Fitness interaction method and apparatus, electronic device, and computer-readable storage medium

Abstract

Embodiments of the present application disclose a fitness interaction method and device, electronic equipment and a computer readable storage medium. The method comprises: displaying a screen projection video projected by a user on a terminal interface; determining a video type of the screen projection video according to content of the screen projection video; starting a fitness guidance mode when the video type indicates that the screen projection video is a fitness video; and performing fitness interaction with the user according to the fitness guidance mode. The user can display different fitness videos based on different needs, which enriches the diversity of the fitness videos and improves the fitness experience. Through analysis of the video type based on the video content, the type of the video can be automatically identified, without identification or screening of the video type on the opposite side of the terminal device, thereby reducing the operation complexity on the opposite side of the terminal device and improving the user experience.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to a fitness interaction method, device, electronic device, and computer-readable storage medium. Background Technology

[0002] As living standards improve, it has become common for users to imitate the movements in videos on the interface to exercise. However, currently, the types of videos on the interface are limited and the update speed is slow, which is not conducive to the user's fitness experience. Summary of the Invention

[0003] This application provides a fitness interaction method, device, electronic device, and computer-readable storage medium that can assist users in exercising and provide guidance for user movements.

[0004] In a first aspect, embodiments of this application provide a fitness interaction method, including:

[0005] Display the screen-cast video from the user's device on the terminal interface;

[0006] The video type of the projected video is determined based on its content;

[0007] When the video type description indicates that the projected video is a fitness video, the fitness guidance mode is activated.

[0008] The fitness guidance mode is used to interact with the user during fitness activities.

[0009] Secondly, embodiments of this application also provide a fitness interactive device, including:

[0010] The display module is used to display the screen-cast video that the user has projected from the other end device on the terminal interface;

[0011] The determining module is used to determine the video type of the projected video based on its content.

[0012] The startup module is used to start the fitness guidance mode when the video type description of the screen-casting video is a fitness video.

[0013] The interactive module is used to interact with the user during fitness activities based on the fitness guidance mode.

[0014] In some embodiments of this application, the display module includes:

[0015] The receiving unit is used to receive the screen-casting video sent by the user through the peer device, wherein the screen-casting video is selected by the user locally on the peer device;

[0016] The display unit is used to display the projected video on the local terminal interface.

[0017] In some embodiments of this application, the determining module includes:

[0018] The selection unit is used to select several video images from the several video images in the projected video as reference video images according to the timing of the several video images in the projected video.

[0019] The determining unit is used to determine the video type of the projected video based on a plurality of the reference video images by means of a motion recognition model.

[0020] In some embodiments of this application, the determining unit includes:

[0021] The input subunit is used to input each reference video image into the action recognition model to obtain the background and human skeleton diagram corresponding to each reference video image.

[0022] The filtering subunit is used to select the human skeleton image corresponding to the reference video image whose skeleton ratio reaches a preset ratio threshold as the reference skeleton image when the background of each reference video image is the same. The skeleton ratio includes the size ratio of the human skeleton image of the reference video image to the reference video image.

[0023] The statistics subunit is used to count the number of reference skeletons that show a pattern when the comparison results of adjacent reference skeletons describe a pattern in a character's movements.

[0024] A sub-unit is defined to use fitness type as the video type of the projected video when the quantity meets a preset quantity threshold.

[0025] In some embodiments of this application, the startup module includes:

[0026] The push unit is used to push a confirmation button for starting the fitness guidance mode to the user on the terminal interface when the video type description of the screen-casting video is a fitness video.

[0027] The activation unit is used to activate the fitness guidance mode when the user triggers the activation confirmation button.

[0028] In some embodiments of this application, the interactive module includes:

[0029] The acquisition unit is used to acquire motion images formed by the user imitating the content of the projected video;

[0030] The playback unit is used to display the motion image on the terminal interface while the projected video is playing.

