Electronic punching bag device

Abstract

An electronic punching bag apparatus is disclosed, comprising a punching bag (1), a fixing unit (2) adapted to fix the apparatus to at least one surface, and an impact measuring unit (3). The unit (3) includes a processor module (3.2) which is operable to process data collected by at least one sensor module (3.1) to determine the location and magnitude of the impact caused by a user striking the body of the bag (1). Thus, the apparatus disclosed herein enhances the tracking of training performance and increases the user's informational involvement when training is performed.

Description

Technical Field

[0001] This application generally relates to body training apparatuses and systems. More specifically, this application relates to punching bags used for professional or recreational training in boxing or martial arts.

Background Art

[0002] Punching bags were originally used by boxers or martial artists to improve overall punching techniques. In recent years, punching bags are being used by people who are not martial artists but who desire to enjoy the physical strength and aerobic exercise effects achieved by performing punching motions. Further, since martial arts training programs have been proven to be an effective way to improve health and fitness, punching bags are currently being used as a stress reliever by many people. Many people are obtaining good results such as improved cardiorespiratory endurance, increased muscle strength and tone, and weight loss from martial arts training. It also helps users gain a sense of inner strength and emotional balance.

[0003] Martial arts training sessions are typically complemented with various apparatuses. One of the most common apparatuses used in martial arts training is the punching bag. The punching bag mimics an opponent and is designed to be repeatedly punched and kicked. Conventional punching bags and other training apparatuses mainly lack the ability to provide performance tracking and feedback. As a result, multiple apparatuses in the prior art incorporate electronic components to enable capturing and providing feedback on user performance data.

Summary of the Invention

Problems to be Solved by the Invention

[0004] Problems with these known punching bag devices include the unreliability of the sensor configuration, which is unsuitable for or unable to accurately record any type of impact at various locations on the punching bag, and / or the possibility that the sensors may give inaccurate readings.

[0005] Therefore, there is a need for an improved punching bag that enhances the tracking of training performance, particularly by accurately identifying the position and magnitude of the user's strikes, regardless of where on the punching bag the impact is delivered, thereby increasing the informational involvement of the trainee during training.

[0006] Therefore, the purpose of this application is to provide solutions to overcome the shortcomings identified in the prior art. [Means for solving the problem]

[0007] To achieve this objective, an electronic punching bag is proposed, comprising an impact measurement unit including a sensor module adapted to detect the impact force generated by a user striking the bag, and a processor module including a machine learning module configured to analyze the impact force data collected by the sensor module as a result of the user's strike and to identify specific pattern responses associated with standard impact force data generated from the user's strike at a specific location on the bag. For this purpose, the striking surface of the bag is divided into quadrants defining specific locations within the bag, and the sensors of the sensor module are positioned along the longitudinal axis inside the bag. In this configuration, a machine learning model is trained to automatically determine which quadrant was struck by the user's strike following the detection of the impact force.

[0008] In the advantageous configuration of the electronic punching bag to be covered by this application, the impact measurement unit further includes a video recording module adapted to record user strikes. Data collected by the sensor module is used to determine the magnitude of the impact force produced by the user's strike, while the combination of data collected by the two modules, namely the sensor module and the video recording module, is used to determine the location on the bag where the user's strike is delivered in a more efficient and accurate manner. In fact, quadrants located at the same distance from the sensor may have very similar pattern responses, so processing the user's strike video data captured by the video recording module is therefore advantageous in enabling the selection of the correct quadrant, and thus the correct location of the strike, in the event of ambiguity. As a result, the magnitude and location of the impact force are determined independently of the type of strike performed by the user and the part of the body used to make contact with the bag.

[0009] Finally, the object of this application is also a method for determining the location and magnitude of the impact force generated by a user striking an electronic punching bag. [Brief explanation of the drawing]

