WO2023188061A1 - トレーニング支援装置、トレーニング支援方法、トレーニング支援プログラム、学習装置、学習方法、および学習プログラム - Google Patents

トレーニング支援装置、トレーニング支援方法、トレーニング支援プログラム、学習装置、学習方法、および学習プログラム Download PDF

Info

Publication number
WO2023188061A1
WO2023188061A1 PCT/JP2022/015798 JP2022015798W WO2023188061A1 WO 2023188061 A1 WO2023188061 A1 WO 2023188061A1 JP 2022015798 W JP2022015798 W JP 2022015798W WO 2023188061 A1 WO2023188061 A1 WO 2023188061A1
Authority
WO
WIPO (PCT)
Prior art keywords
training
learning
state
menu
data
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.)
Ceased
Application number
PCT/JP2022/015798
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
力 江藤
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.)
NEC Corp
Original Assignee
NEC Corp
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 NEC Corp filed Critical NEC Corp
Priority to PCT/JP2022/015798 priority Critical patent/WO2023188061A1/ja
Priority to US18/839,477 priority patent/US20250161753A1/en
Priority to JP2024510847A priority patent/JP7666735B2/ja
Publication of WO2023188061A1 publication Critical patent/WO2023188061A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
    • A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
    • A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
    • A63B71/0622—Visual, audio or audio-visual systems for entertaining, instructing or motivating the user
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
    • A63B24/0062—Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
    • A63B24/0075—Means for generating exercise programmes or schemes, e.g. computerized virtual trainer, e.g. using expert databases
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B69/00—Training appliances or apparatus for special sports
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
    • A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
    • A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
    • A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
    • A63B71/0622—Visual, audio or audio-visual systems for entertaining, instructing or motivating the user
    • A63B2071/0625—Emitting sound, noise or music

