Fascia gun control method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of fascia guns, and discloses a fascia gun control method which comprises the following steps: acquiring pressure data generated when a fascia gun strikes a muscle contact surface, and acquiring motion data when the fascia gun strikes; fusing the pressure data and the motion data to obtain multi-modal characteristics of the fascia gun; analyzing the multi-modal characteristics to obtain muscle hardness data of the muscle contact surface; and working parameters of the fascia gun are adjusted according to the muscle hardness data. By means of the technical scheme, the problem that in the related technology, a fascia gun needs to be manually adjusted, so that the user experience feeling is poor is solved, automatic adjustment of the fascia gun according to different muscle hardness is achieved, and the user experience is improved.

Description

Technical Field

[0001] This application relates to the field of fascia gun technology, specifically to fascia gun control methods, devices, computer equipment, and storage media. Background Technology

[0002] In related technologies, during the operation of a fascia gun, the user needs to manually adjust the fascia gun to change the speed to suit the user's massage needs. However, manually adjusting the fascia gun requires extra time and effort, resulting in a poor user experience.

[0003] Application content

[0004] In view of this, this application provides a control method, device, computer equipment, and storage medium for a fascia gun to solve the problem of poor user experience caused by users manually adjusting the fascia gun in related technologies.

[0005] Firstly, this application provides a method for controlling a fascia gun, the method comprising:

[0006] Acquire pressure data generated when the fascia gun strikes the muscle contact surface, and acquire motion data of the fascia gun during the striking process;

[0007] By fusing pressure data and motion data, the multimodal characteristics of the fascia gun are obtained;

[0008] Analyze the multimodal features to obtain muscle stiffness data at the muscle contact surface;

[0009] Adjust the working parameters of the fascia gun according to muscle stiffness data.

[0010] In one embodiment of this application, acquiring pressure data generated when a fascia gun strikes a muscle contact surface includes:

[0011] When the fascia gun strikes the muscle contact surface, multiple sensors deployed on the head of the fascia gun detect the pressure distribution of the muscle contact surface in three-dimensional space.

[0012] Calculate the pressure mean and pressure variance using the pressure distribution;

[0013] The pressure mean and pressure variance are used as pressure data.

[0014] In one embodiment of this application, acquiring motion data of the fascia gun during impact includes:

[0015] When the fascia gun strikes the muscle contact surface, the motion sensing device built into the fascia gun detects the striking depth and contact angle of the fascia gun on the muscle contact surface, as well as the vibration frequency of the fascia gun during the striking.

[0016] Impact depth, contact angle, and vibration frequency are used as motion data.

[0017] In one embodiment of this application, multimodal features are analyzed to obtain muscle stiffness data of the muscle contact surface, including:

[0018] Input multimodal features into the detection model;

[0019] By performing temporal and dependency analysis on multimodal features using a detection model, multi-level abstract features are obtained. Based on these multi-level abstract features, nonlinear mapping calculations are performed to obtain muscle stiffness data.

[0020] In one embodiment of this application, a detection model is used to perform temporal and dependency analysis on multimodal features to obtain multi-level abstract features, and nonlinear mapping calculations are performed based on these multi-level abstract features to obtain muscle stiffness data, including:

[0021] By performing convolution operations on multimodal features in the detection model, convolution features are obtained, and pooling operations are performed on the convolution features to obtain pooled features with spatiotemporal correlation.

[0022] By performing temporal dependency analysis on pooling features using a recurrent neural network in the detection model, multi-level abstract features are obtained.

[0023] Muscle stiffness data is obtained by performing nonlinear mapping calculations on multi-level abstract features through the output layer of the detection model.

[0024] In one embodiment of this application, the method further includes:

[0025] Acquire pressure data, duration of pressure data generation, and operating temperature of the fascia gun;

[0026] If the pressure data is greater than the pressure threshold, then the target working frequency corresponding to the pressure data is determined based on the current working frequency of the fascia gun. The target working frequency is less than the current working frequency.

[0027] If the duration of pressure data generation exceeds the duration threshold or the operating temperature exceeds the temperature threshold, the fascia gun will stop operating.

[0028] In one embodiment of this application, after adjusting the operating parameters of the fascia gun based on muscle stiffness data, the method further includes:

[0029] Generate a curve showing the change in muscle stiffness over time;

[0030] In the three-dimensional muscle model, different markers are used to identify muscles with different levels of stiffness;

[0031] If the rate of change of muscle stiffness in the curve is greater than the rate of change threshold, a prompt message will be played.

[0032] The change curve is synchronized to the mobile terminal to generate a muscle recovery trend chart, which reflects the time required for muscles of different stiffness to recover to a normal state.

[0033] Obtain the change curves of different users and generate a comparative report on muscle stiffness.

[0034] Secondly, this application provides a control device for a fascia gun, the device comprising:

[0035] The acquisition module is used to acquire pressure data generated when the fascia gun strikes the muscle contact surface, as well as motion data of the fascia gun during the striking process.

[0036] The fusion module is used to fuse pressure data and motion data to obtain the multimodal features of the fascia gun;

[0037] The analysis module is used to analyze multimodal features and obtain muscle stiffness data of the muscle contact surface;

[0038] The adjustment module is used to adjust the working parameters of the fascia gun according to muscle stiffness data.

