Information processing method and device

Abstract

An information processing method and device are provided, which includes a step (S102) of displaying a reference action on a motion assistance interface in response to a task execution command, a step (S104) of collecting correction target actions associated with the reference action and determining correction target action information corresponding to the correction target action, a step (S106) of creating update information corresponding to the motion assistance interface according to the correction target action information and reference action information corresponding to the reference action, and a step (S108) of updating the motion assistance interface to a target motion assistance interface according to the update information and displaying it.

Description

[Technical field]

[0001] The present specification relates to the field of computer technology, and more particularly to information processing methods and apparatus. [Background technology]

[0002] With the development of Internet technology, the field of computer vision has become an important research direction, and the detection of human body key points has been widely paid attention to in the industry. Its main function is to accurately identify the key points of the human body for further processing. For example, patents with publication numbers CN114022512A, CN107281710A and CN112237730A all disclose human-computer interaction schemes, which realize security detection scenes in which the corresponding content can be provided and displayed to the user in response to the key point recognition process, or the alarm device can send an alarm notification in response to the key point recognition process, thereby realizing the provision of corresponding services to users through the manner of action recognition. Summary of the Invention [Problem to be solved by the invention]

[0003] In view of the above, the embodiments of the present specification provide an information processing method, and further relate to an information processing device, a computing device, and a computer-readable storage medium, which solve the technical defects of the prior art, such as low accuracy of motion recognition and inability to correct a user's posture. [Means for solving the problem]

[0004] According to a first aspect of the present embodiment, displaying a reference action on the action assistance interface in response to a task execution command; Collecting correction target actions associated with the reference actions and determining correction target action information corresponding to the correction target actions; creating update information corresponding to the action assistance interface according to the correction target action information and reference action information corresponding to the reference action; and updating and displaying the action assistance interface to a target action assistance interface in accordance with the update information.

[0005] Selectably, before performing the step of displaying a reference action on an action assistance interface in response to a task execution command, receiving an action assistance command committed by a user, and determining an action assistance task in response to the action assistance command; determining an action assistance template and an initial action assistance interface corresponding to the action assistance task; updating the initial action-assistance interface to an intermediate action-assistance interface based on the action-assistance template and displaying the intermediate action-assistance interface; Correspondingly, the step of displaying a reference action on the action assistance interface in response to a task execution command includes: receiving the task execution command committed by the user through the intermediate operation assistance interface; extracting the reference action from the action assistance template in response to the task execution command and updating the intermediate action assistance interface; and displaying the action assistance interface including the reference action according to the updated result.

[0006] Optionally, the step of collecting correction target actions associated with the reference actions comprises: acquiring a target image frame with an image acquisition device; inputting the target image frame into a recognition model for processing to obtain keypoint information corresponding to the target image frame; determining a target motion corresponding to the target image frame based on the key point information as the motion to be corrected that is associated with the reference motion.

[0007] Optionally, the step of determining correction target motion information corresponding to the correction target motion further comprises: determining a number of collection times and key point information corresponding to the motion to be corrected, and creating motion connection information according to the key point information; and determining the number of times of collection and the motion connecting line information as the motion information to be corrected.

[0008] The step of selectively creating update information corresponding to the action assistance interface in accordance with the correction target action information and reference action information corresponding to the reference action includes: reading the reference motion information corresponding to the reference motion, and determining reference motion connection line information according to the reference motion information; determining a degree of motion similarity between the reference motion and the motion to be corrected according to the reference motion connection line information and the motion connection line information; determining a first action score according to the number of collections and the action similarity when a collection time corresponding to the number of collections is less than a first time threshold; and creating the update information corresponding to the action assistance interface based on the first action score, the number of collections, and the action similarity.

[0009] Selectable, creating auxiliary action connection line information according to the reference action connection line information when the collection time is equal to or greater than the first time threshold, and determining a second action score according to the number of collections and the action similarity;

[0010] The method further includes creating the update information corresponding to the action assistance interface based on the second action score, the number of collections, the action similarity, and the assist action connection line information.

[0011] The step of selectively determining a degree of motion similarity between the reference motion and the motion to be corrected in accordance with the reference motion connection line information and the motion connection line information includes: determining reference key point coordinates corresponding to the reference motion according to the reference motion connection line information; and determining motion key point coordinates according to the motion connection line information; preprocessing the reference key point coordinates and the motion key point coordinates to obtain reference relative coordinates corresponding to the reference motion and motion relative coordinates corresponding to the motion to be corrected; calculating an average relative distance according to the reference relative coordinates and the motion relative coordinates; The method includes a step of obtaining the motion similarity between the reference motion and the motion to be corrected by converting the average relative distance.

[0012] Optionally, the step of pre-processing the reference keypoint coordinates to obtain reference relative coordinates corresponding to the reference motion comprises: determining a reference center point coordinate according to the reference key point coordinate; and calculating an initial reference relative coordinate based on the reference key point coordinate and the reference center point coordinate; The method includes a step of calculating a ratio between the initial reference relative coordinate and a target distance, and determining the reference relative coordinate corresponding to the reference motion according to a calculation result.

[0013] After executing the step of selectively updating the action assistance interface to a target action assistance interface in accordance with the update information and displaying the updated action assistance interface, determining an associated action corresponding to the task execution instruction when the action similarity is greater than a similarity threshold; The method further includes a step of setting the related action as the reference action, and executing the step of displaying the reference action on an action assistance interface in response to a task execution command.

[0014] According to a second aspect of the present embodiment, a display module configured to display the reference action on the action assistance interface in response to the task execution command; A collection module configured to collect correction target actions associated with the reference actions and determine correction target action information corresponding to the correction target actions; A creating module configured to create update information corresponding to the action assistance interface according to the correction target action information and reference action information corresponding to the reference action; and an update module configured to update the action assistance interface to a target action assistance interface in response to the update information and display the updated action assistance interface. A memory and a processor are included. The memory is adapted to store computer-executable instructions, and the processor, when executing the computer-executable instructions, provides a computing device adapted to implement the steps of the information processing method.

[0015] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having computer-executable instructions stored thereon, the instructions implementing the steps of the information processing method when executed by a processor. Effect of the Invention

[0016] The information processing method according to the present specification can realize assistance for a user's motion training by displaying a reference motion on the motion assistance interface in response to a task execution command, then collecting motions to be corrected associated with the reference motion, and determining waiting correction information corresponding to the motion to be corrected. At this time, related information of the motion to be corrected taken by the user with respect to the reference motion is determined, and further, update information corresponding to the motion assistance interface is created according to the motion information to be corrected and reference motion information corresponding to the reference motion, and finally, the motion assistance interface is updated according to the update information, thereby obtaining a target motion assistance interface that can present to the user related parameters of the motion to be corrected. By displaying the target motion assistance interface to the user, the user can understand the relationship between the motion to be corrected and the reference motion, thereby realizing the purpose of the user's motion training and improving the effect of posture expression. [Brief description of the drawings]

[0017] [Figure 1] 1 is a flowchart of an information processing method according to an embodiment of the present specification. [Diagram 2] FIG. 2 is a schematic diagram of a motion assistance interface according to an embodiment of the present specification. [Diagram 3] FIG. 13 is a schematic diagram of another motion assistance interface according to an embodiment of the present specification. [Figure 4] 1 is a process flowchart of an information processing method according to an embodiment of the present specification. [Diagram 5] 1 is a structural schematic diagram of an information processing device according to an embodiment of the present specification; [Figure 6] FIG. 2 is a structural block diagram of a computing device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] In order to facilitate a thorough understanding of the present specification, many specific details are set forth in the following description. However, the present specification is not limited to the specific embodiments disclosed below, since the present specification can be embodied in many other forms different from those described herein, and those skilled in the art can make similar promotions without departing from the spirit of the present specification.

