Fighting boxing strength analysis method, device, equipment, medium and product

Abstract

The invention discloses a fight boxing strength analysis method, device and equipment, a medium and a product, and relates to the technical field of intelligent sports. According to the method, after a plurality of vibration time domain signals collected by a plurality of vibration sensors in real time are received, a corresponding signal amplitude is extracted in real time according to the corresponding signal for each signal, and when it is found that the corresponding signal amplitude is a maximum value and exceeds a preset threshold value, the occurrence moment of the corresponding maximum value is recorded; when the occurrence time of the maximum value of each signal is recorded in the current recent time window, establishing an equation set and solving the occurrence time of the boxing event of the fighting sport; and finally, the corresponding time difference value and the corresponding signal extremely-large amplitude value of each signal are imported into a pre-trained fighting boxing strength estimation model based on an artificial intelligence algorithm, and a boxing strength value is output and obtained, so that the boxing strength measurement accuracy can be improved, an acquisition device can be prevented from being damaged in advance, and the acquisition device can be conveniently replaced.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent sports, and particularly relates to a method, device, equipment, medium and product for analyzing boxing power in combat sports. Background Art

[0002] Combat is a highly confrontational sport. Participants use various attack and defense techniques with the aim of defeating opponents as much as possible. Participating in combat can improve physical fitness, enhance willpower and cultivate self-confidence, and is also beneficial to mental health. There are various types of combat sports, each with its unique characteristics and rules. As one of the common combat sports, boxing can not only improve the physical fitness of athletes, but also burn a large amount of calories, helping athletes build a fit body.

[0003] On the basis of good physical fitness and theoretical learning, boxing training also requires regular and gradual training in physical fitness, strength and techniques. Only through correct and scientific long-term stimulation and repeated practice can combat techniques be improved step by step. In boxing training subjects, boxing strength training is of utmost importance, and it is necessary for boxers to perceive the magnitude of the current boxing strength on the spot when hitting the punching target, so as to intuitively understand the current training effect and stimulate training enthusiasm.

[0004] Currently, existing boxing strength measurement schemes mainly involve directly measuring boxing strength by installing force sensors, acceleration sensors or attitude sensors, etc. in the punching target (such as the prior art "CN104596693A, a measurement system and method for multiple multi-dimensional motion parameters for combat training" and "CN214436411U, a boxing strength tester", etc.). However, since these sensors are arranged directly behind the hitting part and are protected by a buffer layer, it will inevitably lead to certain deviations in the measurement results. At the same time, even with the protection of the buffer layer after long-term hitting, the sensors may be damaged in advance and are not easy to replace. Therefore, how to provide a new boxing strength measurement scheme that can not only improve the accuracy of combat sports boxing strength measurement, but also avoid premature damage to the acquisition devices and facilitate the replacement of the acquisition devices is an urgent research topic for those skilled in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, device, computer equipment, computer-readable storage medium and computer program product for analyzing boxing power in combat sports, so as to solve the problems existing in the existing boxing strength measurement scheme, such as the accuracy of the measurement results needs to be improved, the sensors may be damaged in advance and are not easy to replace.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions:

[0007] In a first aspect, a method for analyzing the power of combat sports boxing is provided, including:

[0008] Receiving a plurality of vibration time-domain signals collected in real time by a plurality of vibration sensors, wherein the plurality of vibration sensors are arranged at circumferential intervals along the edge of the combat sports boxing target, and the plurality of vibration time-domain signals correspond one-to-one to the plurality of vibration sensors;

[0009] For each vibration time-domain signal in the plurality of vibration time-domain signals, the corresponding signal amplitude is extracted in real time according to the corresponding signal, and when it is found that the corresponding signal amplitude is a maximum value and exceeds a preset threshold, the occurrence time of the corresponding maximum value is recorded;

[0010] Determine whether the occurrence time of the maximum value of each vibration time-domain signal is recorded within the current nearest time window;

[0011] If so, it is determined that a combat sports boxing event has occurred for the combat sports boxing target, and the following system of equations is established:

[0012]

[0013] In the formula, N represents the total number of sensors of the plurality of vibration sensors, n represents a positive integer less than N, and L n,n+1 represents the known arrangement distance between the nth vibration sensor and the (n + 1)th vibration sensor in the circumferential direction among the plurality of vibration sensors, and L N,1 represents the known arrangement distance between the Nth vibration sensor and the first vibration sensor in the circumferential direction among the plurality of vibration sensors, t n represents the occurrence time of the maximum value of the vibration time-domain signal recorded within the current nearest time window and corresponding to the nth vibration sensor, t n+1 represents the occurrence time of the maximum value of the vibration time-domain signal recorded within the current nearest time window and corresponding to the (n + 1)th vibration sensor, t 0 represents the occurrence time of the combat sports boxing event and is a variable to be solved, v represents the known propagation speed of the boxing shock wave in the combat sports boxing target, and θ n,n+1 represents the angle between the first line segment and the second line segment, and θ N,1denotes the included angle between the third line segment and the fourth line segment, where the first line segment refers to the line segment between the nth vibration sensor and the occurrence position of the combat sports boxing event, the second line segment refers to the line segment between the (n + 1)th vibration sensor and the occurrence position of the combat sports boxing event, the third line segment refers to the line segment between the Nth vibration sensor and the occurrence position of the combat sports boxing event, and the fourth line segment refers to the line segment between the first vibration sensor and the occurrence position of the combat sports boxing event;

[0014] Solve the system of equations to obtain the occurrence time t of the combat sports boxing event 0 ;

[0015] Respectively compare the occurrence times of the maxima of the respective vibration time-domain signals recorded within the current nearest time window with the occurrence time t of the combat sports boxing event 0 and the corresponding signal amplitudes corresponding one-to-one to the occurrence times of the maxima of the respective vibration time-domain signals recorded within the current nearest time window are imported into the combat sports boxing force estimation model that has been pre-trained based on the first artificial intelligence algorithm, and the boxing force value of the combat sports boxing event is output.

