WO2025251263A1 - 健身计划推荐方法及装置、存储介质、程序产品 - Google Patents

健身计划推荐方法及装置、存储介质、程序产品

Info

Publication number
WO2025251263A1
WO2025251263A1 PCT/CN2024/097839 CN2024097839W WO2025251263A1 WO 2025251263 A1 WO2025251263 A1 WO 2025251263A1 CN 2024097839 W CN2024097839 W CN 2024097839W WO 2025251263 A1 WO2025251263 A1 WO 2025251263A1
Authority
WO
WIPO (PCT)
Prior art keywords
fitness
exercise
target
plan
plans
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/097839
Other languages
English (en)
French (fr)
Inventor
霍丽莹
邓耀生
赵振宇
王富成
王宏超
罗晓晨
惠浩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Douyin Vision Co Ltd
Original Assignee
Douyin Vision Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Douyin Vision Co Ltd filed Critical Douyin Vision Co Ltd
Priority to PCT/CN2024/097839 priority Critical patent/WO2025251263A1/zh
Priority to CN202480004142.7A priority patent/CN121488234A/zh
Publication of WO2025251263A1 publication Critical patent/WO2025251263A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation

Definitions

  • This disclosure relates to the field of computer technology, and in particular to a method and apparatus for recommending fitness plans, a storage medium, and a program product.
  • a multi-day fitness plan can be generated directly in one step based on the user's request for a fitness plan.
  • a fitness plan recommendation method including:
  • a first fitness plan corresponding to a target time period is generated, wherein the target time period includes multiple sub-time periods, and the first fitness plan includes the exercise types and target muscle groups for the multiple sub-time periods;
  • a plurality of second fitness plans are generated corresponding to the plurality of sub-time periods, wherein the plurality of second fitness plans include the names and fitness guidance content of a plurality of target fitness movements corresponding to the exercise types and exercise parts of the plurality of sub-time periods in the first fitness plan;
  • the user is shown the first fitness plan and the plurality of second fitness plans.
  • a fitness plan recommendation device comprising:
  • the first generation module is configured to generate a first fitness plan corresponding to a target time period in response to receiving a user's request for a fitness plan.
  • the target time period includes multiple sub-time periods
  • the first fitness plan includes the exercise types and exercise parts of the multiple sub-time periods.
  • the second generation module is configured to generate multiple second fitness plans corresponding to the multiple sub-time periods based on the first fitness plan, wherein the multiple second fitness plans include those described in the first fitness plan.
  • the display module is configured to display the first fitness plan and the plurality of second fitness plans to the user.
  • an electronic device comprising: a memory; and a processor coupled to the memory, the processor being configured to perform a fitness plan recommendation method of any embodiment of the present disclosure based on instructions stored in the memory.
  • a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, performs a fitness plan recommendation method according to any embodiment of the present disclosure.
  • a computer program product that, when the computer program product is run on a computer, causes the computer to implement the fitness plan recommendation method of any of the embodiments.
  • Figure 1 is a flowchart illustrating a fitness plan recommendation method according to some embodiments of the present disclosure
  • Figure 2 is a flowchart illustrating the generation of multiple second fitness plans corresponding to the multiple sub-time periods according to some embodiments of the present disclosure
  • Figure 3 is a flowchart illustrating a fitness plan recommendation method according to some other embodiments of the present disclosure
  • Figure 4A is a schematic diagram illustrating a weekly fitness plan according to some embodiments of the present disclosure.
  • Figure 4B is a schematic diagram illustrating a daily fitness plan according to some embodiments of the present disclosure.
  • Figure 5 is a flowchart illustrating a fitness plan recommendation method according to some other embodiments of the present disclosure.
  • Figure 6 is a block diagram illustrating a fitness plan recommendation device according to some embodiments of the present disclosure.
  • Figure 7 is a block diagram illustrating a fitness plan recommendation device according to some embodiments of the present disclosure.
  • Figure 8 shows a block diagram of an electronic device according to some embodiments of the present disclosure.
  • the term “comprising” and its variations are open-ended terms that include at least the following elements/features but do not exclude other elements/features, i.e., “including but not limited to”. Furthermore, as used in this disclosure, the term “including” and its variations are open-ended terms that include at least the following elements/features but do not exclude other elements/features, i.e., “including but not limited to”. Therefore, “comprising” and “including” are synonymous.
  • the term “based on” means “at least partially based on”.
  • the terms “one embodiment,” “some embodiments,” or “embodiment” mean that a specific feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the invention.
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one additional embodiment”; and the term “some embodiments” means “at least some embodiments.”
  • the appearance of the phrases “in one embodiment,” “in some embodiments,” or “in an embodiment” in various places throughout the specification does not necessarily refer to the same embodiment, but may refer to the same embodiment.
  • LLMs Large language models
  • LLMs are powerful artificial intelligence tools capable of generating and understanding natural language. They are deep learning models trained on large-scale datasets, designed to simulate human language abilities and intelligent thought processes. These models are widely used in natural language processing, dialogue systems, text generation, and other language-related tasks.
  • the training process of large language models involves massive amounts of text data. It acquires statistical knowledge and semantic understanding of language through self-supervised learning on this data.
  • the model learns to predict the next word or sentence in the text to capture context and semantic relationships. In this way, the model gradually builds a deep understanding and generative ability of language.
  • the method of directly generating multi-day fitness plans in one step has low accuracy and poor user experience.
  • This disclosure provides a technical solution that can improve the accuracy of fitness plan recommendations and enhance user experience.
  • Figure 1 is a flowchart illustrating a fitness plan recommendation method according to some embodiments of the present disclosure.
  • the fitness plan recommendation method includes: step S110, in response to receiving a user's request for a fitness plan, generating a first fitness plan corresponding to a target time period, wherein the target time period includes multiple sub-time periods, and the first fitness plan includes the exercise types and target muscle groups for the multiple sub-time periods; step S120, based on the first fitness plan, generating multiple second fitness plans corresponding to the multiple sub-time periods, wherein the multiple second fitness plans include the names and fitness guidance content of multiple target fitness movements corresponding to the exercise types and target muscle groups for the multiple sub-time periods in the first fitness plan; and step S130, displaying the fitness plan to the user.
  • the fitness plan recommendation method is, for example, executed by an intelligent agent system.
  • An intelligent agent can also be called a robot (bot).
  • this disclosure for a fitness plan with multiple sub-time periods, this disclosure generates exercise types and target muscle groups for multiple sub-time periods in a first stage. In a second stage, based on the exercise types and target muscle groups generated in the first stage, the first fitness plan is further refined, generating names of target fitness movements and fitness guidance content for multiple sub-time periods.
  • This disclosure divides the generation process of a fitness plan with multiple sub-time periods into two stages: first, a rough fitness plan is generated, and then a detailed fitness plan is generated based on the rough fitness plan. This simplifies a complex task and can improve the accuracy of fitness plan recommendations.
  • step S110 in response to receiving a user's request to obtain a fitness plan, a first fitness plan corresponding to a target time period is generated, wherein the target time period includes multiple sub-time periods, and the first fitness plan includes the exercise types and exercise parts of the multiple sub-time periods.
  • a model can be used to generate a first fitness plan corresponding to the target time period.
  • a generative model can be used to generate the first fitness plan corresponding to the target time period.
  • a large language model can be used to generate the first fitness plan corresponding to the target time period.
  • generating a first fitness plan corresponding to a target time period in response to receiving a user's request for a fitness plan includes: performing intent understanding on the request information to obtain the user's fitness intent information; and generating the first fitness plan based on the fitness intent information.
  • a natural language processing model can be used to perform intent understanding on the request information.
  • step S120 based on the first fitness plan, multiple second fitness plans corresponding to the multiple sub-time periods are generated.
  • Each of the multiple second fitness plans includes the names and fitness guidance content of multiple target fitness movements corresponding to the exercise types and target muscle groups in the multiple sub-time periods of the first fitness plan.
  • the name of the target fitness movement might be a barbell front squat
  • the fitness guidance content might be a description instructing the user to perform a barbell front squat. This description can be textual or visual.
  • multiple second fitness plans corresponding to the multiple sub-time periods can be generated in parallel based on the first fitness plan.
  • the parallel generation of multiple second fitness plans for multiple sub-time periods in the second stage can improve the efficiency of fitness plan recommendation.
  • multiple second fitness plans corresponding to the multiple sub-time periods can be generated in parallel using a model.
  • a generative model can be used to generate multiple second fitness plans corresponding to the multiple sub-time periods in parallel.
  • a large language model can be used to generate multiple second fitness plans corresponding to the multiple sub-time periods in parallel.
  • Multiple second fitness plans can be generated in parallel using a model, for example, by concurrently calling the model, that is, sending multiple requests to the model at the same time, with each request requesting the generation of at least one second fitness plan.
  • the model used to generate the first fitness plan and the multiple second fitness plans can be the same model or different models.
  • the model used to generate the first fitness plan and the multiple second fitness plans is the same large language model, which generates different fitness plans through different model settings.
  • step S120 of FIG1 can be achieved by steps S121 to S124 as shown in FIG2.
  • Figure 2 is a schematic flowchart illustrating the generation of multiple second fitness plans corresponding to the multiple sub-time periods according to some embodiments of the present disclosure.
  • step S121 multiple reference fitness plans are generated according to the exercise types and exercise parts of the multiple sub-time periods in the first fitness plan.
  • the multiple reference fitness plans include the names of multiple target fitness movements of the multiple sub-time periods.
  • multiple reference fitness plans can be generated in parallel using a model (such as a generative model or a large language model). For example, for the multiple sub-time periods, the model can be invoked in parallel to process the exercise type and target muscle groups for each sub-time period, thereby obtaining the multiple reference fitness plans.
  • a model such as a generative model or a large language model.
  • the multiple reference fitness plans may also include reference fitness guidance content for multiple target fitness movements across the multiple sub-time periods. This depends on the model settings.
  • the plurality of reference fitness plans further include the execution methods of the plurality of target fitness movements, wherein the execution methods include the execution order of the plurality of target fitness movements in the plurality of sub-time periods and the number of times each target fitness movement is executed, and the plurality of second fitness plans further include the execution methods of the plurality of target fitness movements.
  • step S122 if the exercise type corresponding to each target fitness movement meets the first condition, demonstration content for each fitness movement is obtained from the target content platform.
  • exercise types can be divided into aerobic exercise and anaerobic exercise, and the first condition is, for example, that aerobic exercise belongs to the follow-along type.
  • the demonstration content is, for example, content for users to follow along with fitness movements.
  • the target content platform includes, but is not limited to, a target video platform, and the demonstration content includes, but is not limited to, demonstration videos. Demonstration videos are, for example, follow-along videos.
  • a search plugin can be invoked to match multiple videos from the target content platform with each target fitness exercise to obtain demonstration content for each exercise.
  • Multiple pieces of content from the target content platform have content tags, which can be used to match the content tags with the name of each target fitness exercise or... Other descriptive information is matched to obtain the demonstration content for each fitness movement.
