Pelvic floor muscle rehabilitation training monitoring method and related equipment

Abstract

According to the pelvic floor muscle rehabilitation training monitoring method and the related equipment, whether the execution action of the user in the pelvic floor muscle training process is standard or not can be fed back in time, and the pelvic floor muscle recovery effect is improved. The method comprises the steps that motion decomposition is carried out on target motion to obtain a motion decomposition set, and the target motion and pelvic floor muscle rehabilitation training have an association relationship; acquiring first motion data of each motion in the motion decomposition set executed by the target user through a patch of the target user on a preset body part; inputting the first motion data of each action into an identification model one by one to obtain an identification similarity between each action and a corresponding standard action, the identification model being obtained by training a training sample through a neural network in advance, the training sample comprises motion data of each action in the action decomposition set executed by each experimenter in the experimenter set; and generating corresponding prompt information according to the identification similarity.

Description

Technical Field

[0001] The present invention relates to the field of nursing, and in particular to a monitoring method and related equipment for pelvic floor muscle rehabilitation training. Background Art

[0002] The pelvic floor muscles play an important role in providing support for the pelvic organs and maintaining urinary incontinence and bowel control. When patients suffer pelvic floor muscle damage after childbirth or surgery, it can lead to urinary incontinence, sexual dysfunction, etc., seriously affecting the quality of life of patients.

[0003] At present, the main clinical practice is to restore the original tension and coordination of the pelvic floor muscles through standardized Kegel exercises or bioelectric stimulation, so as to improve urinary incontinence and sexual dysfunction. Kegel exercises require patients to feel the pelvic floor muscles and perform muscle contractions under the guidance of medical staff, and cannot get timely feedback. Bioelectric stimulation is generally achieved with the help of larger instruments and equipment, and patients need to travel back and forth between the hospital and home repeatedly, which is time-consuming and labor-intensive. Summary of the invention

[0004] The embodiment of the present invention provides a monitoring method and related equipment for pelvic floor muscle rehabilitation training. By training a recognition model in advance to identify the standardization of each action in a decomposition set of actions performed by a user, timely feedback can be provided on whether the user's actions are performed in a standard manner, thereby improving the recovery effect of the pelvic floor muscles.

[0005] A first aspect of the present invention provides a method for monitoring pelvic floor muscle rehabilitation training, comprising:

[0006] Decomposing the target motion into motions to obtain a motion decomposition set, wherein the target motion is associated with the pelvic floor muscle rehabilitation training;

[0007] Acquire first motion data of each action in the action decomposition set performed by the target user through a patch on a preset body part of the target user;

[0008] Inputting the first motion data of each action into a recognition model one by one to obtain the recognition similarity between each action and a corresponding standard action, wherein the recognition model is obtained by training training samples in advance through a neural network, and the training samples include motion data of each subject in the subject set performing each action in the action decomposition set;

[0009] Generate corresponding prompt information according to the recognition similarity.

[0010] A second aspect of the present invention provides a monitoring device for pelvic floor muscle rehabilitation training, comprising:

[0011] A decomposition module, used for performing action decomposition on the target motion to obtain an action decomposition set, wherein the target motion is associated with the pelvic floor muscle rehabilitation training;

[0012] An acquisition module, used for acquiring first motion data of each action in the action decomposition set when the target user performs the action through a patch on a preset body part of the target user;

[0013] A recognition module, used for inputting the first motion data of each action into a recognition model one by one, so as to obtain the recognition similarity between each action and the corresponding standard action, wherein the recognition model is obtained by training training samples in advance through a neural network, and the training samples include motion data of each subject in the subject set performing each action in the action decomposition set;

[0014] The prompt module is used to generate corresponding prompt information according to the recognition similarity.

[0015] In a possible design, the identification module is further used for:

[0016] Clustering is performed according to the attribute information of each experimenter in the experimenter set to obtain a target experimenter set corresponding to each category in a plurality of categories;

[0017] Collecting second motion data of each subject in the target subject set when performing each action in the action decomposition set, wherein the second motion data includes an action cycle, an action speed, an action start position, an action end position, and a muscle contraction range corresponding to the action;

[0018] Preprocessing the second motion data to obtain a training sample set corresponding to each category in the multiple categories;

[0019] An initial recognition model is constructed, and the initial recognition model is iteratively trained based on a training sample set corresponding to each of the multiple categories until a preset iteration termination condition is reached, thereby obtaining a recognition model corresponding to each of the multiple categories.