[0010] [Figure 1] This figure shows one embodiment of the electronic punching bag of the present application, where the following reference numerals represent: 1-punching bag; 2-fixing unit; 3-impact measurement unit; 3.1-sensor module; 3.2-processor module. [Figure 2] In the context of identifying the location on the bag where a user's blow is applied, an embodiment of a punching bag is shown, in which the striking surface of the bag is divided into multiple levels, each level containing multiple smaller quadrants; the reference numerals below represent: 1 - punching bag; 1.1 - striking surface of the bag; 1.2 - level; 1.3 - quadrant. [Figure 3]This figure shows one embodiment of the electronic punching bag that is the subject of this application, illustrating the position of the sensor submodule of the sensor module relative to the level / quadrant subdivisions of the bag's striking surface; the reference numerals below represent: 1 - punching bag; 1.2 - level; 1.3 - quadrant; 3.1.1 - sensor submodule. [Figure 4] This figure shows one embodiment of the electronic punching bag that is the subject of this application, wherein the fixing unit comprises a base module and a support structure, which protrude to support the bag on a first surface and a second surface, the surfaces being perpendicular to each other; furthermore, the internal core of the bag is formed by a set of four bladders stacked on top of each other; the following reference numerals represent: 1 - punching bag; 1.4 - bladder; 2.1 - base module; 2.2 - support structure; 2.3 - first support surface; 2.4 - second support surface. [Figure 5] This figure shows one embodiment of the electronic punching bag of the present application, the impact measurement unit further including a video recording module used to record user impacts on the punching surface of the bag; reference numerals below represent: 1 - punching bag; 2 - fixing unit; 3 - impact measurement unit; 3.1 - sensor module; 3.2 - processor module; 3.3 - video recording unit. [Modes for carrying out the invention]

[0011] This invention relates to an electronic punching bag device.

[0012] In one embodiment, the electronic punching bag device consists of a punching bag (1), a fixing unit (2), and an impact measuring unit (3).

[0013] In the context of this application, the punching bag (1) should be understood as an impact-resistant body, typically having an elongated cylindrical body, designed to withstand repeated impacts.

[0014] The fixing unit (2) is adapted to fix the device to at least one surface and may be any type of mechanism known in the art that can achieve this objective.

[0015] The impact measurement unit (3) consists of a sensor module (3.1) and a processor module (3.2).

[0016] The sensor module (3.1) is installed inside the bag and comprises sensor means configured to detect the impact force generated by the user's strike on the bag's striking surface (1.1) and to generate corresponding impact force data. In the context of this application, the impact force is the force generated by the user's strike upon reaching the punching bag. The impact force data relates to the measured force, which is the result of detection and processing steps performed in the sensor module, and is expressed in base units of the International System of Units (e.g., kg·m / s²). 2 It can be expressed in units of measurement, derived units (e.g., Newton units), or in a specially developed, proprietary measurement system.

[0017] The processor module (3.2) includes a machine learning module. The machine learning module comprises a training dataset unit adapted to store a training dataset, which includes at least impact force data generated by the sensor module (3.1) and associated class definitions based on the subdivision of the bag's striking surface (1.1) into several levels (1.2), each level comprising quadrants (1.3) progressively decreasing to a predetermined size, and each quadrant (1.3) corresponding to a unique position on the bag's striking surface (1.1). The size of each quadrant (1.3) can be defined as a function of the level of accuracy obtained when identifying the impact location, i.e., the level of accuracy increases as the size of quadrant (1.3) decreases. Since the user's contact with the bag (1) occurs along a specific area following the execution of the strike, for example depending on the degree of bulkiness of a boxing glove, the size of quadrant (1.3) can be 25 cm if higher accuracy is desired when obtaining the impact location. 2 or 50cm2 can be defined as the area. On the other hand, when the required accuracy is small, the size of the quadrant can be defined as 400 cm 2 or 625 cm 2 of area. However, the size of the quadrant (1.3) can be gradually reduced to the minimum value through the evolution and knowledge acquisition of the machine learning module, thereby enabling higher accuracy when identifying the position of the impact.

[0018] The processor module (3.2) further includes an arithmetic unit, which trains a machine learning classifier, uses a training data set, and at least uses the impact force data resulting from the user's strike as a test input to the machine learning classifier to recognize at least one quadrant (1.3) hit by the user's strike and is configured to identify at least one quadrant (1.3) hit by the user's strike. Further, the processor module (3.2) is also configured to identify the position of the user's strike within the bag based on the corresponding at least one quadrant position and has processing means configured to identify the magnitude of the user's strike based on the impact force data generated by the sensor module (3.1).

[0019] With the above-described arithmetic and sensing scheme including a machine learning mechanism, it is possible to accurately identify the position and magnitude of the user's strike regardless of where the strike is applied on the punching bag.

[0020] In another embodiment of the electronic punching bag device of the present application, the punching bag (1) has an elongated body, and its striking surface (1.1) is divided into at least three horizontal levels (1.2), defining the upper, central, and lower sections of the punching bag. In this particular case, the sensor module (3.1) is composed of a plurality of sensor elements adapted to detect the impact force generated by the user's strike on the striking surface (1.1) of the bag, which are incorporated into the elongated body and positioned along at least one longitudinal axis.