[0019] The terminology used in one or more of the embodiments herein is for the purpose of describing a particular embodiment only and is not intended to limit the one or more of the embodiments herein. As used in one or more of the embodiments herein and in the appended claims, the singular forms "a," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should be understood that the term "and / or" as used in one or more of the embodiments herein refers to the inclusion of any and all possible combinations of one or more of the associated listed items.

[0020] It should be understood that while one or more embodiments herein may use terms such as first, second, etc. to describe various types of information, such information is not limited to these terms. These terms are used only to distinguish between the same types of information. For example, a first may be referred to as a second, and similarly, a second may be referred to as a first, without departing from the scope of one or more embodiments herein. Depending on the context, the word "such as" as used herein may be interpreted as "when" or "if" or "determined in response to."

[0021] The present specification provides an information processing method, and the specification further relates to an information processing device, a computing device, and a computer-readable storage medium, each of which will be described in detail in the following embodiments.

[0022] 1 shows a flowchart of an information processing method according to an embodiment of the present specification, which specifically includes the following steps: Step S102: Display a reference action on an action assistance interface in response to a task execution command.

[0023] Specifically, the task execution command is a command committed to the motion training task, and in the motion task training, the user can be instructed on how to perform each motion by displaying a reference motion to the user. For example, in a speech training scene, the motion training task can assist the user in learning a speech and inform the user of how to perform and change the gesture motion, or in an exercise motion training scene, the motion training task can assist the user in learning yoga motion and inform the user of how to perform and change the body motion, or in a catering service motion training scene, the motion training task can assist the user in learning a welcoming service and inform the user of how to perform and change the welcoming motion.

[0024] Correspondingly, the reference action is specifically a standard action that the user needs to learn, and the reference action is associated with an action task training scene, that is, the action training task can be set according to the actual application scene, and different scenes correspond to different reference actions, so that the reference action assists the user in the action training, and this embodiment does not make any limitations here. Correspondingly, the action assistance interface is specifically an interface that provides the user with a display of the reference action and can guide the user to learn the reference action, and the interface includes at least two areas, respectively an area for displaying the reference action, and an area for collecting and displaying the actions taken by the user in real time, and the action assistance interface allows the user to understand the action he or she is taking at the current time and the reference action that needs to be learned, thereby achieving the purpose of learning the reference action. In actual application, in addition to the above two areas, the action assistance interface may be set with other areas such as a control operation area for playing audio according to actual needs, and this embodiment does not make any limitations here.

[0025] Based on this, when the user needs to perform motion training, the front end can commit a task execution command through the interface displayed to the user, and then, in response to the task execution command, determine a reference motion combination that the user needs to learn, where the reference motion combination includes at least one reference motion, and then select the motions in the reference motion combination in order of the highest priority and add them to the motion assistance interface, and display the motion assistance interface including the reference motion to the user, so that the user can later realize the motion training according to the reference motion.

[0026] Furthermore, considering that the reference actions that a user needs to learn in different scenes may be different, that is, different scenes correspond to different motion training tasks, in order to cover a wider range of motion training scenes, it is usually necessary to provide the user with multiple motion training tasks, and based on this, display the reference actions that meet the user's training needs according to the user's selection, therefore, the user's motion training needs can be identified by providing an intermediate motion assistance interface, and in this embodiment, the specific implementation form is as follows:

[0027] The system receives an action assistance command committed by a user, determines an action assistance task according to the action assistance command, determines an action assistance template and an initial action assistance interface corresponding to the action assistance task, and updates and displays the initial action assistance interface to an intermediate action assistance interface based on the action assistance template.

[0028] The task execution command committed by the user through the intermediate action assistance interface is received, the reference action is extracted from the action assistance template in response to the task execution command, the intermediate action assistance interface is updated, and the action assistance interface including the reference action is displayed according to the update result.

[0029] Specifically, the action assistance command is specifically a selection command committed by the front-end display interface when the user needs to perform action training, and the action assistance command can determine the action assistance task selected by the user; correspondingly, the action assistance task is specifically a action training task that meets the needs currently selected by the user, and the action assistance task can clarify the scene corresponding to the action that the user needs to train; correspondingly, the action assistance template is specifically a template including a reference action combination, that is, all the reference actions that the user needs to learn are in the action assistance template, and the action assistance template has corresponding action assistance rules to inform the user how to perform the action assistance task. Correspondingly, the initial action assistance interface is specifically an action assistance interface template, i.e., the initial action assistance interface has no relevant information for the corresponding action assistance task added and is not displayed; correspondingly, the intermediate action assistance template is specifically an interface in which the initial action assistance interface is updated according to the action assistance template, i.e., the intermediate action assistance interface includes information content related to the action assistance task, and is used to inform the user of standard action content information related to the action assistance task, information on how to perform action training, and / or action training rule information, etc., so that the user can easily perform subsequent action training.

[0030] Based on this, after receiving an action assistance command committed by a user, in order to provide the user with a reference action that satisfies his / her action training needs, an action assistance task can be first determined according to the action assistance command, and an action assistance template corresponding to the action assistance task and an initial action assistance interface to be rendered can be determined, thereby clarifying the action assistance template associated with the reference action that the user needs to train, and the initial action assistance interface that needs to be used for later action training.

[0031] Furthermore, at this time, the initial action-assistance interface can be updated based on the action-assistance template, and an intermediate action-assistance interface can be obtained and displayed to the user, thereby realizing the user to be informed of relevant rules regarding action training and relevant information on how to perform action training, etc.

[0032] Furthermore, when the user receives a task execution command committed by the intermediate action assistance interface, it indicates that the user needs to execute a action assistance task to achieve the goal of learning the reference action in the action assistance template and training himself / herself to perform the action correctly. At this time, in response to the task execution command, a reference action for guiding the user's action training is extracted from the action assistance template, and the intermediate action assistance interface is updated based on the reference action, and an action assistance interface including the reference action is obtained and displayed to the user, so that the user can perform the action training according to the reference action in the action assistance interface.

[0033] This embodiment takes the application of the information processing method in a speech movement training scene as an example, that is, the user needs to learn the relevant movements for the speech scene, and for the relevant explanations of other movement training scenes, the user can refer to the same or corresponding explanations of this embodiment, and this embodiment does not make any limitations thereon.