[0020] In a possible design, the identification module is specifically used for:

[0021] Determine the experimenter category to which the target user belongs in the target experimenter set;

[0022] selecting an object recognition model corresponding to the subject category from the plurality of categories;

[0023] The first motion data of each action is input into the target recognition model one by one to obtain the recognition similarity between each action and the corresponding standard action.

[0024] In one possible design, the initial model includes a convolutional layer, a pooling layer, a fully connected layer and a softmax function, wherein the convolutional layer is an LSTM layer containing 128 neurons, and the fully connected layer includes a first fully connected layer of 32 neurons and a second fully connected layer of 16 neurons.

[0025] In a possible design, the identification module is further used for:

[0026] Determine whether the number of iterations reaches a preset threshold, and if so, determine that the preset iteration termination condition is met;

[0027] or,

[0028] Determine whether the loss function of the initial recognition model converges, and if so, determine whether the preset iteration termination condition is met.

[0029] In a possible design, the identification module is further used for:

[0030] Determining an actual similarity corresponding to the first motion data;

[0031] The recognition model is updated according to the actual similarity and the recognition similarity.

[0032] A third aspect of the present invention provides an electronic device, comprising a memory and a processor, wherein the processor is used to implement the steps of the monitoring method for pelvic floor muscle rehabilitation training as described in the first aspect when executing a computer management program stored in the memory.

[0033] A fourth aspect of the present invention provides a computer-readable storage medium having a computer management program stored thereon, which, when executed by a processor, implements the steps of the monitoring method for pelvic floor muscle rehabilitation training as described in the first aspect above.

[0034] In summary, it can be seen that in the embodiment provided by the present invention, the target motion is decomposed to obtain an action decomposition set, and the first motion data of each action in the action decomposition set performed by the target user is obtained through the patch of the target user on the preset body part; the first motion data of each action is input into the recognition model one by one to obtain the recognition similarity between each action and the corresponding standard action, and the recognition model is obtained by pre-training the training samples through a neural network, and the training samples include the motion data of each action in the action decomposition set performed by each experimenter in the experimenter set; the corresponding prompt information is generated according to the recognition similarity. Therefore, by training a recognition model in advance to identify the standardization of each action performed by the user in the action decomposition set, timely feedback can be given on whether the user performs the action in a standard manner, thereby improving the recovery effect of the pelvic floor muscles. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of a flow chart of a method for monitoring pelvic floor muscle rehabilitation training provided by an embodiment of the present invention;

[0036] Figure 2 A virtual structural diagram of a monitoring device for pelvic floor muscle rehabilitation training provided by an embodiment of the present invention;

[0037] Figure 3 A schematic diagram of the hardware structure of a monitoring device for pelvic floor muscle rehabilitation training provided by an embodiment of the present invention;

[0038] Figure 4 A schematic diagram of an electronic device according to an embodiment of the present invention;

[0039] Figure 5 A schematic diagram of an embodiment of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0041] In the following description, specific embodiments of the present invention will be described with reference to steps and symbols performed by one or more computers, unless otherwise stated. Therefore, these steps and operations will be mentioned several times as being performed by a computer, and computer execution referred to herein includes operations by a computer processing unit of electronic signals representing data in a structured form. This operation converts the data or maintains it at a location in the computer's memory system, which can be reconfigured or otherwise change the operation of the computer in a manner familiar to testers in the field. The data structure maintained by the data is a physical location in the memory, which has specific characteristics defined by the data format. However, the principles of the present invention are described in the above text, which does not represent a limitation, and testers in the field will understand that the various steps and operations described below can also be implemented in hardware.

[0042] The principles of the present invention operate with many other general or special purpose computing, communication environments or configurations. Examples of well-known computing systems, environments and configurations suitable for use with the present invention may include, but are not limited to, handheld phones, personal computers, servers, multiprocessor systems, microcomputer-based systems, mainframe computers, and distributed computing environments, including any of the above systems or devices.

[0043] The terms "first", "second", and "third" in the present invention are used to distinguish different objects rather than to describe a specific order. In addition, the terms "include", "have", and any variations thereof are intended to cover non-exclusive inclusions.