Definitions

  • Patent Document 1 discloses a technique for outputting a training menu based on a reference table or mathematical model derived in advance from a statistical database based on customer data or the like. Specifically, Patent Document 1 describes that calorie consumption is calculated from the type and number of training sessions performed by a subject, and a training menu that allows the calorie consumption to reach a target value is returned. Further, Patent Document 1 describes that a training menu that takes into account psychological tendencies is returned based on the results of a questionnaire.
  • Patent Document 1 has room for improvement in that it cannot take various conditions related to training into consideration when determining a training menu. For example, it is conceivable that some of the training events included in the training menu generated by the technique of Patent Document 1 cannot be performed at the training facility used by the subject, or that it is difficult for the subject to carry out the training due to his or her physical strength.
  • One aspect of the present invention has been made in view of the above problems, and one example of the purpose is to provide a technique for generating a training menu in consideration of training-related conditions.
  • a training support device includes a data acquisition means for acquiring status data indicating a status related to training performed by a subject, and learning data indicating a training menu to be applied in the training status according to the training status.
  • generating means for generating a training menu according to the state indicated by the state data by performing an optimization calculation using an objective function generated by inverse reinforcement learning using .
  • a training support method includes at least one processor acquiring state data indicating a state related to training performed by a subject, and a training menu to be applied in the state according to the state related to training.
  • the method includes generating a training menu according to the state indicated by the state data by performing an optimization calculation using an objective function generated by inverse reinforcement learning using learning data showing the state data.
  • a training support program includes a data acquisition means for acquiring status data indicating a status related to training performed by a computer, and a training menu to be applied in the training status according to the training status.
  • a data acquisition means for acquiring status data indicating a status related to training performed by a computer
  • a training menu to be applied in the training status according to the training status.
  • a learning device includes a data acquisition unit that acquires learning data that indicates a training menu to be applied in a training-related state, and performs reverse reinforcement learning using the learning data. , and learning means for generating an objective function for generating a training menu according to the state.
  • a learning method includes the steps of: at least one processor acquiring learning data indicating a training menu to be applied in the training-related state according to the training-related state; and using the learning data to perform inverse reinforcement.
  • the method includes, by learning, generating an objective function for generating a training menu according to the state.
  • a learning program includes a data acquisition means for acquiring learning data indicating a training menu to be applied in a training-related state according to a training-related state, and inverse reinforcement learning using the learning data. By doing so, it functions as a learning means that generates an objective function for generating a training menu according to the state.
  • FIG. 1 is a block diagram showing the configuration of a training support system according to exemplary embodiment 1 of the present invention.
  • FIG. 2 is a flow diagram showing the flow of a learning method according to exemplary embodiment 1 of the present invention.
  • FIG. 2 is a flow diagram showing the flow of a training support method according to exemplary embodiment 1 of the present invention.
  • FIG. 2 is a diagram showing an overview of a training support method according to a second exemplary embodiment of the present invention.
  • FIG. 2 is a block diagram illustrating an example of the configuration of main parts of a training support device according to a second exemplary embodiment of the present invention.
  • FIG. 7 is a diagram illustrating an overview of objective function learning according to exemplary embodiment 2 of the present invention. It is a figure showing an example of generation of a training menu including BGM.
  • FIG. 3 is a flow diagram showing the flow of processing executed by the training support device according to the second exemplary embodiment of the present invention.
  • 1 is a diagram illustrating an example of a computer that executes instructions of a program that is software that implements each function of each device according to each exemplary embodiment of the present invention.
  • FIG. 1 is a diagram illustrating an example of a computer that executes instructions of a program that is software that implements each function of each device according to each exemplary embodiment of the present invention.
  • FIG. 1 is a block diagram showing the configuration of the training support system 3.
  • the training support system 3 is a system for supporting training of a subject, and includes a learning device 1 and a training support device 2 as illustrated.
  • the learning device 1 includes a data acquisition section 11 and a learning section 12.
  • the training support device 2 also includes a data acquisition section 21 and a generation section 22.
  • the data acquisition unit 11 acquires learning data that indicates a training menu that should be applied in a training-related state according to the training-related state.
  • the learning unit 12 generates an objective function for generating a training menu according to the state by performing inverse reinforcement learning using the learning data.
  • the data acquisition unit 21 acquires status data indicating the status related to the training performed by the subject.
  • the generation unit 22 performs optimization calculations using an objective function generated by inverse reinforcement learning using learning data indicating a training menu to be applied in a training-related state.
  • a training menu is generated according to the state indicated by the state data.
  • the objective function used by the generation unit 22 may be one generated by the learning unit 12 of the learning device 1, or may be generated by another device.
  • the learning device 1 includes a data acquisition unit 11 that acquires learning data indicating a training menu to be applied in a training-related state according to the training-related state, and a data acquisition unit 11 that uses the learning data. and a learning unit 12 that generates an objective function for generating a training menu according to the state by performing inverse reinforcement learning. Therefore, according to the learning device 1 according to the present exemplary embodiment, it is possible to generate an objective function for generating a training menu according to the state, so that the training menu is generated in consideration of the state related to training. The effect is that it becomes possible to
