Beat event recognition method and device, electronic equipment and storage medium

Abstract

The invention provides a hit event recognition method and device, electronic equipment and a storage medium, and effectively solves the problem that the accuracy of an existing mode for recognizing a hit event of a user is reduced. The method comprises the following steps: configuring the boxing physiotherapy equipment so that a user can hit the boxing physiotherapy equipment, and collecting various generated initial sensor data; preprocessing the plurality of initial sensor data to obtain a plurality of sensor data, screening out target sensor data in the plurality of sensor data, and fusing the target sensor data to obtain target data; sending the target data to the upper computer, so that the upper computer receives the target data; and controlling the upper computer to screen the target data based on the striking threshold value to obtain target striking data, so as to identify a striking event formed when the user uses the boxing target based on the target striking data and the striking parameters of the target striking data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of physiotherapy equipment, in particular to a hitting event identification method and device, electronic equipment and storage medium. BACKGROUND

[0002] Punching physiotherapy equipment is an innovative product combining the characteristics of boxing and physical therapy principles in recent years. It not only retains the fun of boxing training, but also realizes functions such as sports injury prevention, rehabilitation treatment and physical fitness improvement through scientific and technological means. For example, various sensors are built into the punching target, and the physiotherapy effect of the user's body is analyzed based on the user's hitting data, thereby assisting doctors in formulating a scientific and effective rehabilitation training plan.

[0003] Currently, there are two common ways to identify the user's hitting event. One is to use a single sensor to calculate the threshold value trigger mechanism (such as relying on an accelerometer), and the other is a fixed threshold trigger mechanism that uses a static threshold value (such as a fixed acceleration peak) to determine the hitting event, lacking dynamic adjustment capability. The former is to convert the target physical quantity (such as force, acceleration) into deformation or electrical signal through a single sensor and a sensitive element (such as a strain gauge, piezoelectric material). For example, a piezoresistive pressure sensor uses the resistance change of a strain gauge to reflect the force, and an accelerometer measures acceleration based on the principle of inertia (F = ma). The conversion process follows a linear relationship (such as Hooke's Law) or a nonlinear physical effect (such as piezoresistive effect). It has the advantages of simple structure and low cost, but is greatly affected by environmental interference, error accumulation and insufficient dynamic adaptability. The latter is to pre-set a static value (such as an acceleration peak, a temperature upper limit, an angle threshold) as an event trigger condition, and when the sensor detects a value exceeding the threshold, it is determined as a valid event. The sensor collects real-time data (such as acceleration, temperature, pressure, angle), which is compared with the pre-set threshold value after analog-to-digital conversion. If the data exceeds the threshold, the system triggers a pre-set response (such as counting, statistics, etc.). The threshold value is usually fixed in the hardware register or software configuration file, and modification requires manual intervention, which has poor adaptability. The above two methods also have the problems of weak anti-interference ability, uncorrectable errors, lack of self-adaptive ability, and limited application scenarios, which further leads to a decrease in the accuracy of hitting event identification. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a hitting event identification method, device, electronic equipment and storage medium, which effectively solves the problem of reduced accuracy in the existing way of identifying the user's hitting event.

[0005] In a first aspect, the embodiments of the present application provide a hitting event identification method, applied to a boxing physiotherapy device, the boxing physiotherapy device comprising a boxing target and an upper computer, the boxing target being internally provided with multiple sensors and a microprocessor, and the method comprising: configuring the boxing physiotherapy device so that a user hits the boxing target based on the multiple sensors configured internally, and collects multiple initial sensor data generated in the hitting process based on the multiple sensors; preprocessing the multiple initial sensor data to obtain multiple sensor data, screening out target sensor data in the multiple sensor data for fusion to obtain target data; sending the target data to the upper computer so that the upper computer receives the target data; the upper computer is internally provided with a dynamically adjusted hitting threshold; controlling the upper computer to screen the target data based on the hitting threshold to obtain target hitting data, so as to identify a hitting event formed by the user using the boxing target based on the target hitting data and hitting parameters of the target hitting data. In combination with the first aspect, the embodiments of the present application provide a first possible implementation manner of the first aspect, wherein the controlling the upper computer to screen the target data based on the hitting threshold to obtain target hitting data comprises: determining whether the target data exceeds the hitting threshold obtained by the upper computer based on the multiple initial sensor data, and generating a corresponding determination result; based on the determination result, filtering out the target data below the hitting threshold to screen out the target hitting data.