[0039] Thirdly, this application provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the fascia gun control method of the first aspect or any corresponding embodiment described above.

[0040] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the fascia gun control method of the first aspect or any corresponding embodiment described above.

[0041] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute the fascia gun control method described in the first aspect or any corresponding embodiment.

[0042] The control method of the fascia gun according to the embodiments of the present invention can achieve the following beneficial effects:

[0043] By acquiring pressure data generated when the fascia gun strikes the muscle contact surface, as well as motion data of the fascia gun during the striking process, basic data is provided for the fascia gun to perceive muscle state. By fusing pressure and motion data, multimodal features of the fascia gun are obtained, providing various reference feature data for assessing muscle hardness. By analyzing the multimodal features, muscle hardness data of the muscle contact surface is obtained, enabling adaptive perception of muscle hardness. Based on the muscle hardness data, the working parameters of the fascia gun are adjusted to adjust the massage intensity to a level suitable for muscle hardness, improving the user experience of the fascia gun. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0045] Figure 1 This is a flowchart of a fascia gun control method according to an embodiment of this application;

[0046] Figure 2 This is a flowchart of another fascia gun control method according to an embodiment of this application;

[0047] Figure 3 This is a flowchart of another fascia gun control method according to an embodiment of this application;

[0048] Figure 4 This is a flowchart of another fascia gun control method according to an embodiment of the present invention;

[0049] Figure 5 This is a structural block diagram of the control device for a fascia gun according to an embodiment of this application;

[0050] Figure 6 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of this application. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0052] The technical solutions in this invention embodiment can be applied to the following technical scenarios or fields: In sports recovery and training scenarios, they can be used for personalized recovery for athletes or fitness enthusiasts, adaptively identifying muscle stiffness and providing different massage intensities to avoid overstimulation or damage to muscles. They can also be used for dynamic warm-up before training to activate target muscle groups. Furthermore, they can be used to prevent sports injuries, identifying potential tension points in muscles and automatically focusing on applying appropriate pressure to massage those areas, reducing the risk of strains caused by muscle imbalances. They can also be used in physical therapy, rehabilitation, daily relaxation, and health management. The above application scenarios are merely examples of the use cases for this technical solution, and this embodiment does not limit the application scenarios of this technical solution.

[0053] This application provides a method for controlling a fascia gun, which adjusts the massage intensity by assessing muscle stiffness, thereby enabling the fascia gun to adaptively massage different muscle states and improve user experience.

[0054] According to an embodiment of this application, a control method for a fascia gun is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0055] This embodiment provides a control method for a fascia gun, which can be used with the aforementioned fascia gun. Figure 1 This is a flowchart of a fascia gun control method according to an embodiment of this application, such as... Figure 1 As shown, the process includes the following steps:

[0056] Step S101: Obtain pressure data generated when the fascia gun strikes the muscle contact surface, and obtain motion data of the fascia gun during the striking.

[0057] In this embodiment, the muscle contact surface refers to the area where the muscle contacts the head of the fascia gun during the massage process. Pressure data refers to the resistance generated by the muscle when the fascia gun impacts the muscle contact surface. This pressure data can be collected by a single pressure sensor deployed on the head of the fascia gun, or it can be a matrix of pressure data collected by multiple pressure sensors deployed on the head of the fascia gun. Motion data refers to the impact depth and contact angle of the fascia gun on the muscle contact surface, detected by the built-in sensors during operation, as well as the vibration frequency detected by the fascia gun during impact. When controlling the fascia gun, the pressure and motion data recorded by the fascia gun are first acquired.

[0058] Step S102: Fuse pressure data and motion data to obtain the multimodal features of the fascia gun.

[0059] In this embodiment, multimodal features refer to vectors composed of various types of data, such as vectors composed of data such as impact depth, contact angle, vibration frequency, and pressure data. By fusing pressure data and motion data, multimodal data of the fascia gun is obtained. For example, pressure data and motion data are preprocessed and merged into a single vector, which is used to characterize the physiological characteristics of the muscles collected by the fascia gun's sensors.

[0060] Step S103: Analyze the multimodal features to obtain muscle stiffness data of the muscle contact surface.

[0061] In this embodiment, muscle stiffness data refers to a quantitative indicator of the ability of muscle tissue to resist deformation under mechanical pressure. This quantitative indicator can be collected by mechanical sensors (such as pressure sensors, accelerometers, or impedance sensors). Muscle stiffness data at the muscle contact surface can be obtained by analyzing the multimodal features of the fascia gun. For example, muscle stiffness data can be obtained by classifying or regressing the multimodal features using a deep neural network. Alternatively, a mathematical model can be established based on the multimodal features and muscle stiffness data, and the muscle stiffness data can be calculated using this mathematical model through the multimodal features.

[0062] Step S104: Adjust the working parameters of the fascia gun according to the muscle stiffness data.

[0063] In this embodiment, the operating parameters of the fascia gun refer to the parameters when the fascia gun massages the muscles. These operating parameters include, but are not limited to, the actual vibration frequency of the fascia gun head, the pulse width modulation (PWM) duty cycle of the built-in motor, and the proportional coefficient Kp, integral coefficient Ki, and derivative coefficient Kd of the built-in motor in proportional-integral-derivative (PID) control. In specific implementations, based on muscle stiffness data, the operating parameters of the built-in motor of the fascia gun can be adjusted through PID control, or other methods can be used to adjust the operating parameters of the built-in motor. No specific limitations are imposed here, and the implementation can be determined by those skilled in the art.