[0016] Based on the above-mentioned inventive concept, a new solution for measuring boxing force by performing data analysis based on vibration signals and artificial intelligence algorithms is provided. That is, after receiving multiple vibration time-domain signals collected in real time by multiple vibration sensors, for each signal, the corresponding signal amplitude is extracted in real time according to the corresponding signal, and when it is found that the corresponding signal amplitude is a maximum value and exceeds a preset threshold, the occurrence time of the corresponding maximum value is recorded. Then, when it is determined that the occurrence times of the maxima of all signals are recorded within the current nearest time window, a system of equations is established and the occurrence time of the combat sports boxing event is solved. Finally, the corresponding time differences and the corresponding signal maximum amplitudes of all signals are imported into the combat sports boxing force estimation model that has been pre-trained based on the artificial intelligence algorithm, and the boxing force value is output. In this way, there is no need to arrange acquisition devices directly behind the striking part, which can not only improve the accuracy of measuring the combat sports boxing force, but also avoid premature damage to the acquisition devices. Moreover, since the multiple vibration sensors are arranged at circumferential intervals along the edge of the combat sports boxing target, it is also convenient to replace the acquisition devices, facilitating practical application and popularization.

[0017] In a possible design, the first artificial intelligence algorithm uses a machine learning algorithm based on support vector machine, K-nearest neighbor method, stochastic gradient descent method, multivariate linear regression, multi-layer perceptron, decision tree, backpropagation neural network or radial basis function network.

[0018] In a possible design, the method further includes:

[0019] For each combat sports boxing event among the M combat sports boxing events that have occurred continuously most recently, based on the known positions of the multiple vibration sensors, the known propagation speed v, and the time differences between the occurrence times of the corresponding events and the moments when the maximum values of the respective vibration time-domain signals recorded within the corresponding time window occur, a positioning algorithm is used to determine the hitting positions on the combat sports boxing target body, where M represents a positive integer greater than or equal to 3;

[0020] Taking the hitting position of the first combat sports boxing event that occurred earliest among the M combat sports boxing events as a reference point, the relative coordinates of the hitting positions of each of the other combat sports boxing events among the M combat sports boxing events relative to the reference point are calculated in the order of the occurrence times of the events, obtaining a relative coordinate time series data;

[0021] Taking the occurrence time of the first combat sports boxing event as a reference time, the time differences between the occurrence times of each of the other combat sports boxing events and the reference time are calculated in the order of the occurrence times of the events, obtaining a time difference time series data;

[0022] The relative coordinate time series data and the time difference time series data are imported into a combat sports boxing action recognition model that has been pre-trained based on a second artificial intelligence algorithm, and the current combat sports boxing action recognition result is output;

[0023] According to the combat sports boxing action recognition result, the current combat sports boxing strength value is displayed in the following manner (A) or (B):

[0024] (A) When the combat sports boxing action recognition result is a straight punch, a hook punch, or a jab, the boxing strength value of the combat sports boxing event that occurred last among the M combat sports boxing events is used as the current combat sports boxing strength value for on-site display;

[0025] (B) When the combat sports boxing action recognition result is a combination punch, the average boxing strength of the M combat sports boxing events is used as the current combat sports boxing strength value for on-site display.

[0026] In a possible design, the second artificial intelligence algorithm uses a machine learning algorithm based on LSTM, Bi-LSTM, or Attention-LSTM.

[0027] In a possible design, the method further includes:

[0028] Obtaining on-site video data that is real-time collected by a camera from the front area of the combat sports boxing target body;

[0029] Based on the on-site video data, use a face recognition algorithm to obtain the identity information of the boxer currently located in the front area;

[0030] Based on the identity information of the boxer, access the database to obtain the average boxing power or the maximum boxing power of the boxer during the current most recent historical training period;

[0031] Compare and analyze the boxing power value of the combat sports boxing event with the average boxing power or the maximum boxing power of the boxer during the current most recent historical training period, and obtain the comparison and analysis result and display it on-site.

[0032] In a possible design, the method further includes:

[0033] Bind and store the boxing power value and the occurrence time of the combat sports boxing event to the database together with the identity information of the boxer.

[0034] In a second aspect, a combat sports boxing power analysis device is provided, including a vibration signal receiving unit, a vibration signal processing unit, a judgment unit, a system of equations construction unit, a system of equations solving unit, and a boxing power estimation unit;

[0035] The vibration signal receiving unit is configured to receive a plurality of vibration time-domain signals collected in real time by a plurality of vibration sensors, wherein the plurality of vibration sensors are arranged at intervals circumferentially along the edge of the combat sports boxing target, and the plurality of vibration time-domain signals correspond to the plurality of vibration sensors one by one;

[0036] The vibration signal processing unit is communicatively connected to the vibration signal receiving unit, and is configured to, for each vibration time-domain signal among the plurality of vibration time-domain signals, extract the corresponding signal amplitude in real time according to the corresponding signal, and record the occurrence time of the corresponding maximum value when it is found that the corresponding signal amplitude is a maximum value and exceeds a preset threshold;

[0037] The judgment unit is communicatively connected to the vibration signal processing unit, and is configured to judge whether the occurrence time of the maximum value of each vibration time-domain signal is recorded within the current most recent time window;

[0038] The system of equations construction unit is communicatively connected to the vibration signal processing unit and the judgment unit respectively, and is configured to, if so, determine that a combat sports boxing event against the combat sports boxing target has occurred currently, and establish the following system of equations:

[0039]

[0040] Wherein, N represents the total number of sensors of the plurality of vibration sensors, n represents a positive integer less than N, and L n,n+1 represents the known arrangement distance between the nth vibration sensor and the (n + 1)th vibration sensor in the circumferential direction among the plurality of vibration sensors, and L N,1 represents the known arrangement distance between the Nth vibration sensor and the first vibration sensor in the circumferential direction among the plurality of vibration sensors, and t n represents the occurrence time of the maximum value of the vibration time-domain signal recorded within the current nearest time window and corresponding to the nth vibration sensor, and t n+1 represents the occurrence time of the maximum value of the vibration time-domain signal recorded within the current nearest time window and corresponding to the (n + 1)th vibration sensor, and t 0 represents the occurrence time of the combat sports boxing event and is a variable to be solved, v represents the known propagation speed of the boxing shock wave within the combat sports boxing target, and θ n,n+1 represents the included angle between the first line segment and the second line segment, and θ N,1 represents the included angle between the third line segment and the fourth line segment. The first line segment refers to the line segment between the nth vibration sensor and the occurrence position of the combat sports boxing event. The second line segment refers to the line segment between the (n + 1)th vibration sensor and the occurrence position of the combat sports boxing event. The third line segment refers to the line segment between the Nth vibration sensor and the occurrence position of the combat sports boxing event. The fourth line segment refers to the line segment between the first vibration sensor and the occurrence position of the combat sports boxing event;