[0006] In combination with the first aspect, the embodiments of the present application provide a second possible implementation manner of the first aspect, wherein the determining whether the target data exceeds the hitting threshold obtained by the upper computer based on the multiple initial sensor data comprises: determining an environmental influence factor of the hitting threshold, and dynamically adjusting an environmental influence coefficient corresponding to the environmental influence factor; calculating the environmental influence coefficient and a pre-set initial hitting threshold to obtain the hitting threshold.

[0007] In combination with the first aspect, the embodiments of the present application provide a third possible implementation manner of the first aspect, wherein the screening out the target sensor data in the multiple sensor data for fusion to obtain the target data comprises: based on acceleration data and angular velocity data in the target sensor data, calculating a gravity component; separating the gravity component from the acceleration data, and retaining target data in the acceleration data.

[0008] With reference to the first aspect, embodiments of the present application provide a fourth possible implementation manner of the first aspect, and the fourth possible implementation manner comprises the following steps of: defining a global coordinate system for the punching target and a device coordinate system, and updating a rotation matrix of the global coordinate system converted to the device coordinate system based on the angular velocity data; updating the rotation matrix and the gravity in the global coordinate system based on a preset calculation network to obtain the gravity component.

[0009] With reference to the first aspect, embodiments of the present application provide a fifth possible implementation manner of the first aspect, and the fifth possible implementation manner comprises the following steps of: determining a type of a sensor corresponding to the plurality of sensor data to determine whether the type is a target type; if yes, determining that data collected by the sensor of the target type is target sensor data.

[0010] With reference to the first aspect, embodiments of the present application provide a sixth possible implementation manner of the first aspect, and the sixth possible implementation manner comprises the following steps of: performing data calculation on the additional hitting parameters of the target hitting data based on multiple dimensions to obtain corresponding additional hitting data; generating a personalized hitting report for the user based on the corresponding additional hitting data.

[0011] In the second aspect, embodiments of the present application provide a hitting event recognition device applied to a punching type physiotherapy device, wherein the punching type physiotherapy device comprises a punching target and a host computer, the punching target is internally provided with a plurality of sensors and a microprocessor, and the device comprises the following modules: a configuration module configured to configure the punching type physiotherapy device, so that a user hits the punching target based on the plurality of sensors configured in the punching target, and collects a plurality of initial sensor data generated in a hitting process based on the plurality of sensors; a fusion module configured to preprocess the plurality of initial sensor data to obtain a plurality of sensor data, screen out target sensor data in the plurality of sensor data for fusion, and obtain target data; a sending module configured to send the target data to the host computer, so that the host computer receives the target data; and the host computer is internally provided with a dynamically adjusted hitting threshold value; The identification module is configured to control the host computer to filter the target data based on the hitting threshold, to obtain target hitting data, and to identify a hitting event formed by a user when hitting the punching target based on the target hitting data and a hitting parameter of the target hitting data.

[0012] In a third aspect, an electronic device is provided, which includes a processor, a memory, and a bus. The memory stores machine readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory through the bus. The machine readable instructions are executed by the processor to perform the steps of any one of the hitting event identification methods.

[0013] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of any one of the hitting event identification methods are performed.

