Online feedback method and device for exercise training and medium
By deploying edge devices on user terminals to compare and provide feedback on exercise data, the problem of lack of professional guidance in home fitness and rehabilitation training for middle-aged and elderly people has been solved. This has enabled low-latency, real-time online teaching, improving training effectiveness and safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GEER TECH CO LTD
- Filing Date
- 2025-12-29
- Publication Date
- 2026-05-01
AI Technical Summary
When middle-aged and elderly people engage in scientific fitness or post-illness rehabilitation training at home, they often lack real-time guidance from professional coaches or doctors, leading to deviations in movement, poor training results, or muscle and joint injuries. Furthermore, the uneven distribution of professional resources makes it difficult to obtain face-to-face guidance.
By deploying edge devices on user terminals, motion data is acquired and compared with standard movements to generate teaching feedback content that guides movement adjustments in the form of animation, voice, or illustrations. Edge networks are used to reduce latency, enabling low-latency online teaching.
Real-time motion correction can be achieved without professional guidance, reducing latency, ensuring training effectiveness, avoiding privacy risks, and improving training efficiency and user experience.
Smart Images
Figure CN121964053A_ABST
Abstract
Description
Online feedback methods, equipment and media for sports training Technical Field
[0001] This application relates to the field of online sports training service technology, and more specifically, to an online feedback method, device and medium for sports training. Background Technology
[0002] In recent years, with the increasing aging of the population, the demand for scientific fitness and home-based rehabilitation among middle-aged and elderly people has continued to grow. At the same time, more and more people tend to choose professional, precise, and personalized fitness programs or post-illness rehabilitation training.
[0003] However, personalized fitness programs or post-illness rehabilitation training often require extremely high levels of precision in movement, necessitating real-time observation and guidance from professional coaches or doctors to prevent ineffective training or even secondary injuries to muscles and joints due to incorrect form. However, professional fitness coaches and rehabilitation physicians are unevenly distributed both in terms of time and geography, exhibiting significant scarcity. Many individuals in need find it difficult to consistently receive face-to-face professional guidance due to factors such as living far from professional institutions, conflicting work schedules, or mobility issues.
[0004] Therefore, a training method capable of real-time motion correction in a remote environment is urgently needed. Summary of the Invention
[0005] One objective of this application is to provide an online feedback scheme for exercise training with low latency.
[0006] According to a first aspect of this application, an embodiment of an online feedback method for sports training is provided. The method is implemented by a sports training client running on a user terminal. The method includes: acquiring first sports data generated by a user performing sports training; sending the first sports data to a target edge device for instructional feedback processing, wherein the target edge device is deployed in an edge network domain on the user terminal access side; receiving first instructional feedback content returned by the target edge device through the instructional feedback processing, wherein the first instructional feedback content is generated by comparing a first user action with a standard action corresponding to the first user action, the first user action being reconstructed based on the first sports data, and the first instructional feedback content guiding the user to adjust from the first user action to the standard action using at least one of animation, voice, text, and illustration; and outputting the first instructional feedback content.
[0007] Optionally, before sending the first motion data to the target edge device, the method further includes: initiating a first edge service query request to a network facility deployed in the edge network domain, wherein the first edge service query request carries location identification information indicating the network location of the user terminal; receiving first edge service information returned by the network facility based on the first edge service query, wherein the first edge service information includes a network address of a first edge device adapted to the user terminal, the first edge device being determined based on the network location of the user terminal, and network information and status information of edge devices in the edge device list; and setting the first edge device as the target edge device.
[0008] Optionally, the location identification information carried in the first edge service query is the subnet information of the user terminal, and the network facility determines the network location of the user terminal based on the subnet information.
[0009] Optionally, after setting the first edge device as the target edge device, the method further includes: initiating a second edge service query request to the network facility when the first edge device cannot continuously provide teaching feedback processing; receiving second edge service information returned by the network facility based on the second edge service query request; wherein the second edge service information includes a network address of a second edge device adapted to the user terminal; and updating the target edge device to the second edge device.
[0010] Optionally, the first teaching feedback content includes an animated demonstration, which uses a virtual character as the subject of action execution, renders a continuous sequence of actions from the first user action to the standard action, and marks the target area for the standard action training on the virtual character.