  • step S123 if the exercise type corresponding to each target fitness movement meets the second condition, the exercise diagram and/or dynamic image of each target fitness movement is obtained from the fitness movement library according to the name of each target fitness movement.
  • the fitness movement library includes the names of multiple pre-configured fitness movements and the corresponding exercise diagrams and/or dynamic images.
  • the fitness movement library is constructed based on fitness movements in the fitness field and can be a professional knowledge base in the fitness field. Taking aerobic and anaerobic exercise as examples, the second condition is that anaerobic exercise does not belong to the follow-along type of exercise.
  • steps S122 and S123 can be executed in parallel to further improve efficiency.
  • the name of each fitness movement in the fitness movement library includes a first type name and a second type name, wherein the first type name and the second type name have different probabilities of being used among multiple users.
  • the step of obtaining the motion diagram and/or dynamic image of each target fitness movement from the fitness movement library based on the name of each target fitness movement includes: performing a matching operation between the name of each target fitness movement and the first type name and the second type name of the plurality of fitness movements in the fitness movement library, to obtain the motion diagram and/or dynamic image of each target fitness movement from the fitness movement library.
  • the system by configuring different categories of names for fitness movements in the fitness movement library, corresponding to different probabilities of use by multiple users, the system takes into account the situation where the name of the generated target fitness movement does not match the name in the fitness movement library, thereby improving the matching accuracy and efficiency of the fitness movement library, and thus improving the accuracy and efficiency of fitness plan recommendations.
  • the probability of a first-category name for each fitness exercise being used among the multiple users is higher than the probability of a second-category name for each fitness exercise being used among the multiple users.
  • the step of performing a matching operation between the name of each target fitness exercise and the first and second-category names of the multiple fitness exercises in the fitness exercise library to obtain the motion diagram and/or dynamic image of each target fitness exercise from the fitness exercise library includes the following operations.
  • a first matching operation is performed on the name of each target fitness movement and the first type of names of the plurality of fitness movements in the fitness movement library.
  • a second matching operation is performed on the name of each target fitness movement and the second type of names of the plurality of fitness movements in the fitness movement library to obtain the motion diagram and/or dynamic image of each target fitness movement from the fitness movement library.
  • the motion diagrams and/or dynamic images corresponding to the first category of names that match the names of the target fitness movements are used as the motion diagrams and/or dynamic images of each target fitness movement.
  • prioritizing the matching of first-category names that are more likely to be used among multiple users can further improve matching efficiency, thereby further improving the efficiency of fitness plan recommendations.
  • the plurality of second fitness plans are generated based on at least one of the demonstration content, exercise diagrams, and dynamic images of the plurality of target fitness movements, as well as the plurality of reference fitness plans.
  • the fitness guidance content of the plurality of target fitness movements in the plurality of second fitness plans includes at least one of the demonstration content, exercise diagrams, and dynamic images of the plurality of target fitness movements.
  • the fitness plan is made more in line with the actual fitness scenario, and more accurate fitness plans are recommended to users, thereby further improving the accuracy of fitness plan recommendations and enhancing the user experience.
  • the fitness exercise library further includes at least one of fitness exercise guides and fitness exercise techniques corresponding to the names of multiple fitness exercises, and generating the multiple second fitness plans based on at least one of the demonstration content, exercise diagrams, and dynamic images of the multiple target fitness exercises and the multiple reference fitness plans includes:
  • each target fitness movement meets the second condition, then, based on the name of each target fitness movement, at least one of the fitness movement guide and fitness movement technique for each target fitness movement is obtained from the fitness movement library.
  • the multiple second fitness plans are generated.
  • the fitness guidance content of the multiple target fitness movements in the multiple second fitness plans also includes at least one of the fitness movement guides and fitness movement techniques for the multiple target fitness movements.
  • the recommended fitness plans for different users or the same user at different times can be relatively stable, improving the stability of fitness plan generation.
  • the exercise guides are textual descriptions instructing users on how to perform the exercises.
  • the exercise techniques are textual descriptions providing tips and tricks for performing the exercises.
  • step S130 the first fitness plan and the plurality of second fitness plans are displayed to the user.
  • displaying the first fitness plan and the plurality of second fitness plans to the user includes: rendering the first fitness plan in a first card; rendering each second fitness plan in a second card corresponding to each second fitness plan; displaying the first card to the user and hiding the plurality of second cards corresponding to the plurality of second fitness plans; and displaying the second card corresponding to the trigger operation to the user in response to the user performing a trigger operation on the first card.
  • the jump from the first card to the plurality of second cards is realized. Displaying or showing the first fitness plan and the plurality of second fitness plans to the user in a card-based manner can further improve the user experience.
  • the first fitness plan includes a plurality of first sub-fitness plans corresponding one-to-one with the plurality of sub-time periods, and the plurality of first sub-fitness plans correspond one-to-one with the plurality of second fitness plans.
  • Presenting the first fitness plan and the plurality of second fitness plans to the user includes: rendering the plurality of first sub-fitness plans in a first card; rendering the second fitness plan corresponding to each first sub-fitness plan in a second card corresponding to each first sub-fitness plan; presenting the first card to the user and hiding the second card; and, in response to the user performing a trigger operation on any one of the first sub-fitness plans in the first card, presenting the user with the second card corresponding to that first sub-fitness plan.
  • a fitness summary message is generated and sent to the user based on the first fitness plan and the plurality of second fitness plans.
  • the fitness summary message includes information such as fitness goals for a target time period, expected fitness results, and fitness precautions.
  • Figure 3 is a flowchart illustrating a fitness plan recommendation method according to other embodiments of the present disclosure.
  • the user sends a request to the agent to obtain a fitness plan.
  • the agent returns a message to the user stating "Plan generation in progress, please wait.”
  • the agent then calls the large model (large language model) to generate a simple plan.
  • the simple plan includes the exercise type and muscle groups targeted for each of the seven days of the week.
  • the simple plan includes the exercise type and muscle groups targeted for each day from Monday to Friday, while Saturday and Sunday are rest days with null values for the exercise type and muscle groups targeted.
  • the process of the agent returning the message to the user and calling the large model to generate the simple plan is executed asynchronously.
  • Intelligent agents can use computer program modules (code) to supplement dates on simple plans. For example, a user Request a fitness plan from M3, 20YY to M9, 20YY. The agent generates a seven-day fitness plan and then uses a date completion function or procedure to add the dates from M3, 20YY to M9, 20YY to each day of the simple plan.
  • code computer program modules
  • the agent invokes a large model to generate detailed daily plans for multiple days.
  • the agent can concurrently invoke the large model to generate detailed daily plans for multiple days based on a simple plan.
  • the concurrency of the large model is determined by the number of days when the exercise type and exercise body part are not null values. For example, if the exercise type and exercise body part are not null values from Monday to Friday, the concurrency of the large model is 5.
  • detailed daily plans for Monday to Friday are generated by concurrently invoking the large model. For example, these five days can be divided into aerobic exercise days and anaerobic exercise days.
  • the large model can have two settings: an aerobic setting and an anaerobic setting.
  • the detailed daily plans for Monday to Friday include anaerobic day plans and aerobic day plans.
  • the intelligent agent can also use the large model to perform natural language processing on simple plans and detailed daily plans for multiple days to obtain fitness summary information and send the fitness summary information to the user.
  • the agent retrieves exercise diagrams and/or animated images of the exercises from the detailed daily plan by querying the fitness exercise library, as a supplement to the detailed daily plan. For example, if the fitness exercise library does not contain exercise diagrams and/or animated images of the exercises in the detailed daily plan, the agent searches from the target content platform to obtain at least one of the following: exercise diagrams, animated images, and demonstration content of the exercises in the detailed daily plan, as a supplement to the detailed daily plan.
  • Table 1 illustrates the data structure of the fitness exercise library.
  • the fitness exercise library includes the name of the exercise, an illustration or animation, a description of the exercise, the body part being worked, the exercise equipment used, the major and other muscle groups being worked, exercise guidelines, and exercise techniques.
  • the fitness exercise library can be stored in a database. Table 1 only shows information for one fitness exercise; in reality, the fitness exercise library includes information for multiple fitness exercises.
  • the field for name is represented by “fitness_move_name”
  • the field for exercise illustration or animation is represented by “fitness_move_gif”
  • the field for action description is represented by “fitness_move_description”
  • the field for the body part being exercised is represented by “body_part”
  • the field for the exercise equipment used is represented by “equipment”
  • the field for the primary muscle groups being exercised is represented by “primar_muscles”
  • the field for other muscle groups is represented by “secondary_muscles”
  • the field for fitness exercise guides is represented by “fitness_move_tutorial”
  • the field for fitness exercise tips is represented by “fitness_move_tips”.
  • the fitness exercise library stores the animated images 1 and 2 corresponding to the fitness exercise "barbell front squat”.
  • the description includes "Description Content 1", the target muscle group “Hips”, the exercise equipment “Barbell”, the main muscle groups “Gluteus Maximus, Quadriceps”, the other muscle groups “Adductor Magnus, Soleus”, the fitness exercise guide “Guide 1", and the fitness exercise techniques "Technique 1".
  • the barbell front squat is a strength training exercise that primarily targets the quadriceps, glutes, and core muscles, while also working the upper body and improving overall balance. This exercise is ideal for athletes, weightlifters, and fitness enthusiasts looking to enhance lower body strength, increase muscle mass, and improve functional health. People can choose to incorporate this exercise into their daily routine to achieve better body composition, improve athletic performance, and promote more effective movement patterns in daily life.”
  • Guideline 1 for the exercise “Barbell Front Squat” includes: “Carefully lift the barbell off the rack, then step back with your feet shoulder-width apart and toes slightly turned out. Bend your knees and hips to lower your body, keeping your back straight and chest out, until your thighs are parallel to the floor. Push your heels back to the starting position, keeping your core engaged and the barbell positioned on your shoulders. Repeat the exercise for the desired number of repetitions, then carefully return the barbell to the rack.”
  • the "Tip 1" for the barbell front squat includes "Correct foot placement: Feet should be shoulder-width apart or slightly wider. Toes slightly outward. Incorrect foot placement can lead to instability and potential injury. Maintain a neutral spine: Another common mistake is arching the back during the squat. To avoid this, focus on keeping your chest up and spine neutral throughout the movement. This helps protect your back and ensures you are working the correct muscles. Proper depth: The goal is to lower your body until your thighs are at least parallel to the floor.”
  • the agent searches for demonstration content of fitness movements in the detailed daily plan by searching the target content platform for fitness movements of the aerobic exercise type, as a supplement to the detailed daily plan.
  • Figure 4A shows a card displaying a simple weekly plan to the user.
  • Figure 4A is a schematic diagram illustrating a weekly fitness plan according to some embodiments of the present disclosure.
  • the exercise type and exercise area for Monday are Exercise Type 1, for Tuesday it is Exercise Type 2, for Wednesday it is Exercise Type 3, for Thursday it is Exercise Type 4, for Friday it is Exercise Type 5, for Saturday and Sunday the exercise type and exercise area are empty, indicating rest.
