Fitness course adjustment method and device, storage medium and electronic device

Abstract

The application discloses a fitness course adjustment method and device, a storage medium and an electronic device. The method comprises the following steps: detecting a skip instruction triggered by a target user in the process of the target user participating in a target fitness course, and determining target action information corresponding to the skip instruction in the target fitness course, wherein the target fitness course comprises a plurality of action information; determining a reason why the target user skips the target action information based on body state data of the target user, wherein the reason is at least one of the following: a body state reason, a reason of not meeting user preferences; and adjusting action information after the target action information in the target fitness course based on the reason. Through the application, the problem that the training effect is difficult to guarantee due to the skipping of actions in the fitness course or the quitting of the course in the middle of the user in the process of fitness training in the related art is solved.

Description

Technical Field

[0001] This application relates to the field of fitness class adjustment technology, and more specifically, to a method, apparatus, storage medium, and electronic device for adjusting a fitness class. Background Technology

[0002] In the field of sports and fitness, in order to achieve good training results, users can follow a pre-set fitness course. Specifically, the fitness course includes a list of exercises in sequence. By following the exercise list, users can achieve the expected training results.

[0003] However, different users and the same user at different times have different physical conditions. During the training process of following the fitness course, some users may find the movements difficult or dislike certain movements, thus skipping the movements in the fitness course or dropping out of the course halfway through, making it difficult to persist in completing the training and thus failing to guarantee the training effect.

[0004] There is currently no effective solution to the problem that the training effect is difficult to guarantee because users skip the movements in the fitness course or quit the course midway during the training process. Summary of the Invention

[0005] This application provides a method, apparatus, storage medium, and electronic device for adjusting a fitness course, in order to solve the problem in the related art that the training effect is difficult to guarantee because users skip the movements in the fitness course or quit the course midway during the fitness training process.

[0006] According to one aspect of this application, a method for adjusting a fitness course is provided. The method includes: during a target user's participation in a target fitness course, detecting a skip instruction triggered by the target user, and determining that the skip instruction corresponds to target movement information in the target fitness course, wherein the target fitness course includes multiple movement information; determining the reason why the target user skipped the target movement information based on the target user's physical state data, wherein the reason is at least one of the following: physical state reasons, reasons not conforming to user preferences; and adjusting the movement information following the target movement information in the target fitness course based on the reason.

[0007] Optionally, adjusting the movement information following the target movement information in the target fitness course based on the reason includes: if the reason is physical condition, adjusting the movement difficulty information or movement volume information in the movement information following the target movement information in the target fitness course; if the reason is not in line with user preferences, replacing the target movement information in the target fitness course with preset movement information, wherein the preset movement information is the same as the training target information and movement difficulty information corresponding to the target movement information.

[0008] Optionally, determining the reason why the target user skipped the target action information based on the target user's physical state data includes: inputting the target user's user characteristics, physical state data, characteristics of the target fitness course, and target action information into a first target model for processing to obtain label information for the target action information. The first target model is trained from multiple sets of sample data. Each set of sample data includes the user's user characteristics, physical state data, characteristics of the fitness course attended, skipped action information, and label information for the skipped action information. The label information is either a first label or a second label. The first label indicates that the reason for skipping the action information is due to physical state reasons, and the second label indicates that the reason for skipping the action information is due to not conforming to user preferences. The reason why the target user skipped the target action information is determined based on the label information of the target action information.

[0009] Optionally, before inputting the user characteristics, body state data, target fitness course characteristics, and target movement information of the target user into the first target model for processing to obtain the label information of the target movement information, the method further includes: acquiring the user characteristics, body state data, characteristics of the fitness course attended, skipped movement information, and control instructions after the skipped movement information of the user sample; if the control instructions include at least one skip instruction or an instruction to exit the fitness course, determining the label information of the skipped movement information as the first label information, and determining the user characteristics, body state data, fitness course characteristics, skipped movement information, and the first label information of the user sample as the first sample data; if the control instructions instruct the execution of all movement information after the skipped movement information in the fitness course, determining the label information of the skipped movement information as the second label information, and determining the user characteristics, body state data, fitness course characteristics, skipped movement information, and the second label information of the user sample as the second sample data; multiple sets of sample data are composed of multiple sets of first sample data and multiple sets of second sample data, and a preset logistic regression model is trained based on the multiple sets of sample data to obtain the first target model.

