Data processing method and device

Abstract

An embodiment of the present application provides a data processing method and device, wherein the data processing method includes: determining initial action data and an initial video generated by a target object performing a target action, and comparing the initial action data with preset action data; if the comparison is successful, determining action attribute information corresponding to the target action according to the preset action data; establishing an association relationship between the action attribute information and the video frame according to the execution time of the target action and the timestamp corresponding to the video frame in the initial video; and generating a target video course corresponding to the target action according to the association relationship.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of fitness technology, and more particularly to a data processing method. One or more embodiments of the present application also relate to a data processing device, a computing device, and a computer-readable storage medium. Background Art

[0002] As living standards improve, more and more users begin to pay attention to their bodies. Fitness has become one of the most popular sports nowadays. Fitness can enhance strength, flexibility, increase endurance, improve coordination, and the ability to control various parts of the body.

[0003] Currently, there are many fitness applications available online. These fitness applications can provide users with fitness training courses. When users need to learn fitness training courses, the fitness applications can synchronously play the audio and video images of the course for users. The audio is used to prompt users the number of times to do an action and some key points of the action, so that users can follow the video and make the same actions as the coach in the video, thereby achieving a certain training effect.

[0004] However, the process of generating fitness training courses in current fitness applications usually involves first writing a course script, then shooting a video, then recording and writing action recognition information according to the corresponding actions in the video, and then generating available training courses based on the action recognition information and the shot video. In this process, when recording and writing action recognition information, it may be necessary to mark the shot video frame by frame to mark the actions or punch types made by the user in each video frame, etc. This will cost a lot of manpower and the course production efficiency is low. Therefore, it is urgent to provide an effective method to solve such problems. Summary of the invention

[0005] In view of this, an embodiment of the present application provides a data processing method. One or more embodiments of the present application also relate to a data processing device, a computing device, and a computer-readable storage medium to solve the technical defect of low efficiency of training course generation in the prior art.

[0006] According to a first aspect of an embodiment of the present application, a data processing method is provided, including:

[0007] Determine initial action data and an initial video generated by the target object performing the target action, and compare the initial action data with preset action data;

[0008] If the comparison is successful, determining the action attribute information corresponding to the target action according to the preset action data;

[0009] Establishing an association relationship between the action attribute information and the video frame according to the execution time of the target action and the timestamp corresponding to the video frame in the initial video;

[0010] A target video course corresponding to the target action is generated according to the association relationship.

[0011] According to a second aspect of an embodiment of the present application, there is provided a data processing device, including:

[0012] A comparison module is configured to determine initial action data and an initial video generated by the target object performing the target action, and compare the initial action data with the preset action data;

[0013] A determination module, configured to determine action attribute information corresponding to the target action according to the preset action data when the comparison is successful;

[0014] An establishing module configured to establish an association relationship between the action attribute information and the video frame according to the execution time of the target action and the timestamp corresponding to the video frame in the initial video;

[0015] A generating module is configured to generate a target video course corresponding to the target action according to the association relationship.

[0016] According to a third aspect of an embodiment of the present application, a computing device is provided, including:

[0017] Memory and processor;

[0018] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, wherein the processor implements the steps of the data processing method when executing the computer-executable instructions.

[0019] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the data processing method are implemented.

[0020] An embodiment of the present application implements a data processing method and device, wherein the data processing method includes determining initial action data and an initial video generated by a target object performing a target action, and comparing the initial action data with preset action data. When the comparison is successful, action attribute information corresponding to the target action is determined based on the preset action data, and an association relationship between the action attribute information and the video frame is established based on the execution time of the target action and the timestamp corresponding to the video frame in the initial video, and a target video course corresponding to the target action is generated based on the association relationship.

[0021] In the embodiment of the present application, in the process of generating a target video course, on the one hand, the process of the target object performing the target action is recorded to generate an initial video, and on the other hand, while recording the video, the initial action data of the target object can be collected by a wearable device worn by the target object, and then the action attribute information of the target object can be determined by comparing the initial action data with the preset action data, and then the target video course is automatically generated by establishing an association relationship between the action attribute information and each video frame in the initial video. In this process, the action attribute information of the target action is automatically identified, and the identification result is automatically associated with the video frame in the initial video to generate the target action video, which is conducive to simplifying the course generation process, thereby helping to improve the production efficiency of the video course. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of a data processing method provided by an embodiment of the present application;

[0023] Figure 2 is a schematic diagram of a data processing process provided by an embodiment of the present application;

[0024] Figure 3 is a processing flow chart of a data processing method provided by an embodiment of the present application;

[0025] Figure 4 is a structural schematic diagram of a data processing device provided by an embodiment of the present application;

[0026] Figure 5 It is a structural block diagram of a computing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0027] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0028] The terms used in one or more embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present application. The singular forms of "a", "said" and "the" used in one or more embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of the present application refers to and includes any or all possible combinations of one or more associated listed items.