  • Figure 4B is a schematic diagram illustrating a daily fitness plan according to some embodiments of the present disclosure.
  • each target fitness movement includes squats, Romanian deadlifts, and leg curls.
  • each target fitness movement corresponds to a dynamic image to guide the user in correctly performing each movement.
  • Squats correspond to dynamic image 1, Romanian deadlifts to dynamic image 2, and leg curls to dynamic image 3.
  • the card showing a detailed daily plan for Tuesday may also display the number of sets for each target exercise, the number of repetitions per set, and the sub-muscle muscles targeted for each target exercise. For example, squats are performed in 4 sets of 12 repetitions each; Romanian deadlifts in 4 sets of 10 repetitions each; and leg curls in 3 sets of 15 repetitions each. Another example is that squats target the hips, Romanian deadlifts target the hips, and leg curls target the hamstrings and thighs.
  • the card showing a detailed daily plan for Tuesday may also display rest periods between different target fitness exercises (not shown in Figure 4B).
  • Figures 4A and 4B show that the card may also display the total daily workout time and total energy expenditure (not shown in Figures 4A and 4B).
  • Figures 3 to 4B are merely examples of this disclosure and do not constitute a specific limitation on this disclosure.
  • the division between anaerobic and aerobic exercises can be configured according to actual circumstances.
  • Figure 5 is a flowchart illustrating a fitness plan recommendation method according to other embodiments of the present disclosure.
  • the fitness plan recommendation method includes steps S500 to S570.
  • step S500 the user requests the bot engine to generate a fitness plan.
  • step S510 the intelligent agent engine recognizes the user's request intent and controls the workflow to start generating a fitness plan, which includes a simple plan for a week (weekly fitness plan) and a detailed plan for each day of the week (daily fitness plan).
  • a fitness plan which includes a simple plan for a week (weekly fitness plan) and a detailed plan for each day of the week (daily fitness plan).
  • step S520 the workflow initiates an operation to search for the corresponding exercise diagrams and/or animated images of anaerobic exercises in the fitness exercise library, and to add the corresponding exercise diagrams and/or animated images of anaerobic exercises to the daily detailed plan corresponding to that anaerobic exercise.
  • the fitness exercise library is, for example, a database structure.
  • step S530 the workflow initiates the operation of searching for demonstration content corresponding to aerobic exercise on the target content platform and adding the demonstration content corresponding to aerobic exercise to the daily detailed plan corresponding to that aerobic exercise.
  • step S540 the workflow initiates the operation of sending the fitness plan to the storage module.
  • step S550 the storage module stores the weekly fitness plan and the daily fitness plan for the seven days of the week.
  • step S560 the workflow starts the local plugin to generate cards based on the weekly fitness plan and the daily fitness plan for the seven days of the week stored in the storage module.
  • step S570 the local plugin returns the generated card to the user, displaying the weekly fitness plan and the daily fitness plan for the seven days of the week to the user in the form of a card.
  • the intelligent agent system in Figure 5 consists of the intelligent agent engine, workflow, fitness exercise library, storage module, and local plugins.
  • this intelligent agent system can be called a healthy living intelligent agent.
  • Figure 5 is merely an example of this disclosure and does not constitute a specific limitation on the fitness plan recommendation method of this disclosure.
  • the above describes some embodiments of the fitness plan recommendation method provided in this disclosure.
  • the fitness plan recommendation device in some embodiments of this disclosure will now be described with reference to FIG6.
  • Figure 6 is a block diagram illustrating a fitness plan recommendation device according to some embodiments of the present disclosure.
  • the fitness plan recommendation device 6 includes a first generation module 61, a second generation module 62, and a display module 63.
  • the first generation module 61 is configured to generate a first fitness plan corresponding to a target time period in response to receiving a user's request for a fitness plan.
  • the target time period includes multiple sub-time periods
  • the first fitness plan includes the exercise types and exercise parts of the multiple sub-time periods.
  • the second generation module 62 is configured to generate multiple second fitness plans corresponding to the multiple sub-time periods based on the first fitness plan, wherein the multiple second fitness plans include the names and fitness instructions of multiple target fitness movements corresponding to the exercise types and exercise parts in the multiple sub-time periods of the first fitness plan. Allow.
  • the display module 63 is configured to display the first fitness plan and the plurality of second fitness plans to the user.
  • the fitness plan recommendation device 6 can be used to perform steps S110 to S130 of FIG1. In some embodiments, the fitness plan recommendation device 6 can also perform any steps in other embodiments of this disclosure.
  • modules are logical modules divided according to their specific functions, and are not intended to limit the specific implementation method. For example, they can be implemented in software, hardware, or a combination of both. In actual implementation, the above modules can be implemented as independent physical entities, or they can be implemented by a single entity (e.g., a processor (CPU or DSP, etc.), integrated circuit, etc.). Furthermore, the modules shown in the accompanying drawings with dashed lines indicate that these modules may not actually exist, and the operations/functions they perform can be implemented by the processing circuitry itself.
  • Figure 7 is a block diagram illustrating a fitness plan recommendation device according to some embodiments of the present disclosure.
  • the fitness plan recommendation device 7 includes: a memory 71; and a processor 72 coupled to the memory 71, the processor 72 being configured to execute the fitness plan recommendation method described in any of the foregoing embodiments based on instructions stored in the memory 71.
  • Memory 71 is used to store one or more computer-readable instructions.
  • Memory 71 may include any combination of various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory.
  • RAM random access memory
  • DRAM dynamic random access memory
  • SRAM static random access memory
  • ROM read-only memory
  • flash memory volatile memory and/or non-volatile memory
  • Memory 71 may, for example, store operating systems, application programs, boot loaders, databases, and other programs, as well as various application programs and various data.
  • the processor 72 is configured to execute computer-readable instructions to implement the fitness plan recommendation method described in any of the foregoing embodiments. Specific implementation details of each step of the fitness plan recommendation method can be found in the above embodiments; repeated details will not be elaborated upon here.
  • the processor 72 and the memory 71 can communicate with each other directly or indirectly.
  • the processor 72 and the memory 71 can communicate via a network.
  • the network can include a wireless network, a wired network, and/or any combination of wireless and wired networks.
  • the processor 72 and the memory 71 can also communicate with each other via a system bus, which is not limited in this disclosure.
  • the components of the fitness plan recommendation device 7 shown in Figure 7 are merely exemplary and not limiting.
  • the fitness plan recommendation device 7 may also have other components depending on the actual application requirements.
  • the processor 72 can utilize other components in the fitness plan recommendation device 7 to perform the desired functions.
  • Fitness program recommendation devices can be implemented through software, firmware, and/or hardware, and can be integrated into electronic devices with relevant applications installed.
  • Figure 8 shows a block diagram of an electronic device according to some embodiments of the present disclosure.
  • the electronic device 8 shown in Figure 8 can be a computer system with a dedicated hardware structure, capable of performing corresponding functions when relevant applications are installed.
  • Electronic devices include, but are not limited to, mobile terminals such as smartphones, laptops, personal digital assistants (PDAs), tablet computers (Tablet PCs), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), wearable devices, and fixed terminals such as digital televisions and desktop computers.
  • mobile terminals such as smartphones, laptops, personal digital assistants (PDAs), tablet computers (Tablet PCs), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), wearable devices, and fixed terminals such as digital televisions and desktop computers.
  • PDAs personal digital assistants
  • Tablet PCs tablet computers
  • PMPs portable multimedia players
  • in-vehicle terminals such as in-vehicle navigation terminals
  • wearable devices such as digital televisions and desktop computers.
  • the Central Processing Unit (CPU) 81 performs various processes based on programs stored in the Read-Only Memory (ROM) 82 or programs loaded from the storage section 88 into the Random Access Memory (RAM) 83.
  • the RAM 83 stores data required as needed when the CPU 81 performs various processes.
  • the CPU is merely exemplary and can also be other types of processors, such as the various processors described above.
  • the ROM 82, RAM 83, and storage section 88 can be various forms of computer-readable storage media. It should be noted that although the ROM 82, RAM 83, and storage section 88 are shown separately in Figure 8, one or more of them can be combined or located in the same or different memories or storage modules.
  • CPU 81, ROM 82 and RAM 83 are interconnected via bus 84.
  • Input/output interface 85 is also connected to bus 84.
  • input section 86 such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.
  • output section 87 including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.
  • storage section 88 including hard disk, magnetic tape, etc.
  • communication section 89 including network interface cards such as LAN cards, modems, etc.
  • the communication section 89 allows communication processing to be performed via a network such as the Internet. It is readily understood that although the various devices or modules in the electronic device 8 shown in Figure 8 communicate via bus 84, they can also communicate via a network or other means, wherein the network can include wireless networks, wired networks, and/or any combination of wireless and wired networks.
  • Drive 810 is also connected to input/output interface 85 as needed.
  • Removable media 811 include, for example, hard disks, optical disks, etc. Magneto-optical disks, semiconductor memories, etc., are installed on drive 810 as needed, so that computer programs read from them are installed into storage section 88 as needed.
  • the program constituting the software can be installed from a network such as the Internet or a storage medium such as a removable medium 811.
  • the processes described above with reference to the flowcharts can be implemented as computer software programs.
  • some embodiments of this disclosure include a computer program product that, when run on a computer, causes the computer to implement the fitness plan recommendation method described in any of the foregoing embodiments.
  • the computer program product includes a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts.
  • the computer program can be downloaded and installed from a network via communication section 89, or installed from storage section 88, or installed from ROM 82.
  • the fitness plan recommendation method of the embodiments of this disclosure is performed.
  • a computer-readable medium can be a tangible medium that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable medium may be a computer-readable storage medium, a computer-readable signal medium, or any combination thereof.
  • Computer-readable storage media include, but are not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
  • a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer program is stored on the computer-readable storage medium that, when executed by a processor, implements the fitness plan recommendation method described in any of the foregoing embodiments.
  • Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.
  • Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.
  • the included program code can be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.
  • the aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.
  • a computer program product which, when run on a computer, causes the computer to implement the fitness plan recommendation method described in any of the above embodiments.
  • a computer program comprising: instructions that, when executed by a processor, cause the processor to perform the fitness plan recommendation method of any of the above embodiments.
  • the instructions may be embodied in computer program code.
  • computer program code for performing the operations of this disclosure can be written in one or more programming languages or a combination thereof.
  • programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages such as the "C" language or similar programming languages.
  • the program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server.
  • the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).
  • LAN local area network
  • WAN wide area network
  • each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function.
  • the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.
  • each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
  • exemplary hardware logic components include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application-Specific Integrated Circuits
  • ASSPs Application Standard Products
  • SoCs System-on-Chip
  • CPLDs Complex Programmable Logic Devices