[0064] The fascia gun control method provided in this embodiment acquires pressure data generated when the fascia gun strikes the muscle contact surface, as well as motion data of the fascia gun during the striking process, providing basic data for the fascia gun to perceive muscle state. The pressure and motion data are fused into multimodal features of the fascia gun, providing reliable data for muscle hardness analysis. By analyzing the multimodal features, the muscle hardness data of the muscle contact surface can be accurately identified, achieving adaptive perception of muscle hardness by the fascia gun. The working parameters of the fascia gun are adjusted according to the muscle hardness data, ensuring that the working parameters are adapted to different muscle hardness levels, thereby improving the user experience.

[0065] This embodiment provides a control method for a fascia gun, which can be used with the aforementioned fascia gun. Figure 2 This is a flowchart of another control method for a fascia gun according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0066] Step S201: Obtain pressure data generated when the fascia gun strikes the muscle contact surface, and obtain motion data of the fascia gun during the striking.

[0067] Specifically, the pressure data generated when the fascia gun strikes the muscle contact surface in step S201 above includes:

[0068] In step S2011a, when the fascia gun strikes the muscle contact surface, multiple sensors deployed on the head of the fascia gun detect the pressure distribution of the muscle contact surface in three-dimensional space.

[0069] In this embodiment, firstly, when the fascia gun head contacts the muscle and begins to strike, eight flexible piezoresistive pressure sensors arranged in a ring (sampling rate 200Hz) convert the pressure on the muscle in three-dimensional space into a resistance change signal based on the piezoresistive effect. Their 0-100N measurement range and ±2% high accuracy can accurately capture the feedback from strikes of varying intensities, accurately collecting pressure data whether it's a gentle massage or a deep strike. Secondly, the weak signals output by the sensors are processed by signal conditioning circuits such as amplification and filtering, and then converted into digital signals by an analog-to-digital converter (ADC) module. These digital signals are transmitted to the main control chip at a high-frequency sampling frequency of 200 times per second, ensuring that no moment of pressure change is missed. Then, based on the spatial position information of the eight sensors in the ring layout, a spatial interpolation algorithm is used to calculate and construct the pressure distribution matrix of the muscle contact surface in real time, thus clearly presenting the magnitude, direction, and distribution of pressure in three-dimensional space.

[0070] Step S2012a: Calculate the pressure mean and pressure variance using the pressure distribution.

[0071] In this embodiment, as described above, a pressure sensor array is deployed on the head of the fascia gun; that is, multiple pressure sensors can be set on the outer surface of the fascia gun head. Correspondingly, multiple pressure values ​​will be generated at multiple points in the contact area between the fascia gun head and the muscle contact surface. The pressure distribution indicates the pressure values ​​at these multiple points.

[0072] In practice, the average pressure and pressure variance are calculated based on the pressure distribution. The average pressure reflects the overall impact force of the fascia gun head on the muscle contact surface, while the pressure variance reflects the uniformity of the pressure values ​​at multiple points on the fascia gun head and muscle contact surface. The larger the pressure variance, the greater the difference between the pressure values ​​detected by the multiple pressure sensors set on the outer surface of the fascia gun head.

[0073] Step S2013a: Use the pressure mean and pressure variance as pressure data.

[0074] In this embodiment, multimodal pressure data is provided to enable the fascia gun to adapt to different muscle stiffness adjustment parameters. Specifically, the average pressure reflecting the overall impact force of the fascia gun and the variance of pressure reflecting the uniformity of force distribution on the fascia gun can be used as pressure data.

[0075] Specifically, obtaining the motion data of the fascia gun during the impact in step S201 above includes:

[0076] Step S2011b: When the fascia gun strikes the muscle contact surface, the motion sensing device built into the fascia gun detects the striking depth and contact angle of the fascia gun on the muscle contact surface, as well as the vibration frequency of the fascia gun during striking.

[0077] In this embodiment, the motion sensing device refers to a device that collects the acceleration and angular velocity of the fascia gun head. This motion sensing device can be a 6-axis Inertial Measurement Unit (IMU), which includes a 3-axis accelerometer and a 3-axis gyroscope. The impact depth indicates the maximum length the fascia gun head extends during operation. The impact depth can be obtained by the second integral of the acceleration. The contact angle refers to the angle between the fascia gun head and the muscle contact surface. The contact angle can be calculated from the angular velocity data collected by the gyroscope. The vibration frequency refers to the number of times the fascia gun head extends and retracts per second. When the fascia gun strikes the muscle contact surface, the motion sensing device detects the impact depth and the contact angle between the fascia gun and the muscle contact surface by measuring the vibration frequency of the fascia gun head.

[0078] Step S2012b uses the impact depth, contact angle, and vibration frequency as motion data.

[0079] In this embodiment, the vibration frequency of the fascia gun head, the depth of the fascia gun's impact on the muscle contact surface detected by the motion sensing device, and the contact angle between the fascia gun and the muscle contact surface are used as motion data.

[0080] Step S202: Fuse pressure data and motion data to obtain the multimodal features of the fascia gun.

[0081] Please see details Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0082] Step S203: Analyze the multimodal features to obtain muscle stiffness data of the muscle contact surface.