[0014] The hitting event identification method provided by the embodiments of the present application is applied to a punching type physiotherapy device. The punching type physiotherapy device includes a punching target and a host computer. The punching target is internally provided with multiple sensors and a microprocessor. The method first configures the punching type physiotherapy device, so that a user hits the punching target based on the multiple sensors configured internally, and collects multiple initial sensor data generated in the hitting process based on the multiple sensors. Then, the multiple initial sensor data is preprocessed to obtain multiple sensor data, target sensor data in the multiple sensor data is filtered and fused to obtain target data. Then, the target data is sent to the host computer, so that the host computer receives the target data. The host computer is internally provided with a hitting threshold dynamically adjusted. Finally, the host computer is controlled to filter the target data based on the hitting threshold, to obtain target hitting data, and to identify a hitting event formed by a user when hitting the punching target based on the target hitting data and a hitting parameter of the target hitting data. In this way, the hitting event is accurately identified, and the accuracy of the identification is improved. The problems of weak anti-interference ability, uncorrectable error, lack of adaptive ability, and limited application scenarios of the triggering mechanism of the hitting event triggered by a single sensor and the fixed threshold triggering mechanism are solved, so that the physiotherapy effect of the user using the punching type physiotherapy device is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be regarded as limiting the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0016] Figure 1 A flow diagram of a hitting event identification method provided by an embodiment of the present application is shown; Figure 2 A flow diagram of another hitting event identification method provided by an embodiment of the present application is shown; Figure 3 A flow diagram of screening out target hitting data provided by an embodiment of the present application is shown; Figure 4 A structural block diagram of a hitting event identification device provided by an embodiment of the present application is shown; Figure 5 A structural block diagram of an electronic device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. It should be understood that the drawings in the present application only play the purpose of illustration and description, and are not used to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn according to the actual proportion. The flowchart shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can not be implemented in sequence, and the steps without logical context relationship can be reversed in sequence or implemented simultaneously. In addition, one or more other operations can be added to the flowchart or removed from the flowchart by those skilled in the art under the guidance of the content of the present application.

[0018] In addition, the described embodiments are only some of the embodiments of the present application, not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0019] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the presence of the features that follow, but not to exclude the presence of other features.

[0020] Currently, the identification of the punching event of the boxing physiotherapy equipment generally uses a single sensor to trigger the punching event through statistical calculation threshold and fixed threshold triggering mechanism, but is greatly affected by environmental interference, error accumulation and insufficient dynamic adaptability. The above two ways also have the problems of weak anti-interference ability, uncorrectable error, lack of self-adaptive ability, limited application scene, and thus the accuracy of the punching event identification is reduced.

[0021] Based on this, the embodiments of the present application provide a punching event identification method and device, electronic equipment and storage medium, which are described below through embodiments.

[0022] Embodiment 1 In order to facilitate the understanding of the present embodiment, first, a punching event identification method disclosed in the embodiments of the present application is introduced in detail. As shown in a flow chart of a punching event identification method, Figure 1 As shown in a flow chart of a punching event identification method, Figure 2 Another flow chart of a punching event identification method provided by the present application is shown, and the punching event identification method provided by the present application is applied to a boxing physiotherapy equipment, which includes a boxing target and an upper computer. The boxing target is built-in with multiple sensors and a microprocessor. The method includes: S101, configuring the boxing physiotherapy equipment, so that the user punches the boxing target based on the multiple sensors built-in in the configured boxing physiotherapy equipment, and collects multiple initial sensor data generated in the punching process based on the multiple sensors; S102, preprocessing the multiple initial sensor data to obtain multiple sensor data, screening out target sensor data in the multiple sensor data for fusion to obtain target data; S103, sending the target data to the upper computer, so that the upper computer receives the target data; the upper computer is built-in with a dynamically adjusted punching threshold; S104, controlling the upper computer to screen the target data based on the punching threshold to obtain target punching data, so as to identify the punching event formed by the user using the boxing target based on the target punching data and the punching parameters of the target punching data. In step S101, when the user uses the boxing type physiotherapy device, the built-in multiple sensors are configured in advance, and the specific configuration includes initializing the multiple sensors and dynamic threshold parameters, loading the configuration file corresponding to each sensor, and establishing the communication link between the microprocessor and the upper computer, so that the upper computer can receive the communication link. The multiple sensors include an accelerometer, a gyroscope, and an environmental sensor, including a temperature sensor and a humidity sensor. The accelerometer and the gyroscope both use a high-precision 6-axis sensor MPU6050 range, the accelerometer ±2g / ±4g / ±8g / ±16g, the angular velocity sensor ±250° / s to ±2000° / s, the dynamic threshold parameters include a sliding window size, an initial hitting threshold, etc., and the physical model parameters are set, including an impulse integration time window and a direction correction matrix. The physical model is used to calculate the target data obtained from the multiple sensor data. The setting of the physical model parameters and the configuration of the dynamic threshold parameters occur in the upper computer, that is, the configuration occurs not only in the sensor but also in the microprocessor and the upper computer. After the configuration is completed, the user hits the boxing target based on the multiple sensors in the built-in configured boxing type physiotherapy device, that is, the user has already performed physiotherapy based on the boxing type physiotherapy device, and the multiple initial sensor data generated during the hitting process are collected at a high frequency based on the multiple sensors, that is, the multiple sensor data of the user during the hitting process are collected at a high frequency, including acceleration data, angular velocity data, temperature data, and humidity data. The collected acceleration data, angular velocity data, temperature data, and humidity data are sent to the microprocessor. The I2C bus between the multiple sensors and the processor at 400 kHz clock ensures zero conflict collection of sensor data.