[0029] It should be understood that, although the terms first, second, etc. may be used to describe various information in one or more embodiments of the present application, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0030] In the present application, a data processing method is provided. One or more embodiments of the present application also relate to a data processing apparatus, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0031] See also Figure 1 , Figure 1 A flowchart of a data processing method provided according to an embodiment of the present application is shown, comprising the following steps:

[0032] Step 102, determining initial action data and an initial video generated by the target object performing the target action, and comparing the initial action data with preset action data.

[0033] In specific implementation, determining the initial action data and initial video generated by the target object performing the target action includes:

[0034] determining initial motion data generated by a target object performing a target motion collected by a wearable device; and,

[0035] An initial video is determined by recording a process in which the target object performs the target action through a video data acquisition device.

[0036] Specifically, the embodiment of the present application needs to generate a video course based on the target action performed by the target object to provide the video course to the user for learning. In order to ensure the user's learning effect, during the playback of the video course, the action attribute information of the target action can be played synchronously with the voice while playing the video screen, such as the number of executions of the target action and some action essentials.

[0037] Therefore, in the process of generating the video course, it is necessary to add the aforementioned action attribute information of the target action in the video based on the recorded video of the target action execution process.

[0038] In the embodiment of the present application, the aforementioned action attribute information of the target action can be determined by comparing the initial action data generated by the target object performing the target action with the standard action data. Therefore, the target object can wear a wearable device during the process of performing the target action, so as to use the wearable device to collect the initial action data generated by the target object performing the target action; in addition, the process of performing the target action can be recorded by a video data acquisition device (e.g., a camera, a smart phone, a tablet, a computer, etc.) during the process of the target object performing the target action to generate an initial video.

[0039] Among them, the target object is a user with a certain degree of expertise in the application field of the data processing method, and the target action is a specific field action in the application field; the initial action data, that is, the action data generated by the target object performing the target action, includes but is not limited to the movement speed, movement direction, action type, action posture and other data of the limbs; the preset action data can be the standard action data generated by professionals in the application field performing the target action, which also includes but is not limited to the movement speed, movement direction and other data of the limbs.

[0040] If the data processing method is applied to the field of boxing, the target object may be a boxing coach and the target action may be a boxing action; if the data processing method is applied to the field of fitness, the target object may be a fitness coach and the target action may be a fitness action.

[0041] After determining the initial action data and the initial video, the initial action data can be compared with the preset action data to determine the action attribute information of the target action based on the comparison result, so as to use the action attribute information and the initial video to jointly generate a video course corresponding to the target action.

[0042] In a specific implementation, the initial action data is compared with the preset action data, including:

[0043] The initial action data is parsed according to a preset data transmission protocol, and the parsing result is compared with the preset action data.

[0044] Specifically, since the embodiment of the present application can use a wearable device to collect the initial action data generated by the target object performing the target action, and after the wearable device collects the initial action data, the server that executes the data processing method can obtain the initial action data from the wearable device through a preset data transmission protocol, and parse the initial action data using the preset data transmission protocol. For example, if the wearable device and the server establish a communication connection via Bluetooth, the server can obtain the initial action data collected by the wearable device through the Bluetooth transmission protocol, and parse the initial action data through the Bluetooth transmission protocol to convert it into data information that can be used and read by the server. The parsing result can then be compared with the preset action data.

[0045] Among them, since the preset action data can be the standard action data generated by professionals in the application field of the data processing method performing the target action, and after obtaining the initial action data of the target object, the initial action data needs to be compared with the preset action data, therefore, the preset action data can be determined before determining the initial action data, which can be specifically achieved in the following ways:

[0046] Get the target type action data corresponding to the preset action;

[0047] A corresponding information template is generated based on the preset action and the target type action data, wherein the information template contains an association relationship between the preset action and the target type action data.