[0083] Please see details Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0084] Step S204: Adjust the working parameters of the fascia gun according to the muscle stiffness data.

[0085] Please see details Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0086] In this embodiment, by acquiring pressure and motion data between the head of the fascia gun and the muscle contact surface, especially by using multiple pressure sensors on the head of the fascia gun to collect pressure data at multiple points and collecting data at different locations on the muscle contact surface, the force situation of the muscle in different areas can be analyzed, which helps to obtain accurate pressure data. Combining the pressure data with motion data provides reliable raw data for the fascia gun to identify different muscle hardness.

[0087] This embodiment provides a control method for a fascia gun, which can be used with the aforementioned fascia gun. Figure 3 This is a flowchart of another fascia gun control method according to an embodiment of this application, such as... Figure 3 As shown, the process includes the following steps:

[0088] Step S301: Obtain pressure data generated when the fascia gun strikes the muscle contact surface, and obtain motion data of the fascia gun during the striking.

[0089] Please see details Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0090] Step S302: Fuse pressure data and motion data to obtain the multimodal features of the fascia gun.

[0091] Please see details Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0092] Step S303: Analyze the multimodal features to obtain muscle stiffness data of the muscle contact surface.

[0093] Specifically, step S303 includes:

[0094] Step S3031: Input the multimodal features into the detection model.

[0095] In this embodiment, the detection model refers to a neural network model used to detect muscle stiffness. This detection model receives multimodal features as input.

[0096] Step S3032: Perform temporal and dependency analysis on the multimodal features through the detection model to obtain multi-level abstract features, and perform nonlinear mapping calculation based on the multi-level abstract features to obtain muscle stiffness data.

[0097] In this embodiment, multi-level abstract features are features extracted layer by layer by the neural network when processing input data, progressing from low-level to high-level and from concrete to abstract. Multi-level abstract features are obtained by performing temporal and dependency analysis on the multi-modal features using a detection model. Then, nonlinear mapping calculations are performed on these multi-level abstract features to obtain muscle stiffness data. For example, a nonlinear mapping is established between the multi-level abstract features and muscle stiffness data, and muscle stiffness data is obtained through this nonlinear mapping using the multi-level abstract features.

[0098] As an example, the detection model performs time-series analysis on these multimodal data that change over time, observing the trends of data changes at different points in time. Simultaneously, it conducts dependency analysis to uncover the intrinsic relationships between pressure variance, pressure mean, impact depth, and contact angle. In this process, the neural network first extracts low-level features from the raw data, such as a pressure mean of 50N, pressure variance of 8, impact depth of 12mm, and contact angle of 75° at a given moment. These low-level features are then gradually integrated and refined to form mid-level features such as "when the pressure mean continuously increases and the pressure variance remains stable, the impact depth and contact angle exhibit a specific combination pattern," and high-level features such as "the muscle response pattern under the combined effects of pressure fluctuations, impact depth, and contact angle within a specific time period," thus constructing multi-level abstract features. Subsequently, through extensive training with experimental data, a nonlinear mapping relationship is established between the multi-level abstract features and the actual measured muscle stiffness data. When new multi-level abstract features are input, the current muscle stiffness data can be quickly calculated based on this nonlinear mapping model.

[0099] Step S304: Adjust the working parameters of the fascia gun according to the muscle stiffness data.

[0100] Please see details Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0101] The technical solution in this embodiment constructs multimodal features for collecting pressure and motion data from a fascia gun. A detection model establishes a mapping relationship between these multimodal features and muscle stiffness data, yielding muscle stiffness data corresponding to the multimodal features. This quantifies the muscle state reflected by different multimodal features. By providing muscle stiffness data to the fascia gun, operating parameters can be adjusted to suit the current muscle stiffness for massage.

[0102] In some optional implementations, step S3032 above includes:

[0103] Step a1: Convolutional features are obtained by performing convolutional operations on multimodal features through the Convolutional Neural Network (CNN) in the detection model, and pooling operations are performed on the convolutional features through pooling layers to obtain pooled features with spatiotemporal correlation.

[0104] In this embodiment, pooling features refer to the features extracted through pooling operations in a deep learning model. Multimodal data is input into a CNN in the detection model to perform convolution operations, resulting in convolutional features. Pooling layers are then used to perform pooling operations on these convolutional features, yielding pooled features with spatiotemporal correlation.

[0105] Step a2 involves performing temporal dependency analysis on pooling features using a recurrent neural network in the detection model to obtain multi-level abstract features.

[0106] In this embodiment, the pooling features obtained above are input into the recurrent neural network in the detection model to perform temporal dependency analysis on the pooling features, capturing the sequential relationships and mutual dependencies of the pooling features in the time dimension as multi-level abstract features. For example, a gated recurrent unit (GRU) is used as a feature for analyzing the mutual dependencies of pooling features in the time dimension using the recurrent neural network.

[0107] Step a3: The muscle stiffness data is obtained by performing nonlinear mapping calculations on the multi-level abstract features through the output layer of the detection model.

[0108] In this embodiment, the output layer of the detection model performs nonlinear mapping calculations on the multi-level abstract features obtained through CNN and recurrent neural networks to obtain muscle stiffness data corresponding to the multi-level abstract features.