  • the training support device 2 includes the data acquisition unit 21 that acquires status data indicating the status related to the training performed by the subject, and the data acquisition unit 21 that acquires status data indicating the status related to the training performed by the subject, and the data acquisition unit 21 that acquires status data indicating the status related to the training performed by the subject, and the A generation unit that generates a training menu according to the state indicated by the state data by performing optimization calculation using an objective function generated by inverse reinforcement learning using learning data indicating a training menu to be applied. 22. Therefore, the training support device 2 according to the present exemplary embodiment has the effect that a training menu can be generated in consideration of the training-related state.
  • the functions of the learning device 1 described above can also be realized by a program.
  • the learning program according to the present exemplary embodiment includes a data acquisition means for acquiring learning data indicating a training menu to be applied in a training-related state according to a training-related state, and inverse reinforcement learning using the learning data. By doing so, it functions as a learning means that generates an objective function for generating a training menu according to the state. According to this learning program, it is possible to generate an objective function for generating a training menu according to the state, so it is possible to generate a training menu in consideration of the training-related state. .
  • the functions of the training support device 2 described above can also be realized by a program.
  • the training support program according to the present exemplary embodiment includes a data acquisition means for acquiring status data indicating a status related to training performed by a computer, and a training menu to be applied in the training status according to the training status performed by the subject. By performing an optimization calculation using an objective function generated by inverse reinforcement learning using the learning data shown, it functions as a generation means for generating a training menu according to the state shown by the state data. According to this training support program, it is possible to generate a training menu in consideration of training-related conditions.
  • FIG. 2 is a flow diagram showing the flow of the learning method.
  • the execution entity of each step in this learning method may be a processor provided in the learning device 1, or may be a processor provided in another device, and the execution entity of each step may be provided in a different device.
  • the processor may also be a
  • At least one processor acquires learning data that indicates a training menu to be applied in a training-related state according to the training-related state.
  • At least one processor generates an objective function for generating a training menu according to the state by performing inverse reinforcement learning using the learning data.
  • At least one processor acquires learning data indicating a training menu to be applied in the training-related state according to the training-related state;
  • a configuration is adopted that includes generating an objective function for generating a training menu according to the state by performing inverse reinforcement learning using data. Therefore, according to the learning method according to the present exemplary embodiment, it is possible to generate an objective function for generating a training menu according to the state, so that it is possible to generate a training menu in consideration of the state related to training. This has the effect of making it possible.
  • FIG. 3 is a flow diagram showing the flow of the training support method.
  • the main body executing each step in this training support method may be a processor included in the training support device 2, or may be a processor provided in another device, and the main body executing each step may be a processor provided in a different device. It may be a processor provided.
  • At least one processor acquires state data indicating a state related to training performed by the subject.
  • At least one processor performs optimization calculation using an objective function generated by inverse reinforcement learning using learning data indicating a training menu to be applied in a training-related state according to the training-related state. By doing so, a training menu is generated according to the state indicated by the above state data.
  • At least one processor acquires state data indicating a state related to training performed by a subject, and adjusts the state according to the state related to training. Generate a training menu according to the state indicated by the above state data by performing optimization calculations using an objective function generated by inverse reinforcement learning using learning data indicating the training menu to be applied. A configuration including the following is adopted. Therefore, according to the training support method according to the present exemplary embodiment, it is possible to generate a training menu in consideration of conditions related to training.
  • FIG. 4 is a diagram illustrating an overview of the training support method (hereinafter referred to as the present method) according to the present exemplary embodiment.
  • the input data for this method includes training events that can be selected by the training subject and event properties that indicate their characteristics, user properties that indicate the characteristics of the subject, and information used to generate the training menu.
  • the following constraints are included.
  • the event property and the user property are state data indicating the state related to training performed by the subject.
  • a training menu is generated that satisfies the constraint conditions and corresponds to the state indicated by the above state data.
  • the event properties shown in FIG. 4 show the training events that the subject can select and the effects that can be expected from training for each event.
  • the event properties shown in Figure 4 indicate that a training event called "Event 1" can be selected, and the muscle hypertrophy effect of this event is 80, and the effect of improving muscle output is 70.
  • the method for evaluating the training effect is not particularly limited, and any training effect evaluated by any evaluation method can be included in the event list.
  • the effects of improving calorie consumption and muscular endurance may be associated with each event.
  • exercise intensity, parts of the body to which a load is applied, etc. can also be included in the event properties.
  • the calorie consumption may be the calorie consumption per unit time, or when the training time for the event is determined, the calorie consumption may be the calorie consumption over the entire time.
  • the user properties shown in FIG. 4 indicate the height and weight of the subject.
  • User properties may be anything that indicates characteristics of the target person, such as maximum training time per day, minimum calorie consumption per day, maximum exercise intensity per day, age, gender, occupation, exercise experience, and training. Goals etc. may be user properties. Note that the maximum training time per day, etc. may be set to a different time for each day of the week.
  • constraint conditions shown in FIG. 4 indicate that the calorie consumption is equal to or greater than the target value, and that the total time required for training is within the set value.
