Training support information provision device

Abstract

To provide a technology that can effectively support the training of subjects such as athletes using a simpler and faster method than conventional methods. [Solution] The training support information providing device according to the embodiment includes: an acquisition unit that acquires emission amount information relating to the emission amounts of multiple types of skin gases emitted from the skin of a subject; a calculation unit that calculates at least one objective index value indicating the ratio of the emission amount of a specific skin gas selected from multiple types of skin gases based on the emission amount information; a determination unit that determines the stress state of the subject based on the at least one objective index value and determines the suitability of the subject for training based on the determined stress state; a generation unit that generates training support information relating to the subject based on the suitability of the subject for training; and an output unit that outputs the training support information.

Description

TECHNICAL FIELD

[0001] An embodiment of the present invention relates to a training support information providing apparatus.

BACKGROUND ART

[0002] In general, in training, athletes repeatedly apply loads to their minds and bodies to push themselves into a stress state, and enhance their physical and mental functions through the recovery process from the stress state, leading to improved athletic performance. For this reason, some athletes perform training at the very limit load that may cause injuries or failures in order to maximize functional improvement.

[0003] In recent years, various technologies have been proposed to support the training of such athletes. For example, there is a technology that determines the injury risk level from the magnitude of the discrepancy between the subjective evaluation and the objective evaluation of the fatigue level of each muscle, and supports the pre-adjustment of training intensity. There is also a technology that simultaneously measures and manages exercise information such as heart rate and blood pressure during exercise, health status determined from sweat volume, exercise load, and form, which are considered effective for training support.

PRIOR ART DOCUMENTS

PATENT DOCUMENTS

[0004]

PATENT DOCUMENT 1

PATENT DOCUMENT 2

SUMMARY OF THE INVENTION

PROBLEMS TO BE SOLVED BY THE INVENTION

[0005] However, in the prior art, for example, in competitions involving complex movements, the evaluation may be complicated, and high-level data analysis skills and knowledge may be required for practical use in training.

[0006] Therefore, one of the objectives of the present invention is to provide a technology that can effectively support the training of subjects such as athletes using a simpler and faster method than conventional methods. [Means for solving the problem]

[0007] As an example, the training support information providing device according to the embodiment includes: an acquisition unit that acquires emission amount information relating to the emission amounts of multiple types of skin gases emitted from the skin of a subject; a calculation unit that calculates at least one objective index value indicating the ratio of the emission amount of a specific skin gas selected from the multiple types of skin gases based on the emission amount information; a determination unit that determines the stress state of the subject based on at least one of the objective index values ​​and determines the suitability of the subject for training based on the determined stress state; a generation unit that generates training support information relating to the subject based on the determination of the subject's suitability for training; and an output unit that outputs the training support information. [Effects of the Invention]

[0008] According to the training support information provision device of this embodiment, it is possible to effectively support the training of subjects such as athletes using a simpler and faster method compared to conventional methods. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 shows an example of the hardware configuration of a training support information provision device according to an embodiment. [Figure 2] Figure 2 shows an example of a skin gas detection location according to the embodiment. [Figure 3] Figure 3 shows an example of the functional configuration of a training support information provision device according to an embodiment. [Figure 4] Figure 4 shows an example of a two-dimensional map illustrating the relationship between vascular indicators, metabolic indicators, and stress levels, illustrating the relationship between these factors and the state of mind and body. [Figure 5]Figure 5 shows another example of a two-dimensional map of mental and physical state illustrating the relationship between vascular indicators, metabolic indicators, and stress levels. [Figure 6] Figure 6 shows another example of a two-dimensional map of mental and physical state illustrating the relationship between vascular indicators, metabolic indicators, and stress levels. [Figure 7] Figure 7 is an example of a two-dimensional map showing the relationship between the training intensity and stress levels of subjects over time, and is a diagram illustrating an example of training suitability classification information. [Figure 8] Figure 8 is another example of a two-dimensional map showing the relationship between the time-series changes in training intensity and stress levels of subjects, and is a figure illustrating another example of training suitability classification information. [Figure 9] Figure 9 is another example of a two-dimensional map showing the relationship between the time-series changes in training intensity and stress levels of subjects, and is a figure illustrating another example of training suitability classification information. [Figure 10] Figure 10 is another example of a two-dimensional map showing the relationship between the time-series changes in training intensity and stress levels of subjects, and is a figure illustrating another example of training suitability classification information. [Figure 11] Figure 11 is a flowchart showing an example of the training support information generation process. [Figure 12] Figure 12 shows an example of how training support information is provided to subjects. [Figure 13] Figure 13 is a diagram showing an example of training suitability classification information according to the second embodiment. [Figure 14] Figure 14 shows an example of the relationship between vascular indicator values ​​and stress levels. [Figure 15] Figure 15 shows an example of the relationship between metabolic indicator values ​​and physical stress levels. [Modes for carrying out the invention]