[0034] Based on this, a speech movement training command committed by a user is received, at this time, a speech movement training task can be determined according to the speech movement training command, and then a speech movement training template and an initial movement training interface are determined, and since the speech movement training template includes two speech movements, the initial movement training interface is updated to an intermediate movement training interface based on the speech movement training template and displayed to the user, thereby informing the user that the speech movements include two reference speech movements to be learned, and also informing the user of information such as how to perform the movement training and training rules.

[0035] Furthermore, when the user commits a task execution command through the intermediate action training interface, indicating that the user needs to start learning speech actions, at this time, a first reference speech action is extracted from the speech action training template in response to the task execution command, and the intermediate action training interface is used to update the interface, a schematic diagram of the action training interface shown in Figure 2(a) is generated, and the first reference speech action is displayed to the user.

[0036] As described above, by providing the user with an intermediate action assistance interface, it is possible to assist the user in determining a reference action, and thereby ensure that the user is later shown a reference action that meets the user's learning needs, thereby achieving the purpose of assisting the user to fully learn the reference action. In addition, when the action assistance interface including the reference action is displayed to the user, the action assistance task is started, that is, the user can start learning the reference action to achieve the purpose of action training. In this process, in order to facilitate the user to understand the progress of action learning and the standard level of action learning, information related to action learning, such as the number of action collections, the similarity of the action taken by the user to the reference action, the score of the action taken by the user, the progress of the user's reference action, and the degree of uncompleted progress of the user's reference action, are displayed on the action assistance interface. For example, in the schematic diagram shown in FIG. 2(a), the progress of speech action learning, the number of action collections by the user, the similarity of the action learned by the user to the reference speech action, and the score of the action learned by the user are displayed to the user, thereby achieving the purpose of assisting the user to understand the details of the action training. In actual applications, the contents included in the action assistance interface can be set according to the actual application scene, and this embodiment does not make any limitations here.

[0037] Step S104: Correction target motions associated with the reference motions are collected, and correction target motion information corresponding to the correction target motions is determined.

[0038] Specifically, after the above step of displaying a reference action to the user in response to a task execution command, the user can then perform action learning according to the reference action displayed in the action assistance interface, that is, the user can position his or her limbs according to the reference action to perform the corresponding action to be corrected, at this time, the terminal collects the action to be corrected taken by the user through a collection module, thereby determining the action to be corrected information of the action to be corrected, and later combined with the action information to be corrected to easily determine the standard level of the action taken by the user, which is used to update the action assistance interface, and fully represents the user's action learning status.

[0039] The motion to be corrected is specifically a motion that is taken by the user based on the reference motion and then collected by the collection module, and the collection of the motion to be corrected is actually completed for each frame, that is, the motion to be corrected is collected for each frame and the motion assistance interface is updated after the motion to be corrected, so that the motion learning status can be fed back in real time by the motion assistance interface. Correspondingly, the information on the motion to be corrected is specifically attribute information corresponding to the motion to be corrected, and the number of times the motion to be corrected is collected, the position information of the key points of each limb in the motion to be corrected, etc. can be determined based on the information on the motion to be corrected.

[0040] Furthermore, when collecting the movements to be corrected, in order to ensure the accuracy of collection and to accurately analyze the standard level of movement learning later, a recognition model may be used. In this embodiment, the specific implementation form is as follows:

[0041] A target image frame is collected by an image collection device, the target image frame is input to a recognition model for processing, key point information corresponding to the target image frame is obtained, and a target motion corresponding to the target image frame is determined as the correction target motion associated with the reference motion based on the key point information.

[0042] Specifically, the image collection device is specifically a device that can collect images generated by a terminal such as a mobile phone camera; correspondingly, the target image frame is specifically an image frame collected at the current time that needs to be recognized as the motion to be corrected; correspondingly, the recognition model is specifically a model that can recognize key points that represent the motion to be corrected in the target image frame, i.e., the recognition model can determine key point information of the user's body in the target image frame and be used to construct the motion to be corrected; correspondingly, the key point information is specifically information related to the key points that represent the motion to be corrected, including but not limited to torso key points, limb key points, etc.

[0043] Based on this, after a target image frame is collected by an image collection device, the target image frame is input into a recognition model for processing, and key point information corresponding to the target image frame, i.e., position information on the user's torso and limb key points in the target image frame, is obtained so that accurate motion judgment can be made on the motion to be corrected in the target image frame later. Then, a target motion is constructed based on the key point information, and the target motion is associated with the reference motion, which can be easily used for creating later update information.

[0044] In addition, since the keypoint information corresponds to the keypoints of the user's body, the connecting lines of the keypoints can have a mapping relationship with the actions performed by the user, and by representing the action to be corrected with the connecting lines of the keypoints, the action learning status can be easily detected later based on the connecting lines of the keypoints, and the updating information for updating the interface is determined, thereby completing the interface updating processing operation, and displaying to the user an action assistance interface that can reflect the action learning status. That is, the action to be corrected is the action represented by the connecting lines of the keypoints associated with the user under the corresponding action after the user takes the corresponding action. It is used to represent the action taken by the user at the current time, and realizes the processing by the computer.

[0045] In addition, in order to enable the recognition model to effectively recognize key points and easily construct a target action matching the action taken by the user later, special training can be performed in the training stage, i.e., a sample image frame and a sample label corresponding to the sample image frame are obtained, the sample label is a label that accurately annotates the key points corresponding to the user in the sample image frame, and then the sample image frame is input into the initial recognition model for processing to obtain predicted key frame information, and at this time, tuning is performed on the initial model based on the sample label and the predicted key frame information until a recognition model that satisfies the training stopping condition is obtained, i.e., in actual application scenarios, the obtained recognition model can accurately recognize the key frame information corresponding to the user in the image frame, and is used to construct a correction target action corresponding to the action taken by the user, for later use.

[0046] As described above, by recognizing key point information in combination with a recognition model and determining the action to be corrected based on this, the accuracy of determining the action to be corrected can be effectively ensured, and the actions taken by the user can be fully represented, and the user's motion status can be fully analyzed based on this later to construct accurate update information.

[0047] Furthermore, after the movement to be corrected is determined, information related to the movement learning can be displayed on the interface based on the movement to be corrected. At this time, the movement information to be corrected can be determined according to the number of collections and the movement connection line information, so that update information can be easily constructed later. In this embodiment, the specific implementation form is as follows: The number of collection times and key point information corresponding to the motion to be corrected are determined, motion link information is created according to the key point information, and the number of collection times and the motion link information are set as the motion information to be corrected.

[0048] Specifically, the collection number is specifically the number of times the motion to be corrected is collected, each number indicates one frame, and correspondingly, the key point information is specifically the position information of the key points corresponding to the motion to be corrected, including but not limited to the trunk, the joint points of the limbs, and the five senses of the face, etc. Correspondingly, the motion connection line information is specifically the graphic information connecting each key point, and represents the related information of the motion to be corrected.

[0049] Based on this, the movement to be corrected is determined, and then an accurate update interface and an interface that fully represents the movement learning situation can be constructed based on this. At this time, the number of collections and key point information corresponding to the movement to be corrected are determined, and then movement connection line information is created according to the key point information. Finally, the number of collections and the movement connection line information can be used as the movement information to be corrected.