[0010] Optionally, determining the reason for the target user to skip the target action information based on the target user's physical status data includes: judging whether the value corresponding to the preset physical indicator is within a preset range based on the target user's physical status data; if the value corresponding to the preset physical indicator is within the preset range, determining that the reason for skipping the target action information is due to not conforming to user preferences; if the value corresponding to the preset physical indicator exceeds the preset range, determining that the reason for skipping the target action information is due to physical status.

[0011] Optionally, the method further includes: obtaining action information that does not conform to the target user's preferences within a historical time period to obtain a preset action information list; determining action information that does not conform to the target user's preferences in the fitness course to be attended by the target user based on the preset action information list; and replacing the action information that does not conform to the target user's preferences in the fitness course to be attended to obtain an adjusted fitness course.

[0012] Optionally, obtaining action information that does not conform to the target user's preferences within a historical time period to obtain a preset action information list includes: obtaining the first action information and the second action information of the target user participating in fitness classes within a historical time period, and setting a positive label for the first action information and a negative label for the second action information, wherein the first action information is action information that does not conform to the target user's preferences, and the second action information is action information that has been completed more than a preset number of times; a third sample data is composed of each first action information, a positive label, the characteristics of the fitness class in which the first action information is located, and the user characteristics of the target user, and a fourth sample data is composed of each second action information, a negative label, the characteristics of the fitness class in which the second action information is located, and the user characteristics of the target user; multiple sets of sample data are composed of multiple sets of third sample data and multiple sets of fourth sample data, and a preset gradient boosting model is trained based on multiple sets of sample data to obtain a second target model; the second target model is used to judge multiple action information in the fitness class database to obtain multiple action information with positive labels, and the preset action information list is composed of multiple action information with positive labels.

[0013] According to another aspect of this application, a fitness course adjustment device is provided. The device includes: a detection unit, configured to detect a skip instruction triggered by a target user during the participation of a target fitness course, and determine that the skip instruction corresponds to target movement information in the target fitness course, wherein the target fitness course includes multiple movement information; a determination unit, configured to determine the reason why the target user skipped the target movement information based on the target user's physical state data, wherein the reason is at least one of the following: physical state reasons, reasons not conforming to user preferences; and an adjustment unit, configured to adjust the movement information following the target movement information in the target fitness course based on the reason.

[0014] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein the program, when running, controls the device where the non-volatile storage medium is located to perform a method for adjusting a fitness course.

[0015] According to another aspect of the present invention, an electronic device is also provided, comprising a processor and a memory; the memory stores computer-readable instructions, and the processor is configured to execute the computer-readable instructions, wherein the computer-readable instructions, when executed, perform a method for adjusting a fitness course.

[0016] This application employs the following steps: During a target user's participation in a target fitness course, a skip instruction triggered by the target user is detected, and the target movement information corresponding to the skip instruction in the target fitness course is determined. The target fitness course includes multiple movement information. Based on the target user's physical condition data, the reason for the target user skipping the target movement information is determined, where the reason is at least one of the following: physical condition reasons, reasons not conforming to user preferences. Based on the reason, the movement information following the target movement information in the target fitness course is adjusted. This solves the problem in related technologies where skipping movements or exiting the fitness course midway during training makes it difficult to guarantee the training effect. By adjusting the movement information following the target movement information according to different reasons for the user skipping it, the training effect of the user participating in the fitness course is guaranteed. Attached Figure Description

[0017] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 This is a flowchart of a method for adjusting a fitness course according to an embodiment of this application;

[0019] Figure 2 This is a schematic diagram of an adjustment device for a fitness course provided according to an embodiment of this application. Detailed Implementation

[0020] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0021] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] According to an embodiment of this application, a method for adjusting a fitness course is provided.