[0031] In some embodiments of this application, the device further includes a scoring unit, which includes:

[0032] The scoring subunit is used to score the user's fitness movements based on the deflection angle of the human skeleton in the projected video and the motion image, and to obtain the movement score result.

[0033] The display sub-unit is used to display the scoring results of the action on the terminal interface.

[0034] Thirdly, embodiments of this application also provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the above-described fitness interaction method.

[0035] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the above-described fitness interaction method.

[0036] This application embodiment displays a screen-projected video from a peer device on the terminal interface. The video type is determined based on its content. When the video type description indicates it's a fitness video, a fitness guidance module is activated, and the module interacts with the user based on the guidance mode. Since the fitness video displayed on the terminal interface is projected from the peer device, users can view different videos based on their needs, enriching the diversity of fitness videos and enhancing the fitness experience. The video type analysis based on the video content automatically identifies the video type, eliminating the need for identification or filtering on the peer device, reducing operational complexity and improving user experience. When the video is identified as a fitness video, activating the fitness guidance mode enables interactive fitness activities, providing a guided video environment and enhancing interactivity during the workout. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a schematic diagram of a fitness interaction method provided in an embodiment of this application;

[0039] Figure 2 This is a flowchart illustrating the fitness interaction method provided in the embodiments of this application;

[0040] Figure 3 This is a schematic diagram of the human skeleton provided in an embodiment of this application;

[0041] Figure 4 This is a flowchart illustrating the screen-projection-based fitness interaction method provided in an embodiment of this application.

[0042] Figure 5 This is a schematic diagram of a television interface provided in an embodiment of this application;

[0043] Figure 6 This is another schematic diagram of the television interface provided in the embodiments of this application;

[0044] Figure 7 This is a flowchart illustrating the process of determining the video type based on the video content, provided in an embodiment of this application.

[0045] Figure 8 This is a schematic diagram of the process for scoring user actions provided in an embodiment of this application;

[0046] Figure 9 This is a schematic diagram of the structure of the fitness interactive device provided in the embodiments of this application;

[0047] Figure 10 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0048] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] This application provides a fitness interaction method, device, electronic device, and computer-readable storage medium. Specifically, this application provides a fitness interaction device suitable for electronic devices, wherein the electronic device includes a terminal device or a server. The terminal device can be a computer, a television, or a mobile phone, etc. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The server can be directly or indirectly connected via wired or wireless communication.

[0050] Please see Figure 1 Taking the execution of a fitness interaction method on a terminal device as an example, the specific execution process of the fitness interaction method is as follows:

[0051] Terminal device 10 receives a video projected by a user through terminal device 11 and displays the video on the terminal interface of terminal device 10. Terminal device 10 analyzes the video type of the video based on its content and, if the video type description indicates that the video is a fitness video, it activates a fitness guidance mode in terminal device 10 and interacts with the user based on the fitness guidance mode.

[0052] This application embodiment displays a screen-projected video from a peer device on the terminal interface. The video type is determined based on its content. When the video type description indicates it's a fitness video, a fitness guidance module is activated, and the module interacts with the user based on the guidance mode. Since the fitness video displayed on the terminal interface is projected from the peer device, users can view different videos based on their needs, enriching the diversity of fitness videos and enhancing the fitness experience. The video type analysis based on the video content automatically identifies the video type, eliminating the need for identification or filtering on the peer device, reducing operational complexity and improving user experience. When the video is identified as a fitness video, activating the fitness guidance mode enables interactive fitness activities, providing a guided video environment and enhancing interactivity during the workout.

[0053] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the priority of the embodiments.

[0054] Please see Figure 2 , Figure 2 This is a flowchart illustrating the fitness interaction method provided in an embodiment of this application. The specific flow of the fitness interaction method can be as follows:

[0055] 101. Display the screen-cast video that the user has projected from the other end device on the terminal interface.

[0056] In this embodiment, the terminal interface is used to display the video screen during the playback of the projected video, and the display of the video screen is used to assist the user in fitness activities. Therefore, in this embodiment, the terminal interface includes a screen interface with a large screen, and the terminal corresponding to the terminal interface may include a television, a projector, or a computer device with a large electronic screen.