[0011] Optionally, after outputting the first teaching feedback content, the method further includes: acquiring second motion data of the user performing motion training based on the first teaching feedback content; sending the second motion data to the target edge device for teaching feedback processing; receiving the second teaching feedback content returned by the target edge device through the teaching feedback processing; wherein, if the second user action is closer to the standard action than the first user action, the second teaching feedback content further includes positive incentive content, and the second user action is reconstructed based on the second motion data; and outputting the second teaching feedback content.
[0012] According to a second aspect of this application, another embodiment of an online feedback method for sports training is provided. The method is implemented by a sports training server running on an edge device, comprising: receiving first sports data generated by a user performing sports training, sent by a user terminal, wherein the edge device is deployed in an edge network domain on the access side of the user terminal; reconstructing a first user action based on the first sports data; comparing the first user action with a standard action corresponding to the first user action, generating first instructional feedback content, wherein the first instructional feedback content guides the user to adjust from the first user action to the standard action using at least one of animation, voice, text, and illustration; and sending the first instructional feedback content to the user terminal for display and output.
[0013] Optionally, after receiving the first motion data generated by the user performing exercise training sent by the user terminal, the method further includes: sending the first motion data to a remote server for updating and storing the user's training records.
[0014] According to a third aspect of this application, an electronic device is also provided, including a memory and a processor, the memory being used to store computer programs or instructions, and the processor being used to execute the method according to any one of the first or second aspects under the control of the computer programs or instructions.
[0015] According to a third aspect of this application, a computer-readable storage medium is also provided, having a computer program stored thereon that, when executed by a processor, implements the method according to any one of the first or second aspects.
[0016] This application provides an online feedback method for sports training, implemented by a client running on a user terminal. The method includes: acquiring first sports data generated by a user performing sports training; sending the first sports data to a target edge device for instructional feedback processing, wherein the target edge device is deployed in the edge network domain on the access side of the user terminal; receiving first instructional feedback content returned by the target edge device through instructional feedback processing, wherein the first instructional feedback content is generated by comparing a first user action with a standard action corresponding to the first user action, the first user action being reconstructed based on the first sports data, and the first instructional feedback content guiding the user to adjust from the first user action to the standard action using at least one of animation, voice, text, and illustration; and outputting the first instructional feedback content. This method eliminates the need for professional coaches or doctors, allowing users to receive guidance during sports training, thus achieving a closed-loop instructional process. Furthermore, this method can quickly output the first instructional feedback content, has low latency, meets the real-time requirements of online instruction, and does not pose a risk of user privacy leakage.
[0017] The features and advantages of the embodiments of this specification will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description
[0018] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments of this specification and, together with their description, serve to explain the principles of these embodiments.
[0019] Figure 1 is a schematic diagram of the composition structure of a sports training system that can apply the online training method of the present application according to an embodiment of the present application; Figure 2 is a schematic flowchart of an online feedback method for sports training according to an embodiment of the present application; Figure 3 is a schematic flowchart of a target edge device according to an embodiment of the present application; Figure 4 is a schematic flowchart of an online feedback method for sports training according to an embodiment of the present application; Figure 5 is a schematic diagram of the structure of an online feedback device for sports training according to an embodiment of the present application; Figure 6 is a schematic diagram of the structure of an online feedback device for sports training according to an embodiment of the present application; Figure 7 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Detailed Implementation
[0020] Various exemplary embodiments of this specification will now be described in detail with reference to the accompanying drawings.
[0021] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the embodiments of this specification or their application or use.
[0022] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.
[0023] It should be noted that all actions involving the acquisition of signals, information, or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where the application is located, and with the authorization granted by the owner of the relevant equipment.
[0024] This application relates to an online teaching scheme for user exercise training. This scheme is implemented based on edge devices deployed on the user terminal access side, featuring low latency and meeting the real-time requirements of online teaching, thus achieving a closed-loop teaching mechanism. Figure 1 illustrates an exercise training system 100, which can use the online feedback method of this application embodiment to provide online teaching of user exercise training behavior. As shown in Figure 1, the exercise training system 100 includes a user terminal 110, network facilities 130 deployed on the user terminal access side, edge devices 120 deployed on the user terminal access side, and a remote server 140.
[0025] In the sports training system 100, a client application for sports training runs on the user terminal 110. This client application can be a local application, a lightweight application, or a mini-program. The service provider of the sports training application presents various services to the user through the client application, thereby providing services to the user.
