Cushion adjusting method and device of spinning and electronic equipment

Abstract

The invention discloses a method and a device for adjusting a cushion of a spinning and electronic equipment, and relates to the technical field of software and the field of sports science and technology. The method comprises the steps that under the condition that user authorization is obtained, user data of a user and riding exercise data when the user carries out riding training on the spinning bike according to a target course are obtained; a cushion of the spinning is adjusted to be in an initial state according to the user data; according to the course data of the target course and / or the riding motion data, in the process that the user uses the spinning bike to conduct riding training, the cushion in the initial state is adjusted. The technical problems that in the prior art, due to the fact that a unified cushion is generally provided for helping a user to conduct spinning riding training, the cushion cannot be adjusted in a personalized mode, the training quality and the training experience are affected, and even the training injury risk of the user is likely to be high are solved.

Description

Technical Field

[0001] The present application relates to the fields of software technology and sports technology, and in particular to a seat adjustment method, device and electronic equipment for a spinning bike. Background Art

[0002] Due to the advantages of high-efficiency fat burning and low injury brought by spinning bikes, they have become a common fitness equipment in gyms and homes. However, the design of spinning bikes is often very simple, and the hardware configurations such as seat height, seat cushion length and width are fixed, which makes it difficult to meet the needs of individual differences. However, when the seat cushion length and width do not match the leg length and hip width, it will affect the riding posture and easily cause leg muscle strain or hip pain.

[0003] It can be seen that since the prior art usually provides a unified seat cushion to help users perform spinning bike riding training, the seat cushion cannot be automatically adjusted to be personalized, which affects the training quality and training experience, and may even easily cause a high risk of training injuries to users.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a method, device and electronic device for adjusting the seat of a spinning bike, so as to at least solve the technical problem that a unified seat is usually provided in the prior art to help users perform spinning bike riding training, resulting in the seat being unable to be adjusted individually, thereby affecting the training quality and training experience, and even easily causing a high risk of training injury to users.

[0006] According to one aspect of an embodiment of the present application, a method for adjusting the seat of a spinning bike is provided, comprising: acquiring user data of a user and riding motion data of the user during riding training on a spinning bike according to a target course; adjusting the seat of the spinning bike to an initial state according to the user data; and adjusting the seat in the initial state according to the course data and / or riding motion data of the target course during riding training using the spinning bike by the user.

[0007] Optionally, during the process of the user using the spinning bike for cycling training, adjusting the seat cushion of the spinning bike includes: adjusting the seat cushion of the spinning bike by at least one of the following operations:

[0008] The first operation is used to adjust the hardness of the seat cushion by controlling the airbag built into the seat cushion;

[0009] The second operation is used to adjust the width of the seat cushion by controlling the motor to drive the support rod of the seat cushion to move relative to the slide rail;

[0010] The third operation is used to adjust the height of the seat cushion by controlling the height of the support rod of the seat cushion;

[0011] The fourth operation is used to adjust the relative distance between the seat and the handlebar of the spinning bike by controlling the inclination angle of the support rod of the seat and the position on the slide rail.

[0012] Optionally, adjusting the seat cushion of the spinning bike to an initial state according to the user data includes: extracting user portrait features of the user from the user data; inputting the user portrait features into a first model, and using the prior knowledge learned by the first model in a model training phase to determine initial seat cushion data according to the user portrait features, wherein the first model is a neural network model trained based on the user portrait features of a reference user and the seat cushion data selected by the reference user, and the initial seat cushion data is initialization seat cushion data set when the user starts riding; adjusting the seat cushion of the spinning bike to an initial state according to the initial seat cushion data.

[0013] Optionally, according to the course data of the target course, during the user's cycling training using the spinning bike, the seat cushion in an initial state is adjusted, including: extracting motion intensity characteristics from the course data, wherein the motion intensity characteristics are used to characterize the training intensity information of the training content of the target course; inputting the motion intensity characteristics into the second model, and using the prior knowledge learned by the second model in the model training stage to determine first cushion data of the seat cushion according to the motion intensity characteristics, wherein the model training data of the second model includes reference to the seat cushion data preferred by the user based on different training courses, and the first cushion data is the seat cushion data determined by the second model and having a degree of compatibility with the motion intensity characteristics higher than a preset threshold; and adjusting the seat cushion in the initial state to the first state according to the first cushion data.

[0014] Optionally, according to the cycling motion data, during the process of the user using the spinning bike for cycling training, the seat cushion in an initial state is adjusted, including: extracting cycling motion features from the cycling motion data, wherein the cycling motion features are used to characterize the actual training intensity of the user; inputting the cycling motion features into a third model, and using the prior knowledge learned by the third model in the model training stage to determine second cushion data of the seat cushion according to the cycling motion features, wherein the model training data of the third model includes cushion data preferred by reference users with different cycling motion features, and the second cushion data is cushion data determined by the third model and having a degree of compatibility with the cycling motion features higher than a preset threshold; and adjusting the seat cushion in the initial state to the second state according to the second cushion data.

[0015] Optionally, according to the course data and cycling motion data of the target course, during the user's cycling training using the spinning bike, the seat cushion in an initial state is adjusted, including: extracting motion intensity features from the course data, wherein the motion intensity features are used to characterize the training intensity information of the training content of the target course; extracting cycling motion features from the cycling motion data, wherein the cycling motion features are used to characterize the actual training intensity of the user; determining the difference between the actual training intensity of the user and the training intensity of the training content of the target course according to the motion intensity features and the cycling motion features; inputting the difference value into a fourth model, and determining correction data of the seat cushion according to the difference value using the prior knowledge learned by the fourth model in the model training stage, wherein the model training data of the fourth model includes: seat cushion data selected by reference users with different cycling motion features when they expect to achieve the motion intensity features required by the training course, wherein the correction data is used to reduce the difference value by adjusting the state of the seat cushion; and adjusting the seat cushion in the initial state to the target state according to the correction data.

[0016] Optionally, after obtaining the user data of the user and the riding motion data of the user during riding training on the spinning bike according to the target course, the method for adjusting the seat cushion of the spinning bike also includes: during the user's riding training, detecting the pressure value of each of N areas of the seat cushion, where N is an integer greater than 1; adjusting the seat cushion of the spinning bike during the user's riding training using the spinning bike according to the pressure value of each area, the user data, the course data of the target course and / or the riding motion data.

[0017] Optionally, after obtaining the user data of the user and the riding motion data of the user during riding training on the spinning bike according to the target course, the method for adjusting the seat of the spinning bike also includes: detecting the difference in pedaling frequency on both sides of the user during the user's riding training; adjusting the seat of the spinning bike during the user's riding training using the spinning bike according to the difference in pedaling frequency on both sides of the user, the user data, the course data of the target course and / or the riding motion data.

[0018] According to another aspect of the present application, a seat adjustment device for a spinning bike is also provided, including: an acquisition unit, used to acquire user data of a user and riding motion data of a user during riding training on a spinning bike according to a target course; a first adjustment unit, used to adjust the seat of the spinning bike to an initial state according to the user data; and a second adjustment unit, used to adjust the seat in the initial state according to the course data and / or riding motion data of the target course during riding training of the user using the spinning bike.