[0057] In this embodiment, the peer device is used to select a video to be projected and send the video to the local device, which then displays the video on the terminal interface of the local device. In this embodiment, the peer device may include an electronic device such as a mobile phone, computer, or tablet.

[0058] In this embodiment of the application, the video to be cast is a video selected by the user on the peer device and sent to the local device. The peer device and the local device can cast the corresponding video through a casting protocol, and the cast video can be played on the local device.

[0059] Among them, after displaying or playing the screen-cast video from the other end device, the terminal interface of the local device enriches the number or types of videos on the local device, allowing users to play different video data according to different needs. For example, users can cast fitness videos that are not available on the local device to the terminal interface of the local device to enrich the diversity of fitness videos and improve the fitness experience.

[0060] In this embodiment of the application, the user can select different videos on the peer device for screen casting based on different video playback needs. That is, optionally, in some embodiments of this application, the step "displaying the screen-cast video cast by the user through the peer device on the terminal interface" includes:

[0061] Receive a screen-cast video sent by a user through a peer device, wherein the screen-cast video is selected by the user locally on the peer device;

[0062] The projected video is displayed on the local terminal interface.

[0063] This allows users to select a video to cast on the other device, send the video to their local device, and display the video on the local device's interface. This enriches the diversity of video casting options. For example, users can select any video on the other device to cast and play, so that the videos played on the local device's interface are no longer limited to the local videos on the local device.

[0064] In this embodiment of the application, video can be sent and played between devices based on a screen mirroring protocol.

[0065] 102. Determine the video type of the screen-casting video based on its content.

[0066] The content of the cast video can determine its type, which in turn helps determine whether to enable the fitness guidance mode.

[0067] In this embodiment, the content of the projected video can be analyzed using a deep learning model to identify the video type. Optionally, in this embodiment, the step "determining the video type of the projected video based on its content" includes:

[0068] Based on the timing of several video images in the projected video, select several video images from the several video images as reference video images;

[0069] Based on several reference video images, the video type of the projected video is determined by a motion recognition model.

[0070] In this embodiment of the application, the action recognition mode is pre-trained based on sample data. The action recognition model can analyze video images, extract key points of people in the video images, analyze whether the user's action is a fitness action based on the key points, and then analyze whether the projected video is a fitness type video.

[0071] In this method, by selecting several reference video images from the projected video, the computational load of the action recognition model is reduced compared to inputting all video images from the projected video into the action recognition model. For example, the first few frames of video images are selected from the projected video as reference video images, and the type of the projected video is determined by analyzing the first few frames of reference video images.

[0072] In this embodiment, the motion recognition model analyzes each reference video image to obtain the background and skeletal diagram of the person corresponding to each reference video image. Therefore, the type of the projected video can be determined based on the background and skeletal diagram of each reference image. Optionally, in some embodiments of this application, the step "determining the video type of the projected video based on the several reference video images using the motion recognition model" includes:

[0073] Each reference video image is input into the action recognition model to obtain the background and skeletal diagram of the character corresponding to each reference video image.

[0074] When the background of each reference video image is the same, the human skeleton image corresponding to the reference video image in which the proportion of bones in a plurality of reference video images reaches a preset proportion threshold is used as the reference skeleton image. The proportion of bones includes the size ratio of the human skeleton image of the reference video image to the reference video image.

[0075] When the comparison results of sequentially adjacent reference skeletons describe a regularity in character movements, the number of reference skeletons with such regularity is counted.

[0076] When the quantity meets the preset quantity threshold, the fitness type will be used as the video type of the projected video.

[0077] In this embodiment of the application, the background of the image is the scene corresponding to the area in the video image other than the people. The outline of the people in the video image is obtained by the action recognition model, and the background of the video image can be obtained by removing the outline of the people.