[0041] The equation set solving unit, communicatively connected to the equation set constructing unit, is configured to solve the equation set to obtain the occurrence time t of the combat sports boxing event 0 ;

[0042] The boxing force estimation unit, communicatively connected to the vibration signal processing unit and the equation set solving unit respectively, is configured to respectively import the time difference between the occurrence time of the maximum value of each vibration time-domain signal recorded within the current nearest time window and the occurrence time t of the combat sports boxing event 0 and the respective signal amplitudes corresponding to the occurrence times of the maximum values of each vibration time-domain signal recorded within the current nearest time window into a pre-trained combat sports boxing force estimation model based on the first artificial intelligence algorithm, and output the boxing force value of the combat sports boxing event.

[0043] In a third aspect, the present invention provides a computer device, comprising a memory, a processor and a transceiver that are communicatively connected in sequence. Among them, the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs and execute the fighting sports boxing force analysis method as described in the first aspect or any possible design in the first aspect.

[0044] In a fourth aspect, the present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are run on a computer, the fighting sports boxing force analysis method as described in the first aspect or any possible design in the first aspect is executed.

[0045] In a fifth aspect, the present invention provides a computer program product, comprising a computer program or instructions. When the computer program or the instructions are executed by a computer, the fighting sports boxing force analysis method as described in the first aspect or any possible design in the first aspect is implemented.

[0046] Beneficial effects of the above solutions:

[0047] (1) The present invention creatively provides a new solution for data analysis based on vibration signals and artificial intelligence algorithms to measure boxing force. That is, after receiving multiple vibration time-domain signals collected in real time by multiple vibration sensors, for each signal, the corresponding signal amplitude is extracted in real time according to the corresponding signal. When it is found that the corresponding signal amplitude is a maximum value and exceeds a preset threshold, the occurrence time of the corresponding maximum value is recorded. Then, when it is determined that the occurrence times of the maximum values of each signal are recorded within the current nearest time window, a system of equations is established and solved to obtain the occurrence time of the fighting sports boxing event. Finally, the corresponding time differences and corresponding signal maximum amplitudes of each signal are imported into the fighting sports boxing force estimation model that has been pre-trained based on the artificial intelligence algorithm, and the boxing force value is output. In this way, there is no need to arrange acquisition devices directly behind the striking part, which can not only improve the accuracy of measuring the fighting sports boxing force, but also avoid premature damage to the acquisition devices. Moreover, since the multiple vibration sensors are arranged at intervals circumferentially along the edge of the fighting sports boxing target, it is also convenient to replace the acquisition devices, facilitating practical application and promotion;

[0048] (2) Based on the striking positions and occurrence times of multiple consecutive fighting sports boxing events that have recently occurred, the current fighting sports boxing action can be identified, and the current fighting sports boxing force value can be adaptively displayed on-site according to the identification result, enabling the boxing personnel to intuitively understand the current exercise effect, stimulating the training enthusiasm, and enhancing the user experience;

[0049] (3) It can automatically identify the identity information of the current boxer, automatically retrieve the training effect data of the current nearest historical training period for comparison and analysis with the current training effect data, and display the analysis results on-site, so that boxers can intuitively understand the improvement degree of the current exercise effect, further stimulate the training enthusiasm, and improve the user experience. Brief Description of the Drawings

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0051] Figure 1 It is a flowchart showing the method for analyzing the boxing strength in combat sports provided by an embodiment of the present application.

[0052] Figure 2 It is an exemplary diagram showing the positional relationship among the boxing target, multiple vibration sensors and a display screen in combat sports provided by an embodiment of the present application.

[0053] Figure 3 It is an exemplary diagram showing the signal amplitude in the time domain of four vibration time domain signals provided by an embodiment of the present application.

[0054] Figure 4 It is a structural diagram of the device for analyzing the boxing strength in combat sports provided by an embodiment of the present application.

[0055] Figure 5 It is a structural diagram of the computer device provided by an embodiment of the present application. Detailed Embodiments

[0056] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the present invention in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structural drawings is only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other embodiments can be obtained based on these embodiments. It should be noted here that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation to the present invention.

[0057] It should be understood that although terms such as first and second may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, the first object can be called the second object, and similarly, the second object can be called the first object, without departing from the scope of the exemplary embodiments of the present invention.

[0058] It should be understood that for the term "and / or" that may appear in this text, it is merely a relationship describing the associated objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, B exists alone, or both A and B exist simultaneously; another example, A, B, and / or C can represent any one of A, B, and C or any combination of them; for the term " / and" that may appear in this text, it is a relationship describing another associated object, indicating that there can be two relationships. For example, A / and B can represent two situations: A exists alone or both A and B exist simultaneously; in addition, for the character " / " that may appear in this text, generally it represents that the associated objects before and after are in an "or" relationship.

[0059] Embodiment

[0060] As Figure 1 shown, the boxing force analysis method for combat sports provided in the first aspect of this embodiment can be, but is not limited to, executed by a computer device having certain computing resources and respectively communicatively connected to a plurality of vibration sensors, such as a cloud server, a personal computer (Personal Computer, PC, referring to a multi-purpose computer suitable for personal use in terms of size, price, and performance; desktop computers, laptops, small laptops, tablets, and ultrabooks all belong to personal computers), a smart phone, a personal digital assistant (Personal Digital Assistant, PDA), or a wearable device and other electronic devices. As Figure 1 shown, the boxing force analysis method for combat sports can be, but is not limited to, including the following steps S1 to S6.

[0061] S1. Receive a plurality of vibration time-domain signals collected in real time by a plurality of vibration sensors, where the plurality of vibration sensors are arranged at circumferential intervals along the edge of the combat sports boxing target, and the plurality of vibration time-domain signals correspond one-to-one to the plurality of vibration sensors.

[0062] In step S1, the vibration sensor is used to collect the vibration signal at the location where it is located. As Figure 2 shown, the number of vibration sensors is, for example, four (i.e., Figure 2 the first vibration sensor 201, the second vibration sensor 202, the third vibration sensor 203, and the fourth vibration sensor 204 in Figure 2 ) and are respectively arranged at the four corner points of the square-structured combat sports boxing target (i.e., Figure 2 the square combat sports boxing target 100 in 1 ), namely the P 2 point, the P 3 point, and the P4 Points, etc. In addition, the vibration sensor can be conventionally implemented using relevant products available on the market.