[0044] The following describes the monitoring method for pelvic floor muscle rehabilitation training provided by the present invention from the perspective of a monitoring device for pelvic floor muscle rehabilitation training. The monitoring device for pelvic floor muscle rehabilitation training can be a smart wearable device, a terminal device, or a server. When the monitoring device for pelvic floor muscle rehabilitation training is a server, when prompting the user, the server can send a prompt message to the smart wearable device or the terminal device to prompt the user's exercise, without specific limitation.

[0045] See also Figure 1 , Figure 1 A flow chart of a method for monitoring pelvic floor muscle rehabilitation training provided by an embodiment of the present invention, the method for monitoring pelvic floor muscle rehabilitation training comprising:

[0046] 101. Perform action decomposition on the target motion to obtain an action decomposition set.

[0047] In this embodiment, the monitoring device for pelvic floor muscle rehabilitation training can decompose the target movement to obtain a movement decomposition set. The target movement is associated with the pelvic floor muscle rehabilitation training. The target movement can be a customized movement for pelvic floor muscle rehabilitation training, or a Kegel movement. As long as it can achieve the rehabilitation training of the pelvic floor muscles, there is no specific limitation. That is, before the target user performs the target movement to achieve the rehabilitation training of the pelvic floor muscles, the target movement corresponding to the pelvic floor muscle rehabilitation training can be first determined, and the target movement can be decomposed to obtain a movement decomposition set.

[0048] 102. Obtain first motion data of each action in the action decomposition set performed by the target user through the patch on the preset body part of the target user.

[0049] In this embodiment, before the target user performs each action in the action decomposition set, a patch can be applied to a preset body part corresponding to the pelvic floor muscles of the target user. The patch is used to obtain the first motion data of the target user when performing each action in the action decomposition set. The first motion data includes but is not limited to the action cycle, action speed, action starting position, action ending position, action strength and muscle contraction range corresponding to the action of each action in the action decomposition set. Thus, the monitoring device for pelvic floor muscle rehabilitation training can obtain the first motion data of the target user when performing each action in the action decomposition set through the patch applied to the preset body part of the target user.

[0050] It should be noted that when determining the action speed, the key coordinate point is first determined (the key coordinate point can be artificially defined to identify the coordinate point of the preset body part that can be most identifiable when the target user performs the target action, and the target action is any action in the action decomposition set), and the first moment of the action start position corresponding to the target action and the second moment of the action end position corresponding to the target action are determined, the execution duration of the target action is determined based on the first moment and the second moment, the distance between the action start position and the action end position is determined, and the action speed is determined based on the execution duration and the distance.

[0051] 103. Input the first motion data of each action into the recognition model one by one to obtain the recognition similarity between each action and the corresponding standard action.

[0052] In this embodiment, after acquiring the first motion data of each action, the monitoring device for pelvic floor muscle rehabilitation training can input the first motion data of each action into the recognition model to obtain the recognition similarity between each action and the standard action. The training sample includes the motion data of each action in the action decomposition set performed by each subject in the subject set. The recognition model is obtained by pre-training the training samples through a neural network, and is used to identify the similarity between each action in the action decomposition set and the corresponding standard action according to the first motion data, and obtain the similarity between each action and the corresponding standard action. The higher the similarity, the more accurate the completion of the action, and the higher the completion quality of the action.

[0053] It should be noted that, due to the different physical conditions of each user (such as height, weight, age, and degree of damage to the pelvic floor muscles, etc.), the corresponding pelvic floor muscle rehabilitation training is also different. Therefore, when the monitoring device for pelvic floor muscle rehabilitation training inputs the first motion data of each action into the recognition model one by one to obtain the recognition similarity between each action and the corresponding standard action, it can first determine the experimenter category to which the target user actually belongs in the target experimenter, and select a target recognition model corresponding to the experimenter category from multiple categories, and input the first motion data of each action into the target recognition model one by one to obtain the recognition similarity between each action and the corresponding standard action. Targeted training of a recognition model for each type of user can more accurately monitor and prompt the user's pelvic floor muscle rehabilitation training.

[0054] For ease of understanding, the following describes the training process of the recognition model:

[0055] Step 1: Clustering is performed according to the attribute information of each experimenter in the experimenter set to obtain a target experimenter set corresponding to each category in multiple categories.