[0026] Edge device 120 can be a server or other device with computing capabilities, and it can be deployed on nodes of a Content Delivery Network (CDN). Because CDN nodes are globally deployed, once the server-side program of a sports training application is uploaded to the edge device of a CDN node, it can be deployed online within the target area. Implementing the online feedback method of this application embodiment through edge device 120 enables service provision based on user location proximity, improving business performance.
[0027] User terminal 110 communicates with edge device 120 through network infrastructure 130. The network infrastructure is, for example, a 5G core network infrastructure. This network infrastructure 130 includes, for example, Domain Name System (DNS), Session Management Function (SMF) network elements, User Plane Function (UPF) network elements, Network Repository Function (NRF) network elements, etc. Among them, SMF is used for session management with user terminal 110, DNS is used to match edge devices for user terminal 110, NRF is used to obtain a list of currently available edge devices and the real-time status of edge devices for DNS to match edge devices, and UPF is used to execute the traffic splitting rules issued by SMF and monitor the status of edge devices, etc.
[0028] User terminal 110 is, for example, a mobile phone, augmented reality (AR) glasses, or other terminal devices.
[0029] As shown in Figure 1, the user terminal 110 may include a processor 1101, a memory 1102, an interface device 1103, a communication device 1104, an output device 1105, an input device 1106, etc.
[0030] The processor 1101 executes computer programs, which can be written using instruction sets of architectures such as x86, Arm, RISC, MIPS, and SSE. The memory 1102 includes, for example, ROM (Read-Only Memory), RAM (Random Access Memory), and non-volatile memory such as a hard disk. The interface device 1103 includes, for example, a USB interface and a headphone jack. The communication device 1104 is capable of wired or wireless communication, and may include, for example, any module for 2G / 3G / 4G / 5G communication. The output device 1105 includes, for example, an LCD screen, a touch screen, and a speaker. The input device 1106 includes, for example, a touch screen and a microphone.
[0031] In this embodiment, the memory 1102 of the user terminal 110 is used to store a computer program, which is used to control the processor 1101 to operate, so as to control the user terminal 110 to execute the online feedback method according to the embodiment of this application.
[0032] Edge device 120 runs a server and may also include a processor and memory. The processor executes a computer program, which may be written using an instruction set based on architectures such as JavaScript or WebAssembly. The memory includes, for example, ROM (Read-Only Memory), RAM (Random Access Memory), and non-volatile memory such as a hard disk. The memory of edge device 120 stores the computer program, which controls its processor to operate and execute the online feedback method according to embodiments of this application. In the case where the user terminal is AR glasses, the server may be a holographic coaching service (Edge Application Server, EAS).
[0033] The remote server 140 can communicate with the edge device 120 and the user terminal 110. The remote server 140 can receive user motion data sent by the edge device 120 and / or the user terminal 110, and generate and store user training records based on the user motion data.
[0034] The following uses the sports training system shown in Figure 1 as an example to illustrate various embodiments of online feedback in sports training.
[0035] This application provides an online feedback method for sports training, which is implemented by a client running on a user terminal. As shown in FIG2, the online feedback method for sports training provided by this application includes the following steps S2100 to S2400.
[0036] Step S2100: Obtain the first motion data generated by the user performing exercise training.
[0037] Users can perform exercise training independently or under the guidance of exercise training videos played on the client. During exercise training, initial motion data is generated and collected by the user's terminal's camera and / or sensors.
[0038] The first motion data can be motion data at a single point in time or multiple motion data points within a time period. The first motion data includes motion behavior data and / or physiological state data. Motion behavior data may include motion video data and / or limb posture data, while physiological state data may include at least one data point that reflects the impact of exercise on the body, such as heart rate, electromyography signals, or respiratory rate.
[0039] It is understandable that, since the user generates the first motion data while performing exercise training, the first motion data can reflect the first user action performed by the user while performing exercise training.
[0040] Step S2200: Send the first motion data to the target edge device for teaching feedback processing.
[0041] The target edge devices are deployed in the edge network domain on the user terminal access side.
[0042] After acquiring the first motion data, the client sends it to a target edge device deployed in the edge network domain on the user terminal access side. The target edge device then processes the first motion data for instructional feedback. Compared to processing the first motion data for instructional feedback in a central cloud, this significantly reduces the data transmission distance. Therefore, the target edge device can receive the first motion data earlier, allowing for earlier instructional feedback processing to generate the first instructional feedback content. Furthermore, the target edge device can return the first instructional feedback content to the client earlier, enabling the client to receive it sooner. In other words, the online feedback method for motion training provided in this application features low latency and can meet the real-time requirements of online teaching.