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

本公开涉及健身计划推荐方法及装置、存储介质、程序产品，涉及计算机技术领域。健身计划推荐方法包括：响应于接收用户的获取健身计划的请求信息，生成与目标时间段对应的第一健身计划，其中，所述目标时间段包括多个子时间段，所述第一健身计划包括所述多个子时间段的运动类型和锻炼部位；根据所述第一健身计划，生成与所述多个子时间段对应的多个第二健身计划，其中，所述多个第二健身计划包括与所述第一健身计划中所述多个子时间段的运动类型和锻炼部位对应的多个目标健身动作的名称和健身指导内容；向所述用户展示所述第一健身计划和所述多个第二健身计划。根据本公开，可以提高健身计划推荐的准确性。

Description

健身计划推荐方法及装置、存储介质、程序产品 技术领域
本公开涉及计算机技术领域，特别涉及一种健身计划推荐方法及装置、存储介质、程序产品。
背景技术
随着人工智能技术的发展，智能体的应用已经渗透到我们生活的各个方面，例如智能问答、智能语音助手、智能规划等。
相关技术中，根据用户的获取健身计划的请求，直接一步生成多日的健身计划。
发明内容
提供该发明内容部分以便以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。该发明内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
根据本公开一些实施例的第一方面，提供一种健身计划推荐方法，包括：
响应于接收用户的获取健身计划的请求信息，生成与目标时间段对应的第一健身计划，其中，所述目标时间段包括多个子时间段，所述第一健身计划包括所述多个子时间段的运动类型和锻炼部位；
根据所述第一健身计划，生成与所述多个子时间段对应的多个第二健身计划，其中，所述多个第二健身计划包括与所述第一健身计划中所述多个子时间段的运动类型和锻炼部位对应的多个目标健身动作的名称和健身指导内容；
向所述用户展示所述第一健身计划和所述多个第二健身计划。
根据本公开一些实施例的第二方面，提供一种健身计划推荐装置，包括：
第一生成模块，被配置为响应于接收用户的获取健身计划的请求信息，生成与目标时间段对应的第一健身计划，其中，所述目标时间段包括多个子时间段，所述第一健身计划包括所述多个子时间段的运动类型和锻炼部位；
第二生成模块，被配置为根据所述第一健身计划，生成与所述多个子时间段对应的多个第二健身计划，其中，所述多个第二健身计划包括与所述第一健身计划中所述 多个子时间段的运动类型和锻炼部位对应的多个目标健身动作的名称和健身指导内容；
展示模块，被配置为向所述用户展示所述第一健身计划和与所述多个第二健身计划。
根据本公开的一些实施例的第三方面，提供一种电子设备，包括：存储器；和耦接至存储器的处理器，所述处理器被配置为基于存储在所述存储器中的指令，执行本公开中所述的任一实施例的健身计划推荐方法。
根据本公开的一些实施例的第四方面，提供一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时执行本公开中所述的任一实施例的健身计划推荐方法。
根据本公开的一些实施例的第五方面，提供一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得所述计算机实现所述任一实施例的健身计划推荐方法。
通过以下参照附图对本公开的示例性实施例的详细描述，本公开的其它特征、方面及其优点将会变得清楚。
附图说明
下面参照附图说明本公开的优选实施例。此处所说明的附图用来提供对本公开的进一步理解，各附图连同下面的具体描述一起包含在本说明书中并形成说明书的一部分，用于解释本公开。应当理解的是，下面描述中的附图仅仅涉及本公开的一些实施例，而非对本公开构成限制。在附图中：
图1是示出根据本公开一些实施例的健身计划推荐方法的流程示意图；
图2是示出根据本公开一些实施例的生成与所述多个子时间段对应的多个第二健身计划的流程示意图；
图3是示出根据本公开另一些实施例的健身计划推荐方法的流程示意图；
图4A是示出根据本公开一些实施例的周健身计划的示意图；
图4B是示出根据本公开一些实施例的日健身计划的示意图；
图5是示出根据本公开另一些实施例的健身计划推荐方法的流程示意图；
图6是示出根据本公开一些实施例的健身计划推荐装置的框图；
图7是示出根据本公开一些实施例的健身计划推荐装置的框图；
图8示出根据本公开一些实施例的电子设备的框图。
应当明白，为了便于描述，附图中所示出的各个部分的尺寸并不一定是按照实际的比例关系绘制的。在各附图中使用了相同或相似的附图标记来表示相同或者相似的部件。因此，一旦某一项在一个附图中被定义，则在随后的附图中可能不再对其进行进一步讨论。
具体实施方式
下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，但是显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。以下对实施例的描述实际上也仅仅是说明性的，决不作为对本公开及其应用或使用的任何限制。应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。除非另外具体说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值应被解释为仅仅是示例性的，不限制本公开的范围。
本公开中使用的术语“包括”及其变型意指至少包括后面的元件/特征、但不排除其他元件/特征的开放性术语，即“包括但不限于”。此外，本公开使用的术语“包含”及其变型意指至少包含后面的元件/特征、但不排除其他元件/特征的开放性术语，即“包含但不限于”。因此，包括与包含是同义的。术语“基于”意指“至少部分地基于”。
整个说明书中所称“一个实施例”、“一些实施例”或“实施例”意味着与实施例结合描述的特定的特征、结构或特性被包括在本发明的至少一个实施例中。例如，术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。而且，短语“在一个实施例中”、“在一些实施例中”或“在实施例中”在整个说明书中各个地方的出现不一定全都指的是同一个实施例，但是也可以指同一个实施例。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。除非另有指定，否则“第一”、“第二”等概念并非意图暗示如此描述的对象必须按时间上、空间上、排名上的给定顺序或任何其他方式的给定顺序。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
下面结合附图对本公开的实施例进行详细说明，但是本公开并不限于这些具体的实施例。下面这些具体实施例可以相互结合，对于相同或者相似的概念或过程可能在某些实施例不再赘述。此外，在一个或多个实施例中，特定的特征、结构或特性可以由本领域的普通技术人员从本公开将清楚的任何合适的方式组合。
大语言模型(large language model，LLM)是一种基于人工智能的强大工具，具备生成和理解自然语言的能力。它是在大规模数据集上进行训练的深度学习模型，旨在模拟人类的语言能力和智能思维过程。这些模型被广泛应用于自然语言处理、对话系统、文本生成和其他语言相关的任务中。
大语言模型的训练过程涉及海量的文本数据。它通过对这些数据进行自监督学习来获取语言的统计知识和语义理解。在预训练阶段，模型学习预测文本中下一个字或下一个句子，以捕捉上下文和语义关系。通过这种方式，模型逐渐建立起对语言的深层理解和生成能力。
大语言模型可以应用于各种具体任务。它可以接收用户的输入，并生成相应的文本回复，或者根据给定的上下文生成连贯的文章。模型可以进行语言翻译、文档摘要、问题回答等任务，并且在许多情况下表现出令人印象深刻的语言理解和生成能力。
相关技术中，直接一步生成多日健身计划的方式，多日健身计划的准确性较低，用户体验较差。
本公开提供了一种技术方案，可以提高健身计划推荐的准确性，提升用户体验。
图1是示出根据本公开一些实施例的健身计划推荐方法的流程示意图。
如图1所示，健身计划推荐方法包括：步骤S110，响应于接收用户的获取健身计划的请求信息，生成与目标时间段对应的第一健身计划，其中，所述目标时间段包括多个子时间段，所述第一健身计划包括所述多个子时间段的运动类型和锻炼部位；步骤S120，根据所述第一健身计划，生成与所述多个子时间段对应的多个第二健身计划，其中，所述多个第二健身计划包括与所述第一健身计划中所述多个子时间段的运动类型和锻炼部位对应的多个目标健身动作的名称和健身指导内容；和步骤S130，向所述用户展示所述 第一健身计划和与所述多个第二健身计划。健身计划推荐方法例如由智能体系统执行。智能体也可以称为机器人(bot)。
