Electronic punching bag

Description

1 / 14 ELECTRONIC PUNCHING BAG ORDER FIELD

[0001] This application relates generally to physical training devices and systems. More specifically, this application relates to punching bags used for professional or recreational boxing or martial arts training. STATE OF THE ART

[0002] Punching bags were originally used by boxers or martial arts practitioners to improve general punching techniques. Recently, punching bags are being used by non-practitioners who wish to develop strength and receive the aerobic benefits obtained through the execution of the punching motion. Furthermore, punching bags are now used as a source of stress relief by many people, since martial arts training programs have proven to be an effective way to improve health and fitness. Many people see positive results from martial arts training, such as improved cardiovascular endurance, increased strength and muscle tone, as well as weight loss. It also helps users gain a sense of strength and emotional balance.

[0003] Martial arts training sessions are typically supplemented with various devices. One of the most common devices used in martial arts training is the punching bag. The punching bag resembles an opponent and is designed to be repeatedly punched and kicked. Traditional punching bags and other training devices largely lack the ability to provide performance monitoring and feedback. As a result, several state-of-the-art devices have incorporated electronic components that allow them to capture and provide feedback on user performance data.

[0004] A problem with these known bag devices Petition 870250090828, dated 06 / 10 / 2025, pp. 91 / 115 2 / 14 of the impacts is that the sensor configuration may be unreliable and may not be adequate or capable of accurately recording all types of impacts in various locations on the punching bag, and / or the sensors may provide false readings.

[0005] Consequently, there is a need for an improved punching bag that provides enhanced monitoring of training performance, especially with regard to accurately determining the location and magnitude of the user's strike, regardless of where the strike is delivered on the punching bag, thereby increasing the engagement of the student's intelligence during training. BRIEF DESCRIPTION OF THE ORDER

[0006] It is therefore the objective of the present application to describe a solution that circumvents the deficiencies identified in the prior art.

[0007] To achieve this objective, an electronic punching bag is proposed, comprising an impact measurement unit, including a sensory module adapted to detect the force of an impact produced by a user strike on the bag, and a processing module comprising a machine learning module configured to analyze impact force data collected by the sensory module as a result of a user strike, and to identify specific standardized responses associated with standard impact force data produced from user strikes at specific locations on the bag. To this end, the striking surface of the bag is divided into quadrants, defining said specific locations on the bag, and the sensors of the sensory module are arranged along a longitudinal axis within the bag.With this scheme, a machine learning model is trained so that, after detecting an impact force, it can automatically identify which quadrant or quadrants may have been hit by the user's blow.

[0008] In an advantageous configuration of the electronic punching bag that is the subject of this application, the impact measuring unit includes Petition 870250090828, dated 06 / 10 / 2025, pp. 92 / 115 3 / 14 Additionally, a video recording module, adapted to record the user's strike, is included. The data collected by the sensory 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, i.e., the sensory module and the video recording module, is used to determine, more efficiently and accurately, the location on the bag where the user's strike is delivered. In fact, since quadrants positioned at the same distance from a sensor can have very similar standardized responses, processing the video data of the user's strike, captured by the video recording module, is advantageous because it allows the selection of the correct quadrant and, therefore, the correct location of the strike, in case of ambiguity.As a result, the magnitude and location of the impact force are determined independently of the type of strike executed by the user and the part of the body used to make contact with the bag.

[0009] In short, the present application also concerns a method for determining the location and magnitude of an impact force produced by a user's blow on an electronic punching bag. DESCRIPTION OF THE FIGURES

[0010] Figure 1 - representation of a version of the electronic punching bag of the present application, where the reference signs represent: - punching bag; - anchoring unit; - impact measurement unit; 3.1 - sensory module; 3.2 - processor module.