[0023] In step S102, after receiving the acceleration data, angular velocity data, temperature data, and humidity data included in the multiple sensor data, the microprocessor preprocesses the multiple initial sensor data to obtain multiple sensor data. The specific preprocessing includes filtering processing to avoid the existence of noise or interference when the accelerometer and the gyroscope collect acceleration data and angular velocity data, which causes errors in the high-frequency collected acceleration data and angular velocity data. After filtering processing, the target sensor data in the multiple sensor data is screened and fused to obtain target data. The application achieves the effect of reducing the data calculation amount while obtaining the target data, and improves the recognition rate of the hitting event.

[0024] In the specific implementation process of step S102, there is an embodiment that the screening of the target sensor data in the multiple sensor data for fusion further includes: S10211, determine the type of the sensor corresponding to the plurality of sensor data respectively to determine whether the type is a target type; S10212, if yes, determine the data collected by the sensor of the target type as target sensor data.

[0025] In steps S10211-S10212, the microprocessor determines the type of the sensor corresponding to the plurality of sensor data received by the microprocessor, divides the plurality of sensors into two types, one is a strike-related type and an environment-related type, then determines that the accelerometer and gyroscope corresponding to the acceleration data and angular velocity data belong to the strike-related type, and the temperature sensor and humidity sensor belong to the environment-related type, to determine whether the type is a target type; The present application sets the target type as the strike-related type, so the sensor data detected by the sensor belonging to this type is the target sensor data, therefore, in the present application, the target sensor data includes acceleration data and angular velocity data.

[0026] In the specific implementation process of step S102, another embodiment is that the target sensor data in the plurality of sensor data is screened out for fusion to obtain target data, including: S10221, based on the acceleration data and angular velocity data in the target sensor data, calculate the gravity component; S10222, separate the gravity component from the acceleration data and retain the target data in the acceleration data.

[0027] In steps S10221-S10222, the target data obtained by the microprocessor based on the acceleration sensor data and angular velocity sensor data is linear acceleration data, the acceleration data in the target sensor data is the acceleration data generated by the vibration or movement of the punching target when it is hit by the user and the gravity component received by the punching target, and the angular velocity data is higher than the change in the posture of the punching target. In order to obtain the linear acceleration data generated by the punching target, the gravity component needs to be separated from the acceleration data, which can be achieved by subtracting the acceleration sensor data from the gravity component, and the target data in the acceleration data is retained, that is, the linear acceleration data is retained and the existence of the gravity component is filtered out.