[0019] According to another aspect of the present application, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the above-mentioned spinning bike seat adjustment method.

[0020] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors execute the above-mentioned spinning bike seat adjustment method.

[0021] In this application, firstly, with the authorization of the user, the user data of the user and the riding motion data of the user during riding training on the spinning bike according to the target course are obtained, and then the seat cushion of the spinning bike is adjusted to the initial state according to the user data. Finally, according to the course data and / or riding motion data of the target course, the seat cushion in the initial state is adjusted during the riding training of the user using the spinning bike.

[0022] As can be seen from the above content, firstly, this application obtains and analyzes the user's individual data under the premise of user authorization. These data are crucial to understanding the user's physiological structure and sports preferences. At the same time, this application also collects the user's sports data when riding on a spinning bike according to a specific course, such as cadence, resistance, power, and heart rate, to comprehensively evaluate the user's sports state and needs. By integrating the user's static data (such as height and weight) and dynamic data (such as cadence and resistance during riding), the system can build a more personalized and accurate seat adjustment model. Secondly, based on the user data in the first step, the system can calculate the most suitable initial state of the seat. For example, for a male user with a larger weight, the system may recommend a wider and slightly harder seat to ensure uniform pressure distribution during riding and reduce the pressure on the lower body. On the contrary, for a female user with a lighter weight, a narrower and softer seat may be needed to adapt to her physiological structure while providing sufficient comfort. This initial state adjustment of the seat based on the individual characteristics of the user solves the problem that the traditional unified seat design cannot meet the needs of different users.

[0023] Finally, during cycling training, the system will dynamically adjust the cushion properties based on the target course's scheduling data (such as course intensity changes, duration, etc.) and the user's real-time cycling data. For example, during the high-intensity phase of the course, when the user's pedaling frequency and resistance increase, the system will automatically harden the cushion to provide better support and stability, reducing the loss of exercise efficiency and hip fatigue caused by excessive cushion softness; and during the low-intensity recovery phase, the cushion will soften to help users relieve fatigue and improve training comfort. This dynamic adjustment mechanism can respond to changes in user and course needs in real time, so that the cushion properties are dynamically matched to the cycling intensity, avoiding the reduction of training effects and potential sports injuries caused by mismatched cushion properties.

[0024] It can be seen that through the technical solution of the present application, the spinning bike system can realize the personalization and dynamic adjustment of the seat cushion, overcomes the limitations of the unified design of the seat cushion in the prior art, greatly improves the personalized experience, training quality and safety of the user's cycling training, avoids the common training injury problems in the traditional unified seat cushion design, and provides users with a more comfortable, efficient and safe spinning bike riding environment. It solves the technical problem that the prior art usually provides a unified seat cushion to help users perform spinning bike riding training, which makes the seat cushion unable to be personalized, thereby affecting the training quality and training experience, and even easily causes a high risk of training injuries to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0026] Figure 1 is a flow chart of an optional method for adjusting the seat cushion of a spinning bike according to an embodiment of the present application;

[0027] Figure 2 is a flow chart of an optional seat cushion adjustment process according to an embodiment of the present application;

[0028] Figure 3 is a schematic diagram of an optional seat cushion adjustment process according to an embodiment of the present application;

[0029] Figure 4 It is a schematic diagram of an optional seat adjustment device for a spinning bike according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] It should also be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0033] According to an embodiment of the present application, an embodiment of a method for adjusting the seat of a spinning bike is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] Figure 1 is a flow chart of an optional method for adjusting the seat cushion of a spinning bike according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0035] Step S101, with the authorization of the user, obtaining the user data of the user and the riding motion data of the user during riding training on a spinning bike according to a target course.

[0036] Optionally, a spinning bike control system (hereinafter referred to as the system) can serve as the executor of the spinning bike seat adjustment method of the embodiment of the present application, wherein, in addition to the spinning bike control system, other forms of devices, systems or equipment can also serve as the executor of the method embodiment of the present application. It can be understood by those skilled in the art that the present application does not specifically limit the specific form of expression of the executor.

[0037] Optionally, user data refers to data related to the user's personal identity, health status, preferences, etc. In the context of this application, user data includes but is not limited to information such as the user's height, weight, gender, age, health record, etc. User data is the basis for the initial personalized adjustment of the cushion. Through this information, the system can preliminarily determine the user's basic requirements for the width and softness of the cushion, and ensure that the state of the cushion before riding matches the user's physical characteristics. For example, heavier users may need a wider cushion with more padding to disperse pressure, while female users may need to take into account differences in physiological structure and adjust the shape of the cushion appropriately to improve comfort.

[0038] Optionally, the target course is a specific exercise plan or course selected by the user on the spinning bike, which typically includes information such as the type of course (such as endurance, aerobic, strength, etc.), intensity, duration, etc. The target course data is critical for dynamically adjusting the properties of the saddle. Different course intensities and types have different requirements for saddle properties. For example, in high-impedance, high-cadence courses, the saddle needs to provide adequate support, while in low-impedance, low-cadence leisure courses, the saddle needs to be softer to improve comfort. The target course data helps the system understand the type of exercise the user will perform, so as to pre-set the optimal properties of the saddle to suit the upcoming training.

[0039] Optionally, cycling motion data refers to the motion data generated by the user during cycling training on a spinning bike, including indicators such as cadence, resistance, power, heart rate, etc. Cycling motion data provides a real-time basis for dynamic adjustment of the seat cushion. The system can monitor the user's exercise intensity and body reaction during cycling, and adjust the hardness and width of the seat cushion in real time based on these data to match the current exercise state. For example, when the user's cadence and power rise to high intensity, the seat cushion will automatically become harder to provide better support; while in the low-intensity recovery stage, the seat cushion will become softer to help users relieve fatigue and reduce the possibility of sports injuries.

[0040] Step S102: adjusting the seat cushion of the spinning bike to an initial state according to the user data.

[0041] Optionally, when a user uses a spinning bike for the first time or each time they get on the bike for a new cycling training, the system will automatically adjust the seat cushion to a state that is preset to best suit the user's physical characteristics and cycling preferences based on their user data. This state is called the "initial state". The adjustment of the initial state takes into account the user's comfort and safety, as well as the type and intensity of the upcoming cycling training. For example, for users who are heavier and prefer high-intensity training, the initial state may be set to a harder and wider seat cushion to provide sufficient support during subsequent high-intensity riding, reduce pressure on the lower body stress points, and prevent sports injuries.

[0042] It should be noted that by ensuring that the user is in a comfortable and safe sitting position before starting to ride, the system can help the user enter the training state faster, reduce riding interruptions or poor training results due to seat discomfort, and at the same time reduce the risk of sports injuries, thereby improving the overall cycling training experience.

[0043] Step S203, adjusting the seat cushion in the initial state according to the course data of the target course and / or the cycling motion data while the user is using the spinning bike for cycling training.