[0050] Continuing with the above example, when the movement training interface shown in FIG. 2(a) is displayed, it indicates that the training of the first reference speech movement is started, and the terminal image collecting device collects target image frames, and then the target image frames are input to the recognition model for processing, and the key point information after the user performs the learned speech movement in the target image frames, which is 14 joint point position information corresponding to the user, is obtained, which are the position information corresponding to the joint points associated with the arms, the position information corresponding to the joint points associated with the torso, and the position information corresponding to the joint points associated with the facial expression, and the user's movement to be corrected is thereby determined.

[0051] Furthermore, in order to later update the movement training interface to an interface representing the user's speaking movement learning status in the current frame based on the movement to be corrected, the number of times to collect the movement to be corrected when the user performs the movement to be corrected is determined, the key points corresponding to the joint points are connected, and movement connection line information of the corresponding movement to be corrected is obtained. In addition, in order to facilitate the user's visualization, the corresponding joint point connection lines are displayed on the movement training interface, and the schematic diagram shown in Figure 2(b) is generated, which facilitates later updating the interface to represent the speaking movement learning status based on the number of collections and the movement connection line information corresponding to the movement to be corrected.

[0052] As described above, by constructing the action information to be corrected based on the number of collections and the action connection line information, it is possible to accurately represent the attribute information corresponding to the action to be corrected in the current frame, and it is possible to easily create more accurate update information later based on this.

[0053] Step S106: According to the correction target motion information and reference motion information corresponding to the reference motion, update information corresponding to the motion assistance interface is generated.

[0054] Specifically, after determining the action information to be corrected corresponding to the action to be corrected, the action characteristics of the action to be corrected can be represented based on the action information to be corrected. Since the action to be corrected is an action taken by the user based on a reference action, the difference between the action to be corrected and the reference action can be determined simply by comparing the action information to be corrected with reference action information of the reference action. As a result, update information can be created based on the difference, and the difference content and the action learning status are reflected by the updated action assistance interface.

[0055] The reference action information is specifically feature information corresponding to the reference action, including but not limited to key point information corresponding to the reference action and standard collection number information corresponding to the reference action, etc. Correspondingly, the update information is specifically parameter information for updating the action assistance interface, and the update information can clarify the parameters that need to be updated in the action assistance interface, and the update information represents the difference between the action to be corrected collected in the current frame and the reference action.

[0056] Furthermore, when creating update information according to the reference action information and the action information to be corrected, the difference between the action to be corrected and the reference action is actually reflected by the update information, thereby providing feedback to the user on the learning status of learning the reference action and allowing the difference status to be fully expressed to the user. In this embodiment, this is specifically realized in steps S1062 to S1068.

[0057] Step S1062: The reference motion information corresponding to the reference motion is read, and reference motion connection line information is determined according to the reference motion information.

[0058] Step S1064: A degree of motion similarity between the reference motion and the motion to be corrected is determined according to the reference motion connection line information and the motion connection line information.

[0059] Specifically, the reference action connecting line information is specifically information related to the connecting line that connects the key points corresponding to the reference action, and correspondingly, the action similarity is specifically the similarity between the reference action and the action to be corrected, and the action similarity can determine the situation in which the user learns the reference action in the current frame, and influences whether the user needs to continuously learn the reference action in the current action assistance interface. That is, the higher the action similarity, the more accurate the posture of the action to be corrected by which the user learns the reference action in the current frame, while the lower the action similarity, the more incorrect the posture of the action to be corrected by which the user learns the reference action in the current frame, thereby determining whether the new reference action needs to be changed and continuously learned.

[0060] Based on this, the information on the action to be corrected corresponding to the action to be corrected is determined, and then the reference action information corresponding to the reference action is read and reference action connection line information can be determined according to the reference action information. After that, the similarity between the reference action and the action to be corrected is calculated according to the reference action connection line information and the action connection line information to obtain the action similarity between the two, which is used in constructing subsequent update information.

[0061] Furthermore, when calculating the action similarity between a reference action and an action to be corrected, the action similarity is the basis for determining the content to be included in the update information, so by accurately calculating the action similarity, the difference between the reference action and the action to be corrected can be fully reflected, and in this embodiment, the calculation of the action similarity is realized by the following steps.

[0062] Step S10642: Determine reference key point coordinates corresponding to the reference motion according to the reference motion connecting line information, and determine motion key point coordinates according to the motion connecting line information.

[0063] Step S10644: The reference key point coordinates and the motion key point coordinates are pre-processed respectively to obtain reference relative coordinates corresponding to the reference motion and motion relative coordinates corresponding to the motion to be corrected.

[0064] Specifically, the reference keypoint coordinates are specifically the coordinates in the same coordinate system of the keypoints corresponding to the reference action, and correspondingly, the action keypoint coordinates are specifically the coordinates in the same coordinate system of the keypoints corresponding to the action to be corrected, and correspondingly, the pre-processing of the keypoint coordinates is specifically pre-processing based on the conversion from the keypoint coordinates to the relative coordinates, which realizes reflecting the degree of difference of the same keypoints by the relative distance between the relative coordinates, thereby obtaining the action similarity by integrating the relative distances between the relative coordinates of all the keypoints, and correspondingly, the reference relative coordinates are specifically the relative coordinates obtained by pre-processing the reference keypoint coordinates, and the action coordinates to be corrected are specifically the relative coordinates obtained by pre-processing the action keypoint coordinates.

[0065] Furthermore, when preprocessing the keypoint coordinates, the specific preprocessing process of the reference keypoint coordinates is as follows: A reference center point coordinate is identified according to the reference key point coordinate, an initial reference relative coordinate is calculated based on the reference key point coordinate and the reference center point coordinate, a ratio between the initial reference relative coordinate and a target distance is calculated, and the reference relative coordinate corresponding to the reference motion is determined according to a calculation result.

[0066] Specifically, the reference center point coordinates are specifically center point coordinates identified according to the reference key point coordinates. For example, the key points correspond to each joint of the body. In this case, the center points of both shoulders are identified as the reference center point coordinates by the key point coordinates corresponding to both shoulder key points, and initial reference relative coordinates of each reference key point coordinate relative to the reference center point coordinates are calculated. Correspondingly, the initial reference relative coordinates are specifically the calculated coordinates of each reference key point coordinate relative to the reference center point coordinates. Correspondingly, the target distance is specifically the calculation of the distance between two reference key point coordinates of the reference center point coordinates.

[0067] Based on this, after obtaining the reference keypoint coordinates, the reference center point coordinates can be identified based on them, and the initial reference relative coordinates are calculated based on the reference keypoint coordinates and the reference center point coordinates, and then the ratio between the initial reference relative coordinates and the target distance is further calculated, and finally the reference relative coordinates corresponding to the reference motion can be determined according to the calculation result.

[0068] For example, if the midpoint of both shoulders is taken as the reference center point coordinate, the center point coordinate of both shoulders can be subtracted from each reference key point coordinate to obtain the relative coordinate of each key point with respect to the center point of both shoulders. Furthermore, by dividing the obtained relative coordinate by the distance between the coordinates of both shoulder key points, the reference relative coordinate of each key point with respect to the center point of both shoulders based on a certain ratio can be obtained.