[0048] Furthermore, comparing the initial action data with the preset action data includes:

[0049] The initial action data is compared with a target preset action included in the information template, wherein the target preset action is one of the preset actions.

[0050] Specifically, the information template can be used as preset action data. The preset action is the action involved in the application field of the data processing method. For example, if the application field is the boxing field, the preset action is a plurality of boxing actions, and the target action can be one or at least two of the plurality of boxing actions.

[0051] In addition, since the server executing the data processing method needs to obtain the initial motion data of the target object from the wearable device, and the wearable device usually uses a sensor to collect the motion data of the target object, the target type motion data can be sensor data.

[0052] After obtaining the target type action data corresponding to the preset action, the embodiment of the present application can construct an information template corresponding to the preset action based on the association between the preset action and the target type action data. Therefore, the information template includes the standard action data of each preset action. For example, the standard action data of action A is: fist palm down, fist slightly higher than shoulder, etc.

[0053] After the initial action data is subsequently determined, the initial action data may be compared with the data contained in the information template to determine the action attribute information of the target action.

[0054] Among them, since the information template contains standard action data of each preset action, each preset action in the information template can be used as a target preset action to compare the initial action data with the standard action data of each preset action one by one to generate corresponding comparison results, thereby ensuring the accuracy of the comparison results.

[0055] In addition, the initial action data and the initial video generated by the target object performing the target action are determined, including:

[0056] Determine the action data to be processed and the initial video generated by the target object performing the target action;

[0057] Preprocessing the action data to be processed to generate an action trajectory corresponding to the target action;

[0058] Motion feature information is determined based on the motion trajectory, and initial motion data is determined based on the motion feature information.

[0059] Further, preprocessing the action data to be processed to generate an action trajectory corresponding to the target action includes:

[0060] Extracting angular velocity data of a first coordinate axis, a second coordinate axis, and a third coordinate axis of the wearable device in a spatial coordinate system, which are contained in the action data to be processed and collected by a motion sensor in the wearable device; and / or extracting acceleration data of the wearable device, which are contained in the action data to be processed and collected by an acceleration sensor in the wearable device;

[0061] The motion trajectory corresponding to the target motion is determined according to the angular velocity data and / or the acceleration data.

[0062] Specifically, in an embodiment of the present application, when the target object performs the target action, the wearable device can be worn. The wearable device maintains a Bluetooth communication connection with the server that executes the data processing method, and reports the collected action data to be processed in real time. Since the wearable device may include a motion sensor, the motion sensor can collect angular velocity data of the wearable device on the first, second, and third coordinate axes in the spatial coordinate system, that is, angular velocity data of the x, y, and z axes, as the action data to be processed generated by the target object performing the target action; therefore, after the wearable device uploads the action data to be processed, the server can extract the aforementioned angular velocity data contained in the action data to be processed.

[0063] In addition, the wearable device may include an acceleration sensor, which can collect acceleration data of the wearable device as the action data to be processed generated when the target object performs the target action; therefore, after the wearable device uploads the action data to be processed, the server can extract the aforementioned acceleration data contained in the action data to be processed.

[0064] In actual applications, if the wearable device only includes an angular velocity sensor or only includes an acceleration sensor, the action data to be processed uploaded by the wearable device may only include acceleration data or only include angular velocity data; and if the wearable device includes an angular velocity sensor and an acceleration sensor, the action data to be processed uploaded by the wearable device may include acceleration data and angular velocity data. In addition, the data acquisition components included in the wearable device can be determined according to actual needs and are not limited here.

[0065] In the embodiment of the present application, the action trajectory is the trajectory generated by the target object performing the target action. For example, if the target object performs a straight punch, the action trajectory is a line segment, and if the target object performs an uppercut, the action trajectory is a curve segment. Action feature information is the mean, variance, accumulated arc length, action duration, and other information of the straight line or curve corresponding to the action trajectory.

[0066] Therefore, after determining the angular velocity data and / or acceleration data of the target object, the motion trajectory corresponding to the target action is determined according to the angular velocity data and / or the acceleration data, and then the motion feature information is determined based on the motion trajectory, so as to determine the initial motion data based on the motion feature information.