[0044] Optionally, during the spinning training, the system will dynamically adjust the hardness and width of the seat cushion according to the target course data and / or the user's cycling motion data. This adjustment is immediate and is intended to ensure that the seat cushion is always in the most suitable state at different training stages and when the user's physical strength changes. For example, when the course enters the high-intensity stage, the system will automatically increase the hardness of the seat cushion to provide the necessary support and stability, help the user maintain the correct riding posture, and reduce the fatigue of the hips and lower limbs caused by the seat cushion being too soft; while in the low-intensity recovery stage, the seat cushion will become softer to increase comfort and encourage the user to relax.

[0045] In order to achieve the above dynamic adjustment, the system has built-in algorithms to analyze course data and / or riding data to calculate the optimal parameters for adjusting the cushion properties. By comprehensively considering the user's physical characteristics, exercise preferences and current exercise status, each adjustment is ensured to be personalized and optimized. For example, combining the user's weight, gender information with real-time cadence and resistance data, the system can calculate the softness, hardness and width of the cushion that should be adjusted to meet the user's needs at a specific exercise intensity.

[0046] Based on the contents of the above steps S101 to S103, it can be known that, firstly, the present application obtains and analyzes the user's individual data under the premise of user authorization. These data are crucial to understanding the user's physiological structure and exercise preferences. At the same time, the present application also collects the user's exercise data when riding on a spinning bike according to a specific course, such as cadence, resistance, power, and heart rate, in order to comprehensively evaluate the user's exercise status and needs. By integrating the user's static data (such as height and weight) and dynamic data (such as cadence and resistance during riding), the system can build a more personalized and accurate seat adjustment model. Secondly, based on user data, the system can calculate the most suitable initial state of the seat.

[0047] Finally, during cycling training, the system will dynamically adjust the cushion properties based on the target course's scheduling data (such as course intensity changes, duration, etc.) and the user's real-time cycling data. For example, during the high-intensity phase of the course, when the user's pedaling frequency and resistance increase, the system will automatically harden the cushion to provide better support and stability, reducing the loss of exercise efficiency and hip fatigue caused by excessive cushion softness; and during the low-intensity recovery phase, the cushion will soften to help users relieve fatigue and improve training comfort. This dynamic adjustment mechanism can respond to changes in user and course needs in real time, so that the cushion properties are dynamically matched to the cycling intensity, avoiding the reduction of training effects and potential sports injuries caused by mismatched cushion properties.

[0048] It can be seen that through the technical solution of the present application, the spinning bike system can realize the personalization and dynamic adjustment of the seat cushion, overcomes the limitations of the unified design of the seat cushion in the prior art, greatly improves the personalized experience, training quality and safety of the user's cycling training, avoids the common training injury problems in the traditional unified seat cushion design, and provides users with a more comfortable, efficient and safe spinning bike riding environment. It solves the technical problem that the prior art usually provides a unified seat cushion to help users perform spinning bike riding training, which makes the seat cushion unable to be personalized, thereby affecting the training quality and training experience, and even easily causes a high risk of training injuries to users.

[0049] In an optional embodiment, when a user uses a spinning bike for cycling training, adjusting the seat cushion of the spinning bike includes: adjusting the seat cushion of the spinning bike by at least one of the following operations:

[0050] The first operation is used to adjust the hardness of the seat cushion by controlling the airbag built into the seat cushion;

[0051] The second operation is used to adjust the width of the seat cushion by controlling the motor to drive the support rod of the seat cushion to move relative to the slide rail;

[0052] The third operation is used to adjust the height of the seat cushion by controlling the height of the support rod of the seat cushion;

[0053] The fourth operation is used to adjust the relative distance between the seat and the handlebar of the spinning bike by controlling the inclination angle of the support rod of the seat and the position on the slide rail.

[0054] Optionally, the above-mentioned first operation adjusts the hardness of the seat cushion by controlling the airbag built into the seat cushion. The airbag is filled with gas, and the degree of inflation or deflation directly affects the hardness and softness properties of the seat cushion. When the system receives an instruction to adjust the hardness, the built-in air pump will fill or extract a certain amount of gas according to the instruction, change the air pressure of the airbag inside the seat cushion, and thus achieve instantaneous adjustment of the hardness of the seat cushion. For example, when the user enters a high-intensity training stage, the system will automatically increase the gas in the airbag to make the seat cushion harder and provide better support; while in a low-intensity recovery stage, the system will reduce the gas to make the seat cushion softer and increase comfort.

[0055] Optionally, the second operation described above adjusts the width of the seat cushion by controlling the motor to drive the relative movement of the support rod of the seat cushion on the slide rail. The seat cushion is designed as two pieces on the left and right. Through motor control, the two pieces of the seat cushion can be moved closer or farther away from each other, thereby changing the total width of the seat cushion. This operation is particularly suitable for users of different body shapes, ensuring that the width of the seat cushion can match the width of the user's hips and provide an appropriate support surface. For example, for users with heavier weight, the system will automatically widen the seat cushion to ensure that the pressure is more evenly distributed; for female users, the seat cushion may be appropriately widened to accommodate differences in physiological structure.

[0056] Optionally, the third operation adjusts the position of the seat relative to the pedals and handlebars of the spinning bike by controlling the height of the seat support rod. Height adjustment is crucial to maintaining a riding posture, ensuring that the user's knees and hip joints are at the best angles while riding to reduce sports injuries. The system may preset an initial height based on user data, and then make fine adjustments based on real-time feedback during riding (such as heart rate, cadence, etc.) to optimize the riding experience and efficiency.

[0057] Optionally, the fourth operation adjusts the relative distance between the seat and the handlebar by controlling the inclination angle of the seat support rod and the position on the slide rail. The goal of this operation is to maintain the user's optimal body posture during riding and ensure the coordinated work of the upper and lower body. When the user is training with a high cadence, the system may shorten the distance between the seat and the handlebar, allowing the user to adjust the center of gravity more conveniently and improve riding efficiency; in low-intensity riding or courses that require more upper body participation, the system will increase this distance so that the user can adopt a more relaxed riding posture.

[0058] It should be noted that the above dynamic adjustment operations work together to enable the seat cushion of the spinning bike to automatically adjust its properties according to the user's personal data and real-time riding feedback, as well as the requirements of the target course. For example, the system will consider the user's weight, gender and height data, as well as the current cadence, resistance and power output, and adjust the hardness, width, height and relative distance from the handlebar of the seat cushion in real time to provide users with a more comfortable, safer and more effective cycling training environment. By integrating multiple adjustment functions, the seat cushion becomes a highly adaptive component, which significantly improves the personalized experience and overall training effect of the spinning bike.

[0059] In an optional embodiment, the seat cushion of the spinning bike is adjusted to an initial state according to the user data, including: extracting a user portrait feature of the user from the user data, then inputting the user portrait feature into a first model, using the prior knowledge learned by the first model in the model training phase, and determining initial seat cushion data according to the user portrait feature, wherein the first model is a neural network model trained according to the user portrait feature of the reference user and the seat cushion data selected by the reference user, and the initial seat cushion data is the initialization seat cushion data set when the user starts riding. Finally, the seat cushion of the spinning bike is adjusted to an initial state according to the initial seat cushion data.

