Fitness course recommendation method and device based on artificial intelligence

Abstract

The invention discloses a fitness course recommendation method and device based on artificial intelligence, and relates to the field of fitness sports, and the method comprises the steps: generating fitness video course recommendation information for a user according to a user model; according to a course metadata tag in the course recommendation information, finding a fitness video course matched with the metadata tag in a course video material library; receiving the fitness video course; acquiring an action video of fitness performed by the user according to the fitness video; the action video of the user is processed to obtain action information, the action information is display information of a virtual image of the user, and the motion posture of the user is prompted according to the standard action in the fitness course and the action video of the user.

Description

Technical Field

[0001] The present invention relates to the field of sports and fitness, and in particular to a fitness course recommendation method and device based on artificial intelligence. Background Art

[0002] More and more users are exercising with smart fitness equipment. Some smart fitness equipment will arrange courses according to user settings. The user's physical condition and exercise time will inevitably change, making it impossible for the user to complete the preset course plan. In addition, the user's actual needs and basic conditions are different, and the current course arrangement is difficult to ensure that the different needs of different users are met. Summary of the invention

[0003] The purpose of the present invention is to provide a fitness course recommendation method and device based on artificial intelligence, dynamically adjust the user's course plan, and automatically match the corresponding course video according to the course plan, so as to meet the different needs of different users in a personalized manner. According to one aspect of the present application, a fitness course recommendation method based on artificial intelligence is provided, characterized in that the method comprises:

[0004] Collecting user data, and establishing a user model for the user based on the collected data;

[0005] Generating fitness video course recommendation information for the user according to the user model;

[0006] According to the course metadata tag in the course recommendation information, a fitness video course matching the metadata tag is found in the course video material library; wherein the video course in the course video material library is accompanied by annotation information, and the annotation information is used to describe the content and characteristics of the fitness video course, and the annotation information includes at least one of the course title, description, type, subject, lecturer, duration and difficulty;

[0007] receiving the fitness video course;

[0008] Acquire an action video of the user performing fitness according to the fitness video;

[0009] Processing the action video of the user to obtain action information, wherein the action information is display information of the user's virtual image, and the action characteristics of the user's virtual image correspond to the action characteristics of the user;

[0010] The user's exercise posture is prompted based on the standard movements in the fitness course and the user's movement video.

[0011] In combination with the first aspect, in some implementations of the first aspect, status information of the user is received, the status information including at least one of information about the amount of exercise completed by the user, information about the available fitness time of the user, and physiological data information of the user;

[0012] The fitness video course recommendation information is updated according to the user's status information.

[0013] In combination with the first aspect, in certain implementations of the first aspect, receiving the status information of the user includes receiving motion information recorded by a wearable device of the user, and / or physiological data information of the user recorded by the wearable device.

[0014] In combination with the first aspect, in certain implementations of the first aspect, receiving the user's status information includes receiving information input by the user, wherein the information includes the user's desired exercise time and the user's description of his or her own physical condition.

[0015] In combination with the first aspect, in some implementations of the first aspect, the user model is updated according to user status information.

[0016] In combination with the first aspect, in certain implementations of the first aspect, the user is prompted to provide status information required for generating or updating the course recommendation information.

[0017] In combination with the first aspect, in some implementations of the first aspect, the user is prompted to provide feedback, the feedback including the user's feedback on the fitness course after completing the fitness video course,

[0018] Based on the feedback, update the user model and / or course recommendation information.

[0019] In a second aspect, a terminal device is provided, which can specifically execute each step in the above-mentioned first aspect and any possible implementation method thereof.

[0020] In a third aspect, a computer program product is provided, which includes: a computer program (also referred to as code, or instruction), which, when executed, enables a computer to execute the method in the first aspect and any possible implementation thereof.

[0021] In a fourth aspect, a computer-readable medium is provided, which stores a computer program (also referred to as code or instruction) which, when executed on a computer, enables the computer to execute the method in the first aspect and any possible implementation thereof.