  • Constraints can be set arbitrarily; for example, constraints such as applying load evenly to each part of the body in one week can also be set. Such constraints can be freely set and changed by the subject.
  • the optimal A training menu is generated by performing calculations.
  • the above objective function includes a weight value that indicates how much importance is given to each viewpoint in evaluating the training menu.
  • the first viewpoint is "muscle hypertrophy”
  • the second viewpoint is “muscle output”
  • the third viewpoint is “muscular endurance.”
  • the weight values of each viewpoint are ⁇ , ⁇ , and ⁇ , respectively.
  • the viewpoint can be automatically determined during learning, or the viewpoint can be set and changed by the subject.
  • the viewpoint to be set may be anything related to the training menu, and for example, the compatibility of the combination of training events may be set as the viewpoint.
  • the output data that is, the training menu shown in FIG. 4 shows the training events to be performed on each day of the week and the order in which they are performed.
  • the training menu shown in FIG. 4 indicates that training will be performed in the order of events 3, 2, and 5 on Mondays.
  • this method is not limited to the example shown in FIG. 4, and can generate a training menu in any format. For example, it is possible to generate a training menu that specifies a combination of events without specifying the order in which each event is performed, or it is also possible to generate a monthly training menu.
  • FIG. 5 is a block diagram showing an example of the main part configuration of the training support device 2A.
  • the training support device 2A is a device that supports training of a subject by generating a training menu for the subject.
  • the training support device 2A also has the function of the learning device 1 of the first exemplary embodiment, that is, the function of generating an objective function including a weight value indicating how much importance is given to each viewpoint for evaluating the training menu. .
  • the training support device 2A includes a control unit 20A that centrally controls each part of the training support device 2A, and a storage unit 21A that stores various data used by the training support device 2A.
  • the training support device 2A also includes an input section 22A that receives input of various data to the training support device 2A, and an output section 23A through which the training support device 2A outputs various data.
  • the output section 23A is a display device that displays and outputs various data will be described below, the output section 23A may output data in other output formats such as audio output or printed output. .
  • control unit 20A includes a data acquisition unit 201, a generation unit 202, a search unit 203, and a learning unit 204.
  • the storage unit 21A stores state data 211, objective function 212, training menu 213, and learning data 214.
  • search unit 203 will be explained in the section "Display of search keywords" below.
  • the data acquisition unit 201 acquires status data 211 indicating the status related to the training performed by the subject.
  • the status data 211 may be anything that indicates the status related to the training performed by the subject.
  • the status data 211 may include information related to the training itself, such as event properties shown in FIG. 4, or information related to the subject himself, such as user properties.
  • the data acquisition unit 201 may also acquire constraint conditions when generating a training menu. Furthermore, the data acquisition unit 201 acquires learning data 214 that indicates a training menu that should be applied in a training-related state according to the training-related state.
  • the method for acquiring these data is not particularly limited, and for example, the data acquisition unit 201 may acquire the state data 211, constraints, and learning data 214 that are input via the input unit 22A.
  • the generation unit 202 generates a training menu according to the state indicated by the status data acquired by the data acquisition unit 201. More specifically, the generation unit 202 performs optimization using an objective function 212 generated by inverse reinforcement learning using learning data 214 that indicates a training menu to be applied in a training-related state. By performing the calculation, a training menu 213 is generated according to the state indicated by the state data acquired by the data acquisition unit 201. The method for generating the training menu 213 will be explained in the section "Optimization Calculation" below.
  • the learning unit 204 uses the learning data 214 to generate an objective function 212 for generating a training menu according to the state.
  • the objective function 212 generated by the learning unit 204 includes weight values that indicate each viewpoint for evaluating the training menu and indicate how much emphasis is placed on each viewpoint.
  • the method for generating the objective function 212 will be explained in the section "Learning the objective function" below.
  • the training support device 2A includes the data acquisition unit 201 that acquires the status data 211 indicating the status related to the training performed by the subject, and the data acquisition unit 201 that acquires the status data 211 indicating the status related to the training performed by the subject, and By performing optimization calculations using the objective function 212 generated by inverse reinforcement learning using the learning data 214 indicating the training menu to be trained, the data acquisition unit 201 can perform optimization calculations based on the state indicated by the state data acquired by the data acquisition unit 201.
  • a generation unit 202 that generates a training menu 213 is provided. Therefore, according to the training support device 2A according to the present exemplary embodiment, it is possible to generate a training menu in consideration of conditions related to training.
  • the data acquisition unit 201 acquires the constraint conditions when creating a training menu for the subject, and the generation unit 202 A training menu 213 that satisfies the constraint conditions is generated. Therefore, according to the training support device 2A according to the present exemplary embodiment, in addition to the effects achieved by the training support device 2 according to the first exemplary embodiment, it is possible to generate a training menu 213 that satisfies the desired constraint conditions. This has the effect of being able to.
  • the training support device 2A also has a function as a learning device. That is, the training support device 2A has a data acquisition unit 201 that acquires learning data 214 indicating a training menu to be applied in the training-related state according to the training-related state, and performs reverse reinforcement learning using the learning data 214.
  • the learning unit 204 generates an objective function 212 for generating a training menu according to the state.
  • the training support device 2A according to the present exemplary embodiment it is possible to generate the objective function 212 including a weight value indicating how much importance is given to each viewpoint for evaluating the training menu. The effect is that it becomes possible to generate the training menu 213 in consideration of important viewpoints.
  • FIG. 6 is a diagram showing an overview of learning the objective function 212.
  • the learning data 214 shown in FIG. 6 includes user properties and event properties as state data, as well as constraint conditions and a training menu.