[0010] Hereinafter, a training support information providing system and a training support information providing apparatus according to the present embodiment will be described with reference to the drawings. The configurations of the embodiments described below, as well as the operations and effects brought about by the configurations, are merely examples, and the present invention is not limited to the following descriptions.

[0011] (First Embodiment) Figure 1 is a diagram illustrating an example of the hardware configuration of a training support information providing system 1 according to the first embodiment. The training support information providing system 1 according to the present embodiment includes a skin gas sensor 11 and a training support information providing apparatus 12.

[0012] The skin gas sensor 11 is a sensor that detects skin gas released from the skin of a subject. The skin gas sensor 11 is capable of detecting skin gas generated in association with activities for maintaining homeostasis in the human body, and is capable of detecting at least a blood vessel-related gas associated with vasomotion (contraction or dilation of blood vessels) and a metabolism-related gas associated with metabolic activity.

[0013] The blood vessel-related gas may be, for example, hexanoic acid, propionic acid, or the like.

[0014] The metabolism-related gas may be, for example, acetone, acetic acid, acetaldehyde, or the like.

[0015] The specific configuration of the skin gas sensor 11 is not particularly limited, but for example, oxide semiconductor sensors, QCM (Quartz Crystal Microbalance) sensors, FET (Field Effect Transistor) sensors, and film-type surface stress sensors can be used as skin gas sensors 11. In addition, skin gas emission data collected by a PFS (Passive Flux Sampler) and quantitatively measured for each skin gas type using a GC-MS (Gas Chromatography Mass Spectrometry) instrument can also be used as data for the skin gas sensor 11. A PFS is a small device that collects skin gases diffusing from the surface of a subject's skin by adsorption onto a solid collecting material, and the skin gases are thermally or chemically desorbed from the collecting material for chemical analysis. For example, there is a skin gas sampler (MonoTrap® SG DCC18) manufactured by GL Sciences Inc.

[0016] Figure 2 shows an example of a skin gas detection location according to this embodiment. The skin gas detection location by the skin gas sensor 11 according to this embodiment is the palm 31 of the subject, and is preferably the thenar eminence 32 or the fingertips 33. These areas have many capillaries, are usually hairless, and have little subcutaneous fat, so the amount of skin gas emitted is large, and skin gas can be detected relatively stably. In Figure 2, the fingertip 33 is shown as the fingertip 33 of the thumb, but the fingertip 33 may be the fingertip of another finger (index finger, middle finger, ring finger, or little finger).

[0017] The detection location, specific configuration, and installation location of the skin gas sensor 11 are not limited to those described above. For example, the detection location may be the back of the knee, etc.

[0018] The training support information providing device 12 connects to the skin gas sensor 11 via a predetermined network 15 and performs various information processing to detect the subject's stress based on the detection results of the skin gas sensor 11.

[0019] The training support information provision device 12 illustrated here is constructed using a general-purpose information processing device (computer) and includes a CPU (Central Processing Unit) 21, RAM (Random Access Memory) 22, ROM (Read Only Memory) 23, storage 24, communication I / F (Interface) 25, and user I / F 26.

[0020] The CPU 21 uses the RAM 22 as a workspace to execute predetermined arithmetic processing according to the programs stored in the ROM 23 and storage 24. The storage 24 is a non-volatile memory such as an SSD (Solid State Drive) or HDD (Hard Disk Drive), and enables writing and reading of programs, data necessary for the CPU 21's processing, and data generated by the CPU 21's processing. The communication I / F 25 is a device that enables communication with other electronic devices such as the skin gas sensor 11 connected via a predetermined network 15. The user I / F 26 is a device that enables receiving input from the user (such as the user of the training support information provision system 1) and outputting information to the user, and may be, for example, a keyboard, pointing device, touch panel mechanism, display, speaker, microphone, etc. The CPU 21, RAM 22, ROM 23, storage 24, communication I / F 25, and user I / F 26 are connected via a data bus.