[0043] Furthermore, as an edge device, the target edge device is characterized by its ability to keep data locally and to destroy sensitive data locally during processing. Based on this, after acquiring the first motion data sent by the user terminal and processing its instructional feedback, the target edge device will destroy sensitive user data related to privacy within the first motion data. This avoids the risk of privacy leaks caused by the transmission of sensitive user data over the public internet.
[0044] Regarding step S2200 above, the online feedback method for exercise training provided in this application further includes a step of determining the target edge device before step S2200. In one embodiment of this application, the step of determining the target edge device specifically includes the following steps S2210 to S2230.
[0045] Step S2210: Initiate a first edge service query request to the network settings deployed in the edge network domain.
[0046] The first edge service query request carries location identifier information indicating the network location of the user terminal.
[0047] In this embodiment, the term "network infrastructure" refers to all network elements used to enable communication between the user terminal and the edge device. Network infrastructure includes DNS servers, DNS resolvers, SMF, UPF, NRF, etc., in the 5G core network.
[0048] The first edge service query request is used to request the network facility to allocate an available edge device in the edge network domain deployed on the user terminal's access side.
[0049] Step S2220: Receive the first edge service information returned by the network facility based on the first edge service query.
[0050] The first edge service information includes the network address of the first edge device adapted to the user terminal, the network location of the first edge device based on the user terminal, and the network information and status information of the edge devices in the edge device list.
[0051] Step S2230: Set the first edge device as the target edge device.
[0052] In one embodiment of this application, as shown in Figure 3, the user terminal first initiates a Protocol Data Unit (PDU) session establishment request to the SMF. This PDU session establishment request carries the server's data network name and network slice selection auxiliary information. The network slice selection auxiliary information describes the characteristics of the target edge device. Further, after receiving the PDU session establishment request, the SMF pushes DNS configuration information to the user terminal. The DNS configuration information includes: the DNS server address, DNS security information, and edge computing-specific parameters to ensure that subsequent DNS queries can be intelligently routed. After receiving the DNS configuration pushed by the SMF, the user terminal sends a first edge service query request to the corresponding DNS (usually the one geographically closest to the user's current network access point). Upon receiving the first edge service query request, the DNS determines the user terminal's network location based on the location identifier information (e.g., the user terminal's IP address) carried in the first edge service query request. Furthermore, based on the user terminal's network location, combined with the list of currently available edge devices obtained by the NRF and the real-time status of the edge devices, the DNS selects the optimal first edge device from the available edge devices using, for example, a weighted scoring method, and returns its IP address as the first edge service information to the user terminal. Simultaneously, the SMF generates a corresponding user plane control policy and distributes it to the UPF responsible for forwarding the user's data. Upon receiving the user plane control policy, the UPF immediately configures a traffic splitting rule. This rule ensures that all data traffic belonging to this client is identified and directed to the edge device designated by the SMF, without needing to detour to the central cloud. When the user terminal obtains the IP address of the first edge device, it identifies the first edge device corresponding to that IP address as the target edge device. Further, the user terminal establishes a connection with the target edge device based on its IP address.
[0053] In one embodiment of this application, the location identifier information carried by the first edge service query is the subnet information of the user terminal, and the network facility determines the network location of the user terminal based on the subnet information. In this embodiment, the subnet information of the user terminal, rather than the complete IP address, is used as the network location of the user terminal. In this way, by "blurring the terminal identity + limiting the granularity of location", the privacy risks caused by the leakage of the complete address can be avoided while meeting the requirement of the nearest matching of edge nodes.
[0054] Corresponding to step S2200 above, this application also provides an online feedback method for motion training implemented by a server running on an edge device, as shown in Figure 4, which includes the following steps S4100 to S4400.
[0055] Step S4100: Receive the first motion data generated by the user performing exercise training, sent by the user terminal.
[0056] Among them, edge devices are deployed in the edge network domain on the user terminal access side.
[0057] Step S4200: Reconstruct the first user action based on the first motion data.