[0024] Figure 1 This is a flowchart of a method for adjusting a fitness course according to an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0025] Step S102: During the target user's participation in the target fitness course, detect the skip instruction triggered by the target user and determine the target action information in the target fitness course corresponding to the skip instruction. The target fitness course includes multiple action information.

[0026] Specifically, the target fitness course includes multiple movement information with a preset sequence. The movement information can be displayed on the display interface of the client with the fitness software installed via video. Each movement information can correspond to a set of the same movements, and the target user can train by following the displayed movement information.

[0027] During training, the target user can also choose to skip the display of one or more action information. Accordingly, the training corresponding to that action information will be skipped. For example, the target user can skip the displayed target action information by clicking the skip button on the display interface. The skip detection can monitor the user's behavior of skipping the training corresponding to the target action information by detecting the skip instruction triggered after the user clicks the skip button.

[0028] Step S104: Determine the reason why the target user skipped the target action information based on the target user's physical state data, wherein the reason is at least one of the following: physical state reason, or reason that does not conform to user preference.

[0029] Specifically, the reasons why target users skip target action information vary depending on their physical condition. For example, if a target user skips target information when they are in good physical condition, it may be because the action information does not match their preferences. If a target user skips target information when they are in poor physical condition, it may be because they feel that the training action corresponding to the target action information is too difficult and therefore cannot complete the training.

[0030] The system can collect the target user's physical status data to determine the reason for skipping the target action information based on the physical status data. Specifically, the system can collect physical status data using wearable devices such as wristbands or watches worn by the target user, or it can collect the target user's training movements and postures using image acquisition devices such as cameras to obtain the target user's physical status data. The embodiments of this application do not limit the method of obtaining physical status data.

[0031] Step S106: Adjust the movement information following the target movement information in the target fitness course based on the reasons.

[0032] Specifically, adjusting the motion information following the target motion information can make the adjusted motion information more compatible with the target user's current physical state, which helps the target user to persist in completing the training in the target fitness course and obtain the corresponding training effect.

[0033] The fitness course adjustment method provided in this application embodiment detects skip commands triggered by the target user during the target user's participation in the target fitness course, and determines the target movement information in the target fitness course corresponding to the skip command. The target fitness course includes multiple movement information. Based on the target user's physical state data, the method determines the reason why the target user skipped the target movement information, wherein the reason is at least one of the following: physical state reasons, reasons not conforming to user preferences. Based on the reason, the method adjusts the movement information following the target movement information in the target fitness course. This solves the problem in related technologies where the training effect is difficult to guarantee because users skip movements or exit the fitness course midway during training. By adjusting the movement information following the target movement information according to different reasons why users skip the target movement information, the method achieves the effect of ensuring the training effect of users participating in fitness courses.

[0034] The reasons for skipping target action information vary, and the methods for adjusting the action information following the target action information also differ. Optionally, in the fitness course adjustment method provided in this application embodiment, adjusting the action information following the target action information in the target fitness course based on the reason includes: when the reason is physical condition, adjusting the action difficulty information or action volume information in the action information following the target action information in the target fitness course; when the reason is not in line with user preferences, replacing the target action information in the target fitness course with preset action information, wherein the preset action information is the same as the training target information and action difficulty information corresponding to the target action information.

[0035] Specifically, if the reason for skipping the target action information is due to physical condition, it indicates that the user's physical condition is poor and it is difficult to complete the training action corresponding to the target action information. Therefore, the difficulty or volume of the action information following the target action information can be reduced. For example, if the target action information skipped by the target user includes 20 high knee exercises, and the action information following the target action information is a set of 20 burpees, the 20 burpees can be adjusted to 10 burpees, or the 20 burpees can be adjusted to 20 easy burpees, thereby ensuring that the target user can complete the target course as much as possible under the current physical condition.

[0036] Specifically, if the reason for skipping the target action information is that it does not conform to the user's preferences, it means that the user's physical condition is good, but they are not interested in the action information. Therefore, the target action information can be replaced with different action information of the same type and difficulty. For example, if the target action information skipped by the target user includes 20 sit-ups, the 20 sit-ups can be replaced with 20 abdominal crunches, thus ensuring that the purpose of abdominal training can still be achieved even if the target user does not like sit-ups.