[0063] S2. For each vibration time-domain signal among the multiple vibration time-domain signals, extract the corresponding signal amplitude in real time according to the corresponding signal, and when it is found that the corresponding signal amplitude is a maximum value and exceeds a preset threshold, record the time when the corresponding maximum value appears.

[0064] In the step S2, the signal amplitude refers to the amplitude of the signal or the maximum deviation value of the fluctuation, and can be conventionally extracted from the vibration time-domain signal based on existing technical means. The preset threshold is used to filter the amplitude of the noise signal and can be preset based on empirical values. Based on Figure 2 For example, there will be signal amplitudes of four vibration time-domain signals, and their signal amplitude time-domain diagrams are as Figure 3 shown: The signal amplitude of the vibration time-domain signal corresponding to the first vibration sensor 201 is represented by A 1 denoted, the signal amplitude of the vibration time-domain signal corresponding to the second vibration sensor 202 is represented by A 2 denoted, the signal amplitude of the vibration time-domain signal corresponding to the third vibration sensor 203 is represented by A 3 denoted, and the signal amplitude of the vibration time-domain signal corresponding to the fourth vibration sensor 204 is represented by A 4 denoted. In this way, the time t 1 when the maximum value of the vibration time-domain signal corresponding to the first vibration sensor 201 appears can be respectively recorded, the time t 2 when the maximum value of the vibration time-domain signal corresponding to the second vibration sensor 202 appears, the time t 3 when the maximum value of the vibration time-domain signal corresponding to the third vibration sensor 203 appears, and the time t 4 when the maximum value of the vibration time-domain signal corresponding to the fourth vibration sensor 204 appears.

[0065] S3. Determine whether the time when the maximum value of each vibration time-domain signal appears is recorded within the current nearest time window.

[0066] In the step S3, an example of the current nearest time window is as Figure 3 shown, which is used to distinguish the times when different maximum values of the same vibration time-domain signal are recorded due to different combat sports boxing events (especially two adjacent combat sports boxing events before and after). To achieve the foregoing purpose, the time width of the current nearest time window needs to be greater than the longest propagation delay of the boxing shock wave on the combat sports boxing target (for example Figure 2As shown, that is, the longest propagation delay is equal to the diagonal length of the square combat sports boxing target 100 divided by the known propagation speed of the boxing shock wave in the combat sports boxing target), and is less than the shortest time required for two consecutive punches of the boxer.

[0067] S4. If so, it is determined that a combat sports boxing event has occurred for the combat sports boxing target, and the following system of equations is established:

[0068]

[0069] In the formula, N represents the total number of sensors of the multiple vibration sensors, n represents a positive integer less than N, and L n,n+1 represents the known arrangement distance between the nth vibration sensor and the (n + 1)th vibration sensor in the circumferential direction among the multiple vibration sensors, and L N,1 represents the known arrangement distance between the Nth vibration sensor and the first vibration sensor in the circumferential direction among the multiple vibration sensors, and t n represents the occurrence time of the maximum value of the vibration time-domain signal recorded within the current nearest time window and corresponding to the nth vibration sensor, and t n+1 represents the occurrence time of the maximum value of the vibration time-domain signal recorded within the current nearest time window and corresponding to the (n + 1)th vibration sensor, and t 0 represents the occurrence time of the combat sports boxing event and is a variable to be solved, v represents the known propagation speed of the boxing shock wave in the combat sports boxing target, and θ n,n+1 represents the angle between the first line segment and the second line segment, and θ N,1 represents the angle between the third line segment and the fourth line segment. The first line segment refers to the line segment between the nth vibration sensor and the occurrence position of the combat sports boxing event, the second line segment refers to the line segment between the (n + 1)th vibration sensor and the occurrence position of the combat sports boxing event, the third line segment refers to the line segment between the Nth vibration sensor and the occurrence position of the combat sports boxing event, and the fourth line segment refers to the line segment between the first vibration sensor and the occurrence position of the combat sports boxing event.

[0070] In the step S4, if it is determined that the occurrence times of the maximum values of the respective vibration time-domain signals are recorded within the current nearest time window, it indicates that a combat sports boxing event effective for the combat sports boxing target has occurred at present, and there is: the boxing shock wave generated by this combat sports boxing event has been respectively transmitted to the multiple vibration sensors through the combat sports boxing target (similar to the principle of seismic wave propagation). Therefore, it can be determined that a combat sports boxing event for the combat sports boxing target has occurred at present, and the above equations can be established based on the cosine theorem. For example, as Figure 2 shown, the occurrence position of the combat sports boxing event is represented by point H. Since the number of vibration sensors is four, the following equations can be established:

[0071]

[0072] In the formula, L 1,2 represents the length of the line segment P 1 P 2 , L 2,3 represents the length of the line segment P 2 P 3 , L 3,4 represents the length of the line segment P 3 P 4 , L 4,1 represents the length of the line segment P 4 P 1 , v×(t 1 -t 0 ) represents the length of the line segment HP 1 , v×(t 2 -t 0 ) represents the length of the line segment HP 2 , v×(t 3 -t 0 ) represents the length of the line segment HP 3 , v×(t 4 -t 0 ) represents the length of the line segment HP 4 . In addition, if it is determined that the occurrence times of the maximum values of the respective vibration time-domain signals are not recorded within the current nearest time window (for example, the occurrence time of the maximum value of a certain vibration time-domain signal is missing), it is necessary to return to execute step S3.

[0073] S5. Solve the equations to obtain the occurrence time t 0 of the combat sports boxing event.

[0074] In the step S5, since there is only one variable to be solved in the equations, the occurrence time t 0 of the combat sports boxing event can be obtained by conventional solution.

[0075] S6. Respectively compare the occurrence times of the maxima of the respective vibration time-domain signals recorded within the current nearest time window with the occurrence time t 0 of the combat sports boxing event, as well as the respective signal amplitudes corresponding one-to-one to the occurrence times of the maxima of the respective vibration time-domain signals recorded within the current nearest time window, and import them into a combat sports boxing force estimation model that has been pre-trained based on a first artificial intelligence algorithm to output the boxing force value of the combat sports boxing event.