[0078] In this embodiment of the application, the human skeleton diagram includes the human skeleton; please refer to [link / reference needed]. Figure 3 , Figure 3 This is a schematic diagram of the human skeleton provided in an embodiment of this application, wherein the skeleton diagram contains key points A of each joint of the human body.

[0079] When the background of each video image is the same, it means that the scene of the video image is fixed and matches the scene background of the fitness video. For example, fitness videos mainly demonstrate fitness movements in a specific environment, such as in a gym, and the fitness movements are filmed from basically fixed camera positions. Therefore, the background of fitness videos is basically the same.

[0080] Since the main content of fitness videos is the movement of people, the video images should mainly contain the human skeleton. Therefore, when the proportion of human skeleton in the video image is within a preset threshold (such as 1 / 4), it indicates that the video mainly contains human movement scenes, which meets the characteristics of fitness videos.

[0081] In this process, multiple skeletal diagrams that meet the characteristics of fitness videos are selected and analyzed to determine whether the skeletal movements have certain patterns. When the movement changes of multiple skeletal diagrams have certain patterns, it indicates that the video images meet the characteristics of fitness videos.

[0082] When multiple conditions, such as a consistent background, a proportion of the skeleton in the video image within a preset threshold, and a certain regularity in the changes of the skeleton, meet the characteristics of a fitness video, then the video being cast can be identified as a fitness video, meaning the video type of the video being cast is fitness.

[0083] 103. When the video type description indicates that the projected video is a fitness video, the fitness guidance mode is activated.

[0084] When the video to be projected is determined to be a fitness video, the fitness guidance mode can be enabled, allowing users to perform fitness activities based on the projected video.

[0085] In this embodiment, when the projected video is determined to be a fitness video, a fitness mode start button can be pushed onto the terminal interface to start the fitness mode based on the user's selection. Optionally, in this embodiment, the step "starting the fitness guidance mode when the video type describes the projected video as a fitness video" includes:

[0086] When the video type description indicates that the screen-casting video is a fitness video, a confirmation button for starting the fitness guidance mode is pushed to the user on the terminal interface.

[0087] When the user triggers the start confirmation button, the fitness guidance mode is activated.

[0088] In this embodiment of the application, the start confirmation button is a confirmation prompt button for the fitness guidance mode. After the user triggers the start confirmation button, the fitness guidance mode can be started.

[0089] 104. Interact with the user during fitness activities according to the fitness guidance mode.

[0090] Among them, the fitness guidance mode provides users with a fitness environment, and the fitness guidance mode interacts with users during fitness, which enhances the user experience during the fitness process.

[0091] In this embodiment, the user's fitness movements can be displayed on the terminal interface, creating a simultaneous comparison of the projected video and the user's fitness movements, thus enabling interaction with the user during fitness activities. Specifically, in some embodiments of this application, the step "interacting with the user according to the fitness guidance mode" includes:

[0092] Collect motion images formed by the user imitating the content of the projected video;

[0093] While the projected video is playing, the motion graphics are displayed on the terminal interface.

[0094] This involves capturing user motion images and displaying them on the terminal interface, allowing the terminal interface to both play projected videos and display user motion images, thus creating a side-by-side comparison between the projected video and the user's motion images.

[0095] Among them, the simultaneous comparison of projected videos and user motion images makes it easier for users to adjust their fitness movements based on the comparison results, assisting users in exercising and improving fitness effects and experience.

[0096] In this embodiment of the application, a small window can be set in the terminal interface to display the user's motion image, forming a picture-in-picture interface of the motion image in the projected video.

[0097] In this embodiment of the application, by collecting user motion images in real time, the user motion images can be displayed in real time on the terminal interface, forming a real-time motion comparison effect.

[0098] In some embodiments of this application, the user's actions can be scored based on the projected video and the user's motion image to provide feedback on the standardization of the actions. Specifically, in some embodiments of this application, after the step "displaying the motion image on the terminal interface while the projected video is playing," the method further includes:

[0099] The user's fitness movements are scored based on the deflection angle of the human skeleton in the projected video and the motion image, resulting in a motion score.