[0028] In the specific implementation process of step S10221, one embodiment is that the gravity component is calculated based on the acceleration data and angular velocity data in the target sensor data, including: S102211、define the global coordinate system and the device coordinate system for the punching target, and update the rotation matrix of the global coordinate system to the device coordinate system based on the angular velocity data; S102212、update the rotation matrix and the gravity in the global coordinate system based on the preset calculation network processing to obtain the gravity component.

[0029] In steps S102211-S102212, the microprocessor defines the global coordinate system and the device coordinate system for the punching target, wherein the global coordinate system generally takes the ground as the origin, XW east, YW north, ZW up (or customized according to requirements), and the device coordinate system is centered on the punching target, XB pointing to the right side of the screen (horizontal axis), YB pointing upwards (vertical axis), ZB outwardly perpendicular to the screen (depth axis), wherein the gravity in the global coordinate system is constant, and the gravity component in the device coordinate system needs to be separated by rotating the matrix to convert from the device coordinate system to the global coordinate system, i.e., updating the rotation matrix of the global coordinate system to the device coordinate system based on the angular velocity data, which can be achieved by quaternion integration or direction cosine matrix integration, and then based on the updated rotation matrix, the gravity can be converted from the device coordinate system to the global coordinate system by rotating the matrix, and based on the preset calculation network processing, the updated rotation matrix and the gravity in the global coordinate system are multiplied to obtain the gravity component.

[0030] In step S103, the microprocessor obtains the target data, i.e., linear acceleration data, and transmits the target data to the upper computer in real time through Wifi wireless transmission, so that the upper computer receives the target data; the upper computer receives the linear acceleration data and the temperature data and humidity data detected by the environmental sensor and included in the environmental data transmitted by the microprocessor at the same time, and the upper computer has a built-in dynamically adjusted hitting threshold; the hitting threshold is dynamically adjustable, and is obtained by dynamically adjusting the initial hitting threshold based on the environmental data; based on the dynamically adjustable hitting threshold, a dynamic hitting event triggering mechanism can be realized, the accuracy of hitting event triggering is ensured, and the phenomenon of lack of adaptive ability is avoided.

[0031] In step S104, after obtaining the target data, i.e., the linear acceleration data, the host computer controls the host computer to screen the target data based on the hitting threshold to obtain target hitting data, so as to identify a hitting event formed by a user when hitting the target based on the target hitting data and a hitting parameter of the target hitting data, the hitting parameter including a hitting force, the hitting force being obtained based on a hitting parameter calculation model, the hitting parameter calculation model achieving the effects of impulse integration and direction correction, improving the anti-interference ability and scene adaptability, and reducing the triggering rate of false hitting events to less than 5%. If there are multiple hitting energy values corresponding to the hitting energy parameter, the maximum one needs to be selected as the final hitting energy value. Because it is high-frequency acquisition, the invalid time interval between data points is within 200 ms, so as to achieve the effect of eliminating jitter. At this time, the final hitting energy value is taken as the hitting force, and the remaining hitting energy values are filtered out. If the target hitting data and the hitting parameter, i.e., the hitting force parameter, cannot be collected to form a hitting event, the hitting event cannot be detected. The target hitting data is discarded, and sensor data acquisition is performed again. In the specific implementation process of step S104, there is an embodiment as shown in the following table: Figure 3 The control of the host computer to screen the target data based on the hitting threshold to obtain target hitting data includes: S10411, determining whether the target data exceeds the hitting threshold obtained by the host computer based on the plurality of initial sensor data, and generating a corresponding determination result; S10412, based on the determination result, filtering out the target data below the hitting threshold to screen out the target hitting data.

[0032] In steps S10411-S10412, the host computer determines whether the target data, i.e., the linear acceleration data, exceeds the hitting threshold obtained by the host computer based on the plurality of initial sensor data, and generates a corresponding determination result, the determination result including yes and no. If no, the hitting event recognition fails, and sensor data acquisition needs to be performed again for re-recognition. If yes, the hitting event recognition succeeds, the target data below the hitting threshold is filtered out, and at this time, the determination result is determined to be the target hitting data, achieving screening out the target hitting data to further perform additional hitting parameter calculation based on the target hitting data.