[0037] The reason for skipping target action information can be determined by model prediction. Optionally, determining the reason for skipping target action information based on the target user's physical state data includes: inputting the target user's user characteristics, physical state data, characteristics of the target fitness course, and target action information into a first target model for processing to obtain label information for the target action information. The first target model is trained from multiple sets of sample data. Each set of sample data includes the user's user characteristics, physical state data, characteristics of the fitness course attended, skipped action information, and label information for the skipped action information. The label information is either a first label or a second label. The first label indicates that the reason for skipping the action information is due to physical state, and the second label indicates that the reason for skipping the action information is due to not conforming to user preferences. The reason for skipping target action information is determined based on the label information of the target action information.

[0038] Specifically, the user characteristics of the target user can be gender, age, height and weight, etc., and the body status data can be heart rate collected by wearable devices such as fitness bracelets and watches, and movement and posture data collected by image acquisition devices. The characteristics of the target fitness course can include course duration, course difficulty, and information on each movement included in the course. The above information and target movement information are input into the pre-trained first target model for processing to obtain label information used to indicate the reason for the target user to skip the target movement information.

[0039] The first target model is trained using feature information and label information. Optionally, before inputting the user features, body state data, features of the target fitness course, and target action information into the first target model for processing to obtain the label information of the target action information, the method further includes: acquiring the user features, body state data, features of the fitness course attended, skipped action information, and control instructions after the skipped action information of the user sample; if the control instructions include at least one skip instruction or an instruction to exit the fitness course, determining the label information of the skipped action information as the first label information, and determining the user features, body state data, features of the fitness course, skipped action information, and the first label information of the user sample as the first sample data; if the control instructions instruct the execution of all action information after the skipped action information in the fitness course, determining the label information of the skipped action information as the second label information, and determining the user features, body state data, features of the fitness course, skipped action information, and the second label information of the user sample as the second sample data; multiple sets of sample data are composed of multiple sets of first sample data and multiple sets of second sample data, and a preset logistic regression model is trained based on the multiple sets of sample data to obtain the first target model.

[0040] It should be noted that if a user skips the current action information and then skips the remaining action information in the course multiple times or exits directly, it indicates that the user is not in good physical condition, and the reason for skipping the current action information is due to physical condition. If a user skips the current action information but can still complete the training corresponding to the remaining action information in the course, it indicates that the user does not like the current action information, and the reason for skipping the current action information is that the action does not match the user's preferences.

[0041] Specifically, the reason why the user skips the current action information can be determined based on the control instructions after the first skipped action information in the fitness course, thereby determining the label corresponding to the first skipped action information. The user's user characteristics, body state data, fitness course characteristics, the first skipped action information, and label information are determined as sample data to obtain multiple sample data. Based on the multiple sample data, a preset logistic regression model is trained to obtain the first target model.

[0042] The first target model obtained through training can be a lightweight model. The first target model can predict the label information corresponding to the skipped action information in the course in real time, thereby predicting the reason for skipping the action information. Based on the reason for skipping the action information, the remaining action information of the fitness course can be adjusted to ensure the training effect of the user.

[0043] In addition to predicting the reason for skipping the target action information based on the model, the reason for skipping the target action can also be determined based on preset rules. Optionally, determining the reason for the target user to skip the target action information based on the target user's physical state data includes: determining whether the value corresponding to the preset physical indicator is within a preset range based on the target user's physical state data; if the value corresponding to the preset physical indicator is within the preset range, determining that the reason for skipping the target action information is due to not conforming to user preferences; if the value corresponding to the preset physical indicator exceeds the preset range, determining that the reason for skipping the target action information is due to physical state reasons.

[0044] In one optional implementation, if the heart rate is the preset body indicator, and the bracelet detects that the user's heart rate is greater than the maximum value within the preset range or less than the minimum value within the preset range, the reason for skipping the target action information is determined to be due to physical condition; if the bracelet detects that the user's heart rate is within the preset range, the reason for skipping the target action information is determined to be due to not conforming to user preferences.