在上述实施例中，对于多个子时间段的健身计划，本公开在第一个阶段生成多个子时间段的运动类型和锻炼部位，在第二阶段基于第一个阶段生成的多个子时间段的运动类型和锻炼部位，进一步细化第一健身计划，生成多个子时间段的目标健身动作的名称和健身指导内容。本公开将多个子时间段的健身计划的生成过程划分成两个阶段，先生成粗略的健身计划，进而基于粗略的健身计划生成详细的健身计划，将复杂任务简单化，可以提高健身计划推荐的准确性。
在步骤S110中，响应于接收用户的获取健身计划的请求信息，生成与目标时间段对应的第一健身计划，其中，所述目标时间段包括多个子时间段，所述第一健身计划包括所述多个子时间段的运动类型和锻炼部位。
在一些实施例中，可以利用模型生成与所述目标时间段对应的第一健身计划。例如，可以利用生成模型生成与所述目标时间段对应的第一健身计划。又例如，也可以利用大语言模型生成与所述目标时间段对应的第一健身计划。
在一些实施例中，所述响应于接收用户的获取健身计划的请求信息，生成与目标时间段对应的第一健身计划包括：对所述请求信息进行意图理解，得到所述用户的健身意图信息；根据所述健身意图信息，生成所述第一健身计划。例如，利用自然语言处理模型对请求信息进行意图理解。
在步骤S120中，根据所述第一健身计划，生成与所述多个子时间段对应的多个第二健身计划，其中，所述多个第二健身计划包括与所述第一健身计划中所述多个子时间段的运动类型和锻炼部位对应的多个目标健身动作的名称和健身指导内容。目标健身动作的名称例如为杠铃前蹲，健身指导内容例如为指导用户完成杠铃前蹲的描述信息，该描述信息可以是文本的，也可以是视觉的。
在一些实施例中，可以根据所述第一健身计划，并行生成与所述多个子时间段对应的多个第二健身计划。在该实施例中，在第二个阶段，多个子时间段的多个第二健身计划并行生成，可以提高健身计划推荐的效率。
在一些实施例中，可以利用模型并行生成与所述多个子时间段对应的多个第二健身计划。例如，可以利用生成模型并行生成与所述多个子时间段对应的多个第二健身计划。又例如，也可以利用大语言模型并行生成与所述多个子时间段对应的多个第二健身计划。
利用模型并行生成多个第二健身计划例如通过并发调用模型实现，即同时向模型发送多个请求，每个请求用于请求生成至少一个第二健身计划。
在一些实施例中，生成第一健身计划和生成多个第二健身计划所使用的模型可以是同一个模型，也可以是不同的模型。例如，生成第一健身计划和生成多个第二健身计划所使用的模型是同一个大语言模型，该大语言模型通过不同的模型设定来生成不同的健身计划。
在一些实施例中，可以通过如图2所示的步骤S121～步骤S124实现图1的步骤S120。
图2是示出根据本公开一些实施例的生成与所述多个子时间段对应的多个第二健身计划的流程示意图。
如图2所示，在步骤S121中，根据所述第一健身计划中的所述多个子时间段的运动类型和锻炼部位，生成与所述多个子时间段对应的多个参考健身计划，其中，所述多个参考健身计划包括所述多个子时间段的多个目标健身动作的名称。
在一些实施例中，可以利用模型(如生成模型或大语言模型)并行生成多个参考健身计划。例如，针对所述多个子时间段，并行调用模型，对所述多个子时间段的运动类型和锻炼部位进行处理，得到所述多个参考健身计划。
在一些实施例中，多个参考健身计划还可以包括所述多个子时间段的多个目标健身动作的参考健身指导内容。这取决于模型的设定。
在一些实施例中，所述多个参考健身计划还包括所述多个目标健身动作的执行方式，其中，所述执行方式包括所述多个目标健身动作在所述多个子时间段的执行顺序、执行每个目标健身动作的数量，所述多个第二健身计划还包括所述多个目标健身动作的执行方式。
在步骤S122中，在每个目标健身动作对应的运动类型满足第一条件的情况下，从目标内容平台，获取所述每个健身动作的演示内容。例如，运动类型可以分为有氧运动和无氧运动，第一条件例如为有氧运动属于跟练类型的运动类型。演示内容例如为用于用户跟练健身动作的内容。例如，目标内容平台包括但不限于目标视频平台，演示内容包括但不限于演示视频。演示视频例如为跟练视频。
在一些实施例中，可以调用搜索插件(plugin)，对目标内容平台中的多个视频与所述每个目标健身动作进行匹配操作，得到所述每个健身动作的演示内容。目标内容平台中的多个内容具有内容标签，可以通过内容标签与每个目标健身动作的名称或 其他描述信息进行匹配，得到所述每个健身动作的演示内容。
在步骤S123中，在所述每个目标健身动作对应的运动类型满足第二条件的情况下，根据所述每个目标健身动作的名称，从健身动作库中，获取所述每个目标健身动作的运动图解和/或动态图像，其中，所述健身动作库包括预先配置的多个健身动作的名称和与每个健身动作的名称对应的运动图解和/或动态图像。健身动作库根据健身领域的健身动作构建，可以是健身领域专业的知识库。以有氧运动和无氧运动为例，第二条件为无氧运动不属于跟练类型的运动类型。在一些实施例中，步骤S122和步骤S123可以并行执行，进一步提高效率。
在一些实施例中，所述健身动作库中每个健身动作的名称包括第一类名称和第二类名称，所述第一类名称和所述第二类名称在多个用户中被使用的概率不同。所述根据所述每个目标健身动作的名称，从健身动作库中，获取所述每个目标健身动作的运动图解和/或动态图像包括：对所述每个目标健身动作的名称与所述健身动作库中所述多个健身动作的第一类名称和第二类名称执行匹配操作，以从所述健身动作库中，获取所述每个目标健身动作的运动图解和/或动态图像。
在该实施例中，通过在健身动作库中配置健身动作的对应不同的被多个用户使用的概率的不同类别的名称，考虑了生成的目标健身动作的名称与健身动作库中的名称不相符的情况，提高了健身动作库的匹配准确性和效率，从而提高健身计划推荐的准确性和效率。
在一些实施例中，每个健身动作的第一类名称在所述多个用户中被使用的概率高于所述每个健身动作的第二类名称在所述多个用户中被使用的概率。所述对所述每个目标健身动作的名称与所述健身动作库中所述多个健身动作的第一类名称和第二类名称执行匹配操作，以从所述健身动作库中，获取所述每个目标健身动作的运动图解和/或动态图像包括如下操作。
首先，对所述每个目标健身动作的名称与所述健身动作库中所述多个健身动作的第一类名称执行第一匹配操作。
然后，在所述第一匹配操作失败的情况下，对所述每个目标健身动作的名称与所述健身动作库中所述多个健身动作的第二类名称执行第二匹配操作，以从所述健身动作库中，获取所述每个目标健身动作的运动图解和/或动态图像。
最后，在所述第一匹配操作成功的情况下，从所述健身动作库中，获取与所述每 个目标健身动作的名称匹配的第一类名称对应的运动图解和/或动态图像，作为所述每个目标健身动作的运动图解和/或动态图像。
在该实施例中，优先匹配在多个用户中被使用的概率较高的第一类名称，可以进一步提高匹配的效率，从而进一步提高健身计划推荐的效率。
在步骤S124中，根据所述多个目标健身动作的演示内容、运动图解和动态图像中的至少一种以及所述多个参考健身计划，生成所述多个第二健身计划，其中，所述多个第二健身计划中的所述多个目标健身动作的健身指导内容包括所述多个目标健身动作的演示内容、运动图解和动态图像中的至少一种。
在上述实施例中，基于步骤S121～步骤S124，通过判断运动类型满足第一条件还是第二条件，结合内容平台的内容搜索和健身动作库的运动图解和/或动态图像的搜索，使得健身计划更加贴合实际健身场景，为用户推荐更加精准的健身计划，从而进一步提高健身计划推荐的准确性，提升用户体验。
在一些实施例中，所述健身动作库还包括与多个健身动作的名称对应的健身动作指南和健身动作技巧中的至少一种，所述根据所述多个目标健身动作的演示内容、运动图解和动态图像中的至少一种以及所述多个参考健身计划，生成所述多个第二健身计划包括：
在所述每个目标健身动作对应的运动类型满足第二条件的情况下，根据所述每个目标健身动作的名称，从所述健身动作库中，获取所述每个目标健身动作的健身动作指南和健身动作技巧中的至少一种；
根据所述多个目标健身动作的演示内容、运动图解和动态图像中的至少一种、所述多个参考健身计划以及所述每个目标健身动作的健身动作指南和健身动作技巧中的至少一种，生成所述多个第二健身计划，其中，所述多个第二健身计划中所述多个目标健身动作的健身指导内容还包括所述多个目标健身动作的健身动作指南和健身动作技巧中的至少一种。
在该实施例中，通过预配置的健身动作库提供目标健身动作的健身动作指南和健身动作技巧，可以使得不同用户或相同用户在不同时间被推荐的健身计划相对稳定，提高健身计划生成的稳定性。健身动作指南为文本形式描述的指导用户如何执行健身动作的内容。健身动作技巧为文本形式描述的提示用户在执行健身动作的过程中的动作技巧。
返回图1，在步骤S130中，向所述用户展示所述第一健身计划和所述多个第二健身计划。