[0022] In a fifth aspect, a smart fitness mirror is provided, comprising a display for displaying a user interface or an exercise interface; a mirror arranged in front of the display, the mirror being used to display the user's image on the mirror, and the display displaying the user interface to the user through the mirror; the smart fitness mirror is used to execute each step in the above-mentioned first aspect and any possible implementation method thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flowchart of a fitness course recommendation method based on artificial intelligence provided in an embodiment of the present application;

[0024] Figure 2 A schematic diagram of a terminal device provided in an embodiment of the present application;

[0025] Figure 3 A schematic diagram of another terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0027] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those within the scope of this description. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0028] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0029] The terminal device referred to in this application is not limited to any intelligent electronic product that can interact with the user (for example, through a touchpad), such as a smart phone, a tablet computer, etc. The mobile electronic product can use any operating system, such as an Android operating system, an iOS operating system, etc., or a dedicated fitness smart box, which is connected to an external display device by wired or wireless means; or a smart fitness mirror, a hardware terminal device with a camera and a display screen. The smart fitness mirror may include a processor that partially controls the operation of various subcomponents in the smart fitness mirror and manages the data flow (for example, video content, audio from the user, biometric feedback analysis) flowing into / out of the smart fitness mirror. The smart fitness mirror may include a display for displaying video content, a graphical user interface (GUI) with which the user can interact and control the smart fitness mirror, biometric feedback data and / or other visual content. The sensor may be coupled to the processor to collect user-related data. The antenna may be coupled to the processor to provide data transmission between the smart fitness mirror and another device (for example, a remote control device, a biometric sensor, a wireless router). The antenna may include multiple transmitters and receivers, each transmitter and receiver being customized for a specific frequency and / or wireless standard (e.g., Bluetooth, 802.11a, 802.11b, 802.11g, 802.11n, 802.11ac, 2G, 3G, 4G, 4GLTE, 5G). The amplifier may be coupled to the processor to receive an audio signal from the processor so as to output subsequent sound through the left speaker and / or the right speaker. The network device includes an electronic device capable of automatically performing numerical calculations and information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, a dedicated integrated circuit, a programmable logic device, a field programmable gate array, a digital signal processor, an embedded device, etc. The network device includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets, or a cloud consisting of a plurality of servers; here, the cloud is composed of a large number of computers or network servers based on cloud computing, wherein cloud computing is a type of distributed computing, a virtual supercomputer consisting of a group of loosely coupled computer sets. The network includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, VPN network, wireless ad hoc network, etc. Preferably, the device can also be a program running on the user device, network device, or a device formed by integrating the user device and network device, network device, touch terminal, or network device and touch terminal through a network. Other display devices in this application include but are not limited to televisions, projectors, independent displays, computer display screens, other fitness devices with displays, smart virtual reality glasses, and other smart electronic products.

[0030] According to one aspect of the present application, reference Figure 1 , provides a motion interaction method based on an intelligent device, the method comprising:

[0031] The present invention relates to a fitness course recommendation method based on artificial intelligence, and the specific implementation methods are as follows:

[0032] S101: Collect user data. Collect the user's personal information, such as age, gender, height, weight, exercise preference, exercise goal, exercise ability, etc., in order to build a personal model for the user. The collection method may include: user input, third-party platform authorization consent, etc. Some information can also be obtained through behavioral data analysis during user use, such as finding out the preferred course type, exercise habits, etc. through records.

[0033] In addition, in one embodiment, the user's physical fitness can be tested by a smart fitness device, a test video is played to the user, and the user completes the action according to the video, and the user's action is recognized by the camera, or the user's wearable device collects biological data (such as heart rate, blood oxygen, blood pressure, etc.), and the completion of the action performed by the user according to the test video is evaluated to obtain the user's athletic ability data. S102: Establish a user model. Establish a personal model for the user based on the collected user data. The user model can be implemented based on existing artificial intelligence technologies, such as machine learning, deep learning, etc. Among them, establishing a model can include:

[0034] Data preprocessing: Preprocess the collected user data, such as data cleaning and data normalization, to facilitate subsequent model training and analysis.

[0035] Feature extraction: Extract meaningful features for building user models based on user needs and goals. These features may include the user's physiological indicators (such as heart rate, blood pressure, etc.), exercise preferences, exercise effects, etc.

[0036] Choose the right AI algorithm: Based on the collected data and features, choose the right AI algorithm, such as machine learning, deep learning, etc., to build a user model. You can try different algorithms to find the most suitable model.