[0067] Since the wearable device can be worn on one or at least two positions of the target object, such as the wrist, ankle and waist, the collected motion data to be processed may include angular velocity data and / or acceleration data of the wrist, ankle and waist. In this case, the motion trajectories of different parts can be determined based on the angular velocity data and / or acceleration data corresponding to each part, and then the initial motion data of the target object can be comprehensively determined based on the motion trajectories of different parts, including but not limited to the movement speed, movement direction, motion type, motion posture and other data of the limbs.

[0068] In a specific implementation, the initial action data is compared with the preset action data, including:

[0069] Splitting the target action according to the action trajectory contained in the initial action data to generate at least two sub-actions;

[0070] Determine a comparison rule corresponding to each sub-action, and compare the initial action data corresponding to each sub-action with the preset action data based on the comparison rule for similarity;

[0071] When the similarity comparison result is greater than a preset similarity threshold, it is determined that the comparison is successful.

[0072] Specifically, if the target action contains multiple sub-actions, the target action can be split into multiple sub-actions according to the action trajectory contained in the initial action data. In addition, different sub-actions may correspond to different comparison rules. Therefore, after the sub-actions are split, the initial action data of each sub-action can be compared with the preset action data according to the comparison rule corresponding to each sub-action to determine the similarity between the action performed by the target object and the standard action.

[0073] For example, if the target action is a hook punch, when throwing the hook punch, first bend the knees slightly, move the center of gravity downward, lower the right arm slightly, push the ground with the right foot, quickly twist the waist to the right and throw the right fist, and the right fist should be hooked from the bottom to the top; therefore, the target action can be divided into sub-actions such as slightly bending the knees, moving the center of gravity downward, twisting the waist to the right, and throwing the right fist. For one of the sub-actions "slightly bending the knees", the comparison rule can be to compare the angle between the thigh and the calf, and for the sub-action "twisting the waist to the right", the comparison rule can be the waist rotation angle and / or rotation speed, etc.

[0074] After the sub-actions are split, the initial action data corresponding to each sub-action can be compared with the standard action data corresponding to the sub-actions contained in the standard boxing action in the boxing field for similarity, so as to comprehensively determine the similarity between the hook action and the standard hook action based on the comparison result. If the similarity comparison result is greater than the preset similarity threshold, it is determined that the comparison is successful.

[0075] By splitting the target action into multiple sub-actions and comparing the initial action data of each sub-action with the preset action data according to the comparison rules corresponding to each sub-action, it is helpful to ensure the accuracy of the comparison result.

[0076] Step 104: When the comparison is successful, determine the action attribute information corresponding to the target action according to the preset action data.

[0077] In a specific implementation, determining the action attribute information corresponding to the target action according to the preset action data includes:

[0078] Determining target type action data associated with the target preset action according to the association relationship;

[0079] The target type action data is parsed, and action attribute information corresponding to the target action is generated according to the parsing result.

[0080] Specifically, the action attribute information refers to the action type and action posture information of the target action.

[0081] As mentioned above, since the information template contains the association relationship between the preset action and the target type action data, and in actual applications, the target type action data can be sensor data, therefore, when the sensor data collected by the wearable device is compared with the sensor data in the information template, and when it is determined that the similarity between the sensor data collected by the wearable device and the sensor data of a preset action in the information template is greater than the preset similarity threshold, it can be determined that the target action performed by the target object is the preset action. In this case, the sensor data associated with the preset action can be analyzed to generate action attribute information corresponding to the target action based on the analysis results.

[0082] Step 106: establishing an association relationship between the action attribute information and the video frame according to the execution time of the target action and the timestamp corresponding to the video frame in the initial video.

[0083] In a specific implementation, according to the execution time of the target action and the timestamp corresponding to the video frame in the initial video, an association relationship between the action attribute information and the video frame is established, including:

[0084] Generate course information corresponding to the target action according to the action attribute information;

[0085] Determine feature information contained in each video frame in the initial video, and determine a video segment containing the target action;

[0086] According to the execution time of the target action and the timestamp corresponding to the starting video frame in the video clip, an association relationship between the course information and the starting video frame is established.

[0087] Specifically, course information refers to information related to the target action that needs to be broadcasted or displayed to the user through an interface in a video course, such as the execution time and number of executions of the action. In an embodiment of the present application, course information can be determined based on the information contained in the action attribute information. For example, since the action attribute information can also include the execution time of the target action, the execution time of each target action can be determined based on the execution time, and the execution speed, execution strength and other course information of the target action can also be determined based on the action type or action posture contained in the action attribute information.

