances are obtained; the training segmented distance represents a distance from the ground in the training segmented image; and the training segmented grayscale total value represents the pressure of each posture in the training segmented image at the training segmented distance; Based on the total grayscale values ​​of the multiple training segments and the corresponding training segment distances, a training pressure value is obtained; the multiple total grayscale values ​​of the training segments correspond to one training pressure value; the multiple training segment images correspond to multiple training pressure values; the training pressure value represents the pressure exerted on the ground by the footprints of the entire training segment image; Dividing each of the multiple training pressure values ​​by the sum of the multiple training pressure values ​​to obtain a training pressure ratio; the training pressure ratio represents the ratio of the pressures exerted on the ground by the footprints of the multiple training segmented images; The loss is calculated based on the training pressure ratio and the footprint support vector, and the segmentation discriminant network is trained.

4. The personalized exercise prescription recommendation system based on big data analysis according to claim 1 is characterized in that: The obtaining of the footprint support vector based on the user motion posture image and the user motion footprint image includes: A straight line where the user motion posture image and the user motion footprint image intersect is used as a base straight line; Segmenting the user's motion footprint image in a direction perpendicular to the base straight line to obtain a plurality of first segmented images; Adding the grayscale values ​​in the first segmented image to obtain a footprint pressure value; obtaining a plurality of footprint pressure values ​​corresponding to the plurality of first segmented images; According to the positions of the plurality of first segmented images in the user's motion footprint image, the plurality of footprint pressure values ​​are arranged in sequence to obtain a footprint support vector.

5. The personalized exercise prescription recommendation system based on big data analysis according to claim 3 is characterized in that: The step of cutting the training image based on the training cutting angle and the annotation data to obtain a plurality of training segmented images and corresponding second marking points includes: The first segmented image corresponding to the user running footprint image corresponding to the annotated data is used as the annotated first segmented image; Using the basic straight line corresponding to the annotated first segmented image as the annotated basic straight line; Marking the first segmented image by marking positions on the marking base straight line corresponding to positions on the training image to obtain a plurality of first marking points; The midpoint of two connected first marking points is used as the second marking point; Find the angle difference from the marked base line to train the cutting angle, and use the line passing through the second marked point as the cutting line; The training image is segmented using segmentation lines to obtain a training segmented image.

6. The personalized exercise prescription recommendation system based on big data analysis according to claim 3 is characterized in that: The method of determining the degree of force based on the training segmentation image and the second marking point with the midline as a reference, and obtaining a plurality of training segmentation grayscale total values ​​and corresponding training segmentation distances, includes: According to the training segmentation image and the second marking point, finding the midline of the training segmentation image as the training segmentation midline; Based on the training segmentation image and the training segmentation centerline, projecting the pressure of the user's posture onto the training segmentation centerline to obtain a plurality of training segmentation grayscale total values; each value on the training segmentation centerline corresponds to one training segmentation grayscale total value; Get the position of the value on the training segmentation midline on the training image as the training segmentation position; According to the training segmentation position and the position of the second marking point, the distance to the second marking point is calculated by the Pythagorean theorem to obtain the training segmentation distance; The total grayscale value of the training segment is associated with the corresponding training segment distance.

7. The personalized exercise prescription recommendation system based on big data analysis according to claim 6 is characterized in that: The method of projecting the pressure of the user's posture onto the training segmentation midline based on the training segmentation image and the training segmentation midline to obtain a plurality of training segmentation grayscale total values ​​includes: Get the points on the training split midline as split points; multiple points on the training split midline correspond to multiple split points; Obtain a straight line passing through the split point and perpendicular to the training split midline as the split bisector; multiple split points correspond to multiple split bisectors; In the training segmentation image, the grayscale values ​​on the segmentation bisector are added to obtain a total grayscale value of the training segmentation; and a plurality of training segmentation total grayscale values ​​are obtained corresponding to a plurality of segmentation bisectors.

8. The personalized exercise prescription recommendation system based on big data analysis according to claim 3 is characterized in that: The step of obtaining a training pressure value based on a plurality of training segmentation grayscale total values ​​and corresponding training segmentation distances includes: Add up multiple training segmentation distances to get the total predicted distance value; Dividing the training segmentation distance by the total value of the predicted distance to obtain a predicted distance pressure value; multiple training segmentation distances correspond to multiple predicted distance pressure values; Multiplying the total grayscale value of the training segmentation by the corresponding predicted distance pressure value to obtain a training segmentation pressure value; multiple training segmentation total grayscale values ​​correspond to multiple training segmentation pressure values; Add up the multiple training segmentation pressure values ​​to obtain a training pressure value; the total grayscale values ​​of the multiple training segmentations correspond to one training pressure value; Multiple training segmentation images correspond to multiple training pressure values.

9. The personalized exercise prescription recommendation system based on big data analysis according to claim 6, characterized in that: The step of finding the midline of the training segmentation image as the training segmentation midline based on the training segmentation image and the second marking point includes: If the training segmented image is a quadrilateral, four quadrilateral vertices are obtained; Connect two non-adjacent four-sided vertices to obtain two four-sided line segments; The point where two four-sided line segments intersect is taken as the first focal point; The second marked point corresponding to the training segmentation image is connected to the first key point to obtain the training segmentation centerline.

10. The personalized exercise prescription recommendation system based on big data analysis according to claim 6, characterized in that: The step of finding the midline of the training segmentation image as the training segmentation midline based on the training segmentation image and the second marking point includes: If the training segmented image is a triangle, three triangle vertices are obtained; The angle containing the second marked point is taken as the second marked angle; The side corresponding to the second marked angle is used as the second marked side; Take the midpoint of the second marked side as the first midpoint; Connect the first midpoint with the second marked point to obtain the training segmentation midline.

Images