[0037] Training model: Use the collected data and features to train the model using the selected AI algorithm. During the training process, relevant parameters need to be adjusted to optimize the performance of the model.

[0038] Evaluate the model: Evaluate the accuracy and generalization ability of the model by comparing the model prediction results with the actual data. If necessary, the model can be iteratively optimized to further improve performance.

[0039] Application model: Apply the trained user model to smart fitness equipment to provide users with more personalized fitness plans and suggestions. The model can be updated in real time based on the user's exercise data to keep the model up to date. When users generate new behavior data, this data should be included in the analysis and the user portrait should be updated in real time or regularly. In addition, when collecting user feedback to continuously optimize the recommendation system, the update of the user model also plays a key role.

[0040] Through the above steps, a personalized user model is established for users of smart fitness equipment. This will help provide more accurate fitness plans and suggestions, thereby improving users' exercise effects and satisfaction.

[0041] S103: Generate fitness video course recommendation information. Generate fitness video course recommendation information for the user based on the user model. The recommendation information may include: course classification, instructor, duration, difficulty, etc. The following steps may be included:

[0042] Determine user goals: Based on the information in the user model, clarify the user's fitness goals, such as improving physical fitness, losing weight, gaining muscle, and rehabilitation.

[0043] Analyze user capabilities: Analyze the user's exercise level, health status, physical fitness, etc. based on the historical data collected in the user model, so as to develop a suitable fitness plan for the user.

[0044] Choose the right exercise class: Choose the right exercise class for the user based on their goals and abilities. Class types can include strength training, aerobics, yoga, dance, etc.

[0045] Set course progress: Set the appropriate course difficulty and progress for users based on their goals and abilities. For example, beginners may need to start with lower intensity exercises and gradually increase difficulty and intensity.

[0046] Schedule classes: Schedule fitness classes at appropriate times for users based on their available time, habits, and preferences. For example, exercising in the morning may be more helpful for improving work efficiency, while exercising in the evening can help relieve the stress of the day.

[0047] Set up a program cycle: Plan the program cycle, such as how many times a week to schedule exercise, how long each phase should take. Proper rest and recovery time should also be taken into account to ensure that users avoid overtraining.

[0048] Monitor and adjust courses: Based on the user's performance and feedback in actual exercise, the course plan is tracked in real time and the course is adjusted as needed. For example, if the user performs well in a course, you can try to increase the difficulty or change the course; if the user encounters difficulties in a course, you can appropriately reduce the difficulty or change to another course.

[0049] Plan long-term goals: Plan users' long-term fitness goals while meeting their short-term goals. This can help users maintain positive exercise habits and continue to challenge higher goals after achieving one goal.

[0050] Through the above steps, personalized course recommendation information is generated based on the user model created for fitness users. This helps to improve the user's fitness effect and satisfaction, and create a fitness experience that better meets user needs.

[0051] S104: Filter in the course video material library. According to the generated course recommendation information, filter out fitness video courses that match the recommendation information from the course video material library. The video courses in the course video material library are accompanied by annotation information for describing the content and features of the fitness video courses. This information may include course title, description, type, subject, instructor, duration, and difficulty, etc. The following steps may be included:

[0052] Labeled video content: Label each video in the fitness video library and add relevant keywords or annotation information to each video. The annotation information includes at least one of the course title, description, type, subject, instructor, duration and difficulty; such as exercise type (strength, aerobic, yoga, etc.), exercise difficulty (beginner, intermediate, advanced), target population (fat loss, muscle gain, etc.), etc.

[0053] Set video filtering conditions: According to the fitness course plan generated by AI, set the corresponding video filtering conditions. For example, if the user's fitness goal is to lose fat, the filtering conditions can be set to sports videos of "fat loss"; if the user's sports ability is relatively elementary, the filtering conditions can be further set to videos of elementary difficulty.

[0054] Search for matching videos: Use the filter criteria to search in the fitness video library and obtain a list of videos that meet the criteria. Videos can be sorted according to priority, such as user preferences, popularity, ratings, etc.