[0088] In addition, the feature information contained in the video frame, that is, the action feature information of the target object contained in the video frame, when the duration of a video is long or a video contains multiple actions, the video can be split into video segments according to the action feature information in each video frame, and each video segment corresponds to an action, for example, video segment A corresponds to a left straight punch, and video segment B corresponds to a right straight punch. Then, according to the execution time of each action in the action attribute information and the timestamp corresponding to the starting video frame of each video segment, the association relationship between the course information and the starting video frame is established.

[0089] Since the video recording and the initial action data collection process of the wearable device are carried out synchronously during the process of the target object performing the target action, the time when the target object performs the target action in the recorded initial video should be consistent with the time when the target object performs the target action collected by the wearable device. Therefore, when establishing the association between the course information and the video clip, it can be determined whether the execution time of the target action contained in the course information and the timestamp corresponding to the starting video frame of the video clip are consistent. If they are consistent, the association between the two can be established.

[0090] Step 108: Generate a target video course corresponding to the target action according to the association relationship.

[0091] In a specific implementation, generating a target video course corresponding to the target action according to the association relationship includes:

[0092] The association relationship is verified, and if the verification passes, the action attribute information and the initial video are integrated based on the association relationship to generate a target video course corresponding to the target action.

[0093] Specifically, after establishing the association relationship between the course information and the video, the establishment result of the association relationship can be double-checked to ensure its accuracy. If the verification passes, the action attribute information and the initial video are integrated based on the association relationship to generate a target video course corresponding to the target action.

[0094] In addition, after the target video course is generated, the target video course can be played in response to a user's click instruction on the target video course;

[0095] Collecting target action data generated by the user based on the target video course;

[0096] The target action data is compared with the action attribute information to generate and display the action score of the user.

[0097] Specifically, when the user is learning the target video course, the user can also wear a wearable device to collect the user's target action data using the wearable device. The user's target action data can then be compared with the action attribute information of the target action in the course to determine the accuracy of the user's action execution results. Specifically, the user's action score can be generated and displayed based on the comparison results.

[0098] The schematic diagram of the generation process of the boxing course provided in the embodiment of the present application is as follows Figure 2 As shown, initial action data generated by a coach performing boxing actions is collected through a wearable device, the process of the coach performing the boxing actions is recorded, an initial video is generated, and the initial action data is compared with the standard action data; when the comparison is successful, the action attribute information corresponding to the boxing action is determined according to the standard action data; according to the execution time of the boxing action and the timestamp corresponding to the video frame in the initial video, an association relationship between the action attribute information and the video frame is established, and a boxing video course corresponding to the boxing action is generated according to the association relationship.

[0099] Wearable devices can accurately record and present various data generated during user exercise, reflecting the user's exercise status at the time. Therefore, let the coach wear / use hardware equipment to record the original exercise data (such as boxing punch type and time, dance movement type and time, etc.) while shooting the course. In this way, when shooting video training, you can record the training content taught by the coach while recording the training content information generated by the coach, which is convenient for comparison with the user's training information in subsequent courses, helping users to better correct their movements and achieve better exercise effects. At the same time, it can also save the time spent on marking one by one according to the video after shooting the video. In addition, the generated training content information is bound to the training video, omitting the process of editing movements against the video, simplifying the course production process, and improving the efficiency of course production.

[0100] An embodiment of the present application implements a data processing method and device, wherein the data processing method includes determining initial action data and an initial video generated by a target object performing a target action, and comparing the initial action data with preset action data. When the comparison is successful, action attribute information corresponding to the target action is determined based on the preset action data, and an association relationship between the action attribute information and the video frame is established based on the execution time of the target action and the timestamp corresponding to the video frame in the initial video, and a target video course corresponding to the target action is generated based on the association relationship.

[0101] In the embodiment of the present application, in the process of generating a target video course, on the one hand, the process of the target object performing the target action is recorded to generate an initial video, and on the other hand, while recording the video, the initial action data of the target object can be collected by a wearable device worn by the target object, and then the action attribute information of the target object can be determined by comparing the initial action data with the preset action data, and then the target video course is automatically generated by establishing an association relationship between the action attribute information and each video frame in the initial video. In this process, the action attribute information of the target action is automatically identified, and the identification result is automatically associated with the video frame in the initial video to generate the target action video, which is conducive to simplifying the course generation process, thereby helping to improve the production efficiency of the video course.