[0056] In this step, subjects are selected to undergo pelvic floor muscle rehabilitation training. Before the training, the subject set is clustered according to the subject's attribute information to obtain a target subject set with clustering completed, that is, the subject is clustered according to the subject's height, age, weight and degree of damage to the pelvic floor muscle so as to reduce the training error. In this embodiment, the clustering algorithm k-means can be used to cluster the subjects in the subject set according to the subject's attribute information. Specifically, a preset number of random numbers are generated; k-neighboring values ​​of all random numbers are found; a weight coefficient of each random number is calculated based on the k-neighboring distance; weighted k-means clustering is performed on the random number points to obtain an initial cluster center; the distance between each sample and the cluster center is calculated according to the mean vector of the initial cluster center, and the sample is divided into a corresponding cluster: a new mean vector is calculated for the cluster samples divided for the first time, the new mean vector is used as the center of the cluster, and the steps of calculating the distance and dividing the corresponding cluster are repeated until there is no major change, thereby obtaining a target subject set corresponding to each category in the multiple categories.

[0057] Step 2: Collect the second motion data of each subject in the target subject set when performing each action in the action decomposition set.

[0058] In this step, the monitoring device for pelvic floor muscle rehabilitation training clusters the subject set into a target subject set corresponding to each category in multiple categories. Afterwards, patches can be placed on preset body parts for the subject in the target subject set corresponding to each category to collect the second motion data of each subject in the target subject set when performing each action in the action decomposition set. The second motion data includes action cycle, action speed, action starting position, action ending position, action strength and muscle contraction range corresponding to the action.

[0059] Step 3: pre-process the second motion data to obtain a training sample set corresponding to each of the multiple categories.

[0060] In this step, after obtaining the second motion data, the monitoring device for pelvic floor muscle rehabilitation training can preprocess the second motion data, and the preprocessing includes but is not limited to operations such as data cleaning, missing value interpolation, and sensitive information removal, thereby obtaining a training sample set corresponding to each category in multiple categories.

[0061] Step 4: construct an initial recognition model, and iteratively train the initial recognition model based on a training sample set corresponding to each of the multiple categories until a preset iteration termination condition is reached to obtain a recognition model corresponding to each of the multiple categories.

[0062] In this step, the monitoring device for pelvic floor muscle rehabilitation training can construct an initial recognition model, which is a recognition model constructed by a neural network, including a convolution layer, a pooling layer, a fully connected layer, and a softmax function, wherein the convolution layer is an LSTM layer, including 128 neurons, and the fully connected layer includes a first fully connected layer of 32 neurons and a second fully connected layer of 16 neurons. Of course, the number of layers of the convolution layer and the fully connected layer and the number of neurons can be adjusted according to actual conditions, and are not specifically limited.

[0063] The monitoring device for pelvic floor muscle rehabilitation training can iteratively train the initial recognition model according to the training sample set corresponding to each category in multiple categories, and after each iteration is completed, determine whether the preset iteration termination condition is met, that is, after each iteration is completed, determine whether the number of iterations reaches a preset threshold, if so, determine that the preset iteration termination condition is met; or, determine whether the loss function of the initial recognition model converges, if so, determine that the preset iteration termination condition is met.

[0064] When it is determined that a preset iteration termination condition is reached, the initial recognition model that has reached the preset iteration termination condition is determined as a recognition model that has completed training.

[0065] It should be noted that the monitoring device for pelvic floor muscle rehabilitation training can also divide the training samples in the training sample set into a training sample subset, a test subset and a verification subset, perform model training through the training sample subset, test the trained model through the test subset, and verify the model through the verification subset, thereby improving the prediction accuracy of the model,

[0066] 104. Generate corresponding prompt information according to the recognition similarity.

[0067] In this embodiment, after determining the recognition similarity corresponding to each action of the target user, the monitoring device for pelvic floor muscle rehabilitation training can generate corresponding prompt information based on the recognition similarity. For example, when the recognition similarity of the action reaches a preset parameter range, a success prompt information (smiley face, cheering, cheering, etc.) is generated and displayed to the user. If the recognition similarity does not reach the preset parameter range, the difference between the action and the standard action is determined, and an improvement direction is proposed based on the difference, such as prompt information such as more force, position to the left or right, etc., and the prompt information is displayed to the user.

