Motion data processing method, device and electronic equipment

Abstract

The present invention provides a method, device, and electronic device for processing motion data, relating to the technical field of computer applications. The method comprises: obtaining motion data to be processed; using a pre-established inductive reasoning feature set to identify the motion type corresponding to the motion data to be processed; performing motion data resolution on the basic motion data contained in the motion type to obtain a variety of motion data under the motion type; performing scene action recognition on the various motion data, outputting scene motion data corresponding to the various motion data, and outputting a scene motion result containing the scene motion data. The motion data processing method, device, and electronic device provided by the present invention can identify the motion features of a variety of motion data to cover a variety of motion scenes, thereby realizing the motion data processing process for multiple motion scenes, not only meeting the user's needs for multi-scene motion, but also further enhancing the user's enjoyment of exercise.

Description

Technical Field

[0001] The present invention relates to the technical field of computer applications, and in particular to a method, device and electronic equipment for processing motion data. Background Art

[0002] At present, in order not to affect the user's exercise, smart devices used in sports are generally designed to be worn by the user, so that the user can wear it during exercise and collect corresponding exercise data. After the exercise, the user can view the exercise data through the smart terminal.

[0003] However, when collecting sports data, commonly used smart devices can often only collect and identify simple types of sports data, such as running, walking, etc., with relatively simple functions. It is difficult to identify effective sports data based on specific sports scenes. Not only is it difficult to meet the user's needs for multi-scene sports, it also reduces the user's sports fun. Summary of the Invention

[0004] In view of this, an object of the present invention is to provide a motion data processing method, device and electronic device to alleviate the above technical problems.

[0005] In a first aspect, an embodiment of the present invention provides a method for processing motion data, the method comprising: obtaining motion data to be processed; using a pre-established inductive reasoning feature set to identify the motion type corresponding to the motion data to be processed; wherein the inductive reasoning feature set records the correspondence between action features and motion types; performing motion data solution on the basic motion data contained in the motion type to obtain a plurality of motion data under the motion type; performing scene motion recognition on the plurality of motion data, outputting scene motion data corresponding to the plurality of motion data, and outputting a scene motion result containing the scene motion data.

[0006] In combination with the first aspect, an embodiment of the present invention provides a first possible implementation method of the first aspect, wherein the above method also includes: after obtaining the motion data to be processed, obtaining a preset standard action feature set; judging the motion data to be processed based on the standard action feature set, and outputting the refined scene action features corresponding to the motion data to be processed; integrating the refined scene action features with the scene motion data to obtain refined scene motion data, and outputting the scene motion results including the refined scene motion data.

[0007] In combination with the first possible implementation of the first aspect, an embodiment of the present invention provides a second possible implementation of the first aspect, wherein the above method also includes: inputting the scene motion result into a preset motion program, and presenting the scene motion result through the motion program.

[0008] In combination with the first aspect, an embodiment of the present invention provides a third possible implementation method of the first aspect, wherein the above-mentioned step of obtaining the motion data to be processed includes: obtaining the original motion data sent by the data collection system, wherein the original motion data is the sports data collected by the data collection system based on the inertial sensor module; and filtering the original motion data to obtain the motion data to be processed.

[0009] In combination with the first aspect, an embodiment of the present invention provides a fourth possible implementation method of the first aspect, wherein the above-mentioned step of using a pre-established inductive reasoning feature set to identify the motion type corresponding to the motion data to be processed includes: inputting the motion data to be processed into a pre-trained motion recognition model; enabling the motion recognition model to identify the motion type corresponding to the motion data to be processed based on the pre-established inductive reasoning feature set; wherein the motion recognition model is obtained by learning training data based on machine learning, and the training data contains standard motion features.

[0010] In combination with the first aspect, an embodiment of the present invention provides a fifth possible implementation of the first aspect, wherein the above method also includes: outputting basic motion data contained in the motion type, inputting the basic motion data into a preset motion program, and presenting the basic motion data through the motion program.