[0102] See also Figure 3 , taking the application of the data processing method provided in the embodiment of the present application in the process of generating boxing courses in the field of fitness as an example, the data processing method is further explained. Figure 3 A processing flow chart of a data processing method provided by an embodiment of the present application is shown, which specifically includes the following steps:

[0103] Step 302: Obtain target type action data corresponding to a preset boxing action.

[0104] Step 304: Generate a corresponding information template based on the preset boxing action and the target type action data, wherein the information template includes an association relationship between the preset boxing action and the target type action data.

[0105] Step 306, determining the action data to be processed generated by the boxing coach performing the target boxing action collected by the wearable device.

[0106] Step 308, determining an initial video generated by recording a process of a boxing coach performing a target boxing action through a video recording device.

[0107] Step 310: extract the angular velocity data of the first coordinate axis, the second coordinate axis, and the third coordinate axis of the wearable device in the spatial coordinate system, which are contained in the action data to be processed and collected by the motion sensor in the wearable device; and / or extract the acceleration data of the wearable device, which are contained in the action data to be processed and collected by the acceleration sensor in the wearable device.

[0108] Step 312: determining a motion trajectory corresponding to the target boxing motion according to the angular velocity data and / or the acceleration data.

[0109] Step 314, determining motion feature information based on the motion trajectory, and determining initial motion data based on the motion feature information.

[0110] Step 316: parse the initial action data according to a preset data transmission protocol, and split the target boxing action based on the action trajectory included in the parsing result to generate at least two sub-actions.

[0111] Step 318, determining a comparison rule corresponding to each sub-action, and based on the comparison rule, performing a similarity comparison between the initial action data corresponding to each sub-action and the preset boxing action included in the information template.

[0112] Step 320, when the similarity comparison result is greater than the preset similarity threshold, the target type action data associated with the preset action is determined according to the association relationship between the preset boxing action and the target type action data contained in the information template.

[0113] Step 322, analyzing the target type action data, and generating action attribute information corresponding to the target boxing action according to the analysis result.

[0114] Step 324: Generate boxing course information corresponding to the target boxing action according to the action attribute information.

[0115] Step 326, determining a video segment containing the target boxing action according to the feature information contained in each video frame in the initial video.

[0116] Step 328, establishing an association relationship between the boxing course information and the starting video frame according to the execution time of the target boxing action and the timestamp corresponding to the starting video frame in the video clip.

[0117] Step 330: Generate a boxing course corresponding to the target boxing action according to the association relationship.

[0118] In the embodiment of the present application, in the process of generating a boxing course, on the one hand, a video recording is performed on the process of the boxing coach performing the target boxing action to generate an initial video. On the other hand, while recording the video, the initial action data of the boxing coach can be collected by a wearable device worn by the boxing coach. Then, the action attribute information of the boxing coach can be determined by comparing the initial action data with the preset action data. Then, the boxing course is automatically generated by establishing an association relationship between the action attribute information and each video frame in the initial video. In this process, the action attribute information of the target boxing action is automatically identified, and the identification result is automatically associated with the video frame in the initial video to generate a boxing video, which is conducive to simplifying the generation process of the boxing course, thereby helping to improve the production efficiency of the boxing course.

[0119] Corresponding to the above method embodiment, the present application also provides a data processing device embodiment, Figure 4 FIG. 1 is a schematic diagram showing the structure of a data processing device provided by an embodiment of the present application. Figure 4 As shown, the device comprises:

[0120] A comparison module 402 is configured to determine initial action data and an initial video generated by the target object performing the target action, and compare the initial action data with the preset action data;

[0121] The determination module 404 is configured to determine the action attribute information corresponding to the target action according to the preset action data when the comparison is successful;

[0122] An establishing module 406 is configured to establish an association relationship between the action attribute information and the video frame according to the execution time of the target action and the timestamp corresponding to the video frame in the initial video;

[0123] The generating module 408 is configured to generate a target video course corresponding to the target action according to the association relationship.

[0124] Optionally, the comparison module 402 is further configured to:

[0125] determining initial motion data generated by a target object performing a target motion collected by a wearable device; and,

[0126] An initial video is determined by recording a process in which the target object performs the target action through a video data acquisition device.