[0055] Personalized recommendation: In the obtained matching video list, personalized content can be further recommended to users. For example, if the user likes the teaching style of a certain coach, the coach's video can be recommended first; if the user has watched a series of courses in the past, other course videos in the same series can be recommended.

[0056] Fitness plan and video association: Associate the user's courses in the fitness plan with the corresponding fitness videos so that the user can find appropriate videos for reference when doing the planned exercises.

[0057] User feedback and optimization: Encourage users to provide feedback on recommended fitness videos so as to continuously optimize the recommendation system. For example, users can evaluate the teaching quality and difficulty level of the video. Based on the collected feedback data, adjust and optimize the recommendation algorithm to provide users with matching fitness videos more accurately.

[0058] The fitness course plan selects matching fitness videos for users from the fitness video library, which helps to improve the effect and satisfaction of users' exercise.

[0059] S105: receiving the user's status information, updating the fitness course recommendation information according to the user's status information, and / or updating the user model. This step includes receiving the user's completed exercise information, the user's available fitness time information, and the user's physiological data information. This information can be obtained by synchronizing the exercise records of the wearable device, the user's active input, etc.

[0060] After a fitness plan using smart fitness equipment is formulated for the user, during the daily fitness course in the fitness plan, the user's original fitness course is no longer suitable for the user due to time reasons, physical condition reasons, or having done other exercises. The user feedbacks status information to the smart fitness device, and AI adjusts and determines a new fitness plan based on the user's feedback. The new fitness plan can be an adjustment of the fitness course of the day; it can also be an adjustment of a long-term fitness plan, such as the reason for the user's feedback indicating that the user has been unable to exercise according to the original plan for a period of time. The following steps may be included:

[0061] Receive user feedback: Design a user-friendly interface that allows users to input feedback on their daily fitness plans, including reasons for not doing the fitness classes originally scheduled for the day (time reasons, physical condition reasons, etc.) and desired plan adjustments. Users can also provide relevant information about fitness plan adjustments in the future, such as being unable to exercise as originally planned for some reason. In addition, users can also provide feedback on the course after the course ends, such as whether the intensity is too high or too low, whether they are interested in the type of exercise in the course, etc.

[0062] Fitness plan adjustment: Based on user feedback, the original fitness plan needs to be adjusted. This includes the following two situations:

[0063] a. Adjustment of the day's fitness plan: Based on user feedback, adjust the day's fitness classes, such as reducing the number of certain movements, lowering the difficulty, increasing rest time, or completely canceling the day's classes.

[0064] b. Adjustment of long-term fitness plan: If user feedback indicates that they are unable to exercise as originally planned within a period of time, the long-term fitness plan will be adjusted according to the user's needs, such as adjusting the frequency of fitness classes, arranging appropriate rest days, etc.

[0065] Update fitness plan: Update the adjusted fitness plan to the user's smart fitness device and notify the user of the adjustment information.

[0066] In addition, when users provide feedback on completed fitness video courses, the user feedback is analyzed to understand the types of courses, difficulty, coaching styles, etc. that users like and dislike. Among them, natural language processing technology can be used to analyze the text opinions provided by users and extract key information. Update the user model based on user feedback. For example, increase the user's preference for a certain type of course, reduce the demand for a certain difficulty, etc. In this process, incremental learning technology can be used to continuously optimize the user model as feedback increases. Based on the updated user model, re-sort and filter the available fitness video courses, and select courses that better meet user needs for recommendation. In this step, recommendation algorithms such as collaborative filtering and content-based recommendation can be used. The adjusted course recommendations are displayed to users, with changes made based on user feedback to improve user satisfaction and trust in the recommendation results.

[0067] User interaction and monitoring: When users implement new fitness plans, their feedback and exercise data are continuously collected to further optimize and adjust the plan. At the same time, interactive design is used to motivate users to maintain their exercise habits and improve their motivation and effectiveness.

[0068] Circular optimization process: The above steps constitute a closed-loop system, which optimizes the AI ​​algorithm through real-time feedback and exercise data from users, further improves the user model, and makes the adjustment of fitness plans more accurate and in line with user needs.

[0069] Through the steps, the interaction between the user and the smart fitness device can be realized, ensuring that the fitness plan can be adjusted according to the user's actual situation, thereby improving the exercise effect and satisfaction.