[0033] In the specific implementation process of step S1041, there is an embodiment as follows: S10411, determine the environmental impact factor of the hitting threshold, and dynamically adjust the environmental impact factor corresponding to the environmental impact coefficient; S10412, calculate the environmental impact coefficient and the initial hitting threshold set in advance to obtain the hitting threshold.

[0034] In steps S10411-S10412, the host computer determines the environmental impact factor of the hitting threshold, and the environmental impact factor includes noise, and can also include temperature and humidity. For noise, the current environmental noise is calculated based on a sliding window statistical method, wherein the window in the sliding window statistical method is dynamically adjustable and the environmental impact coefficient corresponding to the environmental impact factor is adjusted based on the size of the environmental noise. The specific adjustment is realized according to formulas (1)-(4): tempEffect = 1.0 + Math.Tanh((Temperature - 25) / 15) * 0.1 (1); humidityEffect = 1.0 - (Humidity - 50) / 100 (2); envNoiseWeight = NoiseLevel / (stdDev + 0.001) (3); dynamicfactor = Math.Max(1.5, 3.2 - stdDev*0.12 - envNoiseWeight*0.5) (4); tempEffect is a smooth transition of temperature compensation coefficient realized by hyperbolic tangent function (tanh), with 25℃ as the reference zero point (common room temperature), when temperature = 25℃: tempEffect = 1.0 (no compensation), when temperature = 40℃: tanh(1) = 0.76 → tempEffect ≈ 1.076 (compensation), when temperature = 10℃: tanh(-1) = -0.76 → tempEffect ≈ 0.924; humidityEffect is based on 50% RH as the reference humidity (humidityEffect = 1.0 at this time); envNoiseWeight refers to the environmental noise weight; dynamicfactor refers to the dynamic factor, which is calculated in real time by fusing environmental noise, and the dynamic factor range is usually ∈ [1.5, 3.0]; the dynamic average baseline dynamicBaseline = accelavg * tempEffect * humidityEffect, that is, the dynamic average baseline is obtained by fusing temperature and humidity; the hitting threshold dynamicThreshold = dynamicBaseline + dynamicfactor * stdDev, that is, the hitting threshold = dynamic average baseline (fusing temperature and humidity) + dynamic factor (fusing environmental noise) * dynamic standard deviation, then the environmental influence coefficient is calculated and the initial hitting threshold is set in advance, the hitting threshold is obtained, so as to realize the dynamic adjustment of the hitting threshold, wherein the real-time collected temperature Temperature includes indoor environment temperature of 18-30℃ and industrial environment temperature of-40-85℃, the real-time collected humidity Humidity (non-condensing) is 10%-95% RH, the real-time collected noise level includes quiet environment of 30-40 dB and urban environment of 50-70 dB, accelavg represents the average value of data in the sliding window; stdDev represents the standard deviation of data in the sliding window.

[0035] In the specific implementation process of step S104, there is another embodiment that after identifying the hitting event formed by the user when using the punching target based on the target hitting data and the additional hitting parameters of the target hitting data, it includes: S10421, data calculation is performed on the additional hitting parameters of the target hitting data based on multiple dimensions, to obtain corresponding additional hitting data; S10422, generating a personalized hitting report for the user based on the corresponding additional hitting data.

[0036] In steps S10421-S10422, additional hitting parameters of the target hitting data are calculated based on multiple dimensions, the additional hitting parameters including a hitting frequency, the hitting frequency being statistically obtained, and then a personalized hitting report for the user is generated based on the corresponding hitting force and hitting frequency, the personalized hitting report including a curve trend graph generated based on the hitting force and hitting frequency, predicting a peak period of the competitive state of the user, helping to make a rehabilitation training plan, preventing training injuries based on the personalized hitting report, warning potential injury risks by dynamically monitoring abnormal patterns of hitting actions (such as one-sided excessive force and hitting angle deviation), and helping to develop a scientific rehabilitation training plan for the user in combination with physical condition monitoring data (such as heart-lung function and muscle endurance) of the user, promoting the popularization of low-cost hitting catharsis training, and promoting the development of catharsis rehabilitation.