[0011] Figure 2 - In the context of determining the location where the user's strike is delivered to the bag, a modality of the punching bag is illustrated, where the striking surface of the bag is divided into a plurality of levels, each level comprising a plurality of smaller quadrants; Petition 870250090828, dated 06 / 10 / 2025, pp. 93 / 115 4 / 14 the reference signs represent: - punching bag; 1.1 - striking surface of the bag; 1.2 - level; 1.3 - quadrant.

[0012] Figure 3 - representation of an embodiment of the electronic punching bag object of the present application, illustrating the position of the sensor submodules of the sensory module in relation to the level / quadrant subdivision of the bag's striking surface; the reference signals represent: - punching bag; 1.2 - level; 1.3 - quadrant; 3.1.1 - sensor submodule.

[0013] Figure 4 - representation of an embodiment of the electronic punching bag object of the present application, where the anchoring unit comprises a base module and a support structure, being designed to provide support for the bag on a first and a second surface, said surfaces being perpendicular to each other; additionally, the inner center of the bag is formed by a set of four bladders stacked one on top of the other; the reference signs represent: - punching bag; 1.4 - bladder; 2.1 - basic module; 2.2 - support structure; 2.3 - first support surface; 2.4 - second support surface.

[0014] Figure 5 - Illustration of an embodiment of the electronic punching bag of the present application, where the impact measuring unit additionally includes a video recording module, used to record the Petition 870250090828, dated 06 / 10 / 2025, pp. 94 / 115 5 / 14 user strike on the bag's striking surface; reference signs represent: - punching bag; - anchoring unit; - impact measurement unit; 3.1 - sensory module; 3.2 - processor module; 3.3 - Video recording unit. ORDER DESCRIPTION

[0015] This application relates to an electronic punching bag device.

[0016] In one embodiment, the electronic punching bag apparatus comprises a punching bag (1), an anchoring unit (2) and an impact measuring unit (3).

[0017] In the context of the present application, a punching bag (1) should be understood as a resistant body designed to be repeatedly struck, commonly with an elongated body of cylindrical shape.

[0018] The anchoring unit (2) is adapted to fix the device to at least one surface, which may be any type of mechanism known in the state of the art that allows achieving this purpose.

[0019] The impact measurement unit (3) comprises a sensory module (3.1) and a processing module (3.2).

[0020] The sensory module (3.1) comprises sensor means installed inside the bag and configured to detect the impact force produced by the user's blow on the striking surface of the bag (1.1) and generate corresponding impact force data. In the context of this application, an impact force is the force produced by the user's blow when striking the punching bag. The impact force data refers to a force measurement, resulting from the detection and processing steps performed in the sensory module, and can be expressed in SI base units. Petition 870250090828, dated 06 / 10 / 2025, pages 95 / 115 6 / 14 (e.g., kg^ / s2), derived units (e.g., in Newtons) or in a specially developed proprietary metric system.

[0021] The processing module (3.2) comprises a machine learning module. Said machine learning module comprises a training dataset unit adapted to store a training dataset including at least impact force data generated by the sensory module (3.1) and the associated class definition based on a subdivision of the bag's striking surface (1.1) into a plurality of levels (1.2), each comprising progressively smaller quadrants (1.3) down to a predefined size, each quadrant (1.3) corresponding to a unique location on said bag's striking surface (1.1). The size of each quadrant (1.3) can be defined as a function of the level of accuracy to be obtained in determining the impact location, i.e., the level of accuracy increases with decreasing quadrant size (1.3).Since the user's contact with the bag (1), after executing a punch, occurs over a certain area, depending, for example, on the volume of the boxing glove, it can be mentioned that the size of a quadrant (1.3) can be defined as an area of ​​25cm2 or 50cm2 if greater precision is desired in obtaining the location of the impact. On the other hand, the size of a quadrant can be defined as an area of ​​400cm2 or 625cm2 if less precision is required. However, the size of a quadrant (1.3) can be progressively reduced to a minimum value, through the evolution and acquisition of knowledge of the machine learning module, which allows greater precision in determining the location of an impact.