[0021] More specifically, in another embodiment, the sensor elements are grouped into at least three sensor sub-modules (3.1.1) that are arranged along one longitudinal axis and equally spaced from each other. Each sensor sub-module (3.1.1) is arranged in the upper, central, and lower horizontal sections (1.2) of the punching bag (1), respectively.

[0022] In this way, a uniform distribution of sensors along the striking surface (1.1) of the bag is ensured, which advantageously serves for the collection and respective processing of data for the purpose of identifying the position of the impact.

[0023] The sensor elements may be the following combination: at least one accelerometer, at least one gyroscope, and at least one magnetometer. Preferably, the sensor elements may be the following combination: at least one three-axis accelerometer, at least one three-axis gyroscope, and at least one three-axis magnetometer. With respect to the sensor sub-module (3.1.1), each may be constituted by at least one three-axis accelerometer, at least one three-axis gyroscope, and at least one three-axis magnetometer.

[0024] In another embodiment of the electronic punching bag device described in the present application, the fixing unit (2) comprises a base module (2.1) and a support structure (2.2).

[0025] The base module (2.1) is connected to the bottom of the bag body and supports the bag on a first surface (2.3). Next, the support structure (2.2) is adapted to fix the bag to a second surface (2.4) perpendicular to the first surface (2.3). Preferably, the support structure (2.3) is fixed to the upper part of the bag body.

[0026] The body of the punching bag has an elongated shape and comprises an inner core portion constituted by a bladder structure including at least one bladder (1.4), and the bladder (1.4) is a container for storing liquid.

[0027] By fixing the bag (1) to two orthogonal surfaces, along with the bag's internal bladder structure, the bag's reaction motion following a user's impact is restricted to a specific range, making it possible to identify more reliable impact force data, contributing to noise reduction in sensor readings, and allowing residual noise to be more effectively ignored through data processing.

[0028] In one embodiment, the bladder structure includes an array of four bladders (1.4) arranged longitudinally along one longitudinal axis. The bladders (1.4) in the array have shapes that are adapted to be stacked on top of each other, and optionally, the volume of each bladder (1.4) is 20 liters, and the liquid is water.

[0029] In another embodiment of the electronic punching bag apparatus of this application, the impact measurement unit (3) further comprises a video recording module (3.3) which is programmed to record the user's training session, in particular the user's impacts against the bag's striking surface (1.1), and to generate corresponding impact video data. In this embodiment, the processing means of the processor module (3.2) is further configured to identify the location of the user's impacts based on the corresponding quadrant position and impact video data.

[0030] More specifically, the data collected by the sensor module (3.1) is used to determine the magnitude of the impact force generated by the user's strike, while the combined data collected by the two modules, namely the sensor module (3.1) and the video recording module (3.3), is used in a more efficient way to determine the location on the bag where the user's strike was delivered. In fact, quadrants located at the same distance from the sensor may have very similar pattern responses, so processing the user's strike video data captured by the video recording module (3.3) is advantageous in allowing the selection of the correct quadrant, and therefore the correct location of the strike, in cases of ambiguity. As a result, the magnitude and location of the impact force are determined regardless of the type of strike performed by the user and the part of the body used to make contact with the bag.

[0031] In another embodiment, a video recording module (3.3) comprises processing means configured to process user impact recording video data using a computer vision algorithm and generate corresponding impact video data. In the context of this application, the computer vision algorithm is an algorithm adapted to analyze specific criteria within user impact recording video data and apply interpretations to a prediction or decision-making task, more specifically, to obtain from the processed video data information about at least a longitudinal section (1.2) of the punching bag (1) hit by the user's blow, wherein the longitudinal section (1.2) refers to a lateral section, i.e., the left or right section, or the central section. Deep learning and optical flow techniques are examples of computer vision algorithms that may be implemented to achieve the specified objectives.

[0032] In another embodiment, the processing means of the video recording module (3.3) is further configured to process the user's impact recording video data using a skeleton analysis algorithm to generate corresponding impact video data. The skeleton analysis algorithm is adapted to obtain information about the type of user's impact from the processed video data. Furthermore, the processor module (3.2) of the impact measurement unit (3) is further configured to determine the direction of the impact force generated by the user's impact, based on the impact location and impact video data.