在一些实施例中，向所述用户展示所述第一健身计划和与所述多个第二健身计划包括：在第一卡片中，渲染所述第一健身计划；在与每个第二健身计划对应的第二卡片中，渲染所述每个第二健身计划；向所述用户展示所述第一卡片，隐藏所述多个第二健身计划对应的多个第二卡片；响应于所述用户对所述第一卡片执行触发操作，向所述用户展示与所述触发操作对应的第二卡片。在该实施例中，通过构建第一卡片和第二卡片之间的关联，实现第一卡片向多个第二卡片的跳转。通过卡片方式向用户显示或展示第一健身计划和多个第二健身计划，可以进一步提高用户体验。
在一些实施例中，所述第一健身计划包括与所述多个子时间段一一对应的多个第一子健身计划，所述多个第一子健身计划与所述多个第二健身计划一一对应，所述向所述用户展示所述第一健身计划和所述多个第二健身计划包括：在第一卡片中，渲染所述多个第一子健身计划；在与每个第一子健身计划对应的第二卡片中，渲染与所述每个第一子健身计划对应的第二健身计划；向所述用户展示所述第一卡片，隐藏所述第二卡片；响应于所述用户对所述第一卡片中的任一个第一子健身计划执行触发操作，向所述用户展示与所述任一个第一子健身计划对应的第二卡片。
在一些实施例中，在向所述用户展示所述第一健身计划和与所述多个第二健身计划之前，根据所述第一健身计划和与所述多个第二健身计划，生成并发送健身总结信息至所述用户。例如，健身总结消息包括目标时间段的健身目标、预期达到的健身效果和健身注意事项等信息。
下面将以生成周健身计划为例，详细描述本公开一些实施例中的健身计划推荐方法。
图3是示出根据本公开另一些实施例的健身计划推荐方法的流程示意图。
如图3所示，用户发送获取健身计划的请求信息到智能体，智能体向用户返回“计划生成中，请稍后”的提示消息。智能体调用大模型(大语言模型)生成简单计划。简单计划包括一周七天的运动类型和锻炼部位。例如，简单计划中周一至周五每天都包括了运动类型和锻炼部位，周六和周日为休息日，运动类型和锻炼部位为空值。智能体向用户返回提示消息和调用大模型生成简单计划的过程是异步执行的。
智能体可以利用计算机程序模块(代码)对简单计划进行日期补充。例如，用户 请求20YY年M月3日到20YY年M月9日的健身计划，智能体生成一周七天的健身计划，然后利用日期补充函数或程序为简单计划的每一天补充20YY年M月3日到20YY年M月9日的日期。
智能体根据简单计划，调用大模型生成多日的详细日计划。例如，智能体可以根据简单计划，并发调用大模型生成多日的详细日计划，大模型的并发度根据运动类型和锻炼部位不为空值的天数确定。例如，周一到周五的运动类型和锻炼部位不为空值，大模型的并发度为5。参考图3，通过并发调用大模型，生成周一到周五的详细日计划。例如，可以将周一到周五这五天划分为有氧运动日和无氧运动日。大模型可以存在两种设定，一种为有氧设定，一种为无氧设定。周一到周五的详细日计划包括无氧日计划和有氧日计划。
如图3所示，智能体利用大模型还可以对简单计划和多日的详细日计划进行自然语言处理，得到健身总结信息，并向用户发送健身总结信息。
参考图3，智能体对运动类型为无氧运动的健身动作，通过查询健身动作库获取详细日计划中的健身动作的运动图解和/或动态图像，作为详细日计划的补充。例如，在健身动作库中不包括详细日计划中的健身动作的运动图解和/或动态图像的情况下，从目标内容平台搜索以获取详细日计划中的健身动作的运动图解、动态图像和演示内容中的至少一种，作为详细日计划的补充。
表1示出了健身动作库的数据结构示意。如表1所示，例如，健身动作库包括健身动作的名称、运动图解或动态图像、动作描述、锻炼的身体部位、使用的运动器械、锻炼的主要肌群和其他肌群、健身动作指南和健身动作技巧等。健身动作库可以是存储在一个数据库中。表1仅示出了一个健身动作的相关信息，实际上健身动作库包括多个健身动作的相关信息。
例如，名称的字段用“fitness_move_name”表示，运动图解或动态图像的字段用“fitness_move_gif”表示，动作描述的字段用“fitness_move_description”表示，锻炼的身体部位的字段用“body_part”表示，使用的运动器械的字段用“equipment”表示，锻炼的主要肌群的字段使用“primar_muscles”表示，其他肌群的字段用“secondary_muscles”表示，健身动作指南的字段用“fitness_move_tutorial”表示，健身动作技巧的字段用“fitness_move_tips”表示。
例如，参考表1，健身动作库存储了健身动作“杠铃前蹲”对应的动态图像1、动 作描述“描述内容1”、锻炼部位“臀部(Hips)”、运动器械“杠铃(Barbell)”、主要肌群“臀大肌(Gluteus Maximus)，四头肌(Quadriceps)”、其他肌群“内收大肌(Adductor Magnus)，比目鱼肌(Soleus)”、健身动作指南“指南1”、健身动作技巧“技巧1”。
例如，健身动作“杠铃前蹲”对应的描述内容1包括“杠铃前蹲是一种力量训练，主要针对股四头肌、臀肌和核心肌群，同时也锻炼上半身并提高整体平衡。这项锻炼非常适合寻求增强下半身力量、增加肌肉质量和改善功能健康的运动员、举重运动员和健身爱好者。人们可以选择将这种锻炼纳入日常锻炼中，以实现更好的身体成分，提高运动表现，并在日常生活中促进更有效的运动模式。”。
例如，健身动作“杠铃前蹲”对应的指南1包括“小心地将杠铃从架子上提起，然后后退一步，双脚与肩同宽，脚趾稍微向外。弯曲膝盖和臀部，降低身体，保持背部挺直，挺胸，直到大腿与地板平行。脚后跟用力站回起始位置，保持核心收紧并保持杠铃在肩膀上的位置。重复该练习达到所需的重复次数，然后小心地将杠铃放回架上。
例如，健身动作“杠铃前蹲”对应的“技巧1”包括“正确的脚部放置：双脚应与肩同宽或稍宽。将脚趾稍微向外。不正确的足部放置可能会导致不稳定和潜在的伤害。保持脊柱中立：另一个常见的错误是在深蹲时弓起背部。为了避免这种情况，请在整个运动过程中集中精力保持挺胸并保持脊柱中立。这有助于保护您的背部并确保您锻炼到正确的肌肉。适当的深度：目标是降低身体，直到大腿至少与地板平行。”
表1健身动作库的数据结构
参考图3，智能体对运动类型为有氧运动的健身动作，通过从目标内容平台搜索以获取详细日计划中的健身动作的演示内容，作为详细日计划的补充。
如图3所示，智能体完成多日的详细日计划的补充后，保存简单计划和多日的详 细日计划，生成并发送渲染了简单计划和多日详细日计划的卡片到用户。卡片的形式可以参考图4A和图4B。
在图4A中，向用户展示了一周的简单计划的卡片。图4A是示出根据本公开一些实施例的周健身计划的示意图。
如图4A，周一的运动类型为运动类型1、锻炼部位为锻炼部位1，周二的运动类型为运动类型2、锻炼部位为锻炼部位2，周三的运动类型为运动类型3、锻炼部位为锻炼部位3，周四的运动类型为运动类型4、锻炼部位为锻炼部位4，周五的运动类型为运动类型5、锻炼部位为锻炼部位5。周六和周日的运动类型和锻炼部位为空值，显示休息。
用户通过点击显示一周简单计划的卡片中周二这一项，卡片跳转到图4B所示的周二的详细日计划的卡片。
图4B是示出根据本公开一些实施例的日健身计划的示意图。
如图4B所示，以周二的详细日计划为腿部无氧锻炼为例，多个目标健身动作包括深蹲、罗马尼亚硬拉、腿弯举。在显示周二的详细日计划的卡片中，每个目标健身动作对应一个动态图像用于引导用户正确执行每个目标健身动作。深蹲对应动态图像1，罗马尼亚硬拉对应动态图像2，腿弯举对应动态图像3。
在一些实施例中，在图4B中示出的显示周二的详细日计划的卡片中，还可以显示执行每个目标健身动作组数、每组的个数、每个目标健身动作对应锻炼部位的子部位。例如，深蹲为4组，每组12个；罗马尼亚硬拉为4组，每组10个；腿弯举为3组，每组15个。又例如，深蹲锻炼髋部，罗马尼亚硬拉锻炼髋部，腿弯举锻炼绳肌和大腿。
在一些实施例中，在图4B中示出的显示周二的详细日计划的卡片中，还可以显示不同目标健身动作之间的休息时间(图4B中未示出)。
在一些实施例中，图4A和图4B示出卡片中，还可以显示每日的总健身时间和总能量消耗(图4A和图4B中未示出)。
图3～图4B仅作为本公开的一种示例，不对本公开构成具体限定。例如，无氧和有氧的划分是可以根据实际情况进行配置的。
图5是示出根据本公开另一些实施例的健身计划推荐方法的流程示意图。
如图5所示，以用户请求生成一周的健身计划为例，健身计划推荐方法包括步骤S500～步骤S570。
在步骤S500中，用户向智能体引擎(bot engine)请求生成健身计划。
在步骤S510中，智能体引擎对用户的请求进行意图识别，控制工作流(workflow)启动生成健身计划的操作，该健身计划包括一周的简单计划(周健身计划)和一周七天中每天的日详细计划(日健身计划)。
在步骤S520中，工作流启动在健身动作库中搜索无氧运动对应的运动图解和/或动态图像，并将无氧运动对应的运动图解和/或动态图像补充到与该无氧运动对应的日详细计划中的操作。健身动作库例如为数据库结构。
在步骤S530中，工作流启动在目标内容平台上搜索有氧运动对应的演示内容，并将有氧运动对应的演示内容补充到与该有氧运动对应的日详细计划中的操作。
在步骤S540中，工作流启动发送健身计划到存储模块的操作。