[0076] In step S6, due to the time differences to the vibration sensor and the vibration intensities generated at the vibration sensor caused by different boxing forces at different striking positions being different, the corresponding boxing forces can be inversely deduced based on the respective time differences of the signals and the respective maximum signal amplitudes. Based on Figures 2 - 3 as shown, for example, the time differences between the occurrence times of the maxima of the respective vibration time-domain signals recorded within the current nearest time window and the occurrence time t 0 of the combat sports boxing event are: t 1 -t 0 、t 2 -t 0 、t 3 -t 0 and t 4 -t 0 , and the respective signal amplitudes corresponding one-to-one to the occurrence times of the maxima of the respective vibration time-domain signals recorded within the current nearest time window are: and Artificial intelligence algorithms are the core artificial intelligence algorithms that specifically study how computers simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve their own performance. They are the fundamental way to make computers intelligent. Specifically, the first artificial intelligence algorithm preferably adopts a linear regression algorithm based on the Python sklearn library to quickly and accurately find the patterns in the data. In this way, based on a certain amount of sample data (which includes model input items and model output items, where the model input items are the corresponding time differences and corresponding signal maximum amplitudes of each vibration time-domain signal, and the model output item is the measured boxing force value of the fighting sports boxing event corresponding to the model input item. This measured boxing force value can be, but is not limited to, determined based on the prior art "CN214436411U, A Boxing Force Tester"), through a conventional calibration verification modeling process (which specifically includes the calibration process and verification process of the model, that is, first comparing the model simulation results with the measured data, and then adjusting the model parameters according to the comparison results to make the simulation results consistent with the actual situation), the fighting sports boxing force estimation model is pre-trained. Preferably, in the calibration verification modeling process of the fighting sports boxing force estimation model, a Bayesian optimization algorithm based on a tree structure is used to optimize the model parameters. In addition, the first artificial intelligence algorithm can also, but is not limited to, adopt machine learning algorithms based on support vector machines, K-nearest neighbor methods, stochastic gradient descent methods, multivariable linear regression, multi-layer perceptrons, decision trees, backpropagation neural networks, or radial basis function networks, etc.

[0077] Based on the fighting sports boxing force analysis method described in the foregoing steps S1 to S6, a new solution for data analysis based on vibration signals and artificial intelligence algorithms to measure boxing force is provided. That is, after receiving multiple vibration time-domain signals collected in real time by multiple vibration sensors, for each signal, the corresponding signal amplitude is extracted in real time according to the corresponding signal. When it is found that the corresponding signal amplitude is a maximum value and exceeds the preset threshold, the occurrence time of the corresponding maximum value is recorded. Then, when it is determined that the occurrence times of the maximum values of each signal are recorded within the current nearest time window, a system of equations is established and solved to obtain the occurrence time of the fighting sports boxing event. Finally, the corresponding time differences and corresponding signal maximum amplitudes of each signal are imported into the fighting sports boxing force estimation model that has been pre-trained based on artificial intelligence algorithms, and the boxing force value is output. In this way, there is no need to arrange acquisition devices directly behind the hitting part, which can not only improve the accuracy of measuring the fighting sports boxing force, but also avoid premature damage to the acquisition devices. Moreover, since the multiple vibration sensors are arranged at circumferential intervals along the edge of the fighting sports boxing target, it is also convenient to replace the acquisition devices, facilitating practical application and promotion.

[0078] Based on the technical solution of the foregoing first aspect, this embodiment further provides a possible design 1 for how to recognize boxing actions in combat sports and adaptively display the current combat sports boxing power value on-site according to the recognition result, that is, the method further includes but is not limited to the following steps S71 to S75.

[0079] S71. For each combat sports boxing event among the M combat sports boxing events that have occurred continuously and most recently, according to the known positions of the multiple vibration sensors, the known propagation speed v, and the time differences between the occurrence times of the maximum values of the respective vibration time-domain signals recorded within the corresponding time window and the occurrence times of the corresponding events, use a positioning algorithm to determine the hitting positions on the combat sports boxing target body and the corresponding hitting positions, where M represents a positive integer greater than or equal to 3.

[0080] In step S71, the positioning algorithm can but is not limited to using existing TOA (Time of Arrival) algorithm or TDOA (Time Difference of Arrival) algorithm to be conventionally modified and implemented. In addition, M can be exemplified as 10.

[0081] S72. Taking the hitting position of the first combat sports boxing event that occurred earliest among the M combat sports boxing events as a reference point, calculate the relative coordinates of the hitting positions of each of the other combat sports boxing events in the M combat sports boxing events relative to the reference point in the order of the occurrence times of the events, and obtain a relative coordinate time series data.

[0082] In step S72, if M is 10, then the relative coordinates of the hitting positions of the nine other combat sports boxing events relative to the reference point can be calculated, that is, the relative coordinate time series data includes nine relative coordinates sorted in the order of the occurrence times of the events.

[0083] S73. Taking the occurrence time of the first combat sports boxing event as a reference time, calculate the time differences between the occurrence times of each of the other combat sports boxing events and the reference time in the order of the occurrence times of the events, and obtain a time difference time series data.

[0084] In step S73, if M is 10, then the time differences between the occurrence times of the nine other combat sports boxing events and the reference time can be calculated, that is, the time difference time series data includes nine time differences sorted in the order of the occurrence times of the events.

[0085] S74. Import the relative coordinate time series data and the time difference value time series data into a combat sports boxing action recognition model that has been pre-trained based on a second artificial intelligence algorithm, and output the current combat sports boxing action recognition result.