[0069] Similarly, the coordinates of the motion center point can be specified according to the coordinates of the motion key points, and then the initial motion relative coordinates can be calculated based on the coordinates of the motion key points and the coordinates of the motion center point, and the ratio between the initial motion relative coordinates and another target distance can be calculated, and the motion relative coordinates corresponding to the motion to be corrected can be determined according to the calculation result. Note that the calculation process of the motion relative coordinates can be referred to the calculation process of the reference relative coordinates, and detailed description is omitted here in this embodiment.

[0070] As described above, by determining the relative coordinates using relative calculation, it is possible to easily calculate an accurate motion similarity later based on the relative coordinates, thereby improving the accuracy of constructing update information.

[0071] Step S10646: An average relative distance is calculated according to the reference relative coordinates and the motion relative coordinates.

[0072] Step S10648: The average relative distance is converted to obtain the motion similarity between the reference motion and the motion to be corrected.

[0073] Specifically, the average relative distance is a distance reflecting the difference between the action to be corrected in the current frame and the reference action, i.e., the average value of the distance between the key points corresponding to the action to be corrected and the reference action. The smaller the average relative distance, the smaller the difference between the action to be corrected and the reference action, while the larger the average relative distance, the larger the difference between the action to be corrected and the reference action. Correspondingly, the conversion of the average relative distance is specifically a conversion processing operation that converts it into a similarity expression format.

[0074] Based on this, after obtaining the reference relative coordinates and the motion relative coordinates, the average relative distance between the reference motion and the motion to be corrected can be calculated according to the reference relative coordinates and the motion relative coordinates, and then the average relative distance can be converted to obtain the motion similarity between the reference motion and the motion to be corrected, thereby reflecting the difference between the reference motion and the motion to be corrected. In addition, when converting the average relative distance to determine the motion similarity, considering that the average relative distance is the distance value between the key point of the reference motion and the key point of the motion to be corrected (the positions of the joints corresponding to the key points are the same), the larger the relative distance, the lower the similarity. Based on this, when the average relative distance is greater than 1, the motion similarity can be directly determined to be 0, while when the average relative distance is less than or equal to 1, the value obtained by subtracting the average relative distance from 1 can be set as the similarity, thereby making it easy to construct update information later.

[0075] As described above, by calculating the action similarity, the similarity between the action to be corrected and the reference action can be reflected, and the similarity between the action to be corrected and the reference action collected in the current frame can be fully represented, making it easy to construct update information that can accurately update the interface later.

[0076] Furthermore, after determining the action similarity, considering that different users have different progress in learning the reference action, in order to fully assist users in accurately learning the reference action, different methods can be selected according to different collection times to construct the update information, and the specific realization is as follows: Step S1066: If the collection time corresponding to the number of collections is less than a first time threshold, a first action score is determined according to the number of collections and the action similarity, and the update information corresponding to the action assistance interface is created based on the first action score, the number of collections, and the action similarity.

[0077] Specifically, the collection time is the time it takes to collect the correction target action corresponding to the current frame, and correspondingly, the first action score is a score obtained by combining the number of collections and the action similarity, where the first action score can reflect the similarity between the correction target action and the reference action, and the similarity of the current frame is high.

[0078] Based on this, when the collection time corresponding to the number of collections is less than a first time threshold, it indicates that the collection of the action to be corrected is completed with only a small number of collections. At this time, a first action score is calculated according to the number of collections and the action similarity, and then an update parameter can be directly constructed based on the first action score, the number of collections, and the action similarity.

[0079] Step S1068: If the collection time is equal to or greater than the first time threshold, auxiliary action connection line information is created according to the reference action connection line information, a second action score is determined according to the number of collections and the action similarity, and the update information corresponding to the action assistance interface is created based on the second action score, the number of collections, the action similarity, and the auxiliary action connection line information.

[0080] Specifically, the auxiliary action connection line information is specifically connection line information that needs to be added to the interface to assist the user in learning the reference action, so that the user can make the action connection line information of the corresponding correction target action closer to the auxiliary action connection line information to realize the correction of the correction target action; correspondingly, the second score is specifically a score obtained by combining the number of collections and the action similarity, and the score indicates that the similarity between the correction target action and the reference action is low.

[0081] Based on this, if the collection time is equal to or greater than the first time threshold, it indicates that the collection time of the action to be corrected is long, and further indicates that the user is unable to perform the action to be corrected that matches the reference action within a short time. At this time, auxiliary action connection line information is created according to the reference action connection line information, and a second action score is determined in combination with the number of collections and the action similarity. Finally, update information corresponding to the action assistance interface can be created based on the second action score, the number of collections, the action similarity and the auxiliary action connection line information.

[0082] In addition, in order to assist the user in quickly completing the learning of the reference movements, auxiliary action connection line information can be created; in order to realize effective guidance through the auxiliary action connection line information, the auxiliary action connection line information can be created in different colors according to the collection time, that is, when the collection time is equal to or greater than the first time threshold and less than the second time threshold, auxiliary action connection line information in S1 color can be created; when the collection time is greater than the second time threshold, auxiliary action connection line information in S2 color can be created; the S1 and S2 colors can be set according to actual application scenarios, and this embodiment is not limited thereto.

[0083] In practical application, when determining the action score, the correlation between the number of collections and the action similarity can be set in advance, and can be divided into multiple levels according to the correlation, for example, if the number of collections is small, it indicates that the collection time is short, and if the action similarity is high, it can get full points, or if the number of collections is large, it indicates that the collection time is average, and if the action similarity is high, it can get half of full points, or if the number of collections is very large, it indicates that the collection time is long, and if the action similarity is low, it can get 0 points. The specific division relationship can be set according to the actual application scenario, and this embodiment is not limited here.

[0084] Continuing with the above example, by reading the reference action information of the first reference speech action to determine the reference action connection line information, it can be determined that the action similarity between the action to be corrected and the first reference speech action is 0.925 according to the reference action connection line information and the action connection line information of the action to be corrected; if the collection time is less than a first time threshold, it can be determined that the action to be corrected gets 100 points (full score) according to the collection number of times and the action similarity; and then the update information of the action training interface can be constructed based on the 100 points, the collection number of times and the action similarity.

[0085] If the collection time is greater than or equal to the first time threshold and less than the second time threshold, it is determined that the movement to be corrected will receive 50 points (half of the full score) according to the number of collections and the movement similarity, and S1 colored auxiliary movement connection line information is created based on the reference movement connection line information of the first reference speech movement, and then update information for the movement training interface can be constructed based on the 50 points, the S1 colored auxiliary movement connection line information, the number of collections and the movement similarity.

[0086] If the collection time is equal to or greater than the second time threshold, it is determined that the movement to be corrected will receive 0 points (half of the full score) according to the number of collections and the movement similarity, and S2 colored auxiliary movement connection line information is created based on the reference movement connection line information of the first reference speech movement, and then update information for the movement training interface can be constructed based on the 0 points, the S2 colored auxiliary movement connection line information, the number of collections and the movement similarity.