[0022] The processing module (3.2) further comprises a computing unit configured to train a machine learning classifier to recognize the quadrants (1.3) struck by a user's blow using the training dataset and using at least the impact force data generated from the user's blow as test input for the machine learning classifier to determine Petition 870250090828, dated 06 / 10 / 2025, pp. 96 / 115 7 / 14 at least one quadrant (1.3) hit by the user's strike. Additionally, the processing module (3.2) also has processing means configured to determine the location of the user's strike on the bag based on at least one corresponding quadrant location and to determine the magnitude of the user's strike based on the impact force data generated by the sensory module (3.1).

[0023] Through the described computational and sensory scheme, which involves machine learning mechanisms, it is possible to accurately determine the location and magnitude of the user's strike, regardless of where the user's strike is delivered on the punching bag.

[0024] In another embodiment of the electronic punching bag apparatus of the present invention, 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 specific case, the sensory module (3.1) comprises a plurality of sensor elements, adapted to detect the impact force produced by the user's blow on the striking surface of the bag (1.1), which are incorporated into the elongated body and positioned along at least one longitudinal axis.

[0025] More particularly, and in another embodiment, the sensor elements are grouped into at least three sensor submodules (3.1.1) positioned along a longitudinal axis and equally spaced from each other. Each sensor submodule (3.1.1) is positioned in the upper, central and lower horizontal sections (1.2) of the punching bag (1), respectively.

[0026] In this way, a uniform distribution of the sensors along the impact surface of the bag is guaranteed (1.1), which favors data collection and processing for the purpose of determining the location of the impact.

[0027] The sensor elements may be a combination of the following: at least one accelerometer, at least one gyroscope and at least Petition 870250090828, dated 06 / 10 / 2025, pp. 97 / 115 8 / 14 a magnetometer. Preferably, the sensor elements may be a combination of the following: at least one 3-axis accelerometer, at least one 3-axis gyroscope, and at least one 3-axis magnetometer. With respect to the sensor submodules (3.1.1), each may comprise at least one 3-axis accelerometer, at least one 3-axis gyroscope, and at least one 3-axis magnetometer.

[0028] In another embodiment of the electronic punching bag apparatus described in this application, the anchoring unit (2) comprises a base module (2.1) and a support structure (2.2).

[0029] The base module (2.1) is connected to a lower part of the bag body and provides support for the bag on a first surface (2.3). In turn, 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 an upper part of the bag body.

[0030] The punching bag body has an elongated shape and comprises an inner center part, consisting of a bladder structure composed of at least one bladder (1.4), said bladder (1.4) being a container for storing liquids.

[0031] Fixing the bag (1) to two perpendicular surfaces, together with the bag’s internal bladder structure, allows for the determination of more reliable impact force data, since the reaction movements of the bag after the user’s strike are limited to a certain range, contributing to the reduction of noise in the sensor readings and also allowing, through data processing, the remaining noise to be more effectively ignored.

[0032] In one embodiment, the bladder structure comprises a set of 4 pouches (1.4) arranged longitudinally along a longitudinal axis. The pouches (1.4) of the set have a shape adapted to be fixed one on top of the other and, optionally, the volume of each pouch (1.4) is Petition 870250090828, dated 06 / 10 / 2025, pp. 98 / 115 9 / 14 liters, the liquid being water.

[0033] In another embodiment of the electronic punching bag apparatus of the present application, the impact measuring unit (3) further comprises a video recording module (3.3), programmed to record the user's training session, particularly the user's strike on the striking surface of the bag (1.1), and to generate the corresponding video impact data. In connection with this embodiment, the processing means of the processor module (3.2) are further configured to determine the location of the user's strike based on the corresponding quadrant location and the video impact data.