[0086] In step S74, since the hitting positions and hitting frequencies of different combat sports boxing actions have different characteristics, the combat sports boxing actions can be inversely deduced based on these feature data (i.e., the relative coordinate time series data and the time difference value time series data). The combat sports boxing action recognition model can also be pre-trained through a conventional calibration verification modeling process based on a certain amount of sample data (which includes another model input item and another model output item, where this another model input item is the relative coordinate time series data and the time difference value time series data corresponding to M consecutive historical combat sports boxing events, and this another model output item is the combat sports boxing action type corresponding to this another model input item: straight punch, hook punch, jab, or combination punch, etc.). Preferably, in the calibration verification modeling process of the combat sports boxing action recognition model, a Bayesian optimization algorithm based on a tree structure is used to optimize the model parameters. Specifically, the second artificial intelligence algorithm can be, but is not limited to, a machine learning algorithm based on LSTM, Bi-LSTM, or Attention-LSTM. The aforementioned LSTM (Long Short-Term Memory), Bi-LSTM, or Attention-LSTM, etc. are all existing machine learning networks. Among them, the Attention-LSTM is an improved network that adds an attention mechanism to the existing LSTM (which is commonly used for time series data prediction), and the added attention mechanism is used to allow the LSTM model to dynamically focus on partial information during training so as to be able to capture more important information and improve the performance of the model. Therefore, in this embodiment, a machine learning algorithm based on the Attention-LSTM is preferably used to train the combat sports boxing action recognition model. In addition, the second artificial intelligence algorithm can also be, but is not limited to, a machine learning algorithm based on support vector machine, K-nearest neighbor method, stochastic gradient descent method, multivariate linear regression, multi-layer perceptron, decision tree, backpropagation neural network, or radial basis function network, etc.

[0087] S75. According to the combat sports boxing action recognition result, display the current combat sports boxing power value in the following manner (A) or (B):

[0088] (A) When the combat sports boxing action recognition result is a straight punch, a hook punch, or a jab, the boxing power value of the last-occurring combat sports boxing event among the M combat sports boxing events will be used as the current combat sports boxing power value and displayed on-site;

[0089] (B) When the recognition result of the combat sport boxing action is a combination punch, the average boxing force of the M combat sport boxing events is used as the current combat sport boxing force value for on-site display.

[0090] In step S75, the current combat sport boxing force value can be specifically displayed on-site through a display screen 300 located directly above the square combat sport boxing target 100.

[0091] Based on the foregoing possible design one, the current combat sport boxing action can be recognized based on the hitting positions and occurrence times of multiple recently consecutive combat sport boxing events, and the current combat sport boxing force value can be adaptively displayed on-site according to the recognition result, enabling boxers to intuitively understand the current exercise effect, stimulating training enthusiasm, and enhancing the user experience.

[0092] Based on the technical solutions of the foregoing first aspect or possible design one, this embodiment further provides a possible design two on how to automatically compare and analyze the current training effect with the historical training effect and display the analysis result on-site, that is, the method further includes but is not limited to the following steps S81 to S84.

[0093] S81. Obtain on-site video data collected in real time by a camera in the front area of the combat sport boxing target.

[0094] In step S81, as Figure 2 shown, the lens 400 of the camera can also be located directly above the square combat sport boxing target 100 to perform real-time video acquisition on the front area of the combat sport boxing target.

[0095] S82. According to the on-site video data, use a face recognition algorithm to obtain the identity information of the boxer currently in the front area.

[0096] In step S82, the face recognition algorithm is an existing algorithm and will not be elaborated here.

[0097] S83. According to the identity information of the boxer, access the database to obtain the average boxing force or the maximum boxing force of the boxer in the current most recent historical training period.

[0098] In the step S83, the current most recent historical training period can be exemplified as the training period of yesterday, so as to analyze the difference in training effects between yesterday and today. In addition, it is also necessary to bind and store the boxing force value and the occurrence time of the combat sports boxing event to the identity information of the boxer in the database, so as to be used for the comparative analysis of the training effects between today and tomorrow.

[0099] S84. Compare and analyze the boxing force value of the combat sports boxing event with the average boxing force or the maximum boxing force of the boxer in the current most recent historical training period, obtain the comparative analysis result and display it on-site.

[0100] In the step S84, the specific analysis means is the prior art means (such as performing subtraction calculation), which will not be elaborated here. In addition, the comparative analysis result can also be specifically displayed on-site through the display screen 300 located directly above the square combat sports boxing target 100.

[0101] Thus, based on the foregoing possible design two, the identity information of the current boxer can be automatically recognized, and the training effect data of the current most recent historical training period can be automatically retrieved and compared with the current training effect data, and the analysis result can be displayed on-site. Furthermore, the boxer can intuitively understand the improvement degree of the current exercise effect, further stimulate the training enthusiasm, and improve the user experience.

[0102] As Figure 4 shown, the second aspect of this embodiment provides a virtual device for implementing the combat sports boxing force analysis method described in the first aspect or any possible design in the first aspect, including a vibration signal receiving unit, a vibration signal processing unit, a judgment unit, a system of equations construction unit, a system of equations solving unit, and a boxing force estimation unit;

[0103] The vibration signal receiving unit is used to receive a plurality of vibration time-domain signals collected in real time by a plurality of vibration sensors. Among them, the plurality of vibration sensors are arranged at intervals circumferentially along the edge of the combat sports boxing target, and the plurality of vibration time-domain signals correspond to the plurality of vibration sensors one by one;

[0104] The vibration signal processing unit is communicatively connected to the vibration signal receiving unit, and is used for each vibration time-domain signal in the plurality of vibration time-domain signals to extract the corresponding signal amplitude in real time according to the corresponding signal, and when it is found that the corresponding signal amplitude is a maximum value and exceeds a preset threshold, record the occurrence time of the corresponding maximum value;

[0105] The judgment unit is communicatively connected to the vibration signal processing unit, and is used to judge whether the occurrence time of the maximum value of each vibration time-domain signal is recorded within the current most recent time window;

[0106] The equation set construction unit is respectively communicatively connected to the vibration signal processing unit and the judgment unit. If so, it determines that a combat sports boxing event has occurred for the combat sports boxing target body, and establishes the following equation set:

[0107]

[0108] In the formula, N represents the total number of sensors of the multiple vibration sensors, n represents a positive integer less than N, and L n,n+1 represents the known layout distance between the nth vibration sensor and the (n + 1)th vibration sensor in the circumferential direction among the multiple vibration sensors, and L N,1 represents the known layout distance between the Nth vibration sensor and the first vibration sensor in the circumferential direction among the multiple vibration sensors, and t n represents the occurrence moment of the maximum value of the vibration time-domain signal recorded in the current nearest time window and corresponding to the nth vibration sensor, and t n+1 represents the occurrence moment of the maximum value of the vibration time-domain signal recorded in the current nearest time window and corresponding to the (n + 1)th vibration sensor, and t 0 represents the occurrence moment of the combat sports boxing event and is a variable to be solved, v represents the known propagation speed of the boxing shock wave in the combat sports boxing target body, and θ n,n+1 represents the angle between the first line segment and the second line segment, and θ N,1 represents the angle between the third line segment and the fourth line segment. The first line segment refers to the line segment between the nth vibration sensor and the occurrence position of the combat sports boxing event, the second line segment refers to the line segment between the (n + 1)th vibration sensor and the occurrence position of the combat sports boxing event, the third line segment refers to the line segment between the Nth vibration sensor and the occurrence position of the combat sports boxing event, and the fourth line segment refers to the line segment between the first vibration sensor and the occurrence position of the combat sports boxing event;