[0045] It should be noted that the preset body indicators can also be other indicators, such as sleep duration. The preset body indicators can also include multiple indicators, such as both heart rate and sleep duration. The embodiments of this application do not limit the type and number of preset body indicators.

[0046] In addition to adjusting the training course movements in real time based on the current physical condition, the method can also adjust the movement information in the fitness course to be attended based on the movement skipping situation in the historical time period. Optionally, the method also includes: obtaining movement information that does not conform to the target user's preferences in the historical time period to obtain a preset movement information list; determining the movement information in the fitness course to be attended that does not conform to the target user's preferences based on the preset movement information list; and replacing the movement information in the fitness course to be attended that does not conform to the target user's preferences to obtain the adjusted fitness course.

[0047] Specifically, after constructing a preset action information list based on action information that does not conform to the target user's preferences within a historical time period, the action information in the fitness course that the target user is about to participate in can be matched with the action information in the preset action information list to obtain the matched action information, that is, the action information in the fitness course that does not conform to the target user's preferences. Then, the action information that does not conform to the target user's preferences is replaced with different action information of the same type and difficulty to obtain the adjusted fitness course. The adjusted fitness course does not contain action information that does not conform to the target user's preferences, thus avoiding the problem of users skipping action information multiple times and making it difficult to guarantee the training effect.

[0048] The model can be used to judge multiple movement information in the fitness course database to obtain a preset movement information list. Optionally, movement information that does not conform to the target user's preferences within a historical time period can be obtained. The preset movement information list includes: obtaining the first movement information and the second movement information of the target user in fitness courses within a historical time period, assigning a positive label to the first movement information and a negative label to the second movement information, wherein the first movement information is the movement information that does not conform to the target user's preferences, and the second movement information is the movement information that has been completed more than a preset number of times; a third sample data is composed of each first movement information, a positive label, the characteristics of the fitness course in which the first movement information is located, and the user characteristics of the target user; and a fourth sample data is composed of each second movement information, a negative label, the characteristics of the fitness course in which the second movement information is located, and the user characteristics of the target user; multiple sets of sample data are composed of multiple sets of third sample data and multiple sets of fourth sample data, and a preset gradient boosting model is trained based on multiple sets of sample data to obtain a second target model; the second target model is used to judge multiple movement information in the fitness course database to obtain multiple movement information with positive labels, and the preset movement information list is composed of multiple movement information with positive labels.

[0049] Specifically, actions that target users historically disliked or couldn't perform are used as positive samples, while actions with high completion rates and high scores are used as negative samples. A pre-defined gradient improvement model is established by combining user characteristics and course characteristics to obtain a second target model. The second target model is then used to predict user-selectable courses in the fitness course database to obtain action information that does not conform to the target user's preferences. The prediction principle is as follows: if a user skips a certain action in the course, the matching score between the skipped action and the user will decrease. When the score is less than a certain threshold, it is judged as not conforming to the user's preferences.

[0050] Furthermore, a list of preset movement information can be generated based on movement information that does not conform to the target user's preferences. This information can then be used to replace movement information that the user dislikes in the fitness class to be attended. Alternatively, movement information that the user dislikes can be filtered out during the course design phase, and then the course can be designed based on the filtered movement information. This ensures that the course does not contain movement information that does not conform to the target user's preferences, which helps to improve the completion rate of the course training and achieve the expected training effect.

[0051] It should be noted that the steps shown in the flowchart in 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 may be executed in a different order than that shown here.

[0052] This application also provides a fitness course adjustment device. It should be noted that the fitness course adjustment device of this application embodiment can be used to execute the fitness course adjustment method provided in this application embodiment. The following describes the fitness course adjustment device provided in this application embodiment.

[0053] Figure 2 This is a schematic diagram of an adjustment device for a fitness course according to an embodiment of this application. Figure 2 As shown, the device includes: a detection unit 10, a determination unit 20, and an adjustment unit 30.