[0021] The hardware configuration of the training support information provider 12 is not limited to the above; for example, it may be configured using FPGA (Field Programmable Gate Array), ASIC (Application Specific Integrated Circuit), etc., or it may be a system in which multiple computers work together.

[0022] Figure 3 shows an example of the functional configuration of the training support information providing device 12 according to this embodiment. The training support information providing device 12 according to this embodiment includes an acquisition unit 101, a vascular index value calculation unit 102, a metabolic index value calculation unit 103, a determination unit 104, a generation unit 105, an output unit 106, and a storage unit 107. These functional units 101 to 107 are configured through the cooperation of hardware elements and software elements (programs, firmware, etc.) that constitute the training support information providing device 12. Furthermore, at least a part of these functional units 101 to 107 may be configured with dedicated hardware (circuits, etc.).

[0023] The acquisition unit 101 acquires emission amount information from the skin gas sensor 11 regarding the amount of skin gas emitted from the subject's skin. In this embodiment, the acquisition unit 101 acquires vascular-related gas information indicating the emission amounts of multiple types of vascular-related gases, and metabolic-related gas information indicating the emission amounts of multiple types of metabolic-related gases. The emission amount may be, for example, a value indicating the amount of gas emitted (detected by the skin gas sensor 11) per predetermined unit time.

[0024] Vascular gas information includes, for example, the amount of hexanoic acid emitted, the amount of propionic acid emitted, etc.

[0025] Metabolism-related gas information includes, for example, the amount of acetone, acetic acid, and acetaldehyde released.

[0026] Furthermore, the emission amount information acquired by the acquisition unit 101 may include information on the emission amounts of skin gases other than vascular-related gases and metabolic-related gases, such as other skin gases emitted in response to homeostatic activities in the body.

[0027] The vascular index value calculation unit 102 calculates the vascular index value based on the vascular-related gas information acquired by the acquisition unit 101. The vascular index value is a value that indicates the ratio of the emission amount of a specific vascular-related gas selected from the multiple types of vascular-related gases to the total emission amount of multiple types of vascular-related gases. For example, if the multiple types of vascular-related gases are hexanoic acid and propionic acid, the specific vascular-related gas is hexanoic acid, and the emission amount of hexanoic acid is A1 and the emission amount of propionic acid is A2, the vascular index value BV can be calculated by the following formula (1).

[0028] BV = A1 / (A1 + A2) …(1)

[0029] In other words, the vascular index value BV may be the ratio of hexanoic acid emissions to the total emissions of hexanoic acid and propionic acid. Note that the above method for calculating the vascular index value BV is illustrative, and the selection of multiple types of vascular-related gases, as well as the selection of specific vascular-related gases, is not limited to the above. For example, the vascular index value BV may be the ratio of propionic acid emissions to the total emissions of hexanoic acid and propionic acid (BV' = A2 / (A1 + A2)).

[0030] As described above, by utilizing the vascular index value BV, which is the ratio of the emission amount of a specific vascular-related gas to the total emission amount of multiple vascular-related gases, it is possible to suppress the effects of fluctuations in skin gas emission caused by climatic conditions and subject-specific factors (constitution, mental state, etc.).

[0031] The metabolic index value calculation unit 103 calculates the metabolic index value based on the metabolism-related gas information acquired by the acquisition unit 101. The metabolic index value is a value that indicates the ratio of the emission amount of a specific metabolism-related gas selected from the multiple types of metabolism-related gases to the total emission amount of multiple types of metabolism-related gases. For example, if the multiple types of metabolism-related gases are acetone, acetic acid, and acetaldehyde, and the specific metabolism-related gas is acetone, and the emission amount of acetone is B1, the emission amount of acetic acid is B2, and the emission amount of acetaldehyde is B3, then the metabolic index value ME can be calculated by the following formula (2).

[0032] ME = B1 / (B1 + B2 + B3) …(2)

[0033] In other words, the metabolic index value ME may be the ratio of acetone emissions to the total emissions of acetone, acetic acid, and acetaldehyde. Note that the above method for calculating the metabolic index value ME is illustrative, and the selection of multiple metabolic gases, as well as the selection of specific metabolic gases, is not limited to the above. For example, the metabolic index value ME may be the ratio of the total emissions of acetic acid and aldehydes to the total emissions of acetone, acetic acid, and acetaldehyde (ME'=(B2+B3) / (B1+B2+B3)).