[0037] Embodiment 2 The application also provides a hitting event identification device, as shown in Figure 4 A block diagram of a hitting event identification device is shown, and the functions implemented by the device correspond to the steps of the above-mentioned method of identifying a hitting event on a terminal device. The device can be understood as a component of a server including a processor. The hitting event identification device described in the application is applied to a boxing type physiotherapy device, which includes a boxing target and an upper computer. The boxing target is built-in with multiple sensors and a microprocessor. The device includes: A configuration module 401 is configured to configure the boxing type physiotherapy device, so that the user hits the boxing target based on the built-in multiple sensors configured, and collects multiple initial sensor data generated during the hitting process based on the multiple sensors; A fusion module 402 is configured to preprocess the multiple initial sensor data to obtain multiple sensor data, screen out target sensor data in the multiple sensor data for fusion, and obtain target data; A sending module 403 is configured to send the target data to the upper computer, so that the upper computer receives the target data. The upper computer is built-in with a dynamically adjusted hitting threshold; An identification module 404 is configured to control the upper computer to screen the target data based on the hitting threshold to obtain target hitting data, and identify a hitting event formed by the user using the boxing target based on the target hitting data and hitting parameters of the target hitting data. In a possible implementation, the identification module includes: A judgment module is configured to judge whether the target data exceeds the hitting threshold obtained by the upper computer based on the multiple initial sensor data, and generate a corresponding judgment result; A filtering module is configured to filter out target data lower than the hitting threshold based on the judgment result to screen out target hitting data.

[0038] In an embodiment, the identifying module further comprises: An adjusting module is configured to determine an environmental impact factor of the hitting threshold and dynamically adjust an environmental impact coefficient corresponding to the environmental impact factor. A first calculating module is configured to calculate the environmental impact coefficient and a preset initial hitting threshold to obtain the hitting threshold.

[0039] In an embodiment, the fusing module comprises: A second calculating module is configured to calculate a gravity component based on acceleration data and angular velocity data in the target sensor data. A separating module is configured to separate the gravity component from the acceleration data and reserve target data in the acceleration data.

[0040] In an embodiment, the fusing module further comprises: A converting module is configured to define a global coordinate system and a device coordinate system for the punching target and update a rotation matrix of the global coordinate system converted to the device coordinate system based on the angular velocity data. A processing module is configured to obtain the gravity component based on a preset calculation network processing the updated rotation matrix and the gravity in the global coordinate system.

[0041] In an embodiment, the identifying module also comprises: A first determining module is configured to determine a type of a sensor corresponding to the plurality of sensor data to determine whether the type is a target type. A second determining module is configured to determine, if yes, that data collected by the sensor of the target type is target sensor data.

[0042] In an embodiment, the identifying module also comprises: A third calculating module is configured to perform data calculation on additional hitting parameters of the target hitting data based on a plurality of dimensions to obtain corresponding additional hitting data. A generating module is configured to generate a personalized hitting report for a user based on the corresponding additional hitting data. Embodiment 3 The application also provides an electronic device, such as Figure 5As shown, it comprises: a processor 501, a memory 502 and a bus 503, the memory 502 stores machine readable instructions executable by the processor 501, when the electronic device is running, the processor 501 and the memory 502 communicate through the bus 503, the machine readable instructions are executed by the processor 501 to perform the steps of any one of the hitting event identification methods.

[0043] Embodiment 4 The application also provides a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program is executed by the processor to perform the steps of any one of the hitting event identification methods.

[0044] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-described system and device can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The above-described device embodiments are only schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some communication interface, indirect coupling or communication connection between the devices or modules, which can be electrical, mechanical or other forms.

[0045] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. According to actual needs, some or all of the units can be selected to achieve the purpose of the embodiment.