[0058] In one embodiment of this application, after receiving the first motion data, the edge device uses a pre-trained deep learning model to predict the positions of key feature points (such as head, shoulder, elbow, wrist, knee, hand, and ankle) of the user's actions reflected in the first motion data, thereby obtaining the positions of the key feature points. Further, a 3D or 2D human body model is rendered based on the positions of the key feature points, and this human body model is used to describe the user's first user action.
[0059] Of course, other methods can also be used to implement the above step S4200, and this application does not limit this.
[0060] Step S4300: Compare the first user action with the standard action corresponding to the first user action to generate the first teaching feedback content.
[0061] The first teaching feedback content uses at least one of the following methods of expression: animation, voice, text, and illustrations, to guide the user to adjust their first user action to the standard action.
[0062] In one embodiment of this application, the edge device stores a standard action library. After reconstructing a first user action, the edge device searches the standard action library for a standard action that matches the first user action based on the characteristics of the first user action, and uses this standard action as the corresponding standard action for the first user action.
[0063] In another embodiment of this application, the edge device stores a standard action library. When the user terminal sends first motion data to the edge device, it also sends an identifier of the guided exercise corresponding to the exercise training video played by the client. Upon receiving the identifier of the guided exercise, the edge device searches the standard action library for a standard action that matches the identifier of the guided exercise, using it as the standard action corresponding to the first user's action.
[0064] After obtaining the standard action of the first user's action, it is compared with the standard action to determine whether the first user's action meets the standard action. If not, an adjustment method is generated for the first user's action as the first teaching feedback content. This adjustment method may include at least one of the following: animation demonstration, voice, text, and illustrations related to slightly bending the legs and tightening the core. Conversely, if the first user's action meets the standard action, encouraging content can be generated and sent to the user's terminal.
[0065] Step S4400: Send the first teaching feedback content to the user terminal for display and output.
[0066] Corresponding to step S4400 above, the client performs the following step S2300.
[0067] Step S2300: Receive the first teaching feedback content returned by the target edge device through the teaching feedback processing.
[0068] The first teaching feedback content is generated by comparing the first user's action with the standard action corresponding to the first user's action. The first user's action is reconstructed based on the first motion data. The first teaching feedback content guides the user to adjust from the first user's action to the standard action through at least one of the following expression methods: animation, voice, text, and illustration.
[0069] After receiving the first teaching feedback content returned by the target edge device through the teaching feedback processing, the user terminal executes the following step S2400.
[0070] Step S2400: Output the first teaching feedback content.
[0071] In one embodiment of this application, the first teaching feedback content includes an animated demonstration. The animation uses a virtual character as the subject of the action, rendering a continuous sequence of movements transforming from a first user action to a standard action, and marking the target area for standard action training on the virtual character. Based on this, after the user terminal outputs the first teaching feedback content, the user can see a more specific and dynamic adjustment method displayed by the virtual character, thereby quickly and effectively achieving the standard action and enhancing the immersion of the exercise training. Furthermore, marking the target area for standard action training on the virtual character helps the user understand the location trained by the standard action corresponding to their own movement. Specifically, the target area can be a muscle region.
[0072] When the user terminal is AR glasses and the first teaching feedback content is at least an animated demonstration, the AR glasses can overlay the first teaching feedback content onto the real environment.
[0073] After users view the initial instructional feedback through the client, they can understand how to adjust their movements to achieve the standard movements based on this feedback.
[0074] Based on the above steps S2100 to S2400, the online feedback method for sports training provided by this application does not require a professional coach or doctor, and users can receive precise guidance when performing sports training.
[0075] This application provides an online feedback method for sports training, implemented by a client running on a user terminal. The method includes: acquiring first sports data generated by a user performing sports training; sending the first sports data to a target edge device for instructional feedback processing, wherein the target edge device is deployed in the edge network domain on the user terminal access side; receiving first instructional feedback content returned by the target edge device through instructional feedback processing, wherein the first instructional feedback content is generated by comparing a first user action with a standard action corresponding to the first user action, the first user action is reconstructed based on the first sports data, and the first instructional feedback content guides the user to adjust from the first user action to the standard action using at least one of animation demonstration, voice, text, and illustration; and outputting the first instructional feedback content. This method does not require a professional coach or doctor, allowing users to receive guidance during sports training, thus achieving a closed-loop instructional process. Furthermore, this method can quickly output the first instructional feedback content, has low latency, meets the real-time requirements of online instruction, and does not pose a risk of user privacy leakage.