在步骤S550中，存储模块存储周健身计划和一周七天的日健身计划。
在步骤S560中，工作流启动本地插件根据存储模块存储的周健身计划和一周七天的日健身计划，生成卡片。
在步骤S570中，本地插件返回生成的卡片到用户，通过卡片形式向用户展示周健身计划和一周七天的日健身计划。
图5中的智能体引擎、工作流、健身动作库、存储模块、本地插件共同构成了智能体系统。例如，该智能体系统成为健康生活智能体。
图5仅作为本公开的一种示例，不对本公开的健身计划推荐方法构成具体限定。
以上为本公开一些实施例提供的健身计划推荐方法。下面将结合图6描述本公开一些实施例中的健身计划推荐装置。
图6是示出根据本公开一些实施例的健身计划推荐装置的框图。
如图6所示，健身计划推荐装置6包括第一生成模块61、第二生成模块62和展示模块63。
第一生成模块61被配置为响应于接收用户的获取健身计划的请求信息，生成与目标时间段对应的第一健身计划，其中，所述目标时间段包括多个子时间段，所述第一健身计划包括所述多个子时间段的运动类型和锻炼部位。
第二生成模块62被配置为根据所述第一健身计划，生成与所述多个子时间段对应的多个第二健身计划，其中，所述多个第二健身计划包括与所述第一健身计划中所述多个子时间段的运动类型和锻炼部位对应的多个目标健身动作的名称和健身指导内 容。
展示模块63被配置为向所述用户展示所述第一健身计划和与所述多个第二健身计划。
健身计划推荐装置6可用于执行图1的步骤S110～步骤S130。在一些实施例中，健身计划推荐装置6还可以执行本公开其他实施例中的任意步骤。
应注意，上述各个模块仅是根据其所实现的具体功能划分的逻辑模块，而不是用于限制具体的实现方式，例如可以以软件、硬件或者软硬件结合的方式来实现。在实际实现时，上述各个模块可被实现为独立的物理实体，或者也可由单个实体(例如，处理器(CPU或DSP等)、集成电路等)来实现。此外，上述各个模块在附图中用虚线示出指示这些模块可以并不实际存在，而它们所实现的操作/功能可由处理电路本身来实现。
以上为本公开一些实施例中的健身计划推荐装置。
图7是示出根据本公开一些实施例的健身计划推荐装置的框图。
如图7所示，健身计划推荐装置7包括：存储器71；以及耦接至该存储器71的处理器72，所述处理器72被配置为基于存储在所述存储器71中的指令，执行前述任一实施例所述的健身计划推荐方法。
存储器71用于存储一个或多个计算机可读指令。存储器71可以包括各种形式的计算机可读存储介质的任意组合，例如易失性存储器和/或非易失性存储器，包括但不限于随机存储存储器(RAM)、动态随机存储存储器(DRAM)、静态随机存取存储器(SRAM)、只读存储器(ROM)、闪存存储器。存储器71例如可以存储操作系统、应用程序、引导装载程序(Boot Loader)、数据库以及其他程序等，也可以存储各种应用程序和各种数据等。
处理器72用于运行计算机可读指令，实现前述任一实施例所述的健身计划推荐方法。关于健身计划推荐方法的各个步骤的具体实现可以参见上述的实施例，重复之处在此不作赘述。
处理器72和存储器71之间可以直接或间接地互相通信。例如，处理器72和存储器71可以通过网络进行通信。网络可以包括无线网络、有线网络、和/或无线网络和有线网络的任意组合。处理器72和存储器71之间也可以通过系统总线实现相互通信，本公开对此不作限制。
应当注意，图7所示的健身计划推荐装置7的组件只是示例性的，而非限制性的，根据实际应用需要，健身计划推荐装置7还可以具有其他组件。处理器72可以健身计划推荐装置7中的其它组件以执行期望的功能。
健身计划推荐装置可以由软件、固件和/或硬件的方式实现，可以集成在安装有相关应用程序的电子设备中。
图8示出根据本公开一些实施例的电子设备的框图。
图8所示的电子设备8可以是具有专用硬件结构的计算机系统，在安装有相关应用程序时，能够执行相应的功能。
电子设备包括但不限于诸如智能手机、笔记本电脑、个人数字助理(Personal Digital Assistant，PDA)、平板电脑(Tablet Personal Computer，Tablet PC)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)、可穿戴设备等等的移动终端以及诸如数字电视、台式计算机等等的固定终端。
如图8所示，中央处理单元(CPU)81，根据只读存储器(ROM)82中存储的程序、或从存储部分88加载到随机存取存储器(RAM)83的程序，执行各种处理。在RAM 83中，根据需要存储当CPU 81执行各种处理等时所需的数据。中央处理单元仅仅是示例性的，其也可以是其它类型的处理器，诸如前文所述的各种处理器。ROM 82、RAM 83和存储部分88可以是各种形式的计算机可读存储介质。需要注意的是，虽然图8中分别示出了ROM 82、RAM 83和存储部分88，但是它们中的一个或多个可以合并，或者位于相同或不同的存储器或存储模块中。
CPU 81、ROM 82和RAM 83经由总线84彼此连接。输入/输出接口85也连接到总线84。
下述部件连接到输入/输出接口85：输入部分86，诸如触摸屏、触摸板、键盘、鼠标、图像传感器、麦克风、加速度计、陀螺仪等；输出部分87，包括显示器，比如阴极射线管(CRT)、液晶显示器(LCD)、扬声器、振动器等；存储部分88，包括硬盘，磁带等；和通信部分89，包括网络接口卡比如LAN卡、调制解调器等。通信部分89允许经由网络比如因特网执行通信处理。容易理解的是，虽然图8中示出电子设备8中的各个装置或模块是通过总线84来通信的，但它们也可以通过网络或其它方式进行通信，其中，网络可以包括无线网络、有线网络、和/或无线网络和有线网络的任意组合。
根据需要，驱动器810也连接到输入/输出接口85。可拆卸介质811比如磁盘、光盘、 磁光盘、半导体存储器等等根据需要被安装在驱动器810上，使得从中读出的计算机程序根据需要被安装到存储部分88中。
在通过软件实现上述系列处理的情况下，可以从因特网等网络或可拆卸介质811等存储介质，安装构成软件的程序。
根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的一些实施例包括一种计算机程序产品，当该计算机程序产品在计算机上运行时，使得所述计算机实现前述任一实施例所述的健身计划推荐方法。计算机程序产品包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分89从网络上被下载和安装，或者从存储部分88被安装，或者从ROM 82被安装。在该计算机程序被CPU 81执行时，执行本公开实施例的健身计划推荐方法。
需要说明的是，在本公开的上下文中，计算机可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。
计算机可读介质可以是计算机可读存储介质，或者计算机可读信号介质，或者是上述两者的任意组合。
计算机可读存储介质包括但不限于：电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。计算机可读存储介质上存储有计算机程序，该程序被处理器执行时实现前述任一实施例所述的健身计划推荐方法。
计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上 包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
在一些实施例中，还提供了一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得所述计算机实现上述任一实施例所述的健身计划推荐方法。
在一些实施例中，还提供了一种计算机程序，包括：指令，指令当由处理器执行时使处理器执行上述任一个实施例的健身计划推荐方法。例如，指令可以体现为计算机程序代码。
在本公开的实施例中，可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言，诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言，诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络(包括局域网(LAN)或广域网(WAN))连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示例性的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
虽然已经通过示例对本公开的一些特定实施例进行了详细说明，但是本领域的技术人员应该理解，以上示例仅是为了进行说明，而不是为了限制本公开的范围。本领域的技术人员应该理解，可在不脱离本公开的范围和精神的情况下，对以上实施例进行修改。本公开的范围由所附权利要求来限定。