[0109] The equation set solving unit is communicatively connected to the equation set construction unit, and is used to solve the equation set to obtain the occurrence moment t of the combat sports boxing event 0 ;

[0110] The boxing force estimation unit is respectively communicatively connected to the vibration signal processing unit and the equation set solving unit, and is used to respectively compare the occurrence moments of the maximum values of the respective vibration time-domain signals recorded in the current nearest time window with the occurrence moment t of the combat sports boxing event 0The time difference value and the respective signal amplitudes corresponding one-to-one to the occurrence times of the maximum values of the respective vibration time-domain signals recorded within the current nearest time window are imported into a combat sports boxing power estimation model that has been pre-trained based on a first artificial intelligence algorithm, and a boxing power value of the combat sports boxing event is output.

[0111] For the working process, working details, and technical effects of the aforementioned device provided in the second aspect of this embodiment, reference can be made to the combat sports boxing power analysis method described in the first aspect or any possible design in the first aspect, and details will not be elaborated here.

[0112] As Figure 5 shown, the third aspect of this embodiment provides a computer device that executes the combat sports boxing power analysis method described in the first aspect or any possible design in the first aspect, including a memory, a processor, and a transceiver that are sequentially communicatively connected. Among them, the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs and execute the combat sports boxing power analysis method described in the first aspect or any possible design in the first aspect. Specifically, by way of example, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first input first output (FIFO), and / or first input last output (FILO), etc.; the processor may be, but is not limited to, a microprocessor of the STM32F105 series. In addition, the computer device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0113] For the working process, working details, and technical effects of the aforementioned computer device provided in the third aspect of this embodiment, reference can be made to the combat sports boxing power analysis method described in the first aspect or any possible design in the first aspect, and details will not be elaborated here.

[0114] The fourth aspect of this embodiment provides a computer-readable storage medium storing instructions for the combat sports boxing force analysis method as described in the first aspect or any possible design in the first aspect. That is, instructions are stored on the computer-readable storage medium, and when the instructions run on a computer, they execute the combat sports boxing force analysis method as described in the first aspect or any possible design in the first aspect. Among them, the computer-readable storage medium refers to a carrier for storing data, which may include, but is not limited to, computer-readable storage media such as floppy disks, optical discs, hard disks, flash memories, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0115] For the working process, working details, and technical effects of the aforementioned computer-readable storage medium provided in the fourth aspect of this embodiment, reference may be made to the combat sports boxing force analysis method as described in the first aspect or any possible design in the first aspect, which will not be elaborated herein.

[0116] The fifth aspect of this embodiment provides a computer program product, including a computer program or instructions, and when the computer program or the instructions are executed by a computer, they implement the combat sports boxing force analysis method as described in the first aspect or any possible design in the first aspect. Among them, the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0117] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for analyzing boxing strength in combat sports, characterized in that: include: Receiving a plurality of vibration time domain signals collected in real time by a plurality of vibration sensors, wherein the plurality of vibration sensors are arranged circumferentially and spaced apart along the edge of a combat sports boxing target, and the plurality of vibration time domain signals correspond one to one to the plurality of vibration sensors; For each vibration time domain signal in the multiple vibration time domain signals, extract the corresponding signal amplitude in real time according to the corresponding signal, and when it is found that the corresponding signal amplitude is a maximum value and exceeds a preset threshold, record the corresponding maximum value occurrence time; Determine whether the maximum value occurrence time of each vibration time domain signal is recorded in the current most recent time window; If yes, it is determined that a combat sports boxing event targeting the combat sports boxing target has occurred, and the following equation group is established: Wherein, N represents the total number of the plurality of vibration sensors, n represents a positive integer less than N, and L n,n+1 represents the known arrangement distance between the nth vibration sensor and the n+1th vibration sensor in the circumferential direction among the plurality of vibration sensors, L N,1 represents the known arrangement distance between the Nth vibration sensor and the first vibration sensor in the circumferential direction among the plurality of vibration sensors, t n represents the time when the maximum value of the vibration time domain signal recorded in the current most recent time window and corresponding to the nth vibration sensor occurs, t n+1 represents the time when the maximum value of the vibration time domain signal recorded in the current most recent time window and corresponding to the n+1th vibration sensor occurs, t0 represents the time when the combat sports boxing event occurs and is a variable to be solved, v represents the known propagation speed of the boxing shock wave in the combat sports boxing target, θ n,n+1 represents the angle between the first line segment and the second line segment, θ N,1 represents the angle between the third line segment and the fourth line segment, the first line segment refers to the line segment between the nth vibration sensor and the occurrence position of the combat sports boxing event, the second line segment refers to the line segment between the n+1th vibration sensor and the occurrence position of the combat sports boxing event, the third line segment refers to the line segment between the Nth vibration sensor and the occurrence position of the combat sports boxing event, and the fourth line segment refers to the line segment between the first vibration sensor and the occurrence position of the combat sports boxing event; Solving the equation group to obtain the occurrence time t0 of the combat sports boxing event; The time difference values ​​between the maximum value occurrence time points of the respective vibration time domain signals recorded in the current most recent time window and the occurrence time point t0 of the combat sports boxing event and the respective signal amplitudes corresponding to the maximum value occurrence time points of the respective vibration time domain signals recorded in the current most recent time window are imported into a combat sports boxing force estimation model that has been pre-trained based on the first artificial intelligence algorithm, and the boxing force value of the combat sports boxing event is obtained as output.

2. The combat sports boxing strength analysis method according to claim 1, characterized in that: The first artificial intelligence algorithm adopts a machine learning algorithm based on support vector machine, K nearest neighbor method, stochastic gradient descent method, multivariate linear regression, multilayer perceptron, decision tree, back propagation neural network or radial basis function network.