[0034] More specifically, the data collected by the sensory module (3.1) 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, i.e., the sensory module (3.1) and the video recording module (3.3), is used to determine, more efficiently, the location on the bag where the user's strike is delivered. In fact, since quadrants positioned at the same distance from a sensor can have very similar standardized responses, processing the video data of the user's strike, captured by the video recording module (3.3), is advantageous because it allows the selection of the correct quadrant and, therefore, the correct location of the strike, in case of ambiguity. As a consequence, the magnitude and location of the impact force are determined independently of the type of strike executed by the user and the part of the body used to make contact with the bag.

[0035] In another embodiment, the video recording module (3.3) comprises processing means configured to process the recorded video data of the user's strike using computer vision algorithms in order to generate corresponding impact video data. In the context of the present application, computer vision algorithms are algorithms adapted to analyze certain criteria in the recorded video data of the Petition 870250090828, dated 06 / 10 / 2025, pp. 99 / 115 10 / 14 user strike and apply interpretations to predictive or decision-making tasks, more particularly to retrieve information from processed video data relating to at least one longitudinal section (1.2) of the punching bag (1) struck by the user strike, wherein the said longitudinal section (1.2) refers to the lateral sections, i.e., the left or right section, or a central section. Deep learning and optical flow techniques are examples of computer vision algorithms that can be implemented to achieve the identified objective.

[0036] In another embodiment, the processing means of the video recording module (3.3) are additionally configured to process the recorded video data of the user's strike using a skeleton analysis algorithm to generate corresponding impact video data. The said skeleton analysis algorithm is adapted to retrieve the processed video data information relating to a type of user strike. Furthermore, the processing module (3.2) of the impact measurement unit (3) is additionally configured to determine the direction of the impact force produced by the user's strike based on the impact location and the impact video data.

[0037] Also the subject of this application is a method for determining the location and magnitude of an impact force produced by a user's blow on an electronic punching bag.

[0038] The method comprises the following steps: i. subdivide, by a control mechanism, a striking surface (1.1) of the punching bag (1) into a plurality of levels (1.2), each comprising progressively smaller quadrants (1.3) up to a predefined size; each quadrant (1.3) corresponding to a single location on said striking surface of the bag (1.1); ii. receive a training dataset comprising at least impact force data and an associated class definition based on the quadrants (1.3) resulting from the subdivision of the striking surface Petition 870250090828, dated 06 / 10 / 2025, pages 100 / 115 11 / 14 of the bag (1.1); iii. train one or more machine learning classifiers to build a model to classify the at least impact strength data into one or more classes based on the training dataset; iv. generate user impact force data by a sensing mechanism installed inside the bag (1), after detecting an impact force produced by a user strike on the bag's striking surface (1.1); v. receive at least the user impact force data as test input for at least one machine learning classifier to classify said user impact force data using the model built into one or more classes; each class representing a quadrant (1.3); vi. associate, by the control mechanism, the user's classified impact force to at least one quadrant (1.3) and determine the user's strike location based on at least one corresponding quadrant location; vii. determine, through the control mechanism, the magnitude of the user's blow based on the impact force data generated by the sensing mechanism.

[0039] In one embodiment of the method, the detection of an impact force comprises the following steps: - measure an impact force signal resulting from the user's action on the bag (1); - Implement a peak detection algorithm in order to identify a peak value in the aforementioned impact force signal; - Compare the peak value with a predefined limit value; - Detect an impact force produced by the user's blow if the peak value is above the predefined threshold value. Petition 870250090828, dated 06 / 10 / 2025, pages 101 / 115 12 / 14

[0040] In another version of the method, it additionally includes the following steps: - Record video data of the user's training session, using a video recording mechanism; said video data comprising at least a plurality of video frames capturing the user's strike on the striking surface of the bag; - To process, using the video recording mechanism, the plurality of video frames related to the user's strike, in order to generate video data of the impact; - To determine, through the control mechanism, the location of the user's strike based on at least one corresponding quadrant location and the impact video data.