[0076] In one embodiment of this application, the online feedback method for exercise training provided in this application further includes steps S2500 to S2800 after step S2400 above.
[0077] Step S2500: Obtain second motion data of the user performing exercise training based on the first teaching feedback content.
[0078] After the user terminal outputs the first instructional feedback content, it adjusts its own movements based on the first instructional feedback content, at which point new first motion data is generated. In this embodiment, the motion data generated by the user's exercise training based on the first instructional feedback content is recorded as the second motion data.
[0079] Step S2600: Send the second motion data to the target edge device for teaching feedback processing.
[0080] It should be noted that the specific implementation of step S2600 is the same as that of step S2200, and will not be repeated here.
[0081] Step S2700: Receive the second teaching feedback content returned by the target edge device through the teaching feedback processing.
[0082] In cases where the second user's action is closer to the standard action than the first user's action, the second teaching feedback content also includes positive incentive content, and the second user's action is reconstructed based on the second motion data.
[0083] Corresponding to step S2600 above, after receiving the second motion data, the target edge device reconstructs the second user action based on the second motion data. Further, the second user action is compared with a standard action to generate an adjustment method for the second user action. Simultaneously, the second user action and the first user action are compared with the standard action to determine whether the second user action is closer to the standard action than the first user action. If so, positive incentive content is generated. The positive incentive content affirms the motion training corresponding to the user's second motion data through at least one of the following methods: animation, voice, text, and illustration, thereby enhancing the user's motivation for exercise. The target edge device sends the generated adjustment method for the second user action and the positive incentive content together as second teaching feedback content to the user terminal for display and output.
[0084] Of course, if it is determined that the second user action is not closer to the standard action than the first user action, then only the adjustment method for the second user action can be sent to the user terminal as the second teaching feedback content.
[0085] Step S2800: Output the second teaching feedback content.
[0086] Upon receiving the second set of instructional feedback, the user terminal outputs the second set of feedback. Based on this, the user can determine whether the adjustments made during the second round of exercise training are correct, thereby increasing their motivation for exercise training.
[0087] When the online feedback method for exercise training provided in this application is implemented by a server running on an edge device, the online feedback method for exercise training further includes the following step S4500 after the above step S4400.
[0088] Step S4500: Send the first motion data to the remote server to update and store the user's training records.
[0089] When the user terminal executes the online feedback method for exercise training provided in this application for the first time, the user terminal uploads the user's identification information to a remote server via a target edge device for recording. Subsequently, after receiving the first motion data sent by the user terminal, the target edge device associates the first motion data with the user's identification information. This enables the recording of the user's first motion data, completing the updating and storage of the user's training records.
[0090] Following step S2230, the target edge device may be unable to continuously provide instructional feedback. Therefore, the online feedback method for exercise training provided in this application further includes steps S2240 to S2260 after step S2230.
[0091] In step S2240, if the first edge device is unable to continuously provide teaching feedback processing, a second edge service query request is initiated to the network facility.
[0092] In this embodiment, when the user terminal crosses different "tracking zones" in the 5G network, it triggers a TAU report and sends the TAU report to the network infrastructure. Furthermore, the SMF in the network infrastructure, upon receiving the TAU report, monitoring the network quality between the user terminal and the first edge device via the UPF (User-Programmable Frame), detecting a network quality preset of the first edge device via the UPF, monitoring a fault in the first edge device via the UPF, and predicting the user terminal will leave the first edge device based on its movement trajectory, determines that the first edge device is not the optimal one at this time. In this case, it informs the user terminal that the first edge device cannot continuously provide teaching feedback processing. Based on this, as shown in Figure 3, the user terminal sends a second edge service query request to the network infrastructure to determine a new target edge device. Further, the user terminal migrates and connects to the second edge device. This achieves a seamless network switch for the user, improving the user experience.
[0093] Step S2250: Receive the second edge service information returned by the network facility based on the second edge service query request.
[0094] The second edge service information includes the network address of the second edge device adapted to the user terminal.
[0095] Step S2260: Update the target edge device to the second edge device.
[0096] It should be noted that the specific implementation of steps S2240 to 2260 can be referred to the specific implementation of steps S2210 to 2230, and will not be repeated here.