[0127] Optionally, the establishing module 406 is further configured to:

[0128] Generate course information corresponding to the target action according to the action attribute information;

[0129] Determine feature information contained in each video frame in the initial video, and determine a video segment containing the target action;

[0130] According to the execution time of the target action and the timestamp corresponding to the starting video frame in the video clip, an association relationship between the course information and the starting video frame is established.

[0131] Optionally, the data processing device further includes an acquisition module configured to:

[0132] Get the target type action data corresponding to the preset action;

[0133] A corresponding information template is generated based on the preset action and the target type action data, wherein the information template contains an association relationship between the preset action and the target type action data.

[0134] Optionally, the comparison module 402 is further configured to:

[0135] Comparing the initial action data with a target preset action included in the information template, wherein the target preset action is one of the preset actions;

[0136] Accordingly, the determining module 404 is further configured to:

[0137] Determining target type action data associated with the target preset action according to the association relationship;

[0138] The target type action data is parsed, and action attribute information corresponding to the target action is generated according to the parsing result.

[0139] Optionally, the comparison module 402 is further configured to:

[0140] The initial action data is parsed according to a preset data transmission protocol, and the parsing result is compared with the preset action data.

[0141] Optionally, the determining module 404 is further configured to:

[0142] Determine the action data to be processed and the initial video generated by the target object performing the target action;

[0143] Preprocessing the action data to be processed to generate an action trajectory corresponding to the target action;

[0144] Motion feature information is determined based on the motion trajectory, and initial motion data is determined based on the motion feature information.

[0145] Optionally, the determining module 404 is further configured to:

[0146] Extracting angular velocity data of a first coordinate axis, a second coordinate axis, and a third coordinate axis of the wearable device in a spatial coordinate system, which are contained in the action data to be processed and collected by a motion sensor in the wearable device; and / or extracting acceleration data of the wearable device, which are contained in the action data to be processed and collected by an acceleration sensor in the wearable device;

[0147] The motion trajectory corresponding to the target motion is determined according to the angular velocity data and / or the acceleration data.

[0148] Optionally, the comparison module 402 is further configured to:

[0149] Splitting the target action according to the action trajectory contained in the initial action data to generate at least two sub-actions;

[0150] Determine a comparison rule corresponding to each sub-action, and compare the initial action data corresponding to each sub-action with the preset action data based on the comparison rule for similarity;

[0151] When the similarity comparison result is greater than a preset similarity threshold, it is determined that the comparison is successful.

[0152] Optionally, the generating module 408 is further configured to:

[0153] The association relationship is verified, and if the verification passes, the action attribute information and the initial video are integrated based on the association relationship to generate a target video course corresponding to the target action.

[0154] Optionally, the data processing device further includes a playing module configured to:

[0155] In response to a click instruction of the target video course, playing the target video course;

[0156] Collecting target action data generated by the user based on the target video course;

[0157] The target action data is compared with the action attribute information to generate and display the action score of the user.

[0158] The above is a schematic scheme of a data processing device of this embodiment. It should be noted that the technical scheme of the data processing device and the technical scheme of the above data processing method belong to the same concept, and the details of the technical scheme of the data processing device that are not described in detail can be referred to the description of the technical scheme of the above data processing method.

[0159] Figure 5 The block diagram of a computing device 500 according to an embodiment of the present application is shown. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and the database 550 is used to store data.

[0160] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0161] In one embodiment of the present application, the above components of the computing device 500 and Figure 5 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 5 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as needed.

[0162] The computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. The computing device 500 may also be a mobile or stationary server.

[0163] The processor 520 is used to execute the following computer executable instructions, wherein the processor is used to execute the computer executable instructions, wherein the processor implements the steps of the data processing method when executing the computer executable instructions.

[0164] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above data processing method.

[0165] An embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions, which implement the steps of the data processing method when executed by a processor.

[0166] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above data processing method.

[0167] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0168] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0169] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present application are not limited by the described action sequence, because according to the embodiments of the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of the present application.

[0170] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0171] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The optional embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of the present application. The present application selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of the present application, so that those skilled in the art can understand and use the present application well. The present application is only limited by the claims and their full scope and equivalents.