[0011] In combination with the first aspect, an embodiment of the present invention provides a sixth possible implementation method of the first aspect, wherein the above-mentioned step of performing motion data calculation on the basic motion data contained in the motion type to obtain multiple motion data under the motion type includes: solving the basic motion data according to a preset calculation method to obtain at least one of the following motion data: angle, speed, strength, distance, strength, number of times, frequency, and duration.

[0012] In combination with the sixth possible implementation of the first aspect, an embodiment of the present invention provides a seventh possible implementation of the first aspect, wherein the above-mentioned steps of performing scene action recognition on multiple types of motion data and outputting scene motion data corresponding to the multiple types of motion data include: obtaining a pre-established standard action feature set, performing scene action recognition on multiple types of motion data through the standard action feature set; outputting structured data containing the scene motion data, and storing the structured data containing the scene motion data in a preset action structured data database.

[0013] In the second aspect, an embodiment of the present invention also provides a motion data processing device, which includes: an acquisition module for acquiring motion data to be processed; a first identification module for using a pre-established inductive reasoning feature set to identify the motion type corresponding to the motion data to be processed; wherein the inductive reasoning feature set records the correspondence between action features and motion types; a solution module for performing motion data solution on the basic motion data contained in the motion type to obtain a variety of motion data under the motion type; a second identification module for performing scene action recognition on a variety of the motion data, outputting scene motion data corresponding to the multiple motion data, and outputting a scene motion result containing the scene motion data.

[0014] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores machine-executable instructions that can be executed by the processor, and the processor executes the machine-executable instructions to implement the method described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first aspect are executed.

[0016] The embodiments of the present invention bring the following beneficial effects:

[0017] The motion data processing method, device and electronic device provided by the embodiments of the present invention can obtain the motion data to be processed; then use a pre-established inductive reasoning feature set to identify the motion type corresponding to the motion data to be processed; and perform motion data solution on the basic motion data contained in the motion type to obtain a variety of motion data under the motion type, and then perform scene action recognition on the multiple motion data, output the scene motion data corresponding to the multiple motion data, and output the scene motion result containing the scene motion data. In addition, the above-mentioned inductive reasoning feature set records the correspondence between action features and motion types. Therefore, the action features of multiple motion data can be identified to cover multiple motion scenes, and then the motion data processing process of multiple motion scenes can be realized, which can not only meet the user's needs for multi-scene motion, but also further enhance the user's sports fun.

[0018] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A flowchart of a method for processing motion data provided by an embodiment of the present invention;

[0022] Figure 2 A flowchart of another method for processing motion data provided by an embodiment of the present invention;

[0023] Figure 3 A schematic structural diagram of a motion data processing device provided by an embodiment of the present invention;

[0024] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0026] When exercising, users often wear wearable smart devices to collect and monitor motion data. These devices are typically equipped with sensors to identify the user's movements. However, currently used sensors can only collect and identify simple types of motion data, such as running and walking, and their functions are relatively limited. Due to factors such as irregular changes in user exercise frequency, widely varying exercise environments, and diverse personal styles, existing smart devices struggle to accurately capture motion gestures through sensors, and even more so to present realistic motion states. This not only makes it difficult to meet users' needs for multi-scenario exercise, but also reduces their enjoyment of exercise.

[0027] Based on this, the embodiments of the present invention provide a motion data processing method, device, and electronic device that can effectively alleviate the above technical problems.

[0028] To facilitate understanding of this embodiment, a motion data processing method disclosed in an embodiment of the present invention is first introduced in detail.

[0029] In one possible implementation, an embodiment of the present invention provides a method for processing motion data. Specifically, the method is applied to a smart device. Smart devices are generally configured with functional modules such as an operation module, an inertial sensor module, and a communication module to facilitate the collection and processing of a user's motion data under user operation. Furthermore, the smart devices in the embodiments of the present invention are generally configured as wearable devices, such as sports gloves, watches, belts, wristbands, etc., so that the collected motion data can be processed during the user's exercise without affecting the user's movements.