[0087] As described above, by creating different update information according to different collection times, when updating the interface, the action similarity at different times can be sufficiently fed back by the updated interface, so as to reflect the details of the user learning the reference action, and achieve the purpose of action training.

[0088] Step S108: The action assistance interface is updated to a target action assistance interface in accordance with the update information and displayed.

[0089] Specifically, after obtaining the above-mentioned update information, the action assistance interface can be further updated according to the update information to obtain a target action assistance interface that reflects the details of the action learning, and by displaying the target action assistance interface to the user, the user can understand the action learning status.

[0090] In practical applications, if the obtained update information determines that the user has not completed the reference action, it indicates that the action to be corrected taken by the user in the current frame does not meet the standard. At this time, the update information only includes the number of collections and the action similarity, and the updated interface also updates only the number of collections and the action similarity score, and steps S104 to S108 are repeated. If the update information determines that the user has completed the reference action, it can be determined that the update information includes the number of collections, the action similarity, the action score, and a new reference action, and the updated interface can display the user's reference action learning status. After a while, the interface is updated again based on the new reference action, and the process of steps S104 to S108 is repeated to learn a new reference action until learning is completed.

[0091] Continuing using the above example, if the update information includes 100 points, the number of collections, and the similarity of the actions, it indicates that the user's learning situation in the current frame is good, and at this time, the schematic diagram shown in Figure 3(a) can be displayed; if the update information includes 50 points, S1 colored auxiliary action connecting line information, the number of collections, and the similarity of the actions, it indicates that the user's learning situation in the current frame is average, and in order to assist the user in learning the first reference speaking action, the schematic diagram shown in Figure 3(b) can be updated, and auxiliary lines are included to express to the user how to adjust the action to be corrected so that it is the same as the first reference speaking action.

[0092] In addition, after the target action assistance interface is displayed to the user, if the user's action similarity in the current frame is greater than the similarity threshold, it indicates that the user's reference action learning process is completed, that is, the action to be corrected is the same as the reference action, and at this time, the next action training can be continued. In this embodiment, the specific realization is as follows: If the action similarity is greater than a similarity threshold, the step of determining an associated action corresponding to the task execution command, setting the associated action as the reference action, and displaying the reference action on an action assistance interface in response to the task execution command is performed.

[0093] Incidentally, for the process of learning a new reference action, reference may be made to the same or corresponding description in the above embodiment, and a detailed description thereof will be omitted here in this embodiment.

[0094] Continuing with the above example, after it is determined that the user has completed learning the first standard speech movement based on the diagram shown in Figure 3(a), the second standard speech movement can be read from the template and the diagram shown in Figure 3(c) can be displayed to the user for further movement training.

[0095] It should be noted that the information processing method according to this embodiment is applied to the entire process of movement training, that is, the interface update process of each frame is realized by the above method, and before the reference movement is switched, it shows that the correction target movement of the user learning the reference movement does not meet the standard, at this time, it is necessary to continue adjustment, during adjustment, the movement assistance interface continues to display the adjusted movement and related parameters, and when it meets the standard of how to take the reference movement, it jumps to the next reference movement and learns, and the learning process of the next reference movement is similar to the description of the above embodiment, and the detailed description is omitted here in this embodiment. When the learning of all the reference movements is completed, the reference movement learning completion interface can be displayed to the user. That is, the interface update of each frame needs to repeat the above interface update processing operation to fully express the user's movement taking situation in the current frame.

[0096] The information processing method according to the present specification can realize assistance for a user's motion training by displaying a reference motion on the motion assistance interface in response to a task execution command, then collecting motions to be corrected associated with the reference motion, and determining waiting correction information corresponding to the motion to be corrected. At this time, related information of the motion to be corrected taken by the user with respect to the reference motion is determined, and further, update information corresponding to the motion assistance interface is created according to the motion information to be corrected and reference motion information corresponding to the reference motion, and finally, the motion assistance interface is updated according to the update information, thereby obtaining a target motion assistance interface that can present to the user related parameters of the motion to be corrected. By displaying the target motion assistance interface to the user, the user can understand the relationship between the motion to be corrected and the reference motion, thereby realizing the purpose of the user's motion training and improving the effect of posture expression.

[0097] Hereinafter, the information processing method according to the present specification will be further described with reference to Fig. 4. Fig. 4 shows a processing flow chart of the information processing method according to an embodiment of the present specification, which specifically includes the following steps: Step S402: Receive a motion assistance command committed by a user, and determine a motion assistance task according to the motion assistance command.

[0098] Step S404: An action assistance template and an initial action assistance interface corresponding to the action assistance task are determined.

[0099] Step S406: The initial action-assist interface is updated to an intermediate action-assist interface based on the action-assist template and displayed.

[0100] Step S408: Receive a task execution command committed by the intermediate operation assistance interface from the user.

[0101] Step S410: In response to the task execution command, a reference action is extracted from the action assistance template, and the intermediate action assistance interface is updated.

[0102] Step S412: A motion assistance interface including a reference motion is displayed according to the updated result.

[0103] Step S414: Acquire target image frames by an image acquisition device.

[0104] Step S416: The target image frame is input to the recognition model for processing, and keypoint information corresponding to the target image frame is obtained. Step S418: The target motion corresponding to the target image frame is determined as a correction target motion associated with the reference motion based on the keypoint information.

[0105] Step S420: The number of collection times and key point information corresponding to the motion to be corrected are determined, and motion connection information is created according to the key point information.

[0106] Step S422: The number of collections and the motion connecting line information are set as motion information to be corrected.

[0107] Step S424: The degree of motion similarity between the reference motion and the motion to be corrected is determined according to the reference motion connection line information and the motion connection line information.

[0108] The calculation of the action similarity includes the steps of determining reference key point coordinates corresponding to the reference action in accordance with the reference action connection line information, determining action key point coordinates in accordance with the action connection line information, pre-processing the reference key point coordinates and the action key point coordinates, respectively, to obtain reference relative coordinates corresponding to the reference action and action relative coordinates corresponding to the action to be corrected, calculating an average relative distance in accordance with the reference relative coordinates and the action relative coordinates, and converting the average relative distance to obtain the action similarity between the reference action and the action to be corrected.

[0109] The coordinate pre-processing process includes the steps of identifying a reference center point coordinate according to a reference key point coordinate, calculating an initial reference relative coordinate based on the reference key point coordinate and the reference center point coordinate, calculating a ratio between the initial reference relative coordinate and a target distance, and determining a reference relative coordinate corresponding to a reference motion according to the calculation result.

[0110] Step S426: If the collection time corresponding to the collection count is less than the first time threshold, a first action score is determined according to the collection count and the action similarity.

[0111] Step S428: Based on the first action score, the number of collections, and the action similarity, update information corresponding to the action assist interface is generated.

[0112] Step S430: If the collection time is equal to or greater than the first time threshold, auxiliary action connection information is created according to the reference action connection information, and a second action score is determined according to the number of collections and the action similarity.