3. The combat sports boxing strength analysis method according to claim 1, characterized in that: The method further comprises: For each combat sports boxing event among the M combat sports boxing events that have occurred recently, a positioning algorithm is used to determine the corresponding striking position on the combat sports boxing target according to the known positions of the multiple vibration sensors, the known propagation speed v, and the time difference between the maximum occurrence time of each vibration time domain signal recorded in the corresponding time window and the occurrence time of the corresponding event, wherein M represents a positive integer greater than or equal to 3; Taking the striking position of the first combat sports boxing event that occurs earliest among the M combat sports boxing events as a reference point, calculating the relative coordinates of the striking positions of each other combat sports boxing event in the M combat sports boxing events relative to the reference point in the order of the time of occurrence of the events, and obtaining a relative coordinate time series data; Taking the occurrence time of the first combat sports boxing event as the reference time, sequentially calculating the time difference between the occurrence time of each other combat sports boxing event and the reference time in the order of the occurrence time of the event, and obtaining a time difference value time series data; Importing the relative coordinate time series data and the time difference value time series data into a combat sports boxing action recognition model that has been pre-trained based on a second artificial intelligence algorithm, and outputting a current combat sports boxing action recognition result; According to the combat sports boxing action recognition result, the current combat sports boxing power value is displayed in the following manner (A) or (B): (A) when the combat sports boxing action recognition result is a straight punch, an uppercut or a jab, the boxing power value of the combat sports boxing event that occurs last among the M combat sports boxing events is displayed on site as the current combat sports boxing power value; (B) When the combat sports boxing action recognition result is a combination punch, the average boxing power of the M combat sports boxing events is used as the current combat sports boxing power value for on-site display.

4. The combat sports boxing strength analysis method according to claim 3, characterized in that: The second artificial intelligence algorithm adopts a machine learning algorithm based on LSTM, Bi-LSTM or Attention-LSTM.

5. The combat sports boxing strength analysis method according to claim 1, characterized in that: The method further comprises: Acquiring live video data collected in real time by a camera of the front area of ​​the combat sports boxing target; According to the live video data, a face recognition algorithm is used to obtain the identity information of the boxer currently located in the front area; Accessing a database to obtain an average or maximum boxing strength of the boxer in a recent historical training period according to the boxer's identity information; A comparative analysis is performed on the boxing power value of the combat sports boxing event and the average boxing power value or the maximum boxing power value of the boxer in the current recent historical training period, and the comparative analysis results are obtained and displayed on site.

6. The combat sports boxing strength analysis method according to claim 5, characterized in that: The method further comprises: The punching force value and the occurrence time of the combat sports boxing event are bound with the identity information of the boxer and stored in the database.

7. A combat sports boxing force analysis device, characterized in that: It includes a vibration signal receiving unit, a vibration signal processing unit, a judgment unit, an equation group building unit, an equation group solving unit and a boxing force estimation unit; The vibration signal receiving unit is used to receive a plurality of vibration time domain signals collected in real time by a plurality of vibration sensors, wherein the plurality of vibration sensors are arranged circumferentially and spaced apart along the edge of the combat sports boxing target, and the plurality of vibration time domain signals correspond one to one to the plurality of vibration sensors; The vibration signal processing unit is communicatively connected to the vibration signal receiving unit, and is used to extract the corresponding signal amplitude in real time according to the corresponding signal for each vibration time domain signal in the multiple vibration time domain signals, and record the corresponding maximum value occurrence time when it is found that the corresponding signal amplitude is a maximum value and exceeds a preset threshold value; The judgment unit is communicatively connected to the vibration signal processing unit, and is used to judge whether the maximum value occurrence time of each vibration time domain signal is recorded in the current most recent time window; The equation group construction unit is respectively connected to the vibration signal processing unit and the judgment unit for determining that a combat sports boxing event has occurred with respect to the combat sports boxing target, and establishing the following equation group: Wherein, N represents the total number of the plurality of vibration sensors, n represents a positive integer less than N, and L n,n+1 represents the known arrangement distance between the nth vibration sensor and the n+1th vibration sensor in the circumferential direction among the plurality of vibration sensors, L N,1 represents the known arrangement distance between the Nth vibration sensor and the first vibration sensor in the circumferential direction among the plurality of vibration sensors, t n represents the time when the maximum value of the vibration time domain signal recorded in the current most recent time window and corresponding to the nth vibration sensor occurs, t n+1 represents the time when the maximum value of the vibration time domain signal recorded in the current most recent time window and corresponding to the n+1th vibration sensor occurs, t0 represents the time when the combat sports boxing event occurs and is a variable to be solved, v represents the known propagation speed of the boxing shock wave in the combat sports boxing target, θ n,n+1 represents the angle between the first line segment and the second line segment, θ N,1 represents the angle between the third line segment and the fourth line segment, the first line segment refers to the line segment between the nth vibration sensor and the occurrence position of the combat sports boxing event, the second line segment refers to the line segment between the n+1th vibration sensor and the occurrence position of the combat sports boxing event, the third line segment refers to the line segment between the Nth vibration sensor and the occurrence position of the combat sports boxing event, and the fourth line segment refers to the line segment between the first vibration sensor and the occurrence position of the combat sports boxing event; The equation group solving unit is communicatively connected to the equation group constructing unit, and is used to solve the equation group to obtain the occurrence time t0 of the combat sports boxing event; The boxing force estimation unit is communicatively connected to the vibration signal processing unit and the equation solving unit, respectively, and is used to import the time difference values ​​between the maximum value occurrence time points of the respective vibration time domain signals recorded in the current most recent time window and the occurrence time point t0 of the combat sports boxing event, as well as the respective signal amplitudes corresponding to the maximum value occurrence time points of the respective vibration time domain signals recorded in the current most recent time window, into a combat sports boxing force estimation model that has been pre-trained based on the first artificial intelligence algorithm, and output the boxing force value of the combat sports boxing event.

8. A computer device, characterized in that: It includes a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the combat sports boxing power analysis method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on the computer, the combat sports boxing strength analysis method as described in any one of claims 1 to 6 is executed.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or the instruction is executed by a computer, the method for analyzing boxing power of combat sports as claimed in any one of claims 1 to 6 is implemented.

Images