  • the learning data 214 may be anything that indicates a training menu that should be applied in a training-related state according to the training-related state.
  • the learning data 214 may indicate a training menu executed by a person (hereinafter referred to as an expert) who has achieved remarkable training results among those who actually trained.
  • the user property in the learning data 214 is the user property of the expert
  • the event property is the property of the training event executed by the expert.
  • the constraint conditions of the learning data 214 may be the constraint conditions when the expert creates a training menu, and the training menu may indicate a training menu executed by the expert.
  • the learning data 214 will be explained in association with experts.
  • the learning data 214 is not limited to experts.
  • the learning data 214 may be a combination of data indicating a state related to training and data indicating a training menu to be applied in the state.
  • the learning data 214 does not necessarily have to be generated based on the actually executed training menu.
  • typical state data may be created and an appropriate training menu corresponding thereto may be created as the learning data 214.
  • the event properties of the training events included in that training menu are associated with the user properties typical for a man in his 20s, and the learning data 214 is created. You can also use it as Furthermore, constraints may be included in the learning data 214 as necessary.
  • the learning unit 204 generates an objective function 212 that includes a weight value indicating how much importance is given to each viewpoint for evaluating the training menu by learning using a plurality of the above-mentioned learning data 214 each having a different state.
  • This learning can be said to be a process in which the expert learns the intention of adopting the training menu included in the learning data 214 when the expert is in a state indicated by the state data included in the learning data 214. Note that, as described above, the viewpoint can be set arbitrarily.
  • the learning unit 204 sets each weight value of the objective function 212 to an initial value.
  • the generation unit 202 generates a training menu according to the state indicated by the state data included in the learning data 214 through optimization calculation using the objective function 212 whose weight value is set to an initial value.
  • the learning unit 204 updates the weight values so that the difference between the training menu shown in the learning data 214 and the training menu generated by the generation unit 202 becomes smaller. Learning of the objective function 212 is completed by repeating these processes until the difference between the training menu shown in the learning data 214 and the training menu generated by the generation unit 202 becomes sufficiently small.
  • various methods used in general inverse reinforcement learning can also be applied.
  • a maximum entropy inverse reinforcement learning method may be applied.
  • the learning unit 204 expresses the probability distribution of the objective function using the maximum entropy principle, and learns the objective function by bringing the probability distribution of the objective function closer to the true probability distribution (ie, maximum likelihood estimation).
  • the objective function 212 generated through learning as described above can also be said to indicate the expert's decision-making criteria.
  • the objective function 212 in which the weight value for the viewpoint of "muscular hypertrophy” is larger than the weight value for the viewpoint of "muscular endurance” is determined by an expert considering both the viewpoints of muscle endurance and muscle hypertrophy. This shows that he created a training menu that emphasized muscle hypertrophy rather than muscular endurance.
  • the generation unit 202 may generate a training menu that maximizes the evaluation value calculated using the objective function 212. Any method can be used to solve the optimization problem using the objective function, state data, and constraints. For example, the generation unit 202 may generate an optimal training menu from the objective function 212, state data 211, and constraints using an optimization solver.
  • the generation unit 202 can also use a general application program such as IBM ILOG CPLEX, Gurobi Optimizer, S CIP, etc. as an optimization solver.
  • a plurality of objective functions 212 prepared in advance may be stored in the storage unit 21A or the like.
  • the generation unit 202 may generate the training menu 213 using an objective function corresponding to the person to be trained among the plurality of objective functions 212 prepared in advance. According to this configuration, it becomes possible to use the objective function 212 that is more suitable for the subject among the plurality of objective functions 212, so in addition to the effects produced by the training support device 2 according to the first exemplary embodiment, The effect is that a training menu 213 suitable for the subject can be generated.
  • a plurality of objective functions 212 depending on the purpose of training may be stored in the storage unit 21A or the like.
  • the generation unit 202 can generate a training menu 213 that matches the target person's purpose using the objective function 212 that corresponds to the target person's training purpose.
  • FIG. 7 is a diagram showing an example of generating a training menu including BGM.
  • the example in Figure 7 differs from the example in Figure 4 in that the state data includes music properties, the contents of the constraints and objective functions, and the songs that serve as BGM for each training event in the generated training menu. The difference is that they are associated with each other.
  • the song properties are data indicating songs that can be used as BGM and their characteristics.
  • the song properties shown in Figure 7 indicate that the song "Song 1" can be used as BGM, and also that the popularity of this song is 80, and that this song has been used as BGM. Usage history is shown.
  • the song property is not limited to the example shown in FIG. 7, as long as it indicates songs that can be used as BGM and their characteristics.
  • song properties may include song title, genre, release date, album name, artist name, song length, volume, tone, tempo, time signature, and the like.
  • the degree to which you are suited to dance may be set as song properties.
  • the live feeling may be set as song properties.
  • the degree to which you receive a positive impression may be set as song properties.
  • constraints related to BGM can also be set.
  • the constraint conditions shown in FIG. 7 include the condition that a new song be used at least once.
  • BGM is determined so that a new song is included at least once during one training session.
  • the definition of a new song may be determined in advance; for example, a song released within six months from the release date may be defined as a new song.
  • an objective function that includes a viewpoint when selecting BGM is used.
  • the viewpoint may be anything related to BGM.
  • the objective function shown in Figure 7 includes, in addition to "exercise intensity," which is a viewpoint for evaluating training menus, "compatibility between event and BGM” and "popularity of BGM” are viewpoints for selecting BGM. include.