[0113] Step S432: Based on the second action score, the number of collections, the action similarity, and the assist action connection line information, update information corresponding to the action assist interface is generated.

[0114] Step S434: The action assist interface is updated to the target action assist interface in accordance with the update information and displayed.

[0115] In addition, if the action similarity is greater than a similarity threshold, a step can be performed of determining an associated action corresponding to the task execution command, and then setting the associated action as a reference action and displaying the reference action on the action assistance interface in response to the task execution command.

[0116] As described above, in order to realize assistance for the user's motion training, a reference motion is displayed on the motion assistance interface in response to a task execution command, and then the motions to be corrected associated with the reference motion are collected and target correction information corresponding to the motion to be corrected is determined. At this time, related information of the motion to be corrected taken by the user with respect to the reference motion is determined. Further, update information corresponding to the motion assistance interface is created according to the motion information to be corrected and reference motion information corresponding to the reference motion. Finally, the motion assistance interface is updated according to the update information, thereby obtaining a target motion assistance interface that can present to the user related parameters of the motion to be corrected. By displaying the target motion assistance interface to the user, the user can understand the relationship between the motion to be corrected and the reference motion, thereby realizing the purpose of the user's motion training and improving the effect of posture expression.

[0117] Corresponding to the above method embodiment, the present specification further provides an embodiment of an information processing device, and FIG. 5 shows a structural schematic diagram of an information processing device according to an embodiment of the present specification. As shown in FIG. 5, the device includes: A display module 502 configured to display the reference action on the action assistance interface in response to the task execution command; A collection module 504 configured to collect correction target actions associated with the reference actions and determine correction target action information corresponding to the correction target actions; A creation module 506 configured to create update information corresponding to the action assistance interface according to the correction target action information and reference action information corresponding to the reference action; and an update module 508 configured to update and display the action assistant interface to a target action assistant interface in response to the update information.

[0118] In one alternative embodiment, the information processing device includes: The present invention further includes a receiving module configured to receive an action assistance command committed by a user, determine an action assistance task according to the action assistance command, determine an action assistance template and an initial action assistance interface corresponding to the action assistance task, and update and display the initial action assistance interface to an intermediate action assistance interface based on the action assistance template; In one alternative embodiment, the display module 502 further comprises: The system is configured to receive the task execution command committed by the user through the intermediate action assistance interface, extract the reference action from the action assistance template in response to the task execution command, update the intermediate action assistance interface, and display the action assistance interface including the reference action according to the update result.

[0119] In one alternative embodiment, the collection module 504 further comprises: The method is configured to collect target image frames using an image collection device, input the target image frames into a recognition model for processing, obtain key point information corresponding to the target image frames, and determine a target motion corresponding to the target image frames as the correction target motion associated with the reference motion based on the key point information.

[0120] In one alternative embodiment, the collection module 504 further comprises: The correction target motion information is configured to determine a number of collection times and key point information corresponding to the correction target motion, generate motion link information according to the key point information, and use the collection number and the motion link information as the correction target motion information.

[0121] In one alternative embodiment, the creation module 506 further comprises: The method is configured to read the reference action information corresponding to the reference action, determine reference action connection line information according to the reference action information, determine an action similarity between the reference action and the action to be corrected according to the reference action connection line information and the action connection line information, and if a collection time corresponding to the number of collections is less than a first time threshold, determine a first action score according to the number of collections and the action similarity, and create the update information corresponding to the action assistance interface based on the first action score, the number of collections, and the action similarity.

[0122] In one alternative embodiment, the creation module 506 further comprises: When the collection time is equal to or greater than the first time threshold, the method is configured to create auxiliary action connection line information according to the reference action connection line information, determine a second action score according to the number of collections and the action similarity, and create the update information corresponding to the action assistance interface based on the second action score, the number of collections, the action similarity, and the auxiliary action connection line information.

[0123] In one alternative embodiment, the creation module 506 further comprises: The method is configured to determine reference key point coordinates corresponding to the reference action according to the reference action connection line information, determine action key point coordinates according to the action connection line information, pre-process the reference key point coordinates and the action key point coordinates, respectively, obtain reference relative coordinates corresponding to the reference action and action relative coordinates corresponding to the action to be corrected, calculate an average relative distance according to the reference relative coordinates and the action relative coordinates, and convert the average relative distance to obtain the action similarity between the reference action and the action to be corrected.

[0124] In one alternative embodiment, the creation module 506 further comprises: The system is configured to identify a reference center point coordinate according to the reference key point coordinate, calculate an initial reference relative coordinate based on the reference key point coordinate and the reference center point coordinate, calculate a ratio between the initial reference relative coordinate and a target distance, and determine the reference relative coordinate corresponding to the reference motion according to a calculation result.

[0125] In one alternative embodiment, the information processing device includes: The method further includes performing the step of determining an associated action corresponding to the task execution command when the action similarity is greater than a similarity threshold, setting the associated action as the reference action, and displaying the reference action on an action assistance interface in response to the task execution command.

[0126] The information processing device according to the present specification can realize assistance for a user's motion training by displaying a reference motion on the motion assistance interface in response to a task execution command, then collecting motions to be corrected associated with the reference motion, and determining waiting correction information corresponding to the motion to be corrected. At this time, related information of the motion to be corrected taken by the user with respect to the reference motion is determined, and further, update information corresponding to the motion assistance interface is created according to the motion information to be corrected and reference motion information corresponding to the reference motion, and finally, the motion assistance interface is updated according to the update information, thereby obtaining a target motion assistance interface that can present to the user related parameters of the motion to be corrected. By realizing the display of the target motion assistance interface to the user, the user can understand the relationship between the motion to be corrected and the reference motion, thereby realizing the purpose of the user's motion training and improving the effect of posture expression.

[0127] The above is an exemplary means of the information processing device of this embodiment. Note that the technical solution of the information processing device belongs to the same idea as the technical solution of the above information processing method, and for details that are not explained in detail in the technical solution of the information processing device, please refer to the explanation of the technical solution of the above information processing method.

[0128] 6 shows a structural block diagram of a computing device 600 according to an embodiment of the present disclosure. Components of the computing device 600 include, but are not limited to, a memory 610 and a processor 620. The processor 620 and the memory 610 are connected via a bus 630, and a database 650 is used to store data.

[0129] Computing device 600 further includes access device 640, which allows computing device 600 to communicate over one or more networks 660. 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. Access device 640 may include one or more of any type of network interface, wired or wireless, such as an IEEE 802.11 wireless LAN (WLAN) radio interface, a Worldwide 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, or the like (e.g., a network interface card (NIC)).

[0130] In one embodiment of the present specification, the above components of the computing device 600 and other components not shown in FIG. 6 may be connected to each other, for example, via a bus. It is understood that the structural block diagram of the computing device shown in FIG. 6 is for illustrative purposes only and does not limit the scope of the present specification. Those skilled in the art can add or replace other components as needed. The computing device 600 may be any type of fixed or portable computing device, such as a portable computer or portable computing device (e.g., tablet computer, personal digital assistant, laptop computer, notebook computer, netbook, etc.), a mobile phone (e.g., smartphone), a wearable computing device (e.g., smart watch, smart glasses, etc.) or other types of portable devices, or a fixed computing device such as a desktop computer or PC. The computing device 600 may also be a portable or fixed server.