[0100] The scoring results of the action are displayed on the terminal interface.

[0101] By comparing projected videos and motion images, the standard of a user's movements can be determined. Furthermore, a scoring system can quantify the standard of a user's movements, allowing users to promptly perceive their own fitness progress.

[0102] This application embodiment displays a screen-projected video from a peer device on the terminal interface. The video type is determined based on its content. When the video type description indicates it's a fitness video, a fitness guidance module is activated, and the module interacts with the user based on the guidance mode. Since the fitness video displayed on the terminal interface is projected from the peer device, users can view different videos based on their needs, enriching the diversity of fitness videos and enhancing the fitness experience. The video type analysis based on the video content automatically identifies the video type, eliminating the need for identification or filtering on the peer device, reducing operational complexity and improving user experience. When the video is identified as a fitness video, activating the fitness guidance mode enables interactive fitness activities, providing a guided video environment and enhancing interactivity during the workout.

[0103] Please see Figure 4 , Figure 4 This is a flowchart illustrating a screen-casting-based fitness interaction method provided in an embodiment of this application. The specific steps of this screen-casting-based fitness interaction method include:

[0104] 201. Users cast their mobile phones to the TV screen;

[0105] 202. After receiving the screen mirroring request from the mobile phone, the TV plays the corresponding screen mirroring video on the TV interface;

[0106] 203. The TV system detects the content of the cast video and determines the type of cast video based on its content;

[0107] 204. When the video type is fitness, proceed to step 205; otherwise, when the video type is not fitness, return to step 203.

[0108] 205. A pop-up window appears on the TV asking whether to enable smart fitness;

[0109] 206. Determine if the user has enabled smart fitness. If so, proceed to step 207.

[0110] 207. Start the camera and display the local image in the small window in the lower right corner of the terminal interface;

[0111] 208. Detect the skeletal diagrams of the main characters in the projected screen and the main characters in the local screen;

[0112] 209. Compare the main character skeletons in the projected screen and the local screen, detect differences, and score user actions;

[0113] 210. Display user action scores based on digital effects on the terminal interface.

[0114] The process involves repeatedly executing steps 207-209 until the projected video finishes playing or the user finishes exercising.

[0115] This feature enriches the diversity of video content on TV by allowing users to cast videos from their mobile phones onto the TV screen. By analyzing the cast videos, and specifically activating smart fitness features when they are identified as fitness videos, a workout environment is provided. Through comparative analysis of human skeletal diagrams, a score is generated for each user's movements, allowing them to assess the accuracy of their form and enhancing their workout experience. Furthermore, the user's workout movements and score are displayed on the TV screen, enabling interactive participation and improving the user experience.

[0116] Please see Figure 5 , Figure 5 This is a schematic diagram of a television interface provided in an embodiment of this application. A camera a is provided at the top of the television for capturing the user's fitness movements and forming a video of the movements. A small window c is provided in the lower right corner of the television screen b for displaying the user's video of the movements, forming a comparison between the projected video and the user's video of the movements. The small window c is set in the television screen to form a picture-in-picture, which makes it easy for the user to compare the execution of the two movements and adjust their own movements in time to help the user exercise.

[0117] Please see Figure 6 , Figure 6 This is another schematic diagram of the television interface provided in this application embodiment. A camera a is positioned at the top of the television for capturing the user's fitness movements and forming a video feed. A small window c is positioned in the lower right corner of the television screen b, displaying the user's movement video and allowing for comparison between the projected video and the user's movement video. The small window c within the television screen creates a picture-in-picture effect, facilitating comparison of the two movements and allowing the user to adjust their movements accordingly, thus aiding in fitness. The television interface also includes a scoring display control d, which displays the user's movement score on the television screen, allowing the user to perceive their progress through the score.