[0060] Optionally, user portrait features refer to key information extracted from user data that describes user attributes and preferences, including but not limited to height, weight, gender, age, health status, and riding preferences, etc. These features constitute the basic profile of the user and are used to predict their personalized needs for spinning bike saddles.

[0061] The first model refers to a neural network model trained through machine learning, which is specifically used to predict the user's initial cushion data. During the model training phase, the system collects a large number of user portrait features of reference users and the cushion data they choose (such as hardness, width, height, etc.). Through training, the model learns the mapping relationship between user portrait features and the optimal cushion settings, that is, which physical conditions and riding preferences correspond to which cushion properties.

[0062] For example, when a new user is ready to start cycling training, the system first extracts the user profile features from the user data, and then inputs these features into the first model. Using the prior knowledge learned by the model during the training phase, the model predicts and outputs an initial cushion data that best suits the user. This data set includes parameters such as the hardness, width, height, and relative distance from the handlebars of the cushion, which constitute the initial cushion settings when the user starts riding, ensuring that the user can get a comfortable and safe riding experience from the beginning.

[0063] Finally, the spinning bike automatically adjusts the hardness, width, height and relative distance from the handlebars of the seat according to the initial seat data output from the first model by controlling the airbags, motors, support rods and other components built into the seat, and adjusts it to the predicted initial state. This process is automatically performed by the bike's control system without manual intervention by the user, ensuring the personalization and optimization of the seat properties at the beginning of cycling training.

[0064] By combining user data with the neural network model, the personalized prediction and automatic initialization of the spinning bike seat properties are achieved, which not only improves the user's riding comfort and safety, but also reduces the need for users to make manual adjustments at the beginning of each training session, thereby improving training efficiency and experience satisfaction. Through the integration of machine learning technology, the spinning bike can intelligently understand and adapt to the needs of different users, providing a more personalized and intelligent cycling training environment.

[0065] Optionally, a training method for a first model is provided below:

[0066] First, a large amount of user data needs to be collected. This data usually includes basic information about the user (such as height, weight, gender, age, etc.), as well as the user's preference for cushion parameters when riding a spinning bike (such as hardness, width, height, etc.). This data can be collected from existing users, or recorded when new users manually adjust the cushion to the most comfortable state. Data collection is the basis for machine learning model training, ensuring that the laws learned by the model are universal and representative. After collecting the data, feature engineering is required, that is, extracting features from the raw data that are helpful for model training, such as user portrait features (height, weight, gender, etc.) and cushion parameter features (hardness, width, height, etc.). Feature engineering is an important step before model training, which can help the model better understand the data and improve the accuracy of predictions.

[0067] Next, a neural network model is used as a tool to predict cushion parameters. In this application, the input of the model is the user portrait features, and the output is the initialized cushion data, that is, the cushion hardness, width, height and other parameters that are most suitable for the user at the beginning of riding. Model training is a process of iterative learning using the collected data set. At this stage, the system inputs the user portrait features and the corresponding cushion parameters into the model. The model calculates the predicted value through forward propagation, compares it with the actual value, and calculates the loss function. Then, the weights and biases of the model are updated through back propagation to minimize the loss function, that is, to make the model's predicted value as close to the actual value as possible. This process is repeated many times until the model achieves satisfactory prediction accuracy. During the training process, it may also be necessary to adjust the model's hyperparameters, such as learning rate, regularization parameter, number of network layers, and number of neurons, to optimize model performance, avoid overfitting or underfitting, and ensure that the model has good generalization ability on unknown data.

[0068] After training, the model needs to be evaluated on the validation and test sets to check its performance and prediction accuracy. The validation and test datasets should be independent of the training data to ensure the robustness of the model, that is, the model can make accurate predictions on unseen data. Finally, when the model is fully trained and its performance is verified, it can be deployed to the cycling system of the spinning bike for real-time prediction and adjustment of the cushion parameters.

[0069] In an optional embodiment, according to the course data of the target course, during the user's cycling training using the spinning bike, the seat cushion in the initial state is adjusted, including: firstly extracting the motion intensity feature from the course data, wherein the motion intensity feature is used to characterize the training intensity information of the training content of the target course. Then, the motion intensity feature is input into the second model, and the first seat cushion data of the seat cushion is determined according to the motion intensity feature using the prior knowledge learned by the second model in the model training stage, wherein the model training data of the second model includes reference to the seat cushion data preferred by the user based on different training courses, and the first seat cushion data is the seat cushion data determined by the second model and having a degree of compatibility with the motion intensity feature higher than a preset threshold. Finally, the seat cushion in the initial state is adjusted to the first state according to the first seat cushion data.

[0070] Optionally, before the user starts a spinning training session, the system extracts exercise intensity features from the course data of the target course. These features describe the intensity information of the training content, including specific intensity stages such as high resistance, low cadence, sprint, aerobic or anaerobic training. Exercise intensity features are the key basis for the system to determine when and how to adjust the cushion properties.

[0071] Optionally, the second model is also constructed based on a neural network, and its training data set consists of cushion preference data of reference users under different training courses, including parameter settings such as hardness, width, and height of the cushion under different intensities. By learning these data, the model masters the mapping relationship between motion intensity characteristics and cushion data, that is, which cushion attribute settings the user may prefer under a specific intensity. When the system receives the motion intensity characteristics of the current training, the system inputs these characteristics into the second model. Using the prior knowledge accumulated by the second model during the training phase, the system can predict a set of cushion data based on the motion intensity characteristics, namely the first cushion data. This data set contains cushion parameters whose compatibility with the current motion intensity characteristics is higher than a preset threshold. The setting of the preset threshold ensures the accuracy and rationality of the cushion adjustment and avoids unnecessary frequent adjustments or invalid adjustments.

[0072] Finally, the system automatically adjusts the seat cushion properties of the spinning bike based on the first seat cushion data output from the second model, changing it from the initial state to the first state that matches the current training intensity. This adjustment process may include increasing or decreasing the hardness of the seat cushion, expanding or contracting the width, increasing or decreasing the height, and adjusting the relative distance from the handlebars, etc. All these changes are to ensure that the user can ride in the most comfortable and safest state at the current training intensity, thereby improving training efficiency and experience.

[0073] For example, if the target course enters a high-resistance, high-cadence sprint phase, the system will adjust the seat cushion to a harder state based on the prediction of the second model to provide better support and avoid hip and lower limb fatigue caused by a seat cushion that is too soft; in the low-intensity recovery phase, the seat cushion will be adjusted to a softer setting to increase comfort and help users relax.

[0074] Optionally, in order to train the second model, it is first necessary to collect a large amount of historical data, which comes from the personalized settings of the saddle by different users when participating in various courses. The data set should contain information such as the type of course the user rides, training intensity, cadence, resistance, power output, and the user's preferred saddle hardness, width, height and other attributes. The collected data needs to be preprocessed, including cleaning, standardization and feature engineering, to ensure the accuracy and efficiency of model training. In the preprocessing stage, the input features (i.e., exercise intensity features) and output labels (i.e., the first saddle data) of the model need to be clarified. Exercise intensity features can be the resistance level, cadence range, power consumption, etc. of the course. The output label is the most suitable saddle attribute setting at different exercise intensities, which can be a set of specific hardness, width and height values.