[0034] As described above, by using the metabolic index value ME, which is the ratio of the emission amount of a specific metabolic-related gas to the total emission amount of multiple metabolic-related gases, it is possible to suppress the effects of fluctuations in skin gas emission caused by climatic conditions and subject-specific factors (constitution, mental state, etc.).

[0035] The determination unit 104 determines the subject's stress state based on at least one index value. Specifically, the determination unit 104 determines whether the subject is in a stress state where they are experiencing stress above a predetermined level, based on the vascular index value BV calculated by the vascular index value calculation unit 102 and the metabolic index value ME calculated by the metabolic index value calculation unit 103.

[0036] Furthermore, the vascular index value BV and metabolic index value ME, which are indicators used by the determination unit 104 for determination, can be called objective indicator values ​​because they are indicator values ​​calculated based on chemical component analysis. In addition, the vascular index value BV and metabolic index value ME are examples of objective indicator values. The determination unit 104 may also determine whether or not a person is in a stressed state based on indicator values ​​other than the vascular index value BV and metabolic index value ME.

[0037] Figure 4 shows an example of a stress state map illustrating the relationship between vascular index value BV, metabolic index value ME, and stress state. An example of the determination method by the determination unit 104 will be explained with reference to the stress state map shown in Figure 4.

[0038] The determination unit 104 determines that the subject is in a stressed state if the relationship between the vascular index value BV and the threshold X1 satisfies predetermined conditions. For example, if the vascular index value BV is defined as the ratio of hexanoic acid to the total emission of hexanoic acid and propionic acid, the subject is determined to be in a stressed state if the vascular index value BV is less than or equal to the threshold X1, that is, if the point (BV, ME) in the graph shown in Figure 4 is within region R1 or region R2. Note that the threshold X1 and predetermined conditions (such as the relationship between BV and X1) change depending on the selection of vascular-related gases or specific vascular-related gases.

[0039] Furthermore, if the determination unit 104 determines that the subject is in a stressed state, it determines, based on the relationship between the metabolic index value ME and the threshold Y1, whether the subject is in a physical stressed state experiencing physical stress or a mental stressed state experiencing mental stress. For example, if the metabolic index value ME is the ratio of acetone emission to the total emission of acetone, acetic acid, and acetaldehyde, the subject is determined to be in a physical stressed state if the vascular index value BV is less than or equal to the threshold X1 and the metabolic index value ME is greater than or equal to the threshold Y1, that is, if the point (BV,ME) is within region R1 in the graph shown in Figure 4.

[0040] Furthermore, the determination unit 104 determines that the subject is in a state of mental stress if the vascular index value BV is less than or equal to the threshold X1 and the metabolic index value ME is less than the threshold Y1, that is, if the point (BV, ME) is within region R2 in the graph shown in Figure 4. Mental stress refers to a stress response that is triggered psychologically by a stress stimulus (stressor), and includes stress accompanied by symptoms such as decreased vitality, irritability, anxiety, and depression (low mood, decreased interest).

[0041] Furthermore, the determination unit 104 determines that the subject is in a neutral state if the vascular index value BV is greater than the threshold X1 and the metabolic index value ME is less than or equal to the threshold Y2, that is, if the point (BV, ME) in the graph shown in Figure 4 is within region R3. A neutral state can be a state of mental and physical stability, not a state of stress.

[0042] Furthermore, the determination unit 104 determines that the subject is in a temporarily high-activity state if the vascular index value BV is greater than the threshold X1 and the metabolic index value ME is greater than the threshold Y2, that is, if the point (BV, ME) in the graph shown in Figure 4 is within region R4. A temporarily high-activity state is not a stress state corresponding to regions R1 or R2, but it is a state in which the physical load is higher than normal and can be considered a type of stress state. Note that the conditions for distinguishing between the thresholds Y1, Y2 and regions R1 to R4 (such as the relative magnitudes of ME, Y1, and Y2) change depending on the selection of metabolic gases and specific metabolic gases.