[0070] S106: Prompt the user's exercise posture according to the user's action information and the standard action of the fitness course. The user's action information is obtained by analyzing the action video of the user performing fitness according to the fitness video, and compared with the standard action of the fitness course, so as to give the user a correct exercise posture prompt.

[0071] Processing the action video of the user to obtain action information, wherein the action information is display information of the user's virtual image, and the action characteristics of the user's virtual image correspond to the action characteristics of the user;

[0072] Optionally, the collected image and video data may be preprocessed, such as scaling, rotating, cropping, etc., to facilitate subsequent processing.

[0073] Computer vision algorithms, such as keypoint detection and optical flow tracking, are used to extract features related to human movements from images.

[0074] In one embodiment, human skeleton points are detected for each image frame to obtain the coordinates of the skeleton points of the user in each image frame. The detected skeleton points may include multiple skeleton points of the following: top of the head, nose tip, left ear, right ear, chin, neck, left shoulder, right shoulder, left elbow, right elbow, left wrist, right wrist, left metacarpophalangeal joint, right metacarpophalangeal joint, left fingertips, right fingertips, left hip, right hip, left knee, right knee, left ankle, right ankle, left toe tip, right toe tip, left heel, right heel, etc.; the straight-line distance between the top skeleton point and the pelvic skeleton point is obtained, and the unit length of the coordinate system is obtained according to the straight-line distance; the straight-line distance between the top skeleton point and the pelvic skeleton point is obtained, and the straight-line distance is converted into One sixth of the distance is taken as the unit length of the coordinate system, that is, the size of the unit length 1 of the coordinate system is one sixth of the straight line distance; the straight line between the top bone point and the pelvic bone point is taken as the ordinate, the pelvic bone point is taken as the origin, and a rectangular coordinate system is constructed with the obtained unit length; the bone point coordinates in the second content are obtained by scaling the user's bone point coordinates in proportion, and a virtual image is obtained according to the bone point coordinates. The virtual image can be a stick figure with bone points, or a human body model with muscle shape. The virtual image is obtained by identifying and processing each frame of fitness action, and the order of the dynamic virtual image generated by the terminal device is determined according to the generation time of the bone point. Through this recognition technology, the user's movement posture can be scored or corrected; the user's actions can also be counted. In addition, optionally, the terminal device sends the data of the virtual image to a remote server or a terminal device of another user. The action information of the virtual image of the user's bone point obtained according to the video image can be called display information, and the dynamic display of the user's virtual image can be realized through the display information. In addition, the action video obtained may not be all videos after the fitness action is completed, and action acquisition and image processing can be performed in real time.

[0075] In another implementation, the trained motion recognition model can be deployed in a mobile phone application. The application reads the image data captured by the mobile phone camera in real time, performs motion recognition through the model, and displays the results in real time.

[0076] By identifying the user's movements, extracting the user's movement features, and comparing them with the movement features of the standard movements in the fitness video, the standardization of the user's movements can be determined. The user's movements are scored, and for irregular movements, prompts and corrections can be given to the user by displaying text, voice or images.

[0077] In addition, smart fitness devices can also collect user dietary information and provide dietary recommendations. The following technical steps can be used:

[0078] User dietary information collection: Design an easy-to-use user interface to allow users to input their dietary information, such as food types, intake, number of meals, etc. In addition, users can upload photos to the smart fitness device and use image recognition technology to automatically identify food types and portions.

[0079] Dietary data analysis: By analyzing the dietary information provided by the user, the calorie, protein, fat, carbohydrate and other nutritional intake of each food is calculated. The total calorie intake required by the user every day is calculated based on the user's exercise status, physical indicators (such as age, gender, weight, etc.) and fitness goals.

[0080] Recipe generation: Plan diets based on user dietary preferences, allergies, cultural background, and fitness plans. For example, on exercise days, users are advised to increase carbohydrate intake to support higher intensity exercise; on rest days, reduce calorie intake to avoid excess calories being converted into fat storage. Generate appropriate recipes for users to ensure balanced nutritional intake. Recipes should take into account user tastes and the availability of ingredients, and provide a variety of choices to stimulate user interest.