[0075] The neural network model is trained using the preprocessed data. In each training iteration, the model receives input features, calculates the predicted saddle property settings through forward propagation, and then compares them with the actual labels to calculate the value of the loss function to evaluate the gap between the prediction and the actual. Subsequently, the weights and biases of the model are adjusted through the backpropagation algorithm to minimize the loss function and optimize the prediction results. The training process is repeated many times until the performance of the model reaches a preset threshold or converges. During the training process, it may be necessary to adjust the model's hyperparameters, such as learning rate, regularization parameters, batch size, etc., to optimize the model's learning efficiency and generalization ability, avoid overfitting, and ensure that the model can make reasonable predictions of saddle property settings for unseen exercise intensity features. After completing the initial training, the model needs to be evaluated on the validation set to check its prediction performance. If the validation results are satisfactory, the model is then tested on an independent test set to ensure the reliability and accuracy of its prediction ability. Finally, once the second model has been trained and tested to prove its prediction accuracy and stability, it can be deployed to the control system of the spinning bike for real-time prediction and adjustment of saddle properties.

[0076] In an optional embodiment, according to the cycling motion data, during the process of the user using the spinning bike for cycling training, the seat cushion in the initial state is adjusted, including: extracting cycling motion features from the cycling motion data, wherein the cycling motion features are used to characterize the actual training intensity of the user. Then, the cycling motion features are input into the third model, and the second seat cushion data of the seat cushion is determined according to the cycling motion features using the prior knowledge learned by the third model in the model training stage, wherein the model training data of the third model includes seat cushion data preferred by reference users with different cycling motion features, and the second seat cushion data is seat cushion data determined by the third model with a degree of compatibility with the cycling motion features higher than a preset threshold. Finally, the seat cushion in the initial state is adjusted to the second state according to the second seat cushion data.

[0077] Optionally, the cycling motion characteristics are information extracted from the cycling motion data generated in real time by the user on the spinning bike, including cadence, resistance, power output, heart rate, etc. These characteristics not only reflect the preset intensity of the course, but also take into account the user's actual performance and physical condition, providing a more accurate basis for saddle adjustment.

[0078] The third model is also built on a neural network, and its training data set contains past reference users' cushion preference data under different cycling motion characteristics. Through deep learning, the model can identify and understand the complex relationship between cycling motion characteristics and cushion attribute settings, that is, under a specific exercise intensity, the user may prefer which cushion hardness, width and other attributes.

[0079] When applied, the system collects the user's riding motion data in real time, extracts motion features, and inputs them into the third model. The model uses the prior knowledge accumulated during the training phase to predict a set of cushion data, namely the second cushion data, based on the input riding motion features. This data set contains cushion attribute settings that are more compatible with the current riding motion features than a preset threshold. The preset threshold is set to ensure that the adjusted cushion attributes can significantly improve the user's sports experience and safety.

[0080] Finally, based on the second cushion data output from the third model, the spinning bike will automatically adjust the cushion properties from the initial state to the second state that adapts to the current riding motion characteristics. This state adjustment may include real-time adjustment of the cushion hardness, dynamic expansion or contraction of the width, instant increase or decrease in height, and timely adjustment of the relative distance from the handlebars, etc. All these changes are to ensure that the user has the best riding experience at the current exercise intensity, reduce the risk of sports injuries, and improve exercise efficiency and comfort.

[0081] For example, when the user's real-time power output reaches a peak, indicating that high-intensity training is underway, the system will adjust the seat cushion to be harder based on the prediction of the third model to provide stability and support, prevent excessive movement of the hips, and reduce energy waste; during the low-intensity recovery phase, the seat cushion will become softer to relieve muscle fatigue and increase comfort.

[0082] It should be noted that the training method of the third model is similar to the training method of the first model / second model mentioned above. The only difference is that the selected training data and training labels are different. This application will not repeat them here.

[0083] In an optional embodiment, according to the course data and riding motion data of the target course, during the process of the user using the spinning bike for riding training, the seat cushion in the initial state is adjusted, including: extracting the motion intensity feature from the course data, wherein the motion intensity feature is used to characterize the training intensity information of the training content of the target course; extracting the riding motion feature from the riding motion data, wherein the riding motion feature is used to characterize the actual training intensity of the user. According to the motion intensity feature and the riding motion feature, the difference between the actual training intensity of the user and the training intensity of the training content of the target course is determined, and then the difference value is input into the fourth model, and the prior knowledge learned by the fourth model in the model training stage is used to determine the correction data of the seat cushion according to the difference value, wherein the model training data of the fourth model includes: the seat cushion data selected by the reference user with different riding motion features when the user expects to achieve the motion intensity feature required by the training course, wherein the correction data is used to reduce the difference value by adjusting the state of the seat cushion. Finally, the seat cushion in the initial state is adjusted to the target state according to the correction data.

[0084] Optionally, first, the motion intensity features are extracted from the course data of the target course. These features describe the training intensity information preset for the course, including changes in parameters such as resistance, cadence, and power at different stages. Cycling motion features are extracted from the real-time cycling motion data generated by the user. These features reflect the actual training intensity of the user, including specific performances such as cadence, real-time resistance, power output, and heart rate. Cycling motion features provide a real-time basis for personalized adjustment of the saddle, ensuring that the adjustment can respond to the real-time needs of the user.

[0085] Optionally, the system compares the motion intensity characteristics (i.e., the training intensity required by the course) with the cycling motion characteristics (i.e., the actual performance of the user) to determine the difference between the two. This difference reflects the gap between the user's current state and the course expectations, and is an important input to the saddle adjustment strategy, ensuring that the saddle attribute adjustment can make up for this gap and help the user better achieve the course goals. Among them, the fourth model is also based on a neural network. The fourth model is trained based on a large amount of reference user data collected. These data record the saddle data selected by the user when he expects to achieve different motion intensity characteristics. During the training phase, the fourth model learned how to correct the saddle data according to the intensity difference value to minimize the gap between actual and expected.

[0086] In the application stage, the system inputs the calculated strength difference value into the fourth model, which uses the prior knowledge accumulated in the training stage to output a set of correction data for the cushion. The correction data includes the specific adjustment amount of the cushion hardness, width and other properties. The purpose is to dynamically adjust the cushion state to make it closer to the strength required by the course, while also taking into account the actual performance of the user, reducing the strength difference, and improving the personalization and safety of training.

[0087] Finally, based on the correction data output by the fourth model, the spinning bike will automatically adjust the state of the seat cushion from the initial state to the target state. This adjustment process may be continuous, that is, as the course intensity and the actual performance of the user change, the seat cushion properties will continue to be dynamically corrected to adapt to the real-time needs of training, ensuring that the user trains in an optimal state, reducing the risk of sports injuries, and improving training efficiency and comfort.