[0046] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0047] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a nonvolatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a platform server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, and various media that can store program codes.

[0048] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for identifying a striking event, characterized in that: Applied to a boxing therapy device, the boxing therapy device includes a boxing target and a host computer, the boxing target has multiple built-in sensors and a microprocessor, and the method includes: Configuring the boxing therapy device so that a user strikes a boxing target equipped with the multiple sensors, and collecting multiple initial sensor data generated during the striking process based on the multiple sensors; Preprocessing the multiple initial sensor data to obtain multiple sensor data, screening out target sensor data from the multiple sensor data for fusion, and obtaining target data; Sending the target data to the host computer so that the host computer receives the target data; the host computer has a built-in dynamically adjusted hitting threshold; The host computer is controlled to filter the target data based on the hitting threshold to obtain target hitting data, so as to identify a hitting event formed when the user uses the boxing target based on the target hitting data and hitting parameters of the target hitting data.

2. The method according to claim 1, characterized in that The controlling the host computer to filter the target data based on the hitting threshold to obtain target hitting data includes: determining whether the target data exceeds a striking threshold value obtained by the host computer based on the multiple initial sensor data, and generating a corresponding determination result; Based on the determination result, target data below the hitting threshold is filtered out to select target hitting data.

3. The method according to claim 2, characterized in that The determining whether the target data exceeds a striking threshold value obtained by the host computer based on the multiple initial sensor data includes: Determining the environmental impact factors of the striking threshold, and dynamically adjusting the environmental impact coefficients corresponding to the environmental impact factors; The environmental impact coefficient and a preset initial striking threshold are calculated to obtain the striking threshold.

4. The method according to claim 1, wherein The step of filtering out target sensor data from the plurality of sensor data and fusing the data to obtain target data includes: Calculating a gravity component based on the acceleration data and the angular velocity data in the target sensor data; The gravity component is separated from the acceleration data, and target data in the acceleration data is retained.

5. The method according to claim 4, characterized in that The calculating the gravity component based on the acceleration data and the angular velocity data in the target sensor data includes: defining a global coordinate system and a device coordinate system for the boxing target, and updating a rotation matrix for converting the global coordinate system to the device coordinate system based on the angular velocity data; The updated rotation matrix and the gravity in the global coordinate system are processed based on a preset computing network to obtain the gravity component.

6. The method according to claim 1, characterized in that The step of filtering out target sensor data from the plurality of sensor data and fusing the data further includes: Determining the types of sensors corresponding to the plurality of sensor data to determine whether the types are target types; If so, it is determined that the data collected by the sensor of the target type is target sensor data.

7. The method according to claim 1, characterized in that After identifying a striking event formed when the user uses the boxing target based on the target striking data and the additional striking parameters of the target striking data, the method includes: performing data calculation on additional striking parameters of the target striking data based on multiple dimensions to obtain corresponding additional striking data; Based on the corresponding additional stroke data, a personalized stroke report for the user is generated.

8. A striking event recognition device, characterized in that: Applicable to boxing therapy equipment, the boxing therapy equipment includes a boxing target and a host computer, the boxing target has multiple built-in sensors and microprocessors, and the device includes: a configuration module, configured to configure the boxing therapy device so that a user can strike a boxing target equipped with the plurality of sensors, and collect a plurality of initial sensor data generated during the striking process based on the plurality of sensors; a fusion module, configured to pre-process the multiple initial sensor data to obtain multiple sensor data, filter out target sensor data from the multiple sensor data, and fuse them to obtain target data; A sending module is used to send the target data to the host computer so that the host computer receives the target data; the host computer has a built-in hitting threshold value obtained by dynamic adjustment; The identification module is used to control the host computer to filter the target data based on the hitting threshold to obtain target hitting data, so as to identify the hitting event formed when the user uses the boxing target based on the target hitting data and the hitting parameters of the target hitting data.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate via the bus. When the machine-readable instructions are executed by the processor, the steps of a striking event recognition method as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of a striking event recognition method according to any one of claims 1 to 7.

Images