Claims

1. A data processing method, comprising: Determine initial action data and an initial video generated by the target object performing the target action, and compare the initial action data with preset action data; If the comparison is successful, determining the action attribute information corresponding to the target action according to the preset action data, the action attribute information including the action type and action posture information of the target action; Generate course information corresponding to the target action according to the action attribute information; Determine feature information contained in each video frame in the initial video, and determine a video segment containing the target action; According to the execution time of the target action and the timestamp corresponding to the starting video frame in the video clip, establishing an association relationship between the course information and the starting video frame; A target video course corresponding to the target action is generated according to the association relationship.

2. The data processing method according to claim 1, wherein the determining the initial action data and the initial video generated by the target object performing the target action comprises: Determine initial motion data generated by a target object performing a target motion collected by a wearable device; as well as, An initial video is determined by recording a process in which the target object performs the target action through a video data acquisition device.

3. The data processing method according to claim 1, further comprising: Get the target type action data corresponding to the preset action; A corresponding information template is generated based on the preset action and the target type action data, wherein the information template contains an association relationship between the preset action and the target type action data.

4. The data processing method according to claim 3, wherein comparing the initial action data with the preset action data comprises: Comparing the initial action data with a target preset action included in the information template, wherein the target preset action is one of the preset actions; Correspondingly, determining the action attribute information corresponding to the target action according to the preset action data includes: Determining target type action data associated with the target preset action according to the association relationship; The target type action data is parsed, and action attribute information corresponding to the target action is generated according to the parsing result.

5. The data processing method according to claim 2, wherein comparing the initial action data with the preset action data comprises: The initial action data is parsed according to a preset data transmission protocol, and the parsing result is compared with the preset action data.

6. The data processing method according to claim 1, wherein the determining the initial action data and the initial video generated by the target object performing the target action comprises: Determine the action data to be processed and the initial video generated by the target object performing the target action; Preprocessing the action data to be processed to generate an action trajectory corresponding to the target action; Motion feature information is determined based on the motion trajectory, and initial motion data is determined based on the motion feature information.

7. The data processing method according to claim 6, wherein the preprocessing of the action data to be processed to generate the action trajectory corresponding to the target action comprises: Extracting angular velocity data of a first coordinate axis, a second coordinate axis, and a third coordinate axis of the wearable device in a spatial coordinate system, which are contained in the action data to be processed and collected by a motion sensor in the wearable device; and / or extracting acceleration data of the wearable device, which are contained in the action data to be processed and collected by an acceleration sensor in the wearable device; The motion trajectory corresponding to the target motion is determined according to the angular velocity data and / or the acceleration data.

8. The data processing method according to claim 1, wherein comparing the initial action data with the preset action data comprises: Splitting the target action according to the action trajectory contained in the initial action data to generate at least two sub-actions; Determine a comparison rule corresponding to each sub-action, and compare the initial action data corresponding to each sub-action with the preset action data based on the comparison rule for similarity; When the similarity comparison result is greater than a preset similarity threshold, it is determined that the comparison is successful.

9. The data processing method according to claim 1, wherein generating a target video course corresponding to the target action according to the association relationship comprises: The association relationship is verified, and if the verification passes, the action attribute information and the initial video are integrated based on the association relationship to generate a target video course corresponding to the target action.

10. The data processing method according to claim 1, further comprising: In response to a click instruction of the target video course, playing the target video course; Collecting target action data generated by the user based on the target video course; The target action data is compared with the action attribute information to generate and display the action score of the user.

11. A data processing device, comprising: A comparison module is configured to determine initial action data and an initial video generated by the target object performing the target action, and compare the initial action data with the preset action data; A determination module, configured to determine, if the comparison is successful, action attribute information corresponding to the target action according to the preset action data, wherein the action attribute information includes an action type and action posture information of the target action; An establishment module is configured to generate course information corresponding to the target action according to the action attribute information; determine the feature information contained in each video frame in the initial video, and determine the video segment containing the target action; and establish an association relationship between the course information and the starting video frame according to the execution time of the target action and the timestamp corresponding to the starting video frame in the video segment; A generating module is configured to generate a target video course corresponding to the target action according to the association relationship.

12. A computing device comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, wherein the processor implements the steps of the data processing method described in any one of claims 1 to 10 when executing the computer-executable instructions.

13. A computer-readable storage medium, characterized in that: It stores computer instructions, which, when executed by a processor, implement the steps of the data processing method described in any one of claims 1 to 10.

Images