[0033] Furthermore, the object of this application is a method for determining the location and magnitude of the impact force generated by a user striking an electronic punching bag.

[0034] This method includes the following steps: i. A step of subdividing the striking surface (1.1) of a punching bag (1) into multiple levels (1.2) by a control mechanism, wherein each level includes quadrants (1.3) that progressively decrease in size to a predetermined size, and each quadrant (1.3) corresponds to a specific position on the striking surface (1.1) of the bag; ii. A step of receiving a training dataset that includes at least impact force data and relevant class definitions based on quadrants (1.3) resulting from the subdivision of the bag's striking surface (1.1); iii. A step of training one or more machine learning classifiers to build a model for classifying at least the impact force data into one or more classes based on the training dataset; iv. A step of generating user impact force data by a sensing mechanism installed inside the bag (1) when detecting the impact force generated by the user striking the striking surface (1.1) of the bag; v. A step of receiving at least user impact force data as test input to at least one machine learning classifier, and classifying the user impact force data into one or more classes using a constructed model, each class representing a quadrant (1.3); vi. A step of associating the classified user's impact force with at least one quadrant (1.3) using a control mechanism, and determining the location of the user's impact based on the position of at least one corresponding quadrant; vii. A process in which the control mechanism determines the magnitude of the user's impact based on the impact force data generated by the sensing mechanism.

[0035] In one embodiment of this method, the detection of impact force includes the following steps: - A process for measuring the impact force signal generated from the user's actions on the bag (1); - A step of performing a peak detection algorithm to identify the peak value on the impact force signal; - A step of comparing the peak value with a predetermined threshold; - A step to detect the impact force generated by the user's blow if the peak value exceeds a predetermined threshold.

[0036] Another embodiment of this method further includes the following steps: - A step of recording video data of a user's workout session using a video recording mechanism, wherein the video data includes at least a number of video frames that capture the user's impacts against the striking surface of the bag; - A process of processing multiple video frames related to the user's impact using a video recording mechanism to generate impact video data; - A step of determining the location of the user's impact based on the corresponding quadrant position and impact video data using a control mechanism.

[0037] Furthermore, the generation of impact video data includes the following steps: - The process of using computer vision algorithms to process multiple video frames corresponding to user hits; - A step of extracting information from processed recorded video data regarding the longitudinal section (1.2) of the bag that is hit by the user's blow, wherein the longitudinal section refers to a transverse section, i.e., the left or right section, or the center section; - A step of generating a corresponding impact video signal that includes at least information about the longitudinal section hit by the user's blow.

[0038] In another embodiment of this method, the location of the user's strike on the striking surface (1.1) of the bag includes: - A process of processing information related to at least one quadrant position and impact video data by a control mechanism; - A step of identifying an interception between the location in at least one quadrant (1.3) hit by the user's blow and the longitudinal section (1.2) of the bag hit by the user's blow.

[0039] In another embodiment of this method, the step of determining the magnitude of the user's impact includes processing impact force data according to a general-purpose measurement metric. [Examples]

[0040] This application relates to an electronic punching bag.

[0041] The main objective is that the developed punching bag (1) can overcome all the shortcomings of conventional devices and can not only detect any type of impact, such as punches, elbows, or kicks, but also detect the location and intensity of these impacts in SI Newton units.

[0042] To achieve the required efficiency, the striking surface (1.1) is divided into nine distinct quadrants (1.3), with each quadrant (1.3) defined as the impact location. This scheme is itself a differentiating factor compared to all existing devices.

[0043] In addition to the above, in a preferred embodiment, the electronic punching bag is based on an array of IMU (Inertial Measurement Unit) sensors consisting of three acceleration axes and three gyroscope axes, each detecting shocks and forces in multiple possible quadrants (1.3). The bag (1) may also include any electronic components that complement it and form a shock measurement unit (sensor module, video recording module, and processor module) connected to a system-on-chip-SoC.

[0044] For example, a low-energy SoC with an architecture that enables the execution of digital signal processing algorithms and real-time inference models may be used.

[0045] Furthermore, it may also feature high energy efficiency and integrates a 2.4GHz transceiver for implementing Bluetooth® Low Energy BLE.