[0030] Specifically, if Figure 1 A flow chart of a method for processing motion data is shown, the method comprising the following steps:

[0031] Step S102, obtaining motion data to be processed;

[0032] In actual use, the motion data to be processed is usually collected by the data collection system of the smart device based on the inertial sensor module, and the above-mentioned inertial sensor module generally includes units such as accelerometers, gyroscopes, and machine learning core functions. When these units collect motion data, there is often a certain amount of noise data in the original data. Therefore, in the above-mentioned step S102, when obtaining the motion data to be processed, it is necessary to first obtain the original motion data sent by the data collection system, wherein the original motion data is the sports data collected by the data collection system based on the inertial sensor module; then the original motion data is filtered to filter out obvious noise data, and then the above-mentioned motion data to be processed is obtained. For example, Kalman filtering of the original motion data can output motion data that is more accurate and close to the real thing.

[0033] Step S104, using a pre-established inductive reasoning feature set to identify the motion type corresponding to the motion data to be processed;

[0034] Among them, the inductive reasoning feature set records the correspondence between action features and motion types;

[0035] In actual use, the process of step S104 is actually the first recognition process of the motion data to be processed, that is, identifying the action type of the motion data to be processed. At this time, the recognition granularity of the motion data to be processed is relatively large, mainly targeting scenarios with high real-time requirements, fast action rhythm, and wide judgment standards. Therefore, the action features recorded in the above-mentioned inductive reasoning feature set are generally action features of large actions, and the motion type corresponding to the action feature is a relatively broad motion type.

[0036] For example, using boxing gloves as a wearable device, the inductive reasoning feature set corresponding to boxing sports typically records the action features of punches, such as straight punches and uppercuts. This allows the inductive reasoning feature set to identify the "boxing-like action" sport type after acquiring the aforementioned motion data to be processed. Furthermore, in addition to boxing-like actions, the inductive reasoning feature set can also include motion features corresponding to fighting, dancing, cycling, track and field, tennis, volleyball, badminton, table tennis, football, bowling, fencing, Frisbee, swimming, rowing, and other sports, thereby covering a variety of sports scenarios.

[0037] Step S106, performing motion data calculation on the basic motion data included in the motion type to obtain a variety of motion data under the motion type;

[0038] In actual use, the motion data solving process in this step is actually to calculate the common action data under this motion type. Specifically, when solving the motion data, the basic motion data can be solved according to the preset solving method to obtain at least one of the following motion data: angle, speed, strength, distance, strength, number of times, frequency, and duration.

[0039] The angles in the motion data are generally defined as the angle around the sensor's X-axis (called pitch), the angle around the sensor's Y-axis (called roll), and the angle around the sensor's Z-axis (γ). The angles around each sensor axis can be calculated based on the projection of gravity acceleration onto the X, Y, and Z axes.

[0040] Furthermore, when calculating the aforementioned velocity data, it's generally necessary to integrate the three-axis composite acceleration a for a specific motion. The resulting value is described as acceleration A, from which velocity can be calculated: v = At2. Distance in the motion data can be directly calculated based on this velocity: distance L = vt, where t represents time.

[0041] In addition, the motion data corresponding to the above force can be used to estimate the mass m based on the motion scene and the human body condition. Combined with the above acceleration A, the force can be calculated using Newton's second law: F=Am.

[0042] Furthermore, the above-mentioned times, frequencies, durations, etc. can be directly obtained according to the attribute functions of the smart device itself, and will not be elaborated here.

[0043] In addition, after identifying the above-mentioned motion type, the above-mentioned basic motion data can be directly output and presented, for example, the basic motion data such as angle, speed, force, distance, strength, number of times, frequency, duration, etc. at this time can be presented. At this time, the basic motion data contained in the motion type can be directly output, such as at least one of the above-mentioned angle, speed, force, distance, strength, number of times, frequency, and duration, and then these basic motion data can be input into a preset motion program, and the basic motion data can be presented through the motion program. Among them, the motion program can be an application installed on the smart device, or it can be a running program of the wearable device itself. The user can set it to automatically present the basic motion data in real time, or to present the basic motion data through playback. The specific setting can be based on the actual usage situation, and the embodiment of the present invention does not limit this.

[0044] Step S108 , performing scene motion recognition on the various motion data, outputting scene motion data corresponding to the various motion data, and outputting a scene motion result including the scene motion data.