[0054] Specifically, the detection unit 10 is used to detect the skip instruction triggered by the target user during the target user's participation in the target fitness course, and to determine the target action information in the target fitness course corresponding to the skip instruction, wherein the target fitness course includes multiple action information.

[0055] The determining unit 20 is used to determine the reason why the target user skips the target action information based on the target user's physical state data, wherein the reason is at least one of the following: physical state reason, or reason that does not conform to user preference.

[0056] Adjusted to Unit 30, used to adjust the movement information following the target movement information in the target fitness course based on the cause.

[0057] The fitness course adjustment device provided in this application embodiment detects skip commands triggered by the target user during the target user's participation in the target fitness course through the detection unit 10, and determines the target action information in the target fitness course corresponding to the skip command. The target fitness course includes multiple action information. The determination unit 20 determines the reason why the target user skipped the target action information based on the target user's physical state data. The reason is at least one of the following: physical state reasons, reasons that do not conform to user preferences. The adjustment unit 30 adjusts the action information after the target action information in the target fitness course based on the reason. This solves the problem in related technologies where the training effect is difficult to guarantee because the user skips the action in the fitness course or quits the course midway during fitness training. By adjusting the action information after the target action information according to different reasons why the user skips the target action information, the training effect of the user participating in the fitness course is guaranteed.

[0058] The fitness course adjustment device includes a processor and a memory. The detection unit 10, determination unit 20 and adjustment unit 30 are all stored in the memory as program units. The processor executes the program units stored in the memory to realize the corresponding functions.

[0059] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address the problem in related technologies where users skipping movements or exiting fitness classes midway through training sessions, leading to inconsistent training results.

[0060] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0061] This application also provides a non-volatile storage medium, which includes a stored program, wherein the program, when running, controls the device where the non-volatile storage medium is located to execute a method for adjusting a fitness course.

[0062] This application also provides an electronic device comprising a processor and a memory; the memory stores computer-readable instructions, and the processor executes the computer-readable instructions, wherein the computer-readable instructions, when executed, perform a method for adjusting a fitness course. The electronic device described herein may be a server, PC, PAD, mobile phone, etc.

[0063] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0064] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0065] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0066] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0067] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0068] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0069] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0070] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0071] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method of adjusting a fitness class, characterized by, The method comprises the following steps: During the participation of a target user in a target fitness course, a skip instruction triggered by the target user is detected, and target action information corresponding to the skip instruction in the target fitness course is determined, wherein the target fitness course comprises a plurality of action information; A reason why the target user skips the target action information is determined based on body state data of the target user, wherein the reason is at least one of a body state reason and a reason of not meeting user preferences; The reason why the target user skips the target action information is determined based on the body state data of the target user, which comprises inputting user characteristics of the target user, the body state data, characteristics of the target fitness course, and the target action information into a first target model for processing to obtain label information of the target action information, wherein the first target model is trained by a plurality of sets of sample data, each set of sample data comprises user characteristics, body state data, characteristics of a fitness course participated in, skipped action information, and label information of the skipped action information of a user sample, the label information is first label information or second label information, the first label information indicates that the reason for skipping the action information is the body state reason, and the second label information indicates that the reason for skipping the action information is the reason of not meeting user preferences; the reason why the target user skips the target action information is determined according to the label information of the target action information; The action information after the target action information in the target fitness course is adjusted based on the reason.

2. The method of claim 1, wherein, The adjustment of the action information after the target action information in the target fitness course based on the reason comprises: In the case where the reason is the body state reason, the action difficulty information or the action capacity information in the action information after the target action information in the target fitness course is adjusted; In the case where the reason is the reason of not meeting user preferences, the target action information in the target fitness course is replaced by preset action information, wherein the preset action information is the same as the training target information and the action difficulty information corresponding to the target action information.