[0068] It should be noted that the monitoring device for pelvic floor muscle rehabilitation training can also determine the actual similarity corresponding to the first motion data. Specifically, a standard template for each action in the action decomposition set is defined. After obtaining the first motion data of each action in the target user's execution action decomposition combination, the first motion data can be compared with the standard template to determine the actual similarity. Then, the recognition model is updated according to the difference between the actual similarity and the recognition similarity. This can achieve real-time updating of the model, making the model's prediction more and more accurate.

[0069] In summary, it can be seen that in the embodiment provided by the present invention, the target motion is decomposed to obtain an action decomposition set, and the first motion data of each action in the action decomposition set performed by the target user is obtained through the patch of the target user on the preset body part; the first motion data of each action is input into the recognition model one by one to obtain the recognition similarity between each action and the corresponding standard action, and the recognition model is obtained by pre-training the training samples through a neural network, and the training samples include the motion data of each action in the action decomposition set performed by each experimenter in the experimenter set; the corresponding prompt information is generated according to the recognition similarity. Therefore, by training a recognition model in advance to identify the standardization of each action performed by the user in the action decomposition set, timely feedback can be given on whether the user performs the action in a standard manner, thereby improving the recovery effect of the pelvic floor muscles.

[0070] The above describes the embodiment of the present invention from the perspective of a monitoring method for pelvic floor muscle rehabilitation training. The following describes the embodiment of the present invention from the perspective of a monitoring device for pelvic floor muscle rehabilitation training.

[0071] See also Figure 2 , a virtual structural diagram of a monitoring device for pelvic floor muscle rehabilitation training in an embodiment of the present invention, the monitoring device 200 for pelvic floor muscle rehabilitation training comprises:

[0072] A decomposition module 201 is used to decompose the target movement to obtain a movement decomposition set, wherein the target movement is associated with the pelvic floor muscle rehabilitation training;

[0073] An acquisition module 202 is used to acquire first motion data of each action in the action decomposition set when the target user performs the action through a patch on a preset body part of the target user;

[0074] The recognition module 203 is used to input the first motion data of each action into the recognition model one by one to obtain the recognition similarity between each action and the corresponding standard action, wherein the recognition model is obtained by training training samples in advance through a neural network, and the training samples include the motion data of each subject in the subject set performing each action in the action decomposition set;

[0075] The prompt module 204 is used to generate corresponding prompt information according to the recognition similarity.

[0076] In a possible design, the identification module 203 is further used for:

[0077] Clustering is performed according to the attribute information of each experimenter in the experimenter set to obtain a target experimenter set corresponding to each category in a plurality of categories;

[0078] Collecting second motion data of each subject in the target subject set when performing each action in the action decomposition set, wherein the second motion data includes an action cycle, an action speed, an action start position, an action end position, and a muscle contraction range corresponding to the action;

[0079] Preprocessing the second motion data to obtain a training sample set corresponding to each category in the multiple categories;

[0080] An initial recognition model is constructed, and the initial recognition model is iteratively trained based on a training sample set corresponding to each of the multiple categories until a preset iteration termination condition is reached, thereby obtaining a recognition model corresponding to each of the multiple categories.

[0081] In a possible design, the identification module 203 is specifically used for:

[0082] Determine the experimenter category to which the target user belongs in the target experimenter set;

[0083] selecting an object recognition model corresponding to the subject category from the plurality of categories;

[0084] The first motion data of each action is input into the target recognition model one by one to obtain the recognition similarity between each action and the corresponding standard action.

[0085] In one possible design, the initial model includes a convolutional layer, a pooling layer, a fully connected layer and a softmax function, wherein the convolutional layer is an LSTM layer containing 128 neurons, and the fully connected layer includes a first fully connected layer of 32 neurons and a second fully connected layer of 16 neurons.

[0086] In a possible design, the identification module 203 is further used for:

[0087] Determine whether the number of iterations reaches a preset threshold, and if so, determine that the preset iteration termination condition is met;

[0088] or,

[0089] Determine whether the loss function of the initial recognition model converges, and if so, determine whether the preset iteration termination condition is met.

[0090] In a possible design, the identification module 203 is further used for:

[0091] Determining an actual similarity corresponding to the first motion data;

[0092] The recognition model is updated according to the actual similarity and the recognition similarity.