[0118] Please see Figure 7 , Figure 7 This is a flowchart illustrating the process of determining a video type based on video content, provided in an embodiment of this application. Specifically, the process of determining a video type based on video content includes:

[0119] 211. Obtain a single frame of video image currently displayed on the TV screen;

[0120] 212. Detect whether the video scene is fixed. If the video scene is fixed, proceed to step 213; otherwise, if the video scene is not fixed, proceed to step 219.

[0121] 213. Obtain the skeletal diagrams of all figures in the video images;

[0122] 214. Determine if there is a human skeleton that occupies more than a quarter of the entire video image. If so, proceed to step 215; otherwise, proceed to step 219.

[0123] 215. Save the skeletal diagram;

[0124] 216. Compare with the previous skeletal diagram to see if there are regular movements of the hands and feet. If yes, proceed to step 217; otherwise, proceed to step 219.

[0125] 217. Record the number of times the condition is met, and determine whether the number of times the condition is met has reached the set threshold. If it has, proceed to step 218; otherwise, return to step 211.

[0126] 218. Use fitness-related content as the type of video to be projected.

[0127] 219. Use non-fitness-related videos as the type of video to be projected.

[0128] Fitness videos typically possess several characteristics, such as consistent backgrounds for the people in the video, a large proportion of the human body in the video image, and certain patterns in the transformation of hands and feet. Therefore, in this embodiment of the application, videos that satisfy the above multiple characteristics are identified as fitness videos, while videos that do not satisfy any of the characteristics are identified as non-fitness videos.

[0129] In this embodiment of the application, both the human skeleton diagram and the background of the video image can be identified using an action recognition model.

[0130] Please see Figure 8 , Figure 8 This is a schematic diagram of a process for scoring user actions provided in an embodiment of this application. The process for scoring user actions specifically includes:

[0131] 221. Obtain the skeletal diagram of the screen in the projected video and the skeletal diagram of the person in the local screen at the same time;

[0132] 222. Calculate the angular differences between the points on the trunk skeleton;

[0133] 223. When the angular difference of the trunk skeletal points is less than 10 degrees, the score is 30 points; when the angular difference of the trunk skeletal points is between 10 and 20 degrees, the score is 20 points; when the angular difference of the trunk skeletal points is greater than 20 degrees, the score is 10 points.

[0134] 224. Using the kneecap as the vertex, calculate and compare the angle between the vertex and the ankle, and the angle between the vertex and the root of the thigh. If the angle difference is within 10 degrees, each is scored 20 points. If the angle difference exceeds 10 degrees, each is scored 10 points.

[0135] 225. Using the elbow as the apex, calculate and compare the angle between the apex and the palm, and between the apex and the shoulder. If the difference in the angle is within 20 degrees, each will be scored 20 points. If the difference in the angle exceeds 20 degrees, each will be scored 10 points.

[0136] 226. The scores of each comparison document are summed and statistically analyzed to obtain the final score;

[0137] 227. Display the final score output on the terminal interface.

[0138] By comparing the projected screen and the local screen at the same time, and accumulating the scores for each key position, an overall score for the user's actions can be obtained, thus scoring the user's fitness movements. When this score is fed back to the TV interface, the user can intuitively understand the completion status of their movements based on the score, thereby improving the user experience.

[0139] To facilitate better implementation of the fitness interaction method of this application, this application also provides a fitness interaction device based on the above-described fitness interaction method. The meaning of the third target term is the same as in the above-described fitness interaction method; specific implementation details can be found in the description of the method embodiments.

[0140] Please see Figure 9 , Figure 9 This is a schematic diagram of the structure of the fitness interactive device provided in the embodiments of this application, wherein the fitness interactive device may include:

[0141] Display module 301 is used to display the screen-cast video that the user casts through the peer device on the terminal interface;

[0142] The determining module 302 is used to determine the video type of the projected video based on the content of the projected video;

[0143] The startup module 303 is used to start the fitness guidance mode when the video type description of the screen-casting video is a fitness video.

[0144] The interactive module 304 is used to interact with the user during fitness activities according to the fitness guidance mode.