[0043] According to the above-described determination method, it is possible to determine whether a subject is in a stressed state based on the vascular index value BV. In addition to the vascular index value BV, it is also possible to determine whether the type of stress the subject is experiencing is physical or mental based on the metabolic index value ME. Furthermore, it is possible to determine other states besides stress (e.g., a neutral state). The results of these determinations regarding other states can be used, for example, to generate stress information or support information.

[0044] Figure 4 illustrates an example of classifying stress states into four states (domains): "physical stress state," "mental stress state," "neutral state," and "temporary high-activity state." However, the number of stress state classifications can be arbitrarily set as needed.

[0045] Figures 5 and 6 show other examples of stress state maps illustrating the relationship between vascular index BV, metabolic index ME, and stress levels. In the example shown in Figure 5, stress levels are classified into two categories: "stressed state" and "neutral state."

[0046] Furthermore, as shown by the black dots in the example in Figure 6, it is also possible to understand the changes in stress status over time by mapping points (BV, ME) corresponding to skin gases acquired at different times onto the stress state map.

[0047] Furthermore, the determination unit 104 performs training suitability determination processing for the subject based on the determined stress state. Specifically, the determination unit 104 generates training suitability classification information using time-series information related to the stress state, and performs training suitability determination processing for the subject using the generated training suitability classification information. Training suitability classification information includes information that shows the relationship between training intensity and the temporal changes in the stress state.

[0048] Here, the training suitability classification information and the training suitability determination process using the training suitability classification information will be explained in detail with reference to Figures 7, 8, and 9.

[0049] Figure 7 is an example of a two-dimensional map showing the relationship between a subject's training intensity and the time-series progression of their stress level, and is an example of training suitability classification information. In the example of training suitability classification information shown in Figure 7, the two-dimensional maps of mental and physical states shown in Figures 5 and 6 are arranged in chronological order in a two-dimensional coordinate system with training intensity TR on the vertical axis and time T on the horizontal axis. Each mental and physical state map includes the progression of stress levels over one week. T1 to T4 each show the time progression in one-week units. That is, each mental and physical state map for the period T1 to T4 corresponds to the progression of stress levels over four weeks when training is performed at training intensity TR1.

[0050] As can be seen from the training suitability classification information shown in Figure 7, during periods T1, T2, and T3, the subject's stress state fluctuates between the stress region (stress present / high stress) and the neutral region (no stress / low stress). In contrast, during period T4, the subject's stress state is almost entirely in the neutral region (no stress / low stress). This indicates that the subject has become accustomed to training at training intensity TR1 (i.e., has transitioned from a moderate stress state to a low stress state). In such cases, from the perspective of allostasis resilience, it is preferable to transition to a higher training intensity TR2 to achieve a greater training effect.

[0051] Figure 8 shows the changes in stress levels over four weeks when training at training intensity TR2 for a period of T4-T7, added to the training suitability classification information shown in Figure 7.

[0052] As can be seen from the training suitability classification information shown in Figure 8, during periods T4, T5, and T6, the subject's stress state fluctuates between the stress region (stress present / high stress) and the neutral region (no stress / low stress). In contrast, during period T7, the subject's stress state is almost entirely in the neutral region (no stress / low stress). This indicates that the subject has become accustomed to training at training intensity TR2 (i.e., has transitioned from a moderate stress state to a low stress state). In such cases, from the perspective of allostasis resilience, it is preferable to transition to a higher training intensity TR3 to achieve a greater training effect.

[0053] Figure 9 shows the changes in stress levels over a three-week period when training was performed at training intensity TR3 for a period of T7-T9, in addition to the training suitability classification information shown in Figure 8.

[0054] As can be seen from the training suitability classification information shown in Figure 9, during the T7-T9 period, the subject's stress state fluctuates between the stress region (stress present / high stress) and the neutral region (no stress / low stress). Furthermore, during the T8 and T9 periods, the number of times the subject's stress state is in the neutral region (no stress / low stress) does not increase. This suggests that the subject is in an overwork state (i.e., a high-stress state) as a result of continuing training at training intensity TR3. In such cases, from the perspective of allostasis resilience, it is preferable to take measures such as reducing the load or taking a period of rest in order to achieve a higher training effect.

[0055] Furthermore, the training suitability classification information is not limited to the examples shown in Figures 7 to 10. In other words, the training suitability classification information can be any information that allows for the determination of training suitability based on the temporal progression of stress levels.