[0045] In actual use, based on the various motion data solved in the above step S106, further scene action recognition can be performed, and then the scene motion data corresponding to the various motion data can be output. Taking boxing action as an example, in the above step S104, the motion type can be identified as boxing. In the above steps S106 and S108, during further identification, it can be identified which specific type of punch is, such as fast punch, slow punch, etc., and finally output as a scene motion result. That is, through the solution process of step S106, specific motion data can be obtained, and then based on the identification of step S108, further scene motion data can be obtained to complete secondary action recognition and obtain more accurate motion recognition results.

[0046] The motion data processing method provided by the embodiment of the present invention can obtain the motion data to be processed; then use a pre-established inductive reasoning feature set to identify the motion type corresponding to the motion data to be processed; and perform motion data solution on the basic motion data contained in the motion type to obtain a variety of motion data under the motion type, and then perform scene action recognition on the multiple motion data, output the scene motion data corresponding to the multiple motion data, and output the scene motion result containing the scene motion data. In addition, the above-mentioned inductive reasoning feature set records the correspondence between action features and motion types. Therefore, the action features of multiple motion data can be identified to cover multiple motion scenes, and then the motion data processing process of multiple motion scenes can be realized, which can not only meet the user's needs for multi-scene motion, but also further enhance the user's sports fun.

[0047] Generally, the above-mentioned scene motion results are usually the result of identifying the user's own motion process. In actual use, the user can also exercise under the guidance of a professional coach. Due to the guidance of a professional coach, the user's movements at this time are generally relatively standard. Therefore, for the recognition of these standard movements, or directly for the recognition of the standard movements of professional coaches, the motion data to be processed can be directly recognized and integrated with the scene motion data obtained by solving the above-mentioned motion data to obtain a more refined scene motion result.

[0048] Therefore, the method for processing motion data provided in the embodiment of the present invention further includes the following process:

[0049] (1) After obtaining the motion data to be processed, obtain a preset standard motion feature set;

[0050] Among them, the standard action feature set in the embodiment of the present invention includes motion features of multiple standard actions, and the standard actions generally come from the standardized actions of professional coaches. These standardized actions can be abstracted into several action trajectories and simplified into various time and space key points to form a standard action feature set. Therefore, the standard action feature set in the embodiment of the present invention is mainly aimed at scenes with high action judgment requirements and fast action rhythm, and is used as an auxiliary reference for scene algorithm calculation or scene algorithm correction.

[0051] (2) Determine the motion data to be processed based on the standard motion feature set and output the refined scene motion features corresponding to the motion data to be processed;

[0052] Specifically, the process of judging the motion data to be processed based on the standard motion feature set is generally a process of identifying the motion features of the motion data to be processed. For example, the motion features of the motion data to be processed are abstracted into corresponding motion trajectories and key points, and then a similarity comparison is performed with the motion trajectories and key points of the standard motions in the standard motion feature set. If the similarity is greater than a preset threshold, such as greater than 80%, the motion corresponding to the motion data to be processed can be considered relatively standard; otherwise, it is non-standard.

[0053] (3) Integrating the refined scene action features with the scene motion data to obtain refined scene motion data, and outputting a scene motion result including the refined scene motion data.

[0054] Among them, the integration process in (3) is the process of integrating the motion data to be processed with the motion scene. Taking boxing as an example, if it is determined in (2) that the current motion data to be processed is a standard boxing action, then in (3), the refined scene action features are integrated into the boxing scene motion data, and then the direct output is a standard punching action under boxing, so as to achieve more refined action recognition.

[0055] Furthermore, after obtaining the scene motion results through the above process, the scene motion results can also be input into a preset motion program, and the scene motion results can be presented through the motion program. The motion program can also be an application installed on the smart device or a running program of the wearable device itself. The user can set it to automatically input the scene motion results into the motion program for processing, or the scene motion results can be presented through playback through user operation. The specific setting can be based on actual usage, and the embodiment of the present invention is not limited to this.