[0145] In some embodiments of this application, the display module 301 includes:

[0146] The receiving unit is used to receive the screen-casting video sent by the user through the peer device, wherein the screen-casting video is selected by the user locally on the peer device;

[0147] The display unit is used to display the projected video on the local terminal interface.

[0148] In some embodiments of this application, the determining module 302 includes:

[0149] The selection unit is used to select several video images from the several video images in the projected video as reference video images according to the timing of the several video images in the projected video.

[0150] The determining unit is used to determine the video type of the projected video based on a plurality of the reference video images by means of a motion recognition model.

[0151] In some embodiments of this application, the determining unit includes:

[0152] The input subunit is used to input each reference video image into the action recognition model to obtain the background and human skeleton diagram corresponding to each reference video image.

[0153] The filtering subunit is used to select the human skeleton image corresponding to the reference video image whose skeleton ratio reaches a preset ratio threshold as the reference skeleton image when the background of each reference video image is the same. The skeleton ratio includes the size ratio of the human skeleton image of the reference video image to the reference video image.

[0154] The statistics subunit is used to count the number of reference skeletons that show a pattern when the comparison results of adjacent reference skeletons describe a pattern in a character's movements.

[0155] A sub-unit is defined to use fitness type as the video type of the projected video when the quantity meets a preset quantity threshold.

[0156] In some embodiments of this application, the startup module 303 includes:

[0157] The push unit is used to push a confirmation button for starting the fitness guidance mode to the user on the terminal interface when the video type description of the screen-casting video is a fitness video.

[0158] The activation unit is used to activate the fitness guidance mode when the user triggers the activation confirmation button.

[0159] In some embodiments of this application, the interactive module 304 includes:

[0160] The acquisition unit is used to acquire motion images formed by the user imitating the content of the projected video;

[0161] The playback unit is used to display the motion image on the terminal interface while the projected video is playing.

[0162] In some embodiments of this application, the device further includes a scoring unit, which includes:

[0163] The scoring subunit is used to score the user's fitness movements based on the deflection angle of the human skeleton in the projected video and the motion image, and to obtain the movement score result.

[0164] The display sub-unit is used to display the scoring results of the action on the terminal interface.

[0165] In this embodiment, the display module 301 displays the screen-projected video sent by the user through the peer device on the terminal interface. Then, the determination module 302 determines the video type of the screen-projected video based on its content. Subsequently, when the video type describes the screen-projected video as a fitness video, the startup module 303 starts the fitness guidance mode. Then, the interaction module 304 interacts with the user in fitness mode according to the fitness guidance mode.

[0166] This application embodiment displays a screen-projected video from a peer device on the terminal interface. The video type is determined based on its content. When the video type description indicates it's a fitness video, a fitness guidance module is activated, and the module interacts with the user based on the guidance mode. Since the fitness video displayed on the terminal interface is projected from the peer device, users can view different videos based on their needs, enriching the diversity of fitness videos and enhancing the fitness experience. The video type analysis based on the video content automatically identifies the video type, eliminating the need for identification or filtering on the peer device, reducing operational complexity and improving user experience. When the video is identified as a fitness video, activating the fitness guidance mode enables interactive fitness activities, providing a guided video environment and enhancing interactivity during the workout.

[0167] In addition, this application also provides an electronic device, such as Figure 10 As shown, it illustrates the structural diagram of the electronic device involved in this application, specifically:

[0168] The electronic device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 10 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0169] The processor 401 is the control center of the electronic device, connecting various parts of the device via various interfaces and lines. It executes various functions and processes data by running or executing software programs and / or modules stored in the memory 402, and by calling data stored in the memory 402. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 401.

[0170] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0171] The electronic device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0172] The electronic device may also include an input unit 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to object settings and function control.

[0173] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the electronic device loads the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 runs the applications stored in the memory 402, thereby implementing the steps in any of the fitness interaction methods provided in this application.