[0109] In one example of this embodiment, the detection model employs a CNN and GRU architecture. The CNN consists of three convolutional layers and a max-pooling layer, with no limit on the number of filters used in the convolutional layers. The GRU has multiple hidden layers and dropout layers. The output layer of the detection model uses the sigmoid activation function to output muscle stiffness data.

[0110] As an example, multimodal feature data includes the mean pressure, variance of pressure, impact depth, and contact angle with the muscle surface for each impact, and this data is input into the detection model. The CNN first performs convolution operations on the multimodal data, sliding different convolution kernels through the data to capture convolutional features such as local trends in the mean pressure and subtle fluctuations in impact depth. Subsequently, pooling layers downsample the convolutional features, reducing the data dimensionality while retaining key information, thereby obtaining pooled features with spatiotemporal correlations, such as integrating feature information related to changes in pressure variance and adjustments in contact angle over a certain period.

[0111] Next, the GRU, acting as a recurrent neural network, performs temporal dependency analysis on the pooled features. Through a gating mechanism, it tracks feature changes over time, uncovering dependencies between features at different times. For example, it discovers that as the average pressure continuously increases, the impact depth and contact angle exhibit specific collaborative change patterns, thus constructing multi-level abstract features from low to high levels. Finally, the output layer of the detection model uses a pre-trained nonlinear function to map and calculate the multi-level abstract features, combining these abstract features into specific muscle stiffness data. This provides a precise basis for the intelligent adjustment of parameters such as impact force and frequency by the fascia gun.

[0112] By mapping multimodal features to muscle stiffness data using the detection model in this embodiment, the estimation of muscle stiffness data is achieved. This provides data support for adjusting different operating parameters of the fascia gun based on different muscle stiffness data.

[0113] In some optional embodiments, the fascia gun control method of the present invention further includes:

[0114] Step b1: Obtain pressure data, the duration of pressure data generation, and the working temperature of the fascia gun.

[0115] In this embodiment, during the operation of the fascia gun, the pressure data of the fascia gun when massaging muscles, the duration of generating pressure data, and the operating temperature of the fascia gun are monitored.

[0116] Step b2: If the pressure data is greater than the pressure threshold, then determine the target working frequency corresponding to the pressure data based on the current working frequency of the fascia gun. The target working frequency is less than the current working frequency.

[0117] In this embodiment, the pressure threshold is a value used to measure whether the pressure data is too high. The target working frequency refers to the working frequency that the fascia gun needs to be adjusted to for the current working frequency; the target working frequency is lower than the current working frequency. If the pressure data is greater than the pressure threshold, the manual indicates that the pressure data is too high. Then, based on the current working frequency of the fascia gun, the target working frequency is calculated. Since the target working frequency is lower than the current working frequency, it means that when the pressure data is too high, the fascia gun will automatically reduce its working frequency to ensure its own safety.

[0118] Step b3: If the duration of generating pressure data exceeds the duration threshold or the operating temperature exceeds the temperature threshold, then stop operating the fascia gun.

[0119] In this embodiment, the duration threshold is a value used to measure whether the duration of the pressure data is too long. The temperature threshold is a value used to measure whether the temperature data is too high. If the duration of the pressure data generated by the fascia gun exceeds the duration threshold or the operating temperature exceeds the temperature threshold, that is, the fascia gun has exceeded its operating time or is overheating, then the fascia gun will be stopped to ensure its working life and safety.

[0120] The technical solution of this embodiment provides a guarantee for the safe operation of the fascia gun by adjusting the working state of the fascia gun through monitoring pressure data, the duration of pressure data generation, and working temperature.

[0121] In some optional embodiments, after step S3032, the fascia gun control method of this embodiment of the invention further includes:

[0122] Step c1 generates a curve showing the change in muscle stiffness over time.

[0123] In this embodiment, the change curve refers to the curve of muscle hardness changing over time during the massage process of the fascia gun.

[0124] Step c2: In the three-dimensional muscle model, muscles with different stiffness are identified by different markers.

[0125] In this embodiment, the three-dimensional muscle model refers to a three-dimensional model constructed using 3D modeling techniques for different muscle groups in the human body. In the three-dimensional muscle model, muscles with different levels of stiffness are identified using different markers. For example, the upper part of the trained biceps brachii, which has higher stiffness, is marked in red, while the lower part, with lower stiffness, is represented in green. This allows for a visual distinction of muscle areas that require enhanced training.

[0126] Step c3: If the rate of change of muscle hardness in the change curve is greater than the rate of change threshold, a prompt message will be played.

[0127] In this embodiment, the rate of change threshold is a value used to measure how quickly muscle stiffness changes. If the rate of change of muscle stiffness in the change curve is greater than the rate of change threshold, a prompt is played. For example, when muscle stiffness rapidly increases and exceeds the rate of change threshold in a short period of time, the user is prompted with the message, "Please pay attention to the massage rhythm, relax appropriately, and gradual training will yield better results."

[0128] Step c4: Synchronize the change curve to the mobile terminal to generate a muscle recovery trend chart. The muscle recovery trend chart reflects the time required for muscles of different stiffness to recover to a normal state.

[0129] In this embodiment, the muscle recovery trend graph refers to a curve showing the time required for muscle recovery. The muscle recovery trend graph reflects the time required for muscles of different stiffness to recover to their normal state. For example, after massaging the biceps brachii with a fascia gun for 1 hour, the biceps brachii will experience some fatigue and soreness, generating a time curve showing the time required for the biceps brachii to recover to a normal, sore state.