[0088] For example, if the user shows a higher power output in the easy phase with low resistance and low cadence, indicating that the actual intensity is higher than the course requirements, the system may use the correction data output by the fourth model to slightly harden the saddle to guide the user to reduce the output power and maintain the balance of training; on the contrary, if the user's power output in the high-resistance sprint phase is lower than expected, the saddle may be immediately softened to reduce fatigue and encourage the user to increase output and achieve the course goals.

[0089] An optional fourth model training method is provided below:

[0090] First, a large amount of user cycling data is collected. This data includes the user's real-time motion parameters in different courses (such as cadence, resistance, power, heart rate, etc.), as well as the personalized adjustments made by the user to the cushion properties (such as hardness, width) in order to achieve the course goals. Each set of data records the user's cushion preferences at a specific exercise intensity, aiming to build a database that comprehensively reflects the user's interaction with the cushion. Useful features are extracted from the collected data, including but not limited to exercise intensity features (training intensity information for the target course) and cycling motion features (user's actual training intensity). These features need to be standardized or normalized to ensure that the input data of the model is on the same scale, thereby improving the training effect and prediction accuracy.

[0091] The extracted features are used as the input of the model, and the personalized adjustment data made by the user to the cushion is used as the output target of the model. In order to train the model, the dataset is further divided into training set, validation set and test set, where the training set is used for model training, the validation set is used for model tuning, and the test set is used to evaluate the generalization ability of the model. The choice of a neural network model suitable for processing this mapping relationship, such as a multi-layer perceptron (MLP), recurrent neural network (RNN), long short-term memory network (LSTM) or convolutional neural network (CNN), depends on the nature of the data and the requirements of the prediction task. Define the structure of the model, including the number of layers, the number of neurons in each layer, activation function, loss function and optimization algorithm.

[0092] The neural network model is trained using the training set data. Through multiple rounds of iterations, the model learns how to convert the differences in exercise intensity characteristics and cycling motion characteristics into adjustment strategies for cushion properties. In each iteration, the adjustment strategy predicted by the model is compared with the adjustments made by the actual user. The prediction error of the model is evaluated by calculating the loss function, and then the parameters of the model are updated using the backpropagation algorithm and optimizer to minimize the prediction error. During the training process, it may be necessary to adjust the hyperparameters of the neural network (such as learning rate, regularization coefficient, batch size, etc.) to improve the training efficiency and performance of the model. The model is verified using the validation set data, and the generalization ability of the model is optimized by adjusting the hyperparameters to avoid overfitting or underfitting. After training, the model is finally evaluated using independent test set data to ensure that the model can make accurate predictions on unseen data sets. This step is crucial to verify the practicality of the model and ensure that the model can make reasonable cushion state adjustments in actual applications.

[0093] Through the above training process, the fourth model can learn how to effectively adjust the cushion properties under different exercise intensities, so as to narrow the difference between the user's actual training intensity and the course design intensity, and achieve personalized training optimization goals.

[0094] In an optional embodiment, after obtaining the user data of the user and the riding motion data of the user during riding training on the spinning bike according to the target course, the method for adjusting the seat cushion of the spinning bike also includes: during the user's riding training, detecting the pressure value of each of N areas of the seat cushion, where N is an integer greater than 1; adjusting the seat cushion of the spinning bike during the user's riding training using the spinning bike according to the pressure value of each area, the user data, the course data of the target course and / or the riding motion data.

[0095] In an optional embodiment, when the user is doing spinning training according to the target course, the system will detect the pressure value of each of the N areas (N is an integer greater than 1) of the seat cushion in real time. This is achieved by installing high-precision pressure sensors in different areas of the seat cushion. The sensors can capture the changes in the force distribution of the user's hips on the seat cushion at different training stages, providing direct physiological feedback data for personalized adjustment of the seat cushion.

[0096] According to the pressure value of each area, user data, course data of the target course and cycling motion data, the system will use deep learning models (such as the second model, third model, fourth model, etc. mentioned above) to determine the adjustment strategy of the saddle. This strategy may include the adjustment of the hardness, width, and even the tilt angle of the saddle to adapt to the user's current riding posture and physiological needs, while taking into account the preset intensity of the course to ensure that the user achieves the best training effect in a comfortable and safe state.

[0097] For example, if a higher pressure value is detected in the middle area of ​​the seat cushion, indicating a concentrated distribution of the user's weight, the system may automatically increase the width and hardness of the seat cushion to better disperse the pressure and provide support; on the contrary, if the pressure value in the edge area is higher, it may mean that the seat cushion is too wide. The system will adjust the width of the seat cushion to a more moderate state to reduce unnecessary pressure and discomfort.

[0098] In addition, during the user's cycling training, the system will continuously detect the pressure value of the cushion, and dynamically adjust the cushion state based on the user's cycling data and course data to ensure that the cushion is always in the best adaptability state during the entire training cycle. This adjustment is continuous and can respond to changes in the user's motion state in a timely manner, whether it is from the high-resistance, high-cadence sprint stage to the low-resistance, low-cadence recovery stage, or at different training intensities, the system can respond quickly and adjust the cushion properties to achieve a more personalized and comfortable riding experience.

[0099] After obtaining the user data of the user and the riding motion data of the user during riding training on the spinning bike according to the target course, the method for adjusting the seat of the spinning bike also includes: detecting the difference in pedaling frequency on both sides of the user during the user's riding training; adjusting the seat of the spinning bike during the user's riding training using the spinning bike according to the difference in pedaling frequency on both sides of the user, the user data, the course data of the target course and / or the riding motion data.

[0100] Optionally, during the user's spinning training, the system will detect the difference in pedaling frequency on both sides of the user in real time. This detection is achieved through sensors installed on the pedals, or by monitoring the interaction data between the cycling shoes fixed on the pedals and the cranks of the spinning bike. The detection of pedaling frequency differences can reveal whether the user's riding posture is symmetrical and whether there is excessive pedaling pressure on one side, which may be caused by saddle discomfort, body imbalance or sports injuries. The system will integrate and analyze the detected difference in pedaling frequency on both sides with the user's personal data (such as height, weight, gender, etc.), the course data of the target course (exercise intensity, type, duration, etc.), and real-time cycling exercise data (such as pedaling frequency, power, heart rate, etc.). This comprehensive consideration of multi-dimensional data enables the system to fully understand the user's riding status and saddle adjustment needs.

[0101] Based on the fused data analysis, the system will generate a saddle adjustment strategy to dynamically adjust the hardness, width or other properties of the saddle to suit the user's riding needs. For example, if it is found that the pedaling frequency on one side is significantly lower than the other side, it may be due to excessive pressure or insufficient support on the unilateral buttocks of the saddle. The system may adjust the hardness or width of the saddle to disperse the pressure or provide better support, reducing reliance on the pedal on the injured or fatigued side, thereby promoting a more balanced riding posture and more efficient energy output.