[0046] Regarding the sensor module, the IMU sensors are distributed across three vertical regions (1.2) of the bag (1) and can not only detect impacts but also determine the impacted zone (top, middle, or bottom) by comparing the vector modules of the three acceleration axes of each sensor. Then, through an algorithm that analyzes the directivity of the impact and using a video recording module (3.3), it is possible to determine whether the impact is in the left, middle, or right section of the bag, thereby narrowing the impact zone to one of nine possible quadrants (1.3).

[0047] These sensors can communicate with the SoC via synchronous serial communication protocols such as I2C.

[0048] Furthermore, the sensor module (3.1) may also be equipped with processing skills adapted to implement a set of digital processing algorithms, which reduce noise, enable parameterization of sampling frequency and sensitivity, perform internal calibration steps necessary for improving measurement accuracy, and identify datasets from accelerometer and gyroscope data such as relative orientation and linear acceleration.

[0049] A set of processing scripts may be implemented to allow real-time visualization of data, for example, by connecting the serial port of a processing device to the SoC, in order to observe data from various IMU sensors and data resulting from implemented digital signal processing algorithms, as well as to understand how the shock detection algorithm is behaving.

[0050] Alternatively, this data may be transmitted to an external processing device, such as a smartphone, via a wireless network communication protocol.

Claims

1. An electronic punching bag device, - Punching bag (1); - A fixing unit (2) adapted to secure the device to at least one surface; - Impact measurement unit (3) The impact measuring unit (3) is equipped with, - Sensor module (3.1); - Processor module (3.2) Includes, The sensor module (3.1) includes a sensor means configured to detect the impact force generated by the user's impact on the striking surface (1.1) of the bag and to generate corresponding impact force data. The processor module (3.2) includes a machine learning module, the machine learning module comprising a training dataset unit adapted to store a training dataset, which includes at least impact force data generated by the sensor module (3.1) and associated class definitions based on the subdivision of the bag's striking surface (1.1) into a plurality of levels (1.2), each level comprising quadrants (1.3) progressively decreasing to a predetermined size, each quadrant (1.3) corresponding to a unique position on the bag's striking surface (1.1), The processor module (3.2) further, - Processing unit; - Processing means Equipped with, The computing unit is configured to train a machine learning classifier, to use the training dataset and at least the impact force data resulting from the user's blow as a test input to the machine learning classifier, to recognize the quadrants (1.3) hit by the user's blow, and to identify at least one quadrant (1.3) hit by the user's blow. The processing means is configured to determine the position of the user's impact within the bag based on at least one corresponding quadrant position, and to determine the magnitude of the user's impact based on impact force data generated by the sensor module (3.1). An apparatus characterized by the following features.

2. The punching bag (1) has an elongated body, and the striking surface (1.1) of the bag is divided into at least three horizontal levels (1.2), defining the upper, middle, and lower sections of the punching bag. The sensor module (3.1) comprises a plurality of sensor elements adapted to detect the impact force generated by the user's strike on the striking surface (1.1) of the bag, the sensor elements being incorporated into the elongated body and positioned along at least one longitudinal axis. The apparatus according to claim 1, characterized in that

3. The apparatus according to claim 2, characterized in that the sensor elements are grouped into at least three sensor submodules (3.1.1) arranged along one longitudinal axis and equally spaced apart from one another, and each sensor submodule (3.1.1) is positioned in the upper, middle, and lower horizontal sections (1.2) of the punching bag (1), respectively.

4. The sensor element is a combination of at least one accelerometer, at least one gyroscope, and at least one magnetometer, preferably the sensor element is a combination of at least one three-axis accelerometer, at least one three-axis gyroscope, and at least one three-axis magnetometer. Each sensor submodule (3.1.1) includes at least one 3-axis accelerometer, at least one 3-axis gyroscope, and at least one 3-axis magnetometer. The apparatus according to claim 3, characterized in that

5. The aforementioned fixed unit (2) is - A base module (2.1) connected to the bottom of the body of the bag and supporting the bag on a first surface (2.3); and - A support structure (2.3) adapted to secure the bag to a second surface (2.4), wherein the second surface (2.4) is perpendicular to the first surface (2.3). Equipped with, The punching bag (1) is - An internal core portion comprising a bladder structure consisting of at least one bladder (1.4), wherein the bladder (1.4) is a container for liquid storage, Having a body that includes The apparatus according to any one of claims 1 to 4, characterized in that

6. The apparatus according to claim 5, characterized in that the bladder structure includes an array of four bladders (1.4) arranged longitudinally along one longitudinal axis, the bladders (1.4) in the array having shapes adapted to be stacked with each other, and optionally each bladder (1.4) having a volume of 20 liters and the liquid being water.