[0097] As shown in Figure 5, this application also provides an online feedback device 500 for sports training. This online feedback device 500 is applied to a user terminal and includes: a first acquisition module 510, used to acquire first sports data generated by a user performing sports training; a first sending module 520, used to send the first sports data to a target edge device for instructional feedback processing, wherein the target edge device is deployed in the edge network domain on the user terminal access side; a first receiving module 530, used to receive first instructional feedback content returned by the target edge device through instructional feedback processing, wherein the first instructional feedback content is generated by comparing a first user action with a standard action corresponding to the first user action, the first user action being reconstructed based on the first sports data, and the first instructional feedback content guiding the user to adjust from the first user action to the standard action using at least one of animation, voice, text, and illustration; and a first output module 540, used to output the first instructional feedback content.
[0098] In one embodiment of this application, an online feedback device 500 for sports training provided by this application further includes: a second sending module, configured to initiate a first edge service query request to a network facility deployed in the edge network domain, wherein the first edge service query request carries location identification information indicating the network location of the user terminal; a second receiving module, configured to receive first edge service information returned by the network facility based on the first edge service query, wherein the first edge service information includes a network address of a first edge device adapted to the user terminal, the first edge device being determined based on the network location of the user terminal, and network information and status information of edge devices in the edge device list; and a setting module, configured to set the first edge device as the target edge device.
[0099] In one embodiment of this application, the location identification information carried by the first edge service query is the subnet information of the user terminal, and the network facility determines the network location of the user terminal based on the subnet information.
[0100] In one embodiment of this application, an online feedback device 500 for sports training provided by this application further includes: a third sending module, configured to initiate a second edge service query request to the network facility when the first edge device cannot continuously provide teaching feedback processing; a third receiving module, configured to receive second edge service information returned by the network facility based on the second edge service query request; wherein the second edge service information includes a network address of a second edge device adapted to the user terminal; and an updating module, configured to update the target edge device to the second edge device.
[0101] In one embodiment of this application, the first teaching feedback content includes an animated demonstration, which uses a virtual character as the subject of action execution, renders a continuous sequence of actions that transforms from the first user action to the standard action, and marks the target area for the standard action training on the virtual character.
[0102] In one embodiment of this application, an online feedback device 500 for sports training provided by this application further includes: a second acquisition module, used to acquire second sports data of a user performing sports training based on the first teaching feedback content; a fourth sending module, used to send the second sports data to the target edge device for teaching feedback processing; a fourth receiving module, used to receive the second teaching feedback content returned by the target edge device through the teaching feedback processing; wherein, when the second user action is closer to the standard action than the first user action, the second teaching feedback content also includes positive incentive content, and the second user action is reconstructed based on the second sports data; and a second output module, used to output the second teaching feedback content.
[0103] As shown in Figure 6, this application also provides another online feedback device 600 for sports training. This online feedback device 600 for sports training is applied to a server and includes: a fifth receiving module 610, used to receive first sports data generated by a user performing sports training sent by a user terminal, wherein the edge device is deployed in the edge network domain on the access side of the user terminal; a reconstruction module 620, used to reconstruct a first user action based on the first sports data; a comparison module 630, used to compare the first user action with a standard action corresponding to the first user action and generate first teaching feedback content, wherein the first teaching feedback content guides the user to adjust from the first user action to the standard action using at least one of animation demonstration, voice, text and illustration; and a fifth sending module 640, used to send the first teaching feedback content to the user terminal for display output.
[0104] In one embodiment of this application, an online feedback device 600 for sports training provided in this application further includes: a sixth sending module, used to send the first sports data to a remote server for updating and storing user training records.
[0105] As shown in Figure 7, this application also provides an electronic device 700, which includes a memory 710 and a processor 720. The memory 710 is used to store computer programs or instructions. When the processor 720 is a user terminal, it is used to execute, under the control of the computer program or instructions, any of the methods described above implemented by a client running on the user terminal. When the processor 720 is an edge device, it is used to execute, under the control of the computer program or instructions, any of the methods described above implemented by a client running on the edge device.
[0106] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method according to any one of the above-described method embodiments.
[0107] This application also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements any of the memory management methods or compilation methods described in the foregoing embodiments of this application. Optionally, the computer-readable storage medium may be a non-transitory storage medium, but is not limited thereto; it may also be a temporary storage medium.
[0108] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.
[0109] This application may be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement any of the methods in the foregoing embodiments of this application.
[0110] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media may include, for example, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), compact disc-read-only memory (CD-ROM), digital versatile disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any combination thereof. The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.