[0056] In actual use, in order to make the identification process of the motion type in the above step S104 more accurate, in the embodiment of the present invention, the motion type is usually identified based on the inductive reasoning feature set in a machine learning manner. Figure 1 On the basis of Figure 2 A flowchart of another method for processing motion data is shown, and the process of identifying the motion type is further explained. Specifically, Figure 2 As shown, it includes the following steps:

[0057] Step S202, obtaining motion data to be processed;

[0058] Step S204: input the motion data to be processed into a pre-trained motion recognition model; and enable the motion recognition model to identify the motion type corresponding to the motion data to be processed based on a pre-established inductive reasoning feature set;

[0059] The action recognition model in the embodiment of the present invention is obtained by learning training data based on machine learning, and the training data contains standard action features.

[0060] In actual use, the above-mentioned motion recognition model is generally provided with a feature module for learning the standard motion features of the training data. The motion recognition model trained in this way can quickly identify the motion features of the motion data to be processed when identifying the motion data to be processed, and quickly and effectively identify the motion type based on the correspondence between the motion features and the motion type recorded in the inductive reasoning feature set.

[0061] Step S206, performing motion data calculation on the basic motion data included in the motion type to obtain a variety of motion data under the motion type;

[0062] Step S208, obtaining a pre-established standard action feature set, and performing scene action recognition on a variety of motion data using the standard action feature set;

[0063] Step S210 : outputting structured data including scene motion data, and storing the structured data including scene motion data into a preset action structured data database.

[0064] Among them, the above-mentioned structured data is actually action structured data. In the embodiment of the present invention, the scene motion data is structured so that it can be stored in the action structured data database, so as to facilitate subsequent data preservation and further viewing and processing.

[0065] In summary, the motion data processing method provided by the embodiment of the present invention can identify the action characteristics of multiple motion data to cover multiple motion scenes, and then realize the processing process of motion data of multiple motion scenes, which can not only meet the user's needs for multi-scene motion, but also further enhance the user's sports fun.

[0066] Furthermore, based on the above embodiment, the embodiment of the present invention also provides a motion data processing device, such as Figure 3 The schematic diagram of the structure of a motion data processing device shown in FIG. 1 includes:

[0067] An acquisition module 30 is used to acquire motion data to be processed;

[0068] A first identification module 32 is configured to identify the motion type corresponding to the motion data to be processed using a pre-established inductive reasoning feature set; wherein the inductive reasoning feature set records the correspondence between motion features and motion types;

[0069] A calculation module 34 is used to perform motion data calculation on the basic motion data included in the motion type to obtain a variety of motion data under the motion type;

[0070] The second recognition module 36 is configured to perform scene motion recognition on the multiple motion data, output scene motion data corresponding to the multiple motion data, and output a scene motion result including the scene motion data.

[0071] The motion data processing device provided in the embodiment of the present invention has the same technical features as the motion data processing method provided in the above embodiment, and therefore can also solve the same technical problems and achieve the same technical effects.

[0072] Furthermore, an embodiment of the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores machine-executable instructions that can be executed by the processor, and the processor executes the machine-executable instructions to implement the above method.

[0073] Furthermore, an embodiment of the present invention also provides a machine-readable storage medium, which stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to implement the above method.

[0074] The embodiment of the present invention further provides an electronic device, see Figure 4 The structure diagram of an electronic device shown in FIG. 4 includes a processor 40 and a memory 41 . The memory 41 stores machine-executable instructions that can be executed by the processor 40 . The processor 40 executes the machine-executable instructions to implement the above method.

[0075] Further, Figure 4 The electronic device shown further includes a bus 42 and a communication interface 43 , and the processor 40 , the communication interface 43 and the memory 41 are connected via the bus 42 .

[0076] Among them, the memory 41 may include high-speed random access memory (RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 43 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The bus 42 can be an ISA (Industrial Standard Architecture, industrial standard structure bus) bus, PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or EISA (Enhanced Industry Standard Architecture, extended industry standard architecture) bus, etc. The above-mentioned bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0077] Processor 40 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be completed by hardware integrated logic circuits or software instructions in processor 40. The above processor 40 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory 41 , and the processor 40 reads the information in the memory 41 and completes the steps of the method of the aforementioned embodiment in combination with its hardware.