[0131] The processor 620 is adapted to execute the following computer-executable instructions. Displaying a reference motion on the motion assistance interface in response to a task execution command; Collecting correction target motions associated with the reference motions, and determining correction target motion information corresponding to the correction target motions; creating update information corresponding to the action assistance interface in response to the correction target action information and reference action information corresponding to the reference action; The action assistance interface is updated to a target action assistance interface in accordance with the update information and displayed.

[0132] The above is an exemplary solution of the computing device in this embodiment, which belongs to the same idea as the technical solution of the information processing method described above, and for details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the information processing method described above.

[0133] An embodiment herein further provides a computer-readable storage medium having stored thereon computer instructions, which, when executed by a processor, Displaying a reference motion on the motion assistance interface in response to a task execution command; Collecting correction target motions associated with the reference motions, and determining correction target motion information corresponding to the correction target motions; creating update information corresponding to the action assistance interface in response to the correction target action information and reference action information corresponding to the reference action; The action assistance interface is updated to a target action assistance interface according to the update information and displayed.

[0134] The above is an exemplary solution of the computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium belongs to the same idea as the technical solution of the information processing method described above, and for details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the information processing method described above.

[0135] Certain embodiments of the present specification have been described above. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in an order different from that in the examples and still achieve desirable results. Also, the processes depicted in the figures do not necessarily require the particular order depicted, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or advantageous.

[0136] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form, etc. The computer readable medium may include any entity or device capable of carrying the computer program code, such as a recording medium, a U-disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, an electrical communication signal, and a software distribution medium, etc. It should be noted that the content included in the computer readable medium may be increased or decreased depending on the requirements of the legislation and patent practice in the relevant jurisdiction, for example, in some jurisdictions, depending on the legislation and patent practice, the computer readable medium does not include electrical carrier signals and electrical communication signals.

[0137] Although the above method embodiments are expressed as a series of combinations of operations for ease of explanation, those skilled in the art will appreciate that the present specification is not limited by the order of operations described, and that some steps may be performed in other orders or simultaneously according to the present specification. In addition, those skilled in the art will further appreciate that the embodiments described in the specification are preferred embodiments, and such operations and modules are not necessarily required by the present specification.

[0138] In the above embodiments, emphasis is placed on the description of each embodiment, and for parts that are not described in detail in one embodiment, reference may be made to the relevant descriptions of other embodiments.

[0139] The preferred examples disclosed hereinabove are intended only to help explain the present specification. The selectable examples do not cover all the details, nor do they limit the invention, but are merely the specific embodiments. Obviously, various modifications and variations can be made according to the contents of the present specification. The purpose of selecting and specifically describing these examples in the present specification is to better interpret the principles and applications of the present specification so that those skilled in the art can better understand and use the present specification. The present specification is limited only by the claims and their full scope and equivalents.

Claims

1. 1. An information processing method, comprising: displaying a reference action on the action assistance interface in response to a task execution command; Collecting correction target actions associated with the reference actions and determining correction target action information corresponding to the correction target actions; creating update information corresponding to the action assistance interface according to the correction target action information and reference action information corresponding to the reference action; updating the action assistance interface to a target action assistance interface in accordance with the update information and displaying the updated action assistance interface; The step of determining correction target motion information corresponding to the correction target motion includes: determining a number of collection times and key point information corresponding to the motion to be corrected, and creating motion connection information according to the key point information; and setting the number of collections and the motion connection line information as the correction target motion information, the step of creating update information corresponding to the action assistance interface in response to the correction target action information and reference action information corresponding to the reference action, reading the reference motion information corresponding to the reference motion, and determining reference motion connection line information according to the reference motion information; determining a degree of motion similarity between the reference motion and the motion to be corrected according to the reference motion connection line information and the motion connection line information; determining a first action score according to the number of collections and the action similarity when a collection time corresponding to the number of collections is less than a first time threshold; creating the update information corresponding to the action assistance interface based on the first action score, the number of collections, and the action similarity.

23. An information processing method comprising:

2. before executing the step of displaying a reference action on an action assistance interface in response to a task execution command, receiving a committed motion assistance command from a user and determining a motion assistance task in response to the motion assistance command; determining an action assistance template and an initial action assistance interface corresponding to the action assistance task; updating the initial action-assistance interface to an intermediate action-assistance interface based on the action-assistance template and displaying the intermediate action-assistance interface; Correspondingly, the step of displaying a reference action on the action assistance interface in response to a task execution command includes: receiving the task execution command committed by the user through the intermediate operation assistance interface; extracting the reference action from the action assistance template in response to the task execution command and updating the intermediate action assistance interface; The information processing method according to claim 1 , further comprising: displaying the action assistance interface including the reference action according to an updated result.

3. The step of collecting a correction target motion associated with the reference motion includes: acquiring a target image frame with an image acquisition device; inputting the target image frame into a recognition model for processing to obtain keypoint information corresponding to the target image frame; The information processing method according to claim 1 , further comprising: determining a target motion corresponding to the target image frame based on the key point information as the correction target motion associated with the reference motion.

4. creating auxiliary action connection line information according to the reference action connection line information when the collection time is equal to or greater than the first time threshold, and determining a second action score according to the number of collections and the action similarity; The information processing method according to claim 1, further comprising: creating the update information corresponding to the action assistance interface based on the second action score, the number of collections, the action similarity, and the assist action connection line information.

5. The step of determining a degree of motion similarity between the reference motion and the motion to be corrected according to the reference motion connection line information and the motion connection line information includes: determining reference key point coordinates corresponding to the reference motion according to the reference motion connection line information; and determining motion key point coordinates according to the motion connection line information; Preprocessing the reference key point coordinates and the motion key point coordinates to obtain reference relative coordinates corresponding to the reference motion and motion relative coordinates corresponding to the motion to be corrected; calculating an average relative distance according to the reference relative coordinates and the motion relative coordinates; The information processing method according to claim 1 , further comprising: acquiring the motion similarity between the reference motion and the motion to be corrected by converting the average relative distance.

6. The step of pre-processing the reference keypoint coordinates and obtaining reference relative coordinates corresponding to the reference motion includes: determining a reference center point coordinate according to the reference key point coordinate; and calculating an initial reference relative coordinate based on the reference key point coordinate and the reference center point coordinate; 6. The information processing method according to claim 5, further comprising the step of calculating a ratio between the initial reference relative coordinates and a target distance, and determining the reference relative coordinates corresponding to the reference motion in accordance with a result of the calculation.

7. After executing the step of updating the action assistance interface to a target action assistance interface in accordance with the update information and displaying the same, determining an associated action corresponding to the task execution instruction when the action similarity is greater than a similarity threshold; The information processing method according to claim 5 , further comprising the step of: setting the related action as the reference action, and executing the step of displaying the reference action on an action assistance interface in response to a task execution command.

8. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, cause the implementation of the steps of the method according to any one of claims 1 to 7.

Images