[0102] For example, when it detects that the pedaling frequency on the right side is significantly lower than that on the left side, which may indicate fatigue or injury on the right leg, the system will adjust the hardness of the right side of the seat cushion to make it softer than the left side, thereby reducing pressure on the right hip and encouraging users to distribute power more evenly during riding, avoiding further aggravating potential imbalances.

[0103] In addition, during the entire cycling training process, the system will continuously monitor the difference in pedaling frequency on both sides and adjust the seat cushion status in real time as needed to ensure that users can get the best riding experience during the entire training period. This dynamic adjustment strategy based on real-time monitoring and data analysis can significantly improve the intelligence level of spinning bikes, make seat cushion adjustment more accurate, and also help prevent sports injuries and improve sports efficiency and comfort.

[0104] In an optional embodiment, Figure 2is a flow chart of an optional seat cushion adjustment process according to an embodiment of the present application, such as Figure 2 As shown, after the target user sits on the seat, he or she manually adjusts the seat through the system according to his or her personal body feeling, and then the system stores the seat adjustment data in the seat standard database. When the target user is ready to ride an action bike at a later time, the system can adjust the seat to an initial state according to the target user's user data and the data in the seat standard database. Subsequently, the system generates a dynamic adjustment rule set using the course data and / or real-time riding data, and uses the dynamic adjustment rule set to continue to make real-time adjustments to the seat in the initial state, including but not limited to adjusting the hardness, width, height, etc. of the seat.

[0105] In an optional embodiment, Figure 3 is a schematic diagram of an optional seat cushion adjustment process according to an embodiment of the present application, such as Figure 3 As shown, the process of seat cushion adjustment can be divided into four stages.

[0106] During the data collection stage, the system can collect user data including: motion data, basic body data, seat preference data, health data, hip pressure location / area / intensity, hip force angle, hand force angle and strength, footstep pressure, frequency, trajectory and angle; pressure data collected by the pressure sensor on the seat, pressure data collected by the pressure sensor on the handle, and heart rate data collected by the heart rate sensor on the handle.

[0107] During the cycling data management and saddle model matching stage, the system needs to process the cycling course data and real-time cycling data, and preliminarily determine the saddle model.

[0108] During the algorithm service stage, the system can call AI models and / or rule libraries to determine the adjustment strategy for the seat cushion.

[0109] During the seat cushion adjustment process, the system can perform seat cushion adjustment before training, seat cushion adjustment during training, and seat cushion adjustment after training according to the adjustment strategy.

[0110] It can be seen that through the technical solution of the present application, the spinning bike system can realize the personalization and dynamic adjustment of the seat cushion, overcomes the limitations of the unified design of the seat cushion in the prior art, greatly improves the personalized experience, training quality and safety of the user's cycling training, avoids the common training injury problems in the traditional unified seat cushion design, and provides users with a more comfortable, efficient and safe spinning bike riding environment. It solves the technical problem that the prior art usually provides a unified seat cushion to help users perform spinning bike riding training, which makes the seat cushion unable to be personalized, thereby affecting the training quality and training experience, and even easily causes a high risk of training injuries to users.

[0111] According to another aspect of the embodiment of the present application, a seat adjustment device for a spinning bike is provided, wherein: Figure 4 is a schematic diagram of an optional seat adjustment device for a spinning bike according to an embodiment of the present application, such as Figure 4 As shown, the seat cushion adjustment device of the spinning bike includes: an acquisition unit 401, a first adjustment unit 402, and a second adjustment unit 403. The acquisition unit 401 is used to acquire the user data of the user and the riding motion data of the user when riding on the spinning bike according to the target course; the first adjustment unit 402 is used to adjust the seat cushion of the spinning bike to an initial state according to the user data; the second adjustment unit 403 is used to adjust the seat cushion in the initial state according to the course data of the target course and / or the riding motion data when the user uses the spinning bike for riding training.

[0112] Optionally, the second adjustment unit 403 includes: an adjustment subunit, configured to adjust the seat cushion of the spinning bike by adopting at least one of the following operations:

[0113] The first operation is used to adjust the hardness of the seat cushion by controlling the airbag built into the seat cushion;

[0114] The second operation is used to adjust the width of the seat cushion by controlling the motor to drive the support rod of the seat cushion to move relative to the slide rail;

[0115] The third operation is used to adjust the height of the seat cushion by controlling the height of the support rod of the seat cushion;

[0116] The fourth operation is used to adjust the relative distance between the seat and the handlebar of the spinning bike by controlling the inclination angle of the support rod of the seat and the position on the slide rail.

[0117] Optionally, the first adjustment unit 402 includes: a first processing subunit, used to extract user portrait features of the user from the user data; a second processing subunit, used to input the user portrait features into the first model, and use the prior knowledge learned by the first model in the model training phase to determine the initial cushion data according to the user portrait features, wherein the first model is a neural network model trained based on the user portrait features of the reference user and the cushion data selected by the reference user, and the initial cushion data is initialization cushion data set when the user starts riding; a third processing subunit, used to adjust the seat cushion of the spinning bike to an initial state based on the initial cushion data.

[0118] Optionally, the second adjustment unit 403 includes: a fourth processing subunit, used to extract motion intensity characteristics from the course data, wherein the motion intensity characteristics are used to characterize the training intensity information of the training content of the target course; a fifth processing subunit, used to input the motion intensity characteristics into the second model, and use the prior knowledge learned by the second model in the model training stage to determine first cushion data of the cushion based on the motion intensity characteristics, wherein the model training data of the second model includes reference to the cushion data preferred by the user based on different training courses, and the first cushion data is cushion data determined by the second model and having a degree of adaptability to the motion intensity characteristics higher than a preset threshold; a first adjustment subunit, used to adjust the cushion in an initial state to a first state based on the first cushion data.

[0119] Optionally, the second adjustment unit 403 includes: a sixth processing subunit, used to extract cycling motion features from the cycling motion data, wherein the cycling motion features are used to characterize the actual training intensity of the user; a seventh processing subunit, used to input the cycling motion features into the third model, and use the prior knowledge learned by the third model in the model training stage to determine second cushion data of the cushion based on the cycling motion features, wherein the model training data of the third model includes cushion data preferred by reference users with different cycling motion features, and the second cushion data is cushion data determined by the third model whose compatibility with the cycling motion features is higher than a preset threshold; the second adjustment subunit is used to adjust the cushion in an initial state to a second state based on the second cushion data.

[0120] Optionally, the second adjustment unit 403 includes: an eighth processing subunit, used to extract motion intensity characteristics from the course data, wherein the motion intensity characteristics are used to characterize the training intensity information of the training content of the target course; a ninth processing subunit, used to extract cycling motion characteristics from the cycling motion data, wherein the cycling motion characteristics are used to characterize the actual training intensity of the user; a first determination subunit, used to determine the difference between the actual training intensity of the user and the training intensity of the training content of the target course according to the motion intensity characteristics and the cycling motion characteristics; a second determination subunit, used to input the difference value into the fourth model, and determine the correction data of the cushion according to the difference value using the prior knowledge learned by the fourth model in the model training stage, wherein the model training data of the fourth model includes: the cushion data selected by the reference user with different cycling motion characteristics when he expects to achieve the motion intensity characteristics required by the training course, wherein the correction data is used to reduce the difference value by adjusting the state of the cushion; a third adjustment subunit, used to adjust the cushion in the initial state to the target state according to the correction data.