[0078] The motion data processing method, device and computer program product of the electronic device provided in the embodiments of the present invention include a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the previous method embodiments. The specific implementation can be found in the method embodiments and will not be repeated here.

[0079] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0080] In addition, in the description of the embodiments of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical connections or electrical connections; they may refer to direct connections or indirect connections through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0081] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0082] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0083] Finally, it should be noted that the above embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for processing motion data, characterized in that: The method comprises: Obtaining motion data to be processed; Using a pre-established inductive reasoning feature set to identify the motion type corresponding to the motion data to be processed; wherein the inductive reasoning feature set records the correspondence between motion features and motion types; Performing motion data calculation on basic motion data included in the motion type to obtain a variety of motion data under the motion type; Performing scene motion recognition on the plurality of motion data, outputting scene motion data corresponding to the plurality of motion data, and outputting a scene motion result including the scene motion data; The method further comprises: After obtaining the motion data to be processed, obtaining a preset standard motion feature set; Determining the motion data to be processed based on the standard motion feature set, and outputting refined scene motion features corresponding to the motion data to be processed; The step of judging the motion data to be processed based on the standard motion feature set includes: comparing the motion data to be processed with the standard motions in the standard motion feature set for similarity; if the similarity is greater than a preset threshold, the motion corresponding to the motion data to be processed is considered to be standard, otherwise it is considered to be non-standard; If it is determined that the current motion data to be processed is a standard motion, the refined scene motion feature is integrated with the scene motion data to obtain refined scene motion data, and a scene motion result including the refined scene motion data is output; Among them, the scene motion results may include fast punching and slow punching.

2. The method according to claim 1, characterized in that The method further comprises: The scene motion result is input into a preset motion program, and the scene motion result is presented through the motion program.

3. The method according to claim 1, characterized in that The steps for obtaining the motion data to be processed include: Acquiring original motion data sent by a data collection system, wherein the original motion data is sports data collected by the data collection system based on an inertial sensor module; The original motion data is filtered to obtain the motion data to be processed.

4. The method according to claim 1, wherein The step of using a pre-established inductive reasoning feature set to identify the motion type corresponding to the motion data to be processed includes: Inputting the motion data to be processed into a pre-trained motion recognition model; The action recognition model is enabled to identify the motion type corresponding to the motion data to be processed based on a pre-established inductive reasoning feature set; wherein, the action recognition model is obtained by learning training data based on machine learning, and the training data contains standard motion features.

5. The method according to claim 1, wherein The method further comprises: Output basic motion data included in the motion type, input the basic motion data into a preset motion program, and present the basic motion data through the motion program.

6. The method according to claim 1, wherein The step of performing motion data calculation on the basic motion data included in the motion type to obtain multiple motion data under the motion type includes: According to a preset solution method, the basic motion data is solved to obtain at least one of the following motion data: angle, speed, strength, distance, power, number of times, frequency, and duration.

7. The method according to claim 5, characterized in that The step of performing scene motion recognition on the plurality of motion data and outputting scene motion data corresponding to the plurality of motion data comprises: Obtaining a pre-established standard action feature set, and performing scene action recognition on a plurality of the motion data using the standard action feature set; The structured data including the scene motion data is output, and the structured data including the scene motion data is stored in a preset action structured data database.

8. A motion data processing device, characterized in that: For implementing the method according to claim 1, the device comprises: An acquisition module, used for acquiring motion data to be processed; A first identification module is configured to identify a motion type corresponding to the motion data to be processed using a pre-established inductive reasoning feature set, wherein the inductive reasoning feature set records a correspondence between motion features and motion types; A calculation module, configured to perform motion data calculation on the basic motion data included in the motion type to obtain a variety of motion data under the motion type; The second recognition module is configured to perform scene motion recognition on the multiple motion data, output scene motion data corresponding to the multiple motion data, and output a scene motion result including the scene motion data.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores machine-executable instructions that can be executed by the processor, and the processor executes the machine-executable instructions to implement the method according to any one of claims 1 to 7.

Images