  • the above-mentioned objective function for generating a training menu including BGM is based on learning using learning data 214 that indicates the training menu to be applied in the training state and the music to be played during the training, depending on the training state. It can be generated by For example, learning data 214 may be used that indicates a training menu and event properties executed by the expert, BGM played by the expert while executing the training menu, and music properties of the BGM. As a result, it is possible to generate an objective function that indicates decision-making criteria when an expert selects BGM.
  • the "compatibility between the event and the BGM" can be evaluated using, for example, the usage history of the music.
  • a song that has been used frequently or frequently as BGM in a certain training event can be evaluated as having good compatibility with that event. In this way, it is sufficient to determine in advance what properties are used to evaluate a viewpoint. The same is true from the perspective of training.
  • the learning unit 204 may automatically select a viewpoint such as "compatibility between event and BGM” using any feature selection technique.
  • “Teaching Risk” is an example of a feature quantity selection method in inverse reinforcement learning that can be used by the learning unit 204.
  • Feature selection using “Teaching Risk” is to assume ideal parameters in the objective function, compare them with the parameters of the learning process, and select features (i.e. viewpoints) that reduce the difference between the two parameters as important features. It is selected as follows.
  • the feature quantity selection technique that can be used by the learning unit 204 is not limited to "Teaching Risk.”
  • the learning unit 204 can also perform feature quantity selection using, for example, the method disclosed in Publication PCT/JP2020/032848.
  • a training menu indicating training events for each day of the week and music to be used as BGM is generated from the above state data, constraints, and objective functions.
  • the training menu in FIG. 7 shows that the first training event to be performed on Monday is "Event 2" and that the BGM during training for this event is "Song 1.”
  • the training support device 2A can also generate a training menu in which a plurality of songs are associated with one training event. Further, the training support device 2A can also generate a training menu in which one or more pieces of music are associated with a plurality of training items to be executed continuously. In addition, when presenting a plurality of songs to the subject, the training support device 2A may present the plurality of songs as one playlist.
  • the generation unit 202 uses the objective function 212 learned using the learning data 214 including information indicating the music to be played during training.
  • a training menu 213 including music to be played is generated. Therefore, according to the training support device 2A according to the present exemplary embodiment, in addition to the effects achieved by the training support device 2 according to the first exemplary embodiment, a more attractive training menu 213 can be generated. is obtained.
  • the training support device 2A may present the music identified as described above to be used as BGM during training to the subject, and allow the subject to make a final decision on the music. This will be explained based on FIG. 8.
  • FIG. 8 is a diagram showing an example of a training menu and BGM display screen.
  • the generation unit 202 may display the training events and recommended playlists after "Event 5" in response to, for example, an operation to scroll the display screen in the horizontal direction. Furthermore, the generation unit 202 may also display training events and recommended playlists for Monday and thereafter in accordance with a predetermined operation. Further, the generation unit 202 may also display each song included in the playlist, or may display each song included in the playlist in response to an operation by the target person.
  • the target person may perform an operation to that effect. Furthermore, the target person may select the music to be used as BGM by himself/herself without adopting the recommended playlist.
  • the “keyword” in the display screen example of FIG. 8 helps the target person select a song, and is displayed by the search unit 203.
  • the search unit 203 displays, as search words for searching for songs, phrases that indicate viewpoints related to music among the viewpoints for evaluating the training menu shown in the objective function 212. Since the training support device 2A includes the search unit 203, in addition to the effects of the training support device 2 according to the first exemplary embodiment, the training support device 2A has the effect of easily searching for songs that match a viewpoint. can get.
  • the example display screen in FIG. 8 shows two keywords: "compatibility with event” and "popularity.” These keywords are all words and phrases that indicate viewpoints related to music among the viewpoints shown in the objective function.
  • the search unit 203 searches for a song that matches the keyword from among the songs that can be selected as BGM, and displays the search results. If the desired song is included in the displayed search results, the subject can select it as BGM during training.
  • the search unit 203 may select the above-mentioned viewpoint by using the structure of the objective function. For example, the search unit 203 may display "popularity" as a keyword when the weight of "popularity" is high in the learned objective function.
  • the search unit 203 refers to the song properties as shown in FIG.
  • the songs may be displayed as BGM candidates.
  • the training support device 2A may accept registration of favorite songs and playlists.
  • the training support device 2A may also display songs and playlists registered as favorites together with recommended playlists. Thereby, it is possible to easily set BGM that the target person likes.
  • FIG. 9 is a flow diagram showing the flow of processing executed by the training support device 2A. Note that an example will be described below in which a training menu including music to be played during training is generated.
  • the data acquisition unit 201 acquires status data 211 indicating the status related to the training performed by the subject. Furthermore, the data acquisition unit 201 may also acquire the constraint conditions when generating the training menu in S31.
  • the generation unit 202 generates a training menu 213 according to the state indicated by the state data 211 acquired in S31. Specifically, the generation unit 202 performs optimization using an objective function 212 generated by inverse reinforcement learning using learning data 214 indicating a training menu to be applied in a training-related state.
  • a training menu 213 is generated by calculation. This training menu 213 includes songs to be played during training.
  • the generation unit 202 causes the output unit 23A to display and output the training menu 213 generated in S32 and the music played when the training menu 213 is executed.
  • the search unit 203 causes the output unit 23A to display and output a search word for searching for a song.
  • the search term displayed by the search unit 203 is a phrase indicating a viewpoint related to music among the viewpoints for evaluating the training menu shown in the objective function 212.
  • the songs may be displayed one by one, or a plurality of songs may be displayed together as one playlist (see FIG. 8).
  • the search unit 203 determines whether to execute a search. For example, the search unit 203 may determine to perform a search when it detects that an operation to select a displayed keyword has been performed. If the determination is YES in S34, the process proceeds to S35, and if the determination is NO in S34, the process proceeds to S36.