[0174] This application embodiment displays a screen-projected video from a peer device on the terminal interface. The video type is determined based on its content. When the video type description indicates it's a fitness video, a fitness guidance module is activated, and the module interacts with the user based on the guidance mode. Since the fitness video displayed on the terminal interface is projected from the peer device, users can view different videos based on their needs, enriching the diversity of fitness videos and enhancing the fitness experience. The video type analysis based on the video content automatically identifies the video type, eliminating the need for identification or filtering on the peer device, reducing operational complexity and improving user experience. When the video is identified as fitness-related, activating the fitness guidance mode enables interactive fitness activities, providing a guided video environment and enhancing interactivity during the workout.

[0175] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0176] Therefore, this application provides a computer-readable storage medium storing a computer program that can be loaded by a processor to perform the steps in any of the fitness interaction methods provided in this application.

[0177] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0178] Since the instructions stored in the computer-readable storage medium can execute the steps of any of the fitness interaction methods provided in this application, the beneficial effects that any of the fitness interaction methods provided in this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0179] The above provides a detailed description of a fitness interactive method, device, electronic device, and computer-readable storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A fitness interactive method, characterized in that, include: Display the screen-cast video from the user's device on the terminal interface; The video type of the projected video is determined based on its content; When the video type description indicates that the projected video is a fitness video, the fitness guidance mode is activated. The fitness guidance mode is used to interact with the user during fitness activities. Determining the video type of the projected video based on its content includes: Based on the timing of several video images in the projected video, select several video images from the several video images as reference video images; Based on several reference video images, the video type of the projected video is determined by an action recognition model.

2. The method according to claim 1, characterized in that, Displaying the screen-projected video from the user's device on the terminal interface includes: Receive a screen-cast video sent by a user through a peer device, wherein the screen-cast video is selected by the user locally on the peer device; The projected video is displayed on the local terminal interface.

3. The method according to claim 1, characterized in that, The step of determining the video type of the projected video based on a plurality of reference video images using an action recognition model includes: Each reference video image is input into the action recognition model to obtain the background and skeletal diagram of the character corresponding to each reference video image. When the background of each reference video image is the same, the human skeleton image corresponding to the reference video image in which the proportion of bones in a plurality of reference video images reaches a preset proportion threshold is used as the reference skeleton image. The proportion of bones includes the size ratio of the human skeleton image of the reference video image to the reference video image. When the comparison results of sequentially adjacent reference skeletons describe a regularity in character movements, the number of reference skeletons with such regularity is counted. When the quantity meets the preset quantity threshold, the fitness type will be used as the video type of the projected video.

4. The method according to claim 1, characterized in that, When the video type description indicates that the projected video is a fitness video, the fitness guidance mode is activated, including: When the video type description indicates that the screen-casting video is a fitness video, a confirmation button for starting the fitness guidance mode is pushed to the user on the terminal interface. When the user triggers the start confirmation button, the fitness guidance mode is activated.

5. The method according to claim 1, characterized in that, The fitness interaction with the user based on the fitness guidance mode includes: Collect motion images formed by the user imitating the content of the projected video; While the projected video is playing, the motion graphics are displayed on the terminal interface.

6. The method according to claim 5, characterized in that, The method further includes displaying the motion graphics on the terminal interface while the projected video is playing. The user's fitness movements are scored based on the deflection angle of the human skeleton in the projected video and the motion image, resulting in a motion score. The scoring results of the action are displayed on the terminal interface.

7. A fitness interactive device, characterized in that, include: The display module is used to display the screen-cast video that the user has projected from the other end device on the terminal interface; The determining module is used to determine the video type of the projected video based on its content. The startup module is used to start the fitness guidance mode when the video type description of the screen-casting video is a fitness video. An interactive module is used to interact with the user during fitness activities based on the fitness guidance mode. Determining the video type of the projected video based on its content includes: Based on the timing of several video images in the projected video, select several video images from the several video images as reference video images; Based on several reference video images, the video type of the projected video is determined by an action recognition model.

8. An electronic device, characterized in that, The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the fitness interaction method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the fitness interaction method as described in any one of claims 1-6.

Images