[0093] above Figure 2 The monitoring device for pelvic floor muscle rehabilitation training in the embodiment of the present invention is described from the perspective of modular functional entities. The monitoring device for pelvic floor muscle rehabilitation training in the embodiment of the present invention is described in detail from the perspective of hardware processing. Please refer to FIG. 300, which is a schematic diagram of an embodiment of a monitoring device 300 for pelvic floor muscle rehabilitation training in the embodiment of the present invention. The monitoring device 300 for pelvic floor muscle rehabilitation training includes:

[0094] An input device 301, an output device 302, a processor 303 and a memory 304 (the number of the processor 303 can be one or more, Figure 3 In some embodiments of the present invention, the input device 301, the output device 302, the processor 303 and the memory 304 may be connected via a communication bus or other means, wherein: Figure 3 The communication bus connection is taken as an example.

[0095] Wherein, by calling the operation instruction stored in the memory 304, the processor 303 is used to perform the following steps:

[0096] Decomposing the target motion into motions to obtain a motion decomposition set, wherein the target motion is associated with the pelvic floor muscle rehabilitation training;

[0097] Acquire first motion data of each action in the action decomposition set performed by the target user through a patch on a preset body part of the target user;

[0098] Inputting the first motion data of each action into a recognition model one by one to obtain the recognition similarity between each action and a corresponding standard action, wherein the recognition model is obtained by training training samples in advance through a neural network, and the training samples include motion data of each subject in the subject set performing each action in the action decomposition set;

[0099] Generate corresponding prompt information according to the recognition similarity.

[0100] By calling the operation instructions stored in the memory 304, the processor 303 is also used to execute Figure 1 Any method in the corresponding embodiment.

[0101] See also Figure 4 , Figure 4 A schematic diagram of an electronic device according to an embodiment of the present invention.

[0102] like Figure 4 As shown, an embodiment of the present invention provides an electronic device, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented:

[0103] Decomposing the target motion into motions to obtain a motion decomposition set, wherein the target motion is associated with the pelvic floor muscle rehabilitation training;

[0104] Acquire first motion data of each action in the action decomposition set performed by the target user through a patch on a preset body part of the target user;

[0105] Inputting the first motion data of each action into a recognition model one by one to obtain the recognition similarity between each action and a corresponding standard action, wherein the recognition model is obtained by training training samples in advance through a neural network, and the training samples include motion data of each subject in the subject set performing each action in the action decomposition set;

[0106] Generate corresponding prompt information according to the recognition similarity.

[0107] In the specific implementation process, when the processor 420 executes the computer program 411, it can achieve Figure 1 Any implementation manner in the corresponding embodiments.

[0108] Since the electronic device introduced in this embodiment is a device used to implement a monitoring device for pelvic floor muscle rehabilitation training in the embodiment of the present invention, based on the method introduced in the embodiment of the present invention, technical personnel in this field can understand the specific implementation of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present invention is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present invention is within the scope of protection of the present invention.

[0109] Please refer to Figure 500, which is a schematic diagram of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention.

[0110] As shown in Figure 500, the embodiment of the present invention further provides a computer-readable storage medium 500, on which a computer program 511 is stored. When the computer program 511 is executed by a processor, the following steps are implemented:

[0111] Decomposing the target motion into motions to obtain a motion decomposition set, wherein the target motion is associated with the pelvic floor muscle rehabilitation training;

[0112] Acquire first motion data of each action in the action decomposition set performed by the target user through a patch on a preset body part of the target user;

[0113] Inputting the first motion data of each action into a recognition model one by one to obtain the recognition similarity between each action and a corresponding standard action, wherein the recognition model is obtained by training training samples in advance through a neural network, and the training samples include motion data of each subject in the subject set performing each action in the action decomposition set;

[0114] Generate corresponding prompt information according to the recognition similarity.

[0115] In the specific implementation process, the computer program 511 is executed by the processor to achieve Figure 1 Any implementation manner in the corresponding embodiments.

[0116] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0118] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0119] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0120] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0121] The embodiment of the present invention also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the following Figure 1 The process in the corresponding embodiment.