[0121] Optionally, the seat adjustment device of the spinning bike also includes: a first detection unit, used to detect the pressure value of each of N areas of the seat during the user's cycling training, where N is an integer greater than 1; a target adjustment unit, used to adjust the seat of the spinning bike according to the pressure value of each area, user data, course data of the target course and / or cycling motion data during the user's cycling training using the spinning bike.

[0122] Optionally, the seat adjustment device of the spinning bike also includes: a second detection unit, used to detect the difference in pedaling frequency on both sides of the user during the user's cycling training; a seat adjustment unit, used to adjust the seat of the spinning bike according to the difference in pedaling frequency on both sides of the user, user data, course data of the target course and / or cycling motion data during the user's cycling training using the spinning bike.

[0123] According to another aspect of the present application, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the above-mentioned spinning bike seat adjustment method.

[0124] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors execute the above-mentioned spinning bike seat adjustment method.

[0125] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0126] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0129] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0130] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0131] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for adjusting the seat cushion of a spinning bike, characterized in that: include: Acquire user data of the user and riding motion data of the user during riding training on a spinning bike according to a target course; adjusting the seat cushion of the spinning bike to an initial state according to the user data; According to the course data of the target course and / or the cycling motion data, the seat cushion in the initial state is adjusted during the cycling training performed by the user using the spinning bike.

2. The seat adjustment method for a spinning bike according to claim 1, characterized in that: When the user uses the spinning bike for cycling training, adjusting the seat cushion of the spinning bike includes: The seat cushion of the spinning bike is adjusted by at least one of the following operations: The first operation is used to adjust the hardness of the seat cushion by controlling the airbag built into the seat cushion; The second operation is used to adjust the width of the seat cushion by controlling the motor to drive the support rod of the seat cushion to move relative to the slide rail; A third operation is used to adjust the height of the seat cushion by controlling the height of the support rod of the seat cushion; The fourth operation is used to adjust the relative distance between the seat and the handlebar of the spinning bike by controlling the inclination angle of the support rod of the seat and the position on the slide rail.

3. The seat adjustment method for a spinning bike according to claim 1, characterized in that: Adjusting the seat cushion of the spinning bike to an initial state according to the user data includes: Extracting user portrait features of the user from the user data; Inputting the user portrait features into a first model, using the prior knowledge learned by the first model in the model training phase, and determining initial cushion data according to the user portrait features, wherein the first model is a neural network model trained according to the user portrait features of a reference user and the cushion data selected by the reference user, and the initial cushion data is initialization cushion data set when the user starts riding; The seat cushion of the spinning bike is adjusted to an initial state according to the initial seat cushion data.

4. The seat adjustment method for a spinning bike according to claim 1, characterized in that: According to the course data of the target course, during the riding training of the user using the spinning bike, the seat cushion in the initial state is adjusted, including: Extracting a motion intensity feature from the course data, wherein the motion intensity feature is used to characterize the training intensity information of the training content of the target course; Inputting the motion intensity feature into the second model, using the prior knowledge learned by the second model in the model training phase, and determining first cushion data of the cushion according to the motion intensity feature, wherein the model training data of the second model includes reference to cushion data preferred by the user based on different training courses, and the first cushion data is cushion data determined by the second model and having a degree of fit with the motion intensity feature higher than a preset threshold; The seat cushion in the initial state is adjusted to a first state according to the first seat cushion data.

5. The seat adjustment method for a spinning bike according to claim 1, characterized in that: According to the cycling motion data, during the cycling training of the user using the spinning bike, the seat cushion in the initial state is adjusted, including: Extracting cycling motion features from the cycling motion data, wherein the cycling motion features are used to characterize actual training intensity of the user; Inputting the cycling motion characteristics into a third model, using the prior knowledge learned by the third model in a model training phase, and determining second cushion data of the cushion according to the cycling motion characteristics, wherein the model training data of the third model includes cushion data preferred by reference users with different cycling motion characteristics, and the second cushion data is cushion data determined by the third model to have a degree of compatibility with the cycling motion characteristics higher than a preset threshold; The seat cushion in the initial state is adjusted to a second state according to the second seat cushion data.

6. The seat adjustment method for a spinning bike according to claim 1, characterized in that: According to the course data of the target course and the cycling motion data, during the cycling training of the user using the spinning bike, the seat cushion in the initial state is adjusted, including: Extracting a motion intensity feature from the course data, wherein the motion intensity feature is used to characterize the training intensity information of the training content of the target course; Extracting cycling motion features from the cycling motion data, wherein the cycling motion features are used to characterize actual training intensity of the user; Determining, according to the exercise intensity feature and the cycling exercise feature, a difference value between the actual training intensity of the user and the training intensity of the training content of the target course; The difference value is input into a fourth model, and the correction data of the seat cushion is determined according to the difference value by using the prior knowledge learned by the fourth model in the model training stage, wherein the model training data of the fourth model includes: seat cushion data selected by reference users with different cycling motion characteristics when they expect to achieve the motion intensity characteristics required by the training course, wherein the correction data is used to reduce the difference value by adjusting the state of the seat cushion; The seat cushion in the initial state is adjusted to a target state according to the correction data.

7. The seat adjustment method for a spinning bike according to claim 1, characterized in that: After obtaining the user data of the user and the riding motion data of the user during riding training on the spinning bike according to the target course, the seat adjustment method of the spinning bike further includes: During the user's cycling training, detecting the pressure value of each of the N areas of the seat cushion, wherein N is an integer greater than 1; According to the pressure value of each area, the user data, the course data of the target course and / or the cycling motion data, the seat cushion of the spinning bike is adjusted during the cycling training performed by the user using the spinning bike.

8. The seat adjustment method for a spinning bike according to claim 1, characterized in that: After obtaining the user data of the user and the riding motion data of the user during riding training on the spinning bike according to the target course, the seat adjustment method of the spinning bike further includes: During the cycling training of the user, detecting the difference between the pedaling frequencies of the user on both sides; According to the difference in pedaling frequencies of the user on both sides, the user data, the course data of the target course and / or the cycling motion data, the seat cushion of the spinning bike is adjusted during the cycling training of the user using the spinning bike.

9. A seat adjustment device for a spinning bike, characterized in that: include: An acquisition unit, used to acquire user data of the user and riding motion data of the user during riding training on a spinning bike according to a target course; A first adjustment unit, configured to adjust the seat cushion of the spinning bike to an initial state according to the user data; The second adjustment unit is used to adjust the seat cushion in the initial state according to the course data of the target course and / or the cycling motion data during the cycling training performed by the user using the spinning bike.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the seat adjustment method for a spinning bike according to any one of claims 1 to 8.

11. An electronic device, characterized in that: The invention comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the seat adjustment method for a spinning bike as described in any one of claims 1 to 8.

Images