[0081] Dietary suggestions: The recipes and daily calorie intake generated for users are pushed to users to guide them to eat properly. At the same time, it can also provide dietary focus points, such as controlling sugar intake, increasing protein intake, etc.

[0082] Diet plan adjustment and optimization: Based on user feedback and actual diet as well as the user's actual amount of exercise or type of exercise that day, the smart fitness device continuously updates the diet recommendations to make them more in line with user needs.

[0083] Through these technical steps, smart fitness devices can provide users with personalized dietary recommendations based on their changing needs and goals, helping users better achieve their fitness goals.

[0084] Figure 2 2 is a schematic block diagram of a terminal device 200 provided in an embodiment of the present application. As shown in the figure, the terminal device 200 may include: a transceiver unit 210, a processing unit 220, and a video acquisition unit 230.

[0085] It should be understood that the terminal device 200 may correspond to the terminal device in the method according to the embodiment of the present application, and the various units in the terminal device 200 and the above-mentioned other operations and / or functions are the corresponding processes of the above-mentioned method embodiments.

[0086] Wherein, when the terminal device 200 is used to execute Figure 1 In method 100, the video acquisition unit 230 is used to acquire the user's action video, the transceiver unit 210 is used to receive the fitness video and send a request to the server to acquire the fitness video, as well as other steps involving the sending and receiving of data and / or information, and the processing unit 820 can be used to execute other steps in the method.

[0087] Figure 3 is a schematic block diagram of a terminal device 300 provided in an embodiment of the present application. Figure 3 As shown, the terminal device 300 includes: at least one processor 310 and a communication interface 320. The processor 310 is coupled to a memory and is used to execute instructions stored in the memory to control the communication interface 320 to send and / or receive information or video files, etc. Exemplarily, the terminal device 300 also includes a memory 330 for storing instructions.

[0088] It should be understood that the processor 310 and the memory 330 can be combined into one processing device, and the processor 310 is used to execute the program code stored in the memory 330 to implement the above functions. In specific implementation, the memory 330 can also be integrated into the processor 310, or independent of the processor 310.

[0089] An example of the terminal device 200 or the terminal device 300 can be a smart fitness mirror, which includes a communication interface for receiving a video image of a fitness coach, a display operably coupled to the communication interface to display the video image of the fitness coach, and a mirror arranged in front of the display to reflect the image of the person opposite to the display. The mirror has a reflection area portion to transmit the video image of the fitness coach to the person opposite to the display so that the video image of the fitness coach appears to be superimposed on a part of the image of the person. The reflection area portion can overlap with the display area, or at least cover the area of ​​the display. The reflection area in the embodiment of the present application can also be referred to as a partial reflection portion.

[0090] An example of an interactive fitness method includes the steps of: streaming fitness content to an interactive video system including a mirror having a partially reflective portion and a display disposed on one side of the partially reflective portion; displaying the fitness content to a user via the display and the partially reflective portion of the mirror; and reflecting an image of the user using the mirror so that the image of the user is at least partially superimposed on the fitness content displayed via the display and the partially reflective portion of the mirror.

[0091] An example of a method for using a smart fitness mirror includes the following steps: while displaying fitness content to a user on a video display behind a partially transmissive mirror: reflecting an image of the user using the partially transmissive mirror; measuring the user's heart rate using a heart rate monitor attached to the user; transmitting the heart rate from the heart rate monitor to an antenna operably coupled to the video display; displaying the user's heart rate on the video display; and displaying the user's target heart rate on the video display.

[0092] The interactive object is used to show the user the controls or operations that the user can perform, such as page switching, selection, pause / play of the course, etc. The interactive object can be an icon, text, highlight selection, other forms that can prompt the user to interact, or a combination thereof.

[0093] In addition, an embodiment of the present application provides a fitness system, which includes a remote server and a terminal device installed with an application program for executing the above method. The fitness system may further include terminal devices of other users. And the system may further include a display device for displaying a video screen to a user by means of screen projection using the display device.

[0094] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0095] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0096] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0097] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0098] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be an intelligent fitness mirror device, a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape) or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0099] The above embodiments may be implemented in a variety of ways. For example, the embodiments may be implemented using hardware, software, or a combination thereof. When implemented in software, the software code may be executed on a suitable processor or set of processors, whether provided in a single computer or distributed among multiple computers.