[0111] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include one or more of copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to computer-readable storage media in the respective computing / processing device.
[0112] The computer program instructions used to perform the operations of this application may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object programs written in any combination of one or more programming languages. These programming languages may include object-oriented programming languages (e.g., Smalltalk, C++, etc.) and conventional procedural programming languages (e.g., the "C" language or similar programming languages). The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer may be connected to the user's computer via any type of network (e.g., a local area network or a wide area network), or it may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuits, such as programmable logic circuits, field-programmable gate arrays, or programmable logic arrays, are personalized using state information from the computer-readable program instructions. These electronic circuits can execute the computer-readable program instructions to implement various aspects of the embodiments of this application.
[0113] Various aspects of this application are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.
[0114] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.
[0115] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.
[0116] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. It should be noted that implementation in hardware, implementation in software, and implementation using a combination of software and hardware are all equivalent.
[0117] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of this application is defined by the appended claims.
Claims
1. An online feedback method for exercise training, characterized in that, Implemented by a client running on a user terminal, the method includes: acquiring first motion data generated by a user performing exercise training; sending the first motion data to a target edge device for instructional feedback processing, wherein the target edge device is deployed in the edge network domain on the access side of the user terminal; receiving first instructional feedback content returned by the target edge device through instructional feedback processing, wherein the first instructional feedback content is generated by comparing a first user action with a standard action corresponding to the first user action, the first user action being reconstructed based on the first motion data, and the first instructional feedback content guiding the user to adjust from the first user action to the standard action using at least one of animation, voice, text, and illustration; and outputting the first instructional feedback content.
2. The method according to claim 1, characterized in that, Before sending the first motion data to the target edge device, the method further includes: initiating a first edge service query request to a network facility deployed in the edge network domain, wherein the first edge service query request carries location identification information indicating the network location of the user terminal; receiving first edge service information returned by the network facility based on the first edge service query, wherein the first edge service information includes a network address of a first edge device adapted to the user terminal, the first edge device being determined based on the network location of the user terminal, and network information and status information of edge devices in the edge device list; and setting the first edge device as the target edge device.
3. The method according to claim 2, characterized in that, The location identifier information carried in the first edge service query is the subnet information of the user terminal, and the network facility determines the network location of the user terminal based on the subnet information.
4. The method according to claim 2, characterized in that, After setting the first edge device as the target edge device, the method further includes: initiating a second edge service query request to the network facility when the first edge device cannot continuously provide teaching feedback processing; receiving second edge service information returned by the network facility based on the second edge service query request, wherein the second edge service information includes a network address of a second edge device adapted to the user terminal; and updating the target edge device to the second edge device.
5. The method according to claim 1, characterized in that, The first teaching feedback content includes an animated demonstration, which uses a virtual character as the subject of action execution, renders a continuous sequence of actions that transforms from the first user action to the standard action, and marks the target area for the standard action training on the virtual character.
6. The method according to any one of claims 1 to 5, characterized in that, After outputting the first teaching feedback content, the method further includes: acquiring second motion data of the user performing motion training based on the first teaching feedback content; sending the second motion data to the target edge device for teaching feedback processing; receiving the second teaching feedback content returned by the target edge device through the teaching feedback processing; wherein, if the second user action is closer to the standard action than the first user action, the second teaching feedback content also includes positive incentive content, and the second user action is reconstructed based on the second motion data; and outputting the second teaching feedback content.
7. An online feedback method for exercise training, characterized in that, Implemented by a server running on an edge device, the method includes: receiving first motion data generated by a user performing exercise training sent by a user terminal, wherein the edge device is deployed in an edge network domain on the access side of the user terminal; reconstructing a first user action based on the first motion data; comparing the first user action with a standard action corresponding to the first user action, generating first teaching feedback content, wherein the first teaching feedback content guides the user to adjust from the first user action to the standard action using at least one of animation, voice, text, and illustration; and sending the first teaching feedback content to the user terminal for display and output.
8. The method according to claim 7, characterized in that, After receiving the first motion data generated by the user performing exercise training sent by the user terminal, the method further includes: sending the first motion data to a remote server for updating and storing the user training records.
9. An electronic device, characterized in that, It includes a memory and a processor, the memory being used to store computer programs or instructions, and the processor being used to execute the method according to any one of claims 1 to 8 under the control of the computer programs or instructions.
10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method according to any one of claims 1-8.