Claims (14)

  1. 一种健身计划推荐方法，包括：
    响应于接收用户的获取健身计划的请求信息，生成与目标时间段对应的第一健身计划，其中，所述目标时间段包括多个子时间段，所述第一健身计划包括所述多个子时间段的运动类型和锻炼部位；
    根据所述第一健身计划，生成与所述多个子时间段对应的多个第二健身计划，其中，所述多个第二健身计划包括与所述第一健身计划中所述多个子时间段的运动类型和锻炼部位对应的多个目标健身动作的名称和健身指导内容；
    向所述用户展示所述第一健身计划和所述多个第二健身计划。
  2. 根据权利要求1所述的健身计划推荐方法，其中，所述根据所述第一健身计划，生成与所述多个子时间段对应的多个第二健身计划包括：
    根据所述第一健身计划中的所述多个子时间段的运动类型和锻炼部位，生成与所述多个子时间段对应的多个参考健身计划，其中，所述多个参考健身计划包括所述多个子时间段的多个目标健身动作的名称；
    在每个目标健身动作对应的运动类型满足第一条件的情况下，从目标内容平台，获取所述每个健身动作的演示内容；
    在所述每个目标健身动作对应的运动类型满足第二条件的情况下，根据所述每个目标健身动作的名称，从健身动作库中，获取所述每个目标健身动作的运动图解和/或动态图像，其中，所述健身动作库包括预先配置的多个健身动作的名称和与每个健身动作的名称对应的运动图解和/或动态图像；
    根据所述多个目标健身动作的演示内容、运动图解和动态图像中的至少一种以及所述多个参考健身计划，生成所述多个第二健身计划，其中，所述多个第二健身计划中的所述多个目标健身动作的健身指导内容包括所述多个目标健身动作的演示内容、运动图解和动态图像中的至少一种。
  3. 根据权利要求2所述的健身计划推荐方法，其中，所述健身动作库中每个健身动作的名称包括第一类名称和第二类名称，所述第一类名称和所述第二类名称在多个 用户中被使用的概率不同，所述根据所述每个目标健身动作的名称，从健身动作库中，获取所述每个目标健身动作的运动图解和/或动态图像包括：
    对所述每个目标健身动作的名称与所述健身动作库中所述多个健身动作的第一类名称和第二类名称执行匹配操作，以从所述健身动作库中，获取所述每个目标健身动作的运动图解和/或动态图像。
  4. 根据权利要求3所述的健身计划推荐方法，其中，每个健身动作的第一类名称在所述多个用户中被使用的概率高于所述每个健身动作的第二类名称在所述多个用户中被使用的概率，所述对所述每个目标健身动作的名称与所述健身动作库中所述多个健身动作的第一类名称和第二类名称执行匹配操作，以从所述健身动作库中，获取所述每个目标健身动作的运动图解和/或动态图像包括：
    对所述每个目标健身动作的名称与所述健身动作库中所述多个健身动作的第一类名称执行第一匹配操作；
    在所述第一匹配操作失败的情况下，对所述每个目标健身动作的名称与所述健身动作库中所述多个健身动作的第二类名称执行第二匹配操作，以从所述健身动作库中，获取所述每个目标健身动作的运动图解和/或动态图像；
    在所述第一匹配操作成功的情况下，从所述健身动作库中，获取与所述每个目标健身动作的名称匹配的第一类名称对应的运动图解和/或动态图像，作为所述每个目标健身动作的运动图解和/或动态图像。
  5. 根据权利要求2-4任一项所述的健身计划推荐方法，其中，所述健身动作库还包括与多个健身动作的名称对应的健身动作指南和健身动作技巧中的至少一种，所述根据所述多个目标健身动作的演示内容、运动图解和动态图像中的至少一种以及所述多个参考健身计划，生成所述多个第二健身计划包括：
    在所述每个目标健身动作对应的运动类型满足第二条件的情况下，根据所述每个目标健身动作的名称，从所述健身动作库中，获取所述每个目标健身动作的健身动作指南和健身动作技巧中的至少一种；
    根据所述多个目标健身动作的演示内容、运动图解和动态图像中的至少一种、所述多个参考健身计划以及所述每个目标健身动作的健身动作指南和健身动作技巧中的 至少一种，生成所述多个第二健身计划，其中，所述多个第二健身计划中所述多个目标健身动作的健身指导内容还包括所述多个目标健身动作的健身动作指南和健身动作技巧中的至少一种。
  6. 根据权利要求2-4任一项所述的健身计划推荐方法，其中，所述根据所述第一健身计划中的所述多个子时间段的运动类型和锻炼部位，生成与所述多个子时间段对应的多个参考健身计划包括：
    针对所述多个子时间段，并行调用模型，对所述多个子时间段的运动类型和锻炼部位进行处理，得到所述多个参考健身计划。
  7. 根据权利要求2-4任一项所述的健身计划推荐方法，其中，所述多个参考健身计划还包括所述多个目标健身动作的执行方式，其中，所述执行方式包括所述多个目标健身动作在所述多个子时间段的执行顺序、执行每个目标健身动作的数量，所述多个第二健身计划还包括所述多个目标健身动作的执行方式。
  8. 根据权利要求1-4任一项所述的健身计划推荐方法，其中，所述向所述用户展示所述第一健身计划和所述多个第二健身计划包括：
    在第一卡片中，渲染所述第一健身计划；
    在与每个第二健身计划对应的第二卡片中，渲染所述每个第二健身计划；
    向所述用户展示所述第一卡片，隐藏所述多个第二健身计划对应的多个第二卡片；
    响应于所述用户对所述第一卡片执行触发操作，向所述用户展示与所述触发操作对应的第二卡片。
  9. 根据权利要求1-4任一项所述的健身计划推荐方法，还包括：
    在向所述用户展示所述第一健身计划和与所述多个第二健身计划之前，根据所述第一健身计划和与所述多个第二健身计划，生成并发送健身总结信息至所述用户。
  10. 根据权利要求1-4任一项所述的健身计划推荐方法，其中，所述响应于接收用户的获取健身计划的请求信息，生成与目标时间段对应的第一健身计划包括：
    对所述请求信息进行意图理解，得到所述用户的健身意图信息；
    根据所述健身意图信息，生成所述第一健身计划。
  11. 一种健身计划推荐装置，包括：
    第一生成模块，被配置为响应于接收用户的获取健身计划的请求信息，生成与目标时间段对应的第一健身计划，其中，所述目标时间段包括多个子时间段，所述第一健身计划包括所述多个子时间段的运动类型和锻炼部位；
    第二生成模块，被配置为根据所述第一健身计划，生成与所述多个子时间段对应的多个第二健身计划，其中，所述多个第二健身计划包括与所述第一健身计划中所述多个子时间段的运动类型和锻炼部位对应的多个目标健身动作的名称和健身指导内容；
    展示模块，被配置为向所述用户展示所述第一健身计划和与所述多个第二健身计划。
  12. 一种健身计划推荐装置，包括：
    存储器；以及
    耦接至所述存储器的处理器，所述处理器被配置为基于存储在所述存储器中的指令，执行如权利要求1至10中任一项所述的健身计划推荐方法。
  13. 一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现权利要求1至10中任一项所述的健身计划推荐方法。
  14. 一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得所述计算机实现权利要求1至10中任一项所述的健身计划推荐方法。
PCT/CN2024/097839 2024-06-06 2024-06-06 健身计划推荐方法及装置、存储介质、程序产品 Pending WO2025251263A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2024/097839 WO2025251263A1 (zh) 2024-06-06 2024-06-06 健身计划推荐方法及装置、存储介质、程序产品
CN202480004142.7A CN121488234A (zh) 2024-06-06 2024-06-06 健身计划推荐方法及装置、存储介质、程序产品

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2024/097839 WO2025251263A1 (zh) 2024-06-06 2024-06-06 健身计划推荐方法及装置、存储介质、程序产品

Publications (1)

Publication Number Publication Date
WO2025251263A1 true WO2025251263A1 (zh) 2025-12-11

Family

ID=97959890

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/097839 Pending WO2025251263A1 (zh) 2024-06-06 2024-06-06 健身计划推荐方法及装置、存储介质、程序产品

Country Status (2)

Country Link
CN (1) CN121488234A (zh)
WO (1) WO2025251263A1 (zh)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160196759A1 (en) * 2015-01-06 2016-07-07 Samsung Electronics Co., Ltd. Electronic device and method for providing workout service in electronic device
CN110289072A (zh) * 2019-05-10 2019-09-27 咪咕互动娱乐有限公司 健身方案的生成方法、装置、电子设备及可读存储介质
WO2023024400A1 (zh) * 2021-08-23 2023-03-02 成都拟合未来科技有限公司 一种健身训练方法及系统及装置及介质

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160196759A1 (en) * 2015-01-06 2016-07-07 Samsung Electronics Co., Ltd. Electronic device and method for providing workout service in electronic device
CN110289072A (zh) * 2019-05-10 2019-09-27 咪咕互动娱乐有限公司 健身方案的生成方法、装置、电子设备及可读存储介质
WO2023024400A1 (zh) * 2021-08-23 2023-03-02 成都拟合未来科技有限公司 一种健身训练方法及系统及装置及介质

Also Published As

Publication number Publication date
CN121488234A (zh) 2026-02-06

Similar Documents

Publication Publication Date Title
CN116610784B (zh) 一种保险业务场景问答推荐方法及其相关设备
JP2025060386A (ja) プログラム、方法、情報処理装置、システム
CN113422986B (zh) 用于直播间推荐的方法、装置、设备、介质和程序产品
Bernhaupt et al. Introduction to this Special Issue on HCI and Games
Zhang et al. Using augmented reality to promote homogeneity in learning achievement
US11734589B2 (en) Virtual assistant negotiation system and method thereof
Awalin et al. Students’ perceptions on the impact of artificial intelligence on English grammar learning
CN109299378B (zh) 搜索结果的展示方法、装置、终端及存储介质
CN117079809B (zh) 基于生成式模型构建导医场景助手的方法和系统、设备
Kupershtein et al. ChatGPT as a Game-Changer for Embedding Emojis in Faculty Feedback
US20210098086A1 (en) System and method for conversational data collection
US20140101596A1 (en) Language and communication system
Chiang et al. Developing a course-specific chatbot powered by generative ai for assisting students’ learning in a programming course
WO2025251263A1 (zh) 健身计划推荐方法及装置、存储介质、程序产品
CN112132118B (zh) 人物关系识别方法、装置、电子设备及计算机存储介质
CN118378692B (zh) 基于博弈生成对抗网络的知识问答模型训练方法及系统
Tam An intelligent e‐learning software for learning to write correct Chinese characters on mobile devices
CN119782473A (zh) 个体化问题交互方法、装置、相关设备及计算机程序产品
CN117539989A (zh) 对话评估模型训练方法及对话评估方法、装置及存储介质
WO2025251265A1 (zh) 交互方法、装置、电子设备、存储介质和程序产品
WO2025251254A1 (zh) 健身计划推荐方法及装置、存储介质、程序产品
Hoi et al. Visualizing the behavior of learning European Portuguese in different regions of the world through a mobile application
KR20230131630A (ko) 언어 기반 요리 강습 서비스 제공 방법 및 시스템
JP7236711B1 (ja) プログラム、方法、情報処理装置、システム
CN115080708A (zh) 问答方法及装置、计算机可读存储介质、终端

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24942185

Country of ref document: EP

Kind code of ref document: A1