[0041] Additionally, the generation of impact video data comprises the following steps: - Process the plurality of video frames corresponding to the user's swipe using a computer vision algorithm; - extract information from the processed recorded video data, relating to the longitudinal section of a punching bag (1.2) struck by the user's blow; the said longitudinal section referring to the lateral sections, i.e., left or right section, or a central section; - Generate a corresponding impact video signal including at least information about the longitudinal section struck by the user's blow.

[0042] In another embodiment of the method, the location of the user's strike on the striking surface of the bag (1.1) comprises: - To process, through the control mechanism, information related to at least one quadrant location and video impact data; - determine the intersection between the location of at least one quadrant (1.3) hit by the user's blow and the longitudinal section (1.2) of Petition 870250090828, dated 06 / 10 / 2025, pages 102 / 115 13 / 14 bag hit by the aforementioned user's blow.

[0043] In another embodiment of the method, the step of determining the magnitude of the user's blow involves processing the impact force data according to a universal measurement metric. EXAMPLE OF IMPLEMENTATION

[0044] This application relates to an electronic punching bag.

[0045] The main objective is that the punching bag (1) developed has the capacity to fill all the gaps of the state-of-the-art devices, having the capacity not only to detect all types of impacts, whether they are punches, elbows or kicks, but also the location of the impacts and their force, in the SI unit Newton.

[0046] To achieve the necessary efficiency, the striking surface (1.1) is divided into 9 distinct quadrants (1.3), defining each quadrant (1.3) as a location of the impact. This scheme is, in itself, a differentiating aspect in relation to all existing devices.

[0047] Furthermore, in a preferred embodiment, the electronic punching bag is based on a set of IMU (inertial measurement unit) sensors, consisting of 3 acceleration axes and 3 gyroscope axes, each to detect impacts and force in various possible quadrants (1.3). The bag (1) may also include all the electronic components that complement it, forming the impact measurement unit (sensory module, video recording module and processor module) connected to a System on Chip - SoC.

[0048] As an example, a low-energy SoC can be used with an architecture that allows running Digital Signal Processing algorithms and real-time inference models.

[0049] Additionally, it can also feature high energy efficiency and integrate a 2.4 GHz transceiver to implement Bluetooth Low Energy (BLE). Petition 870250090828, dated 06 / 10 / 2025, pages 103 / 115 14 / 14

[0050] Regarding the sensory module, the IMU sensors are distributed across three vertical areas (1.2) of the bag (1) allowing not only the detection of impacts, but also the comparison of the vector module of the 3 acceleration axes of each sensor, to perceive in which zone (above, in the middle or below) the impact occurred so that, through impact directivity analysis algorithms and with the help of the video recording module (3.3) it is possible to perceive whether the impact was in the left, central or right section of the bag and consequently be able to limit the impact zone to one of the nine possible quadrants (1.3).

[0051] These sensors can communicate with the SoC via a synchronous serial communication protocol, such as I2C.

[0052] Additionally, the sensory module (3.1) may also include adapted processing capabilities to implement a set of digital processing algorithms to reduce noise and enable parameterization of sampling frequency and sensitivity, and also to internally perform calibration steps necessary to increase measurement accuracy, as well as determine a data set from accelerometer and gyroscope data, such as relative orientation and linear acceleration.

[0053] In order to observe the data from the various IMU sensors and the data resulting from the implemented digital signal processing algorithms, as well as to understand how the impact detection algorithms are behaving, a set of processing scripts can be implemented to connect, for example, the serial port of a processing device to the SoC and allow the visualization of the data in real time.