[0130] Step c5: Obtain the change curves of different users and generate a comparison report of muscle stiffness.

[0131] In this embodiment, the change curves of muscle hardness over time generated by different users using a neck massage gun are obtained, and a comparison report of muscle hardness between different users is generated. This helps trainees communicate massage methods and find the working parameters of a massage gun suitable for most users.

[0132] Through the technical solution of this embodiment, after adjusting the working parameters of the fascia gun according to the muscle hardness data, it provides users with a curve of muscle hardness change over time, a three-dimensional display of different muscle hardness, a massage rhythm prompt based on the rate of change of muscle hardness, a muscle recovery trend graph, and a muscle comparison report of different users, providing users with richer functions and improving the user experience.

[0133] This embodiment provides another method for controlling a fascia gun, which can be used with the fascia gun described above. Figure 4 Another control method for a fascia gun according to an embodiment of the present invention achieves the adaptive adjustment function of the fascia gun based on muscle hardness through the following steps:

[0134] Step S401: Multimodal data acquisition.

[0135] Among them, multimodal data is Figures 1 to 3 Sub-concepts of multimodal features.

[0136] 1. Pressure data acquisition.

[0137] The above Figure 2Step S2011a describes the arrangement of eight flexible piezoresistive pressure sensors in a ring around the head of the fascia gun. The sampling rate can be 200Hz, each sensor unit has a measurement range of 0-100N and an accuracy of ±2%, and the pressure distribution matrix P(x,y,t) of the contact surface is collected in real time. This pressure distribution matrix reflects the pressure distribution of the eight pressure sensors deployed on the fascia gun head in the three-dimensional space of the muscle contact surface.

[0138] 2. Motion parameter detection.

[0139] Among them, the motion parameters are Figures 1 to 3 The sub-concept of motion data.

[0140] The above Figure 2 In step S2012b, the fascia gun uses the impact depth, contact angle, and vibration frequency as motion data during application. For example, the fascia gun's built-in 6-axis IMU is used to detect and measure the impact depth d, contact angle θ, and vibration frequency f in real time, and (d, θ, f) is used as motion parameters.

[0141] 3. Data preprocessing.

[0142] The above Figure 2 In step S2012a, the pressure mean and pressure variance are calculated using the pressure distribution. Specifically, a moving average filter (window width 50ms) can be applied to the pressure data to obtain the pressure mean P_avg and pressure variance P_var.

[0143] The above Figure 2 Step S202 fuses pressure data and motion data to obtain the multimodal features of the fascia gun. For example, Kalman filtering can be used to fuse IMU data to construct the feature vector of the multimodal features as [P_avg,P_var,d,θ,f], with a dimension of 1×5.

[0144] Step S402: Use the detection model to intelligently assess muscle stiffness.

[0145] 1. Architecture of the detection model.

[0146] As mentioned above Figure 3The network structure of the detection model in step S3032 consists of a convolutional neural network and a recurrent neural network. In one example of this embodiment, the detection model uses a 1D-CNN+GRU hybrid neural network, where the input layer of the detection model is used to receive a 5-dimensional feature vector (time series length 50). The CNN part includes three convolutional layers (number of filters 32 / 64 / 128, kernel_size=3) and a max pooling layer (pool_size=2). The convolutional layers of the CNN extract spatiotemporally correlated convolutional features from the multimodal features, and the pooling layers further extract spatiotemporally correlated pooling features. After CNN processing, the recurrent neural network of the detection model performs temporal dependency analysis on the above pooling features to extract multi-level abstract features. For example, a modified GRU network of the recurrent neural network is used, which includes 64 hidden units and a dropout of 0.3. For the extracted multi-level abstract features, the nonlinear function Sigmoid is used as the activation function in the output layer of the detection model, and the score H∈[0,1] of the muscle stiffness data is calculated through nonlinear mapping.

[0147] For example, by extracting the temporal dependency relationship between the pressure data of 10 sites collected from the head of the fascia gun within 30 seconds and the motion data of the fascia gun, the temporal dependency analysis of the multimodal data is realized, and multi-level abstract features with temporal and spatial correlation are obtained.

[0148] 2. Training the detection model.

[0149] In use Figure 2 and Figure 3 Before the detection model in the process can extract features from multimodal features and infer muscle stiffness, it needs to be trained.

[0150] For example, a dataset of 10,000 clinical electromyography-pressure correspondence data points was used, with mean squared error (MSE) and L2 regularization as the loss function, and Adam (learning rate lr = 0.001) as the optimizer. The model size was compressed to 500KB during deployment, and the inference latency was <15ms.

[0151] Step S403: Dynamic parameter adjustment.

[0152] According to the above Figure 1 Step S104 involves adjusting the working parameters of the fascia gun based on muscle stiffness data. After determining the muscle stiffness data, the working parameters of the fascia gun to be adjusted can be determined according to a pre-set stiffness-parameter mapping table. The specific method for adjusting the working parameters of the fascia gun is as follows:

[0153] 1. Control strategy for fascia guns.

[0154] The working parameters of the fascia gun are adjusted using PID control based on the hardness-parameter mapping table shown below.

[0155] Different hardness ranges correspond to different frequencies, amplitudes, and recommended usage times.