  • the search unit 203 searches for songs using the keywords selected by the subject among the keywords displayed in S33, and causes the output unit 23A to display and output the search results.
  • the search unit 203 may search for songs using keywords input by the target person or narrowing conditions selected by the target person.
  • the search unit 203 determines whether a song to be used as BGM has been selected. Note that the music to be selected may be the one displayed in S33 or the one displayed in S35. Moreover, the selection of music may be accepted via the input section 22A. If the determination is YES in S36, the process proceeds to S37, and if the determination is NO in S37, the process returns to S34.
  • the generation unit 202 determines the music selected in S36 as BGM to be played during training. As a result, the training menu 213 including the music to be played during training is completed, and the process in FIG. 9 ends.
  • a training support system having the same functions as the training support device 2A can be constructed using a plurality of devices that can communicate with each other. For example, by distributing and providing each block shown in FIG. 5 in a plurality of devices, it is possible to construct a training support system having the same functions as the training support device 2A.
  • Some or all of the functions of the learning device 1 and the training support devices 2, 2A may be realized by hardware such as an integrated circuit (IC chip), or may be realized by software.
  • the learning device 1 and the training support devices 2, 2A are realized by, for example, a computer that executes instructions of a program that is software that realizes each function.
  • a computer that executes instructions of a program that is software that realizes each function.
  • An example of such a computer (hereinafter referred to as computer C) is shown in FIG.
  • Computer C includes at least one processor C1 and at least one memory C2.
  • a program P for operating the computer C as the learning device 1 and the training support devices 2 and 2A is recorded in the memory C2.
  • the processor C1 reads the program P from the memory C2 and executes it, thereby realizing the functions of the learning device 1 and the training support devices 2 and 2A.
  • Examples of the processor C1 include a CPU (Central Processing Unit), GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating Point Number Processing Unit), and PPU (Physics Processing Unit). , TPU (Tensor Processing Unit), quantum processor, microcontroller, or a combination thereof.
  • the memory C2 for example, a flash memory, an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a combination thereof can be used.
  • the computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and temporarily storing various data. Further, the computer C may further include a communication interface for transmitting and receiving data with other devices. Further, the computer C may further include an input/output interface for connecting input/output devices such as a keyboard, a mouse, a display, and a printer.
  • RAM Random Access Memory
  • the program P can be recorded on a non-temporary tangible recording medium M that is readable by the computer C.
  • a recording medium M for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit can be used.
  • Computer C can acquire program P via such recording medium M.
  • the program P can be transmitted via a transmission medium.
  • a transmission medium for example, a communication network or broadcast waves can be used.
  • Computer C can also obtain program P via such a transmission medium.
  • a training support device comprising: generating means for generating a training menu according to a state indicated by the state data by performing optimization calculation using an objective function.
  • the learning data includes information indicating music to be played during training, and the generating means generates the training menu including the music to be played during training. training support equipment.
  • the training support device according to supplementary note 4, further comprising a search means for displaying, as a search term for searching for a song, a phrase indicating the perspective regarding a song among the perspectives for evaluating a training menu shown in the objective function.
  • Appendix 6 at least one processor An objective function generated by acquiring state data indicating the training-related state of the subject and performing inverse reinforcement learning using learning data indicating the training menu to be applied in the training-related state according to the training-related state.
  • a training support method comprising: generating a training menu according to the state indicated by the state data by performing optimization calculation using the above-mentioned state data.
  • a training support program that functions as a generation means for generating a training menu according to a state indicated by the state data by performing an optimization calculation using a generated objective function.
  • a learning device comprising: learning means for generating an objective function.
  • At least one processor acquires learning data indicating a training menu to be applied in the training-related state according to the training-related state, and performs reverse reinforcement learning using the learning data, thereby providing a training menu according to the state.
  • a learning method comprising: generating an objective function for generating .
  • (Appendix 10) computer Data acquisition means for acquiring learning data indicating a training menu to be applied in a training-related state according to the training-related state, and generating a training menu according to the state by performing reverse reinforcement learning using the learning data.
  • a learning program that functions as a learning means to generate the objective function.
  • the processor includes at least one processor, and the processor performs a data acquisition process of acquiring state data indicating a state related to training performed by the subject, and learning data indicating a training menu to be applied in the state according to the state related to training.
  • a training support device that executes a generation process of generating a training menu according to a state indicated by the state data by performing optimization calculation using an objective function generated by inverse reinforcement learning using the above-mentioned state data.
  • this training support device may further include a memory, and this memory may store a program for causing the processor to execute the data acquisition process and the generation process. Further, this program may be recorded on a computer-readable non-transitory tangible recording medium.
  • the processor includes at least one processor, and the processor performs data acquisition processing to acquire learning data indicating a training menu to be applied in the training-related state according to the training-related state, and performs reverse reinforcement learning using the learning data.
  • a learning device that executes a learning process that generates an objective function for generating a training menu according to a state.
  • this learning device may further include a memory, and this memory may store a program for causing the processor to execute the data acquisition process and the learning process. Further, this program may be recorded on a computer-readable non-transitory tangible recording medium.