7. The impact measuring unit (3) further, - A video recording module (3.3) programmed to record the user's impact on the impact surface (1.1) of the bag and generate corresponding impact video data. Equipped with, The processing means of the processor module (3.2) is further configured to identify the location of the user's impact based on the corresponding quadrant position and the impact video data. The apparatus according to any one of claims 1 to 6, characterized in that

8. The video recording module (3.3) of the impact measurement unit (3) comprises processing means configured to process the user's impact recording video data using a computer vision algorithm and generate corresponding impact video data; the computer vision algorithm is adapted to obtain information from the processed video data regarding at least the longitudinal section (1.2) of the punching bag (1) that was hit by the user's blows; the longitudinal section (1.2) refers to the transverse section, i.e., the left or right section, or the central section. The apparatus according to claim 7, characterized in that

9. The processing means of the video recording module (3.3) is further configured to process the user's impact recording video data using a skeleton analysis algorithm to generate corresponding impact video data; the skeleton analysis algorithm is adapted to obtain information about the type of user's impact from the processed video data; The processor module (3.2) of the impact measurement unit (3) is further configured to determine the direction of the impact force generated by the user's blow, based on the impact location and impact video data. The apparatus according to claim 8, characterized in that

10. A method for determining the location and magnitude of the impact force generated by a user striking an electronic punching bag, i. A step of subdividing the striking surface (1.1) of a punching bag (1) into a plurality of levels (1.2) by a control mechanism, wherein each level includes a quadrant (1.3) that progressively decreases to a predetermined size, and each quadrant (1.3) corresponds to a specific position on the striking surface (1.1) of the bag; ii. A step of receiving a training dataset that includes at least impact force data and relevant class definitions based on quadrants (1.3) arising from the subdivision of the striking surface (1.1) of the bag; iii. A step of training one or more machine learning classifiers to construct a model for classifying the at least impact force data into one or more classes based on the training dataset; iv. A step of detecting the impact force generated by the user striking the striking surface (1.1) of the bag, by generating impact force data of the user using a sensing mechanism installed inside the bag (1); v. A step of receiving at least the user's impact force data as test input to at least one machine learning classifier, and classifying the user's impact force data into one or more classes using the constructed model, each class representing a quadrant (1.3); vi. A step of associating the classified user's impact force with at least one quadrant (1.3) by the control mechanism, and determining the location of the user's impact based on the position of at least one corresponding quadrant; vii. The process of determining the magnitude of the user's impact based on the impact force data generated by the sensing mechanism, using the control mechanism. A method characterized by including

11. The detection of the aforementioned impact force is performed by - A step of measuring the impact force signal generated from the user's actions on the bag (1); - A step of performing a peak detection algorithm to identify the peak value on the impact force signal; - A step of comparing the peak value with a predetermined threshold; - If the peak value exceeds a predetermined threshold, a step to detect the impact force generated by the user's blow. The method according to claim 10, characterized by including the following:

12. - A step of recording video data of the user's workout session using a video recording mechanism, wherein the video data includes at least a number of video frames that capture the user's impacts on the striking surface of the bag; - A process of processing the plurality of video frames related to the user's impact using the video recording mechanism and generating impact video data; - The control mechanism determines the location of the user's impact based on the corresponding at least one quadrant position and the impact video data. The method according to claim 10 or 11, further comprising:

13. The generation of the aforementioned impact video data is - A process of processing multiple video frames corresponding to the user's blows using a computer vision algorithm; - A step of extracting information from the processed recorded video data regarding the longitudinal section (1.2) of the bag that is hit by the user's blow, wherein the longitudinal section refers to a transverse section, i.e., the left or right section, or the center section; - A step of generating a corresponding impact video signal that includes at least information about the longitudinal section hit by the user's blow. The method according to claim 12, characterized by including

14. The location of the user's strike on the striking surface (1.1) of the bag is determined by: - A step of processing information related to the at least one quadrant position and the impact video data using the control mechanism; - The process of identifying the blockage between the location in at least one quadrant (1.3) hit by the user's blow and the longitudinal section (1.2) of the bag that was struck by the user's blow. The method according to claim 12 or 13, characterized by including the following:

15. The method according to any one of claims 10 to 14, characterized in that the step of determining the magnitude of the user's impact includes the step of processing the impact force data according to a general measurement metric.

Images