[0156] Hardness range Frequency (Hz) Amplitude (mm) Suggested duration H>0.7 30±2 12±1 90s 0.3≤H≤0.7 20±1.5 8±0.5 120s H<0.3 10±1 5±0.3 60s

[0157] 2. Motor control of the fascia gun.

[0158] The motor of the fascia gun adopts PID closed-loop control. The control variables include: the PWM duty cycle of the brushless motor, the actual vibration frequency obtained by the Hall sensor, parameters such as Kp=0.8, Ki=0.05, and Kd=0.1, and the amplitude adjustment achieved by the eccentric wheel mechanical structure.

[0159] 3. Safety protection for fascia guns.

[0160] Due to prolonged use of the fascia gun or the detection of abnormal pressure values ​​at the muscle contact surface, safety protection measures need to be implemented for the fascia gun. For example, real-time monitoring should be conducted to check if the single-point pressure at the fascia gun head exceeds 50N. If so, a first-level protection mechanism should be triggered, reducing the frequency by 20%. If the pressure exceeds the value for more than 3 seconds, a second-level protection mechanism should be triggered, pausing the operation and issuing an alarm. Real-time monitoring of the motor temperature is also necessary; if the motor temperature exceeds 65℃, operation should automatically stop.

[0161] Step S404: Visualize and interact with the fascia gun.

[0162] Based on the above Figure 1 After adjusting the working parameters of the fascia gun according to the muscle stiffness data in step S104, the fascia gun can also support the following functions:

[0163] 1. Interface display of the fascia gun.

[0164] The main interface is divided into sections: the left side displays the real-time stiffness curve (with a sliding window of 30 seconds on the time axis), the middle displays the three-dimensional muscle model (high stiffness area marked in red), and the bottom displays the current parameters (frequency / amplitude / remaining duration).

[0165] 2. Interactive functions of the fascia gun.

[0166] Supports touch operation; long-pressing the hardness curve allows viewing historical data. Target intensity can be adjusted by sliding (±15% offset). Voice prompts are also available; when the rate of change in muscle hardness exceeds 10%, it will announce: "Muscle relaxation detected, intensity automatically reduced."

[0167] 3. Use of data stored in the fascia gun.

[0168] It locally stores the most recent 1000 massage records and supports Bluetooth syncing to the mobile app to generate muscle recovery trend charts. It also compares the recorded massage data with data from similar users.

[0169] In this embodiment, through the synergistic effect of precision sensing, intelligent algorithms and closed-loop control, the fascia gun achieves adaptive massage for different muscle hardness, thus improving the user experience.

[0170] This embodiment also provides a control device for a fascia gun, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0171] This embodiment provides a control device for a fascia gun, such as... Figure 5 As shown, it includes:

[0172] The acquisition module 501 is used to acquire pressure data generated when the fascia gun strikes the muscle contact surface, and to acquire motion data of the fascia gun during the striking.

[0173] The fusion module 502 is used to fuse pressure data and motion data to obtain the multimodal features of the fascia gun.

[0174] Analysis module 503 is used to analyze multimodal features and obtain muscle stiffness data of the muscle contact surface.

[0175] The adjustment module 504 is used to adjust the working parameters of the fascia gun according to muscle stiffness data.

[0176] In some optional implementations, the acquisition module 501 includes:

[0177] The pressure detection unit is used to detect the pressure distribution of the muscle contact surface in three-dimensional space by multiple sensors deployed on the head of the fascia gun when the fascia gun strikes the muscle contact surface.

[0178] The pressure data calculation unit is used to calculate the pressure mean and pressure variance based on the pressure distribution.

[0179] The pressure data determination unit is used to determine the pressure mean and pressure variance as pressure data.

[0180] In some optional implementations, the acquisition module 501 further includes:

[0181] The motion data detection unit is used to detect the depth and angle of the fascia gun's impact on the muscle contact surface, as well as the vibration frequency of the fascia gun during the impact, through the motion sensing device built into the fascia gun.

[0182] The motion data determination unit is used to take the impact depth, contact angle, and vibration frequency as motion data.

[0183] In some alternative implementations, the analysis module 503 includes:

[0184] The feature input subunit is used to input multimodal features into the detection model;

[0185] The muscle stiffness determination subunit is used to perform temporal and dependency analysis on multimodal features through a detection model to obtain multi-level abstract features, and to perform nonlinear mapping calculations based on the multi-level abstract features to obtain muscle stiffness data.

[0186] In some optional implementations, the muscle stiffness determination subunit is used for:

[0187] By performing convolution operations on multimodal features in the detection model, convolution features are obtained, and pooling operations are performed on the convolution features to obtain pooled features with spatiotemporal correlation.

[0188] By performing temporal dependency analysis on pooling features using a recurrent neural network in the detection model, multi-level abstract features are obtained.

[0189] Muscle stiffness data is obtained by performing nonlinear mapping calculations on multi-level abstract features through the output layer of the detection model.

[0190] In some alternative implementations, the control device for the fascia gun further includes:

[0191] Multiple data acquisition modules are used to acquire pressure data, the duration of pressure data generation, and the working temperature of the fascia gun.

[0192] The overpressure protection module is used to determine the target working frequency corresponding to the pressure data based on the current working frequency of the fascia gun if the pressure data is greater than the pressure threshold. The target working frequency is less than the current working frequency.