[0056] Figure 10 is another example of a two-dimensional map showing the relationship between a subject's training intensity and the time-series progression of their stress level, and illustrates another example of training suitability classification information. In the example of Figure 10, the two-dimensional maps of each physical and mental state in Figures 7, 8, and 9 are abstracted into "low stress," "medium stress," and "high stress" based on the progression of stress levels over a certain period in each two-dimensional map, and mapped onto a two-dimensional coordinate system with training intensity TR on the vertical axis and time T on the horizontal axis. Training suitability can also be determined from the time-series progression of stress levels using the training suitability classification information exemplified in Figure 10.

[0057] The determination unit 104 generates training suitability classification information, as illustrated in Figures 7 to 10, using multiple stress state maps, including the most recent stress state map, and the training intensity corresponding to each stress state map. Using the generated training suitability classification information, the determination unit 104 performs a training suitability determination process to determine whether the training currently being performed by the subject is appropriate or not.

[0058] The generation unit 105 generates training support information about the subject based on the results of the training suitability determination process performed by the determination unit 104.

[0059] Here, training support information refers to information that includes at least one of the results of the subject's training suitability assessment process and management information based on those results. For example, if the assessment unit 104 determines that "the training the subject is currently undergoing is unsuitable," the generation unit 105 generates management information such as information informing the subject that the current training is unsuitable, information informing the subject that it is overtraining, information informing the subject that there is a high risk of injury or breakdown, and information informing the subject that a predetermined period of rest is necessary. Also, for example, if the assessment unit 104 determines that "the training the subject is currently undergoing is appropriate," the generation unit 105 generates management information such as information informing the subject that the current training is appropriate, and information such as "there is no risk in continuing the current training."

[0060] Furthermore, the training support information may include information to reduce the subjects' stress. The training support information may also include training suitability classification information as shown in Figures 7, 8, and 9.

[0061] Furthermore, various methods can be employed by the generation unit 105 to generate training support information. For example, the generation unit 105 can generate training support information using a database (or table) in which the results of multiple training suitability judgment processes are associated with multiple management information sets. Alternatively, the generation unit 105 can also generate training support information using a pre-trained model that takes the results of training suitability judgment processes as input and outputs management information.

[0062] The output unit 106 outputs (presents) the training support information generated by the generation unit 105 in a predetermined format.

[0063] The memory unit 100 stores, for each subject, skin gas information acquired by the acquisition unit 101, vascular index value BV calculated by the vascular index value calculation unit 102, metabolic index value ME, judgment results by the judgment unit 104, time-series information on stress states determined in the past, generated training suitability classification information, and training support information.

[0064] The presented training support information allows participants to easily and quickly obtain and confirm the appropriateness of their current training and specific measures for improvement.

[0065] (Training support information generation process) Figure 11 is a flowchart showing an example of the training support information generation process according to the embodiment. The training support information generation process will be explained in accordance with Figure 11.

[0066] First, the acquisition unit 101 acquires skin gas information from the skin gas sensor 11 (step S1).

[0067] The vascular index value calculation unit 102 calculates the vascular index value BV based on the skin gas information acquired by the acquisition unit 101 (step S2). The vascular index value BV is, for example, the ratio of the amount of hexanoic acid emitted to the total amount of hexanoic acid and propionic acid emitted.

[0068] The metabolic index value calculation unit 103 calculates the metabolic index value ME based on the skin gas information acquired by the acquisition unit 101 (step S3). The metabolic index value ME is, for example, the ratio of the amount of acetone emitted to the total amount of acetone, acetic acid, and acetaldehyde emitted.

[0069] The determination unit 104 uses the calculated vascular index value BV, metabolic index value ME, and stress state map to perform a stress state determination process for the subject (step S4).

[0070] The determination unit 104 generates training suitability classification information using the determined stress state and time-series information on past stress states stored in the storage 24 (step S5).

[0071] The determination unit 104 uses the generated training suitability classification information to perform a training suitability determination process for the subject (step S6).

[0072] The generation unit 105 generates training support information about the subject based on the results of the training suitability determination process performed by the determination unit 104 (step S7).

[0073] The output unit 106 outputs the generated stress information in a predetermined format (step S8).

[0074] Figure 12 shows an example of how training support information is provided to subjects. In the training support information provision system 1 illustrated in Figure 12, the training support information provision device 12 acquires