[0054] Alternatively, this data can be transmitted via wireless network communication protocol to an external processing device, such as a smartphone. Petition 870250090828, dated 06 / 10 / 2025, pages 104 / 115

Claims

1 / 7 CLAIMS 1. Electronic punching bag apparatus, characterized by comprising: - a punching bag (1); - an anchoring unit (2), adapted to fix the apparatus to at least one surface; - an impact measurement unit (3) comprising: - a sensory module (3.1) comprising sensor means configured to detect an impact force produced by a user strike on the punching surface of the bag (1.1) and to generate corresponding impact force data; - a processing module (3.2) comprising a machine learning module; said machine learning module comprising: - a training dataset unit adapted to store a training dataset including at least impact force data generated by the sensory module (3.1) and associated class definition based on a subdivision of the punching surface of the bag (1.1) into a plurality of levels (1.2), each comprising progressively smaller quadrants (1.3) down to a predefined size; each quadrant (1.3) corresponding to a single location on said striking surface of the bag (1.1); the processing module (3.2) further comprising: - a computing unit configured to train a machine learning classifier to recognize quadrants (1.3) struck by a user's strike using the training dataset and using at least the impact force data generated from the user's strike as test input for the machine learning classifier to determine at least one quadrant (1.3) struck by the user's strike; - processing means configured to determine Petition 870250090828, dated 06 / 10 / 2025, p.105 / 115 2 / 7 location in the user's blow bag based on at least one corresponding quadrant location and to determine the magnitude of the user's blow based on impact force data generated by the sensory module (3.1).

2. Apparatus, according to claim 1, characterized in that the punching bag (1) has an elongated body and the striking surface of the bag (1.1) is divided into at least three horizontal levels (1.2), defining an upper, central and lower section of the punching bag; and wherein, the sensory module (3.1) comprises a plurality of sensor elements adapted to detect the impact force produced by the user's blow on the striking surface of the bag (1.1); said sensor elements being incorporated within the elongated body and positioned along at least one longitudinal axis.

3. Apparatus, according to claim 2, characterized in that the sensor elements are grouped into at least three sensor submodules (3.1.1) positioned along a longitudinal axis and equally spaced from each other; each sensor submodule (3.1.1) being positioned in the upper, central and lower horizontal sections (1.2) of the punching bag (1), respectively.

4. Apparatus according to claim 3, characterized in that the sensor elements are a combination of the following: at least one accelerometer, at least one gyroscope and at least one magnetometer; preferably, the sensor elements are a combination of the following: at least one 3-axis accelerometer, at least one 3-axis gyroscope and at least one 3-axis magnetometer; and wherein each sensor submodule (3.1.1) comprises at least one 3-axis accelerometer, at least one 3-axis gyroscope and at least one 3-axis magnetometer.

5. Apparatus, according to any of the preceding claims, characterized in that the anchoring unit (2) comprises: Petition 870250090828, dated 06 / 10 / 2025, page 106 / 115 3 / 7 - a base module (2.1) being connected to a lower part of the bag body; the base module (2.1) providing support for the bag on a first surface (2.3); and - a support structure (2.2) adapted for fixing the bag to a second surface (2.4); said second surface (2.4) being perpendicular to the first surface (2.3); and wherein the punching bag (1) has a body comprising: - an inner center part consisting of a bladder structure comprising at least one bladder (1.4); said bladder (1.4) being a container for storing liquids.

6. Apparatus, according to claim 5, characterized by the bladder structure comprising a set of 4 bladders (1.4) arranged longitudinally on a longitudinal axis; the bladders (1.4) of the set having a shape adapted to be fixed one on top of the other; optionally, the volume of each bladder (1.4) is 20 liters and the liquid is water.

7. Apparatus, according to any of the preceding claims, characterized in that the impact measuring unit (3) further comprises: - a video recording module (3.3) programmed to record the user's strike on the striking surface of the bag (1.1) and generate corresponding impact video data; and wherein, the processing means of the processing module (3.2) being further configured to determine the location of the user's strike based on the corresponding quadrant location and the impact video data.