3. The method of claim 1, wherein, Before the user characteristics of the target user, the body state data, the characteristics of the target fitness course, and the target action information are input into the first target model for processing to obtain the label information of the target action information, the method further comprises: The user characteristics, the body state data, the characteristics of the fitness course participated in, the skipped action information, and a control instruction after skipping the action information of the user sample are obtained; In the case where the control instruction comprises at least one skip instruction or an instruction to exit the fitness course, the label information of the skipped action information is determined as the first label information, and the user characteristics, the body state data, the characteristics of the fitness course, the skipped action information, and the first label information of the user sample are determined as first sample data. In a case where the control instruction indicates all action information after the skipped action information in the fitness course is executed, the label information of the skipped action information is determined as the second label information, and the user feature of the user sample, the body state data, the feature of the fitness course, the skipped action information, and the second label information are determined as second sample data; The first target model is obtained by training a preset logistic regression model according to the plurality of groups of sample data.

4. The method of claim 1, wherein, The reason why the target user skips the target action information is determined based on the body state data of the target user, including: determining whether a value corresponding to a preset body index is within a preset range based on the body state data of the target user; in a case where the value corresponding to the preset body index is within the preset range, determining that the reason for skipping the target action information is the user preference inconsistency reason; in a case where the value corresponding to the preset body index exceeds the preset range, determining that the reason for skipping the target action information is the body state reason.

5. The method of claim 1, wherein, The method further includes: obtaining action information that does not meet the target user's preference in a historical time period to obtain a preset action information list; determining action information that does not meet the target user's preference in a fitness course to be attended by the target user based on the preset action information list; replacing the action information that does not meet the target user's preference in the fitness course to be attended to obtain an adjusted fitness course.

6. The method of claim 5, wherein, The method further includes: obtaining action information that does not meet the target user's preference in a historical time period to obtain a preset action information list; obtaining first action information and second action information in a fitness course attended by the target user in the historical time period, and setting a positive label for the first action information and a negative label for the second action information, wherein the first action information is action information that does not meet the target user's preference, and the second action information is action information with a number of completed exercises greater than a preset number; constructing third sample data from each of the first action information, the positive label, the feature of the fitness course in which the first action information is located, and the user feature of the target user, and constructing fourth sample data from each of the second action information, the negative label, the feature of the fitness course in which the second action information is located, and the user feature of the target user; constructing a plurality of groups of sample data from a plurality of the third sample data and a plurality of the fourth sample data, and training a preset gradient boosting model according to the plurality of groups of sample data to obtain a second target model; 7. An apparatus for adjusting a fitness program, characterized by using the second target model to judge a plurality of action information in a fitness course database to obtain a plurality of action information with the positive label, and constructing the preset action information list from the plurality of action information with the positive label. The method further includes: The detection unit is configured to detect a skip instruction triggered by the target user during participation of the target user in the target fitness course, and determine target action information corresponding to the skip instruction in the target fitness course, wherein the target fitness course comprises a plurality of action information. The determination unit is configured to determine a reason for skipping the target action information by the target user based on the body state data of the target user, wherein the reason is at least one of a body state reason and a user preference inconsistency reason. The determination of the reason for skipping the target action information by the target user based on the body state data of the target user comprises: inputting user characteristics of the target user, the body state data, characteristics of the target fitness course, and the target action information into a first target model for processing to obtain label information of the target action information, wherein the first target model is trained by a plurality of sets of sample data, each set of sample data comprising user characteristics of a user sample, body state data, characteristics of a participated fitness course, skipped action information, and label information of the skipped action information, the label information being first label information or second label information, the first label information indicating that the reason for skipping the action information is the body state reason, and the second label information indicating that the reason for skipping the action information is the user preference inconsistency reason; and determining the reason for skipping the target action information by the target user according to the label information of the target action information. The adjustment unit is configured to adjust action information after the target action information in the target fitness course based on the reason.

8. A non-volatile storage medium, comprising: The non-volatile storage medium comprises a stored program, wherein the program controls a device in which the non-volatile storage medium is located to perform the adjustment method of the fitness course according to any one of claims 1 to 6 when the program is executed.

9. An electronic device, comprising: The device comprises a processor and a memory, and the memory stores computer readable instructions, and the processor is configured to execute the computer readable instructions, wherein the computer readable instructions perform the adjustment method of the fitness course according to any one of claims 1 to 6 when executed.

Images