Landscapes

  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Business, Economics & Management (AREA)
  • Primary Health Care (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Epidemiology (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Public Health (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Databases & Information Systems (AREA)
  • Tourism & Hospitality (AREA)
  • Educational Technology (AREA)
  • Educational Administration (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
PCT/JP2022/015798 2022-03-30 2022-03-30 トレーニング支援装置、トレーニング支援方法、トレーニング支援プログラム、学習装置、学習方法、および学習プログラム Ceased WO2023188061A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/JP2022/015798 WO2023188061A1 (ja) 2022-03-30 2022-03-30 トレーニング支援装置、トレーニング支援方法、トレーニング支援プログラム、学習装置、学習方法、および学習プログラム
US18/839,477 US20250161753A1 (en) 2022-03-30 2022-03-30 Workout support apparatus, workout support method, training apparatus, and storage medium
JP2024510847A JP7666735B2 (ja) 2022-03-30 2022-03-30 トレーニング支援装置、トレーニング支援方法、トレーニング支援プログラム、学習装置、学習方法、および学習プログラム

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2022/015798 WO2023188061A1 (ja) 2022-03-30 2022-03-30 トレーニング支援装置、トレーニング支援方法、トレーニング支援プログラム、学習装置、学習方法、および学習プログラム

Publications (1)

Publication Number Publication Date
WO2023188061A1 true WO2023188061A1 (ja) 2023-10-05

Family

ID=88200237

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/015798 Ceased WO2023188061A1 (ja) 2022-03-30 2022-03-30 トレーニング支援装置、トレーニング支援方法、トレーニング支援プログラム、学習装置、学習方法、および学習プログラム

Country Status (3)

Country Link
US (1) US20250161753A1 (https=)
JP (1) JP7666735B2 (https=)
WO (1) WO2023188061A1 (https=)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021038781A1 (ja) * 2019-08-29 2021-03-04 日本電気株式会社 学習装置、学習方法および学習プログラム
WO2021075289A1 (ja) * 2019-10-15 2021-04-22 ソニー株式会社 情報処理装置、情報処理方法、及びプログラム
WO2021229625A1 (ja) * 2020-05-11 2021-11-18 日本電気株式会社 学習装置、学習方法および学習プログラム

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9433843B2 (en) 2011-11-18 2016-09-06 Tomtom International B.V. Method and apparatus for creating cost data for use in generating a route across an electronic map
US11103747B1 (en) 2012-02-04 2021-08-31 Thomas Chu-Shan Chuang Athletic training optimization
WO2018223194A1 (en) 2017-06-09 2018-12-13 Alerte Digital Sport Pty Ltd Systems and methods of prediction of injury risk with a training regime
EP4003543B1 (en) 2019-07-23 2025-12-10 Monster Smart Solutions, LLC Physical training system with machine learning-based training programs
WO2022067832A1 (zh) 2020-10-01 2022-04-07 曹庆恒 一种乐器教学系统及其使用方法、计算机可读存储介质

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021038781A1 (ja) * 2019-08-29 2021-03-04 日本電気株式会社 学習装置、学習方法および学習プログラム
WO2021075289A1 (ja) * 2019-10-15 2021-04-22 ソニー株式会社 情報処理装置、情報処理方法、及びプログラム
WO2021229625A1 (ja) * 2020-05-11 2021-11-18 日本電気株式会社 学習装置、学習方法および学習プログラム

Also Published As

Publication number Publication date
US20250161753A1 (en) 2025-05-22
JPWO2023188061A1 (https=) 2023-10-05
JP7666735B2 (ja) 2025-04-22

Similar Documents

Publication Publication Date Title
CN115066681B (zh) 音乐内容生成
US11562722B2 (en) Cognitive music engine using unsupervised learning
CN105659314B (zh) 通过自动地调整样本特征来组合音频样本
JP4581476B2 (ja) 情報処理装置および方法、並びにプログラム
CN105684077B (zh) 自动扩展音频样本集合
CN105659322B (zh) 推荐音频样本组合
US20130297599A1 (en) Music management for adaptive distraction reduction
US20160267177A1 (en) Music steering with automatically detected musical attributes
Crossley Music worlds and body techniques: On the embodiment of musicking
AU2016330618A1 (en) Machines, systems and processes for automated music composition and generation employing linguistic and/or graphical icon based musical experience descriptors
US20140059430A1 (en) System and method for generating a mood gradient
TW200808062A (en) Creation and navigation of media content with chaptering elements
US9734810B2 (en) Automatic harmony generation system
US20220406280A1 (en) Information processing apparatus, information processing method, and information processing program
TWI533148B (zh) 具導航特性之音樂推薦系統與方法
JP7666735B2 (ja) トレーニング支援装置、トレーニング支援方法、トレーニング支援プログラム、学習装置、学習方法、および学習プログラム
Otani et al. Generating a melody based on symbiotic evolution for musicians' creative activities
CN104906775B (zh) 用以辅助健身的多媒体编辑方法
Sinha Artificial composition: an experiment on Indian music
WO2022215250A1 (ja) 選曲装置、モデル作成装置、プログラム、選曲方法、およびモデル作成方法
KR102623459B1 (ko) 사용자의 보컬 평가에 기반한 오디션 이벤트 서비스 제공 방법, 장치 및 시스템
US20240296182A1 (en) Systems and methods for filtering large audio libraries using perceptive distribution binning
KR102623449B1 (ko) 사용자 보컬 평가 결과 맞춤형 보컬 트레이닝 서비스 제공 방법, 장치 및 시스템
CN101023427A (zh) 提供符合性信息的方法
JP5099716B2 (ja) メディア・コンテンツ情報分析装置および方法

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: 22935208

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 18839477

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2024510847

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22935208

Country of ref document: EP

Kind code of ref document: A1

WWP Wipo information: published in national office

Ref document number: 18839477

Country of ref document: US