8. Apparatus, according to claim 7, characterized by the video recording module (3.3) of the impact measurement unit (3) comprising processing means configured to process video data recorded from the user's blow using computer vision algorithms to generate corresponding impact video data; said computer vision algorithms being adapted to retrieve information from processed video data relating to at least one longitudinal section (1.2) of the punching bag (1) struck by the user's blow; said longitudinal section (1.2) referring to side sections, i.e., left or right section, or a central section.

9. Apparatus according to claim 8, characterized in that the processing means of the video recording module (3.3) are further configured to process the recorded video data of the user's strike using a skeleton analysis algorithm to generate corresponding impact video data; said skeleton analysis algorithm being adapted to retrieve information from processed video data relating to a type of user strike; and wherein, the processing module (3.2) of the impact measurement unit (3) is further configured to determine the direction of the impact force produced by the user's strike based on the impact location and the impact video data.

10. Method for determining the location and magnitude of an impact force produced by the user's strike on an electronic punching bag; the method characterized by comprising the following steps: i. subdividing, by a control mechanism, a striking surface (1.1) of the punching bag (1) into a plurality of levels (1.2), each comprising progressively smaller quadrants (1.3) up to a predefined size; each quadrant (1.3) corresponding to a single location on said striking surface of the bag (1.1); ii. receiving a training dataset comprising at least impact force data and an associated class definition based on the quadrants (1.3) resulting from the subdivision of the striking surface of the bag (1.1); iii. training one or more machine learning classifiers. Petition 870250090828, dated 06 / 10 / 2025, p.108 / 115 5 / 7 to build a model to classify the at least impact force data into one or more classes based on the training dataset; iv. generate user impact force data by a sensing mechanism installed inside the bag (1), after detecting an impact force produced by a user strike on the bag's striking surface (1.1); v. receive at least the user impact force data as test input for at least one machine learning classifier to classify said user impact force data using the built model into one or more classes; each class representing a quadrant (1.3); vi. associate, by the control mechanism, the classified user impact force to at least one quadrant (1.3) and determine the location of the user strike based on at least one corresponding quadrant location; vii.To determine, through the control mechanism, the magnitude of the user's blow based on the impact force data generated by the sensing mechanism.

11. Method according to claim 10, characterized by detecting an impact force comprising: - measuring an impact force signal resulting from the user's action on the bag (1); - implementing a peak detection algorithm in order to identify a peak value in said impact force signal; - comparing the peak value with a predefined threshold value; - detecting an impact force produced by the user's blow if the peak value is above the predefined threshold value.

12. Method, according to any of the preceding claims 9 to 11, characterized by further comprising the steps of: - recording video data of the user's training session, by a video recording mechanism; said video data comprising at least a plurality of video frames capturing the user's strike on the striking surface of the bag; - processing, by the video recording mechanism, the plurality of video frames related to the user's strike, in order to generate video data of the impact; - determining, by the control mechanism, the location of the user's strike based on at least one corresponding quadrant location and the video data of the impact.

13. Method according to claim 12, characterized by the generation of impact video data comprising the following steps: - processing the plurality of video frames corresponding to the user's blow using a computer vision algorithm; - extracting information from the processed recorded video data, relating to the longitudinal section of a punching bag (1.2) struck by the user's blow; said longitudinal section referring to the lateral sections, i.e., left or right section, or a central section; - generating a corresponding impact video signal including at least information about the longitudinal section struck by the user's blow.

14. Method, according to claims 12 and 13, characterized by the location of the user's strike on the striking surface of the bag (1.1) comprising: - processing, by the control mechanism, the information relating to at least one quadrant location and the video data of the impact; - determining the intercept between the location of at least one quadrant (1.3) struck by the user's strike and the longitudinal section (1.2) of the bag struck by said user's strike.

15. Method, according to any one of the preceding claims 9 to 14, characterized by the step of determining the magnitude of the user's blow comprising processing the impact force data according to a universal measurement metric. Petition 870250090828, dated 06 / 10 / 2025, pp. 111 / 115

Images