[0193] The timeout and over-temperature protection module is used to stop the fascia gun from running if the duration of pressure data generation exceeds the duration threshold or the operating temperature exceeds the temperature threshold.

[0194] In some optional implementations, the muscle stiffness determination subunit, after adjusting the fascia gun's operating parameters based on muscle stiffness data, is also used for:

[0195] Generate a curve showing the change in muscle stiffness over time;

[0196] In the three-dimensional muscle model, different markers are used to identify muscles with different levels of stiffness;

[0197] If the rate of change of muscle stiffness in the curve is greater than the rate of change threshold, a prompt message will be played.

[0198] The change curve is synchronized to the mobile terminal to generate a muscle recovery trend chart, which reflects the time required for muscles of different stiffness to recover to a normal state.

[0199] Obtain the change curves of different users and generate a comparative report on muscle stiffness.

[0200] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0201] In this embodiment, the control device of the fascia gun is presented in the form of a functional unit. Here, a unit refers to an application-specific integrated circuit (ASIC) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0202] This application also provides a computer device having the above-described features. Figure 5 The control device for the fascia gun shown.

[0203] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of this application, such as... Figure 6 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.

[0204] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0205] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0206] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0207] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0208] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 6 Taking the example of a connection between China and Israel via a bus.

[0209] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0210] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0211] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0212] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for controlling a fascia gun, characterized in that, The method includes: Acquire pressure data generated when the fascia gun strikes the muscle contact surface, and acquire motion data of the fascia gun during the striking process; By fusing the pressure data and the motion data, the multimodal characteristics of the fascia gun are obtained; By analyzing the multimodal features, muscle stiffness data of the muscle contact surface are obtained; The operating parameters of the fascia gun are adjusted based on the muscle stiffness data.

2. The method according to claim 1, characterized in that, The acquisition of pressure data generated when the fascia gun strikes the muscle contact surface includes: When the fascia gun strikes the muscle contact surface, multiple sensors deployed on the head of the fascia gun detect the pressure distribution of the muscle contact surface in three-dimensional space. The pressure mean and pressure variance are calculated using the pressure distribution described above. The pressure mean and the pressure variance are used as the pressure data.

3. The method according to claim 1, characterized in that, The acquisition of motion data of the fascia gun during impact includes: When the fascia gun strikes the muscle contact surface, the motion sensing device built into the fascia gun detects the striking depth and contact angle of the fascia gun on the muscle contact surface, as well as the vibration frequency of the fascia gun during the striking. The impact depth, the contact angle, and the vibration frequency are used as the motion data.

4. The method according to claim 1, characterized in that, The analysis of the multimodal features yields muscle stiffness data of the muscle contact surface, including: The multimodal features are input into the detection model; The detection model is used to perform temporal and dependency analysis on the multimodal features to obtain multi-level abstract features, and nonlinear mapping calculation is performed based on the multi-level abstract features to obtain the muscle stiffness data.

5. The method according to claim 4, characterized in that, The process involves performing temporal and dependency analysis on the multimodal features using the detection model to obtain multi-level abstract features, and then performing nonlinear mapping calculations based on these multi-level abstract features to obtain the muscle stiffness data, including: The multimodal features are convolved by the convolutional neural network in the detection model to obtain convolutional features, and then pooled by the convolutional features to obtain pooled features with spatiotemporal correlation. The pooling features are subjected to temporal dependency analysis using the recurrent neural network in the detection model to obtain multi-level abstract features. The muscle stiffness data is obtained by performing nonlinear mapping calculations on the multi-level abstract features through the output layer of the detection model.

6. The method according to claim 1, characterized in that, The method further includes: Acquire the pressure data, the duration of generating the pressure data, and the operating temperature of the fascia gun; If the pressure data is greater than the pressure threshold, then a target working frequency corresponding to the pressure data is determined based on the current working frequency of the fascia gun, wherein the target working frequency is less than the current working frequency; If the duration of generating the pressure data exceeds a duration threshold or the operating temperature exceeds a temperature threshold, then the fascia gun will stop operating.

7. The method according to claim 5, characterized in that, After adjusting the operating parameters of the fascia gun according to the muscle stiffness data, the method further includes: Generate the curve of muscle stiffness changing over time; In the three-dimensional muscle model, different markers are used to identify the muscles corresponding to different muscle stiffness. If the rate of change of muscle stiffness in the change curve is greater than the rate of change threshold, a prompt message will be played. The change curve is synchronized to the mobile terminal to generate a muscle recovery trend chart, which reflects the time required for muscles of different stiffness to recover to a normal state. Obtain the change curves of different users and generate a comparison report of muscle stiffness.

8. A control device for a fascia gun, characterized in that, The device includes: The acquisition module is used to acquire pressure data generated when the fascia gun strikes the muscle contact surface, and to acquire motion data of the fascia gun during the striking process. A fusion module is used to fuse the pressure data and the motion data to obtain the multimodal features of the fascia gun. The analysis module is used to analyze the multimodal features to obtain muscle stiffness data of the muscle contact surface; An adjustment module is used to adjust the working parameters of the fascia gun according to the muscle stiffness data.

9. A computer device, characterized in that, include: The device includes a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the control method of the fascia gun according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the control method of the fascia gun according to any one of claims 1 to 7.

11. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the control method for the fascia gun according to any one of claims 1 to 7.

Images