[0122] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0123] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0124] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There are other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0125] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0126] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0127] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0128] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A monitoring method for pelvic floor muscle rehabilitation training, characterized in that: include: Decomposing the target motion into motions to obtain a motion decomposition set, wherein the target motion is associated with the pelvic floor muscle rehabilitation training; Acquire first motion data of each action in the action decomposition set performed by the target user through a patch on a preset body part of the target user; Inputting the first motion data of each action into a recognition model one by one to obtain the recognition similarity between each action and a corresponding standard action, wherein the recognition model is obtained by training training samples in advance through a neural network, and the training samples include motion data of each subject in the subject set performing each action in the action decomposition set; Generate corresponding prompt information according to the recognition similarity.

2. The method according to claim 1, characterized in that The method further comprises: Clustering is performed according to the attribute information of each experimenter in the experimenter set to obtain a target experimenter set corresponding to each category in a plurality of categories; Collecting second motion data of each subject in the target subject set when performing each action in the action decomposition set, wherein the second motion data includes an action cycle, an action speed, an action start position, an action end position, and a muscle contraction range corresponding to the action; Preprocessing the second motion data to obtain a training sample set corresponding to each category in the multiple categories; An initial recognition model is constructed, and the initial recognition model is iteratively trained based on a training sample set corresponding to each of the multiple categories until a preset iteration termination condition is reached, thereby obtaining a recognition model corresponding to each of the multiple categories.

3. The method according to claim 2, characterized in that The step of inputting the first motion data of each action into the recognition model one by one to obtain the recognition similarity between each action and the corresponding standard action comprises: Determine the experimenter category to which the target user belongs in the target experimenter set; selecting an object recognition model corresponding to the subject category from the plurality of categories; The first motion data of each action is input into the target recognition model one by one to obtain the recognition similarity between each action and the corresponding standard action.

4. The method according to claim 2, characterized in that: The initial model includes a convolutional layer, a pooling layer, a fully connected layer and a softmax function, wherein the convolutional layer is an LSTM layer including 128 neurons, and the fully connected layer includes a first fully connected layer of 32 neurons and a second fully connected layer of 16 neurons.

5. The method according to any one of claims 2 to 4, characterized in that The method further comprises: Determine whether the number of iterations reaches a preset threshold, and if so, determine that the preset iteration termination condition is met; or, Determine whether the loss function of the initial recognition model converges, and if so, determine whether the preset iteration termination condition is met.

6. The method according to any one of claims 1 to 4, characterized in that The method further comprises: Determining an actual similarity corresponding to the first motion data; The recognition model is updated according to the actual similarity and the recognition similarity.

7. A monitoring device for pelvic floor muscle rehabilitation training, characterized in that: include: A decomposition module, used for performing action decomposition on the target motion to obtain an action decomposition set, wherein the target motion is associated with the pelvic floor muscle rehabilitation training; An acquisition module, used for acquiring first motion data of each action in the action decomposition set when the target user performs the action through a patch on a preset body part of the target user; A recognition module, used for inputting the first motion data of each action into a recognition model one by one, so as to obtain the recognition similarity between each action and the corresponding standard action, wherein the recognition model is obtained by training training samples in advance through a neural network, and the training samples include motion data of each subject in the subject set performing each action in the action decomposition set; The prompt module is used to generate corresponding prompt information according to the recognition similarity.

8. The device according to claim 7, characterized in that The identification module is also used for: Clustering is performed according to the attribute information of each experimenter in the experimenter set to obtain a target experimenter set corresponding to each category in a plurality of categories; Collecting second motion data of each subject in the target subject set when performing each action in the action decomposition set, wherein the second motion data includes an action cycle, an action speed, an action start position, an action end position, and a muscle contraction range corresponding to the action; Preprocessing the second motion data to obtain a training sample set corresponding to each category in the multiple categories; An initial recognition model is constructed, and the initial recognition model is iteratively trained based on a training sample set corresponding to each of the multiple categories until a preset iteration termination condition is reached, thereby obtaining a recognition model corresponding to each of the multiple categories.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to implement the monitoring method for pelvic floor muscle rehabilitation training as described in any one of claims 1 to 6 when executing a computer management program stored in the memory.

10. A computer-readable storage medium having a computer management program stored thereon, characterized in that: When the computer management program is executed by the processor, the monitoring method for pelvic floor muscle rehabilitation training as described in any one of claims 1 to 6 is implemented.

Images