[0100] Furthermore, the computer may be embodied in any of a variety of forms, such as a rack-mounted computer, a desktop computer, a laptop computer, or a tablet computer. In addition, the computer may be embedded in a device not generally regarded as a computer but having suitable processing capabilities, including a personal digital assistant (PDA), a smart phone, or any other suitable portable or fixed electronic device.

[0101] In addition, the computer may have one or more input and output devices. Among other things, these devices may also be used to present a user interface. Examples of output devices that may be used to provide a user interface include a printer or display screen for visual presentation of the output and a speaker or other sound-generating device for audible presentation of the output. Examples of input devices that may be used for a user interface include a keyboard and a pointing device, such as a mouse, a touch pad, and a digitized tablet computer. As another example, a computer may receive input information through speech recognition or other audible formats.

[0102] Such computers may be interconnected in a suitable form through one or more networks, including local area networks or wide area networks, such as enterprise networks, intelligent networks (IN) or the Internet. Such networks may be based on suitable technologies, may operate according to suitable protocols, and may include wireless networks, wired networks or fiber optic networks.

[0103] The various methods or processes outlined herein may be encoded as software that can be executed on one or more processors using any of a variety of operating systems or platforms. In addition, such software may be written using any of a number of suitable programming languages ​​and / or programming or scripting tools, and may also be compiled into executable machine language code or intermediate code that is executed on a framework or virtual machine. Some embodiments may specifically employ one or more of a specific operating system or platform and a specific programming language and / or scripting tool to facilitate execution.

[0104] In the claims and the description above, all transitional phrases such as "includes," "comprising," "carrying," "having," "containing," "involving," "holding," "consisting of," etc. should be understood as open-ended, i.e., including but not limited to.

[0105] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A fitness course recommendation method based on artificial intelligence, characterized in that: The method comprises: Collecting user data, and establishing a user model for the user based on the collected data; Generating fitness video course recommendation information for the user according to the user model; According to the course metadata tag in the course recommendation information, a fitness video course matching the metadata tag is found in the course video material library; wherein the video course in the course video material library is accompanied by annotation information, and the annotation information is used to describe the content and characteristics of the fitness video course, and the annotation information includes at least one of the course title, description, type, subject, lecturer, duration and difficulty; receiving the fitness video course; Acquire an action video of the user performing fitness according to the fitness video; Processing the action video of the user to obtain action information, wherein the action information is display information of the user's virtual image, and the action characteristics of the user's virtual image correspond to the action characteristics of the user; The user's exercise posture is prompted based on the standard movements in the fitness course and the user's movement video.

2. The method according to claim 1, further comprising: receiving status information of the user, wherein the status information includes at least one of information about the amount of exercise completed by the user, information about the available fitness time of the user, and physiological data information of the user; The fitness video course recommendation information is updated according to the user's status information.

3. The method according to claim 2, further comprising: Receiving the status information of the user includes receiving motion information recorded by a wearable device of the user and / or physiological data information of the user recorded by the wearable device.

4. The method according to claim 2 or 3, further comprising: Receiving the user's status information includes receiving information input by the user, wherein the information includes the user's desired exercise time and the user's description of his or her own physical status.

5. The method according to any one of claims 2 to 4, further comprising: The user model is updated according to the user's status information.

6. The method according to any one of claims 1 to 5, further comprising: Providing dietary advice to the user based on the user's exercise information and / or status information.

7. The method according to any one of claims 1 to 6, further comprising: Prompts the user to provide status information required to generate or update course recommendation information.

8. The method according to any one of claims 1 to 7, further comprising: Prompting the user to provide feedback, wherein the feedback includes the user's feedback on the fitness course after completing the fitness video course, Based on the feedback, update the user model and / or course recommendation information.

9. A terminal device, characterized in that: The terminal device is used to execute the method according to any one of claims 1-8.

10. A smart fitness mirror, comprising a display for displaying a user interface or an exercise interface; a mirror disposed in front of the display, the mirror being used to display the image of the user on the mirror, and the display showing the user interface to the user through the mirror; The smart fitness mirror is used to execute any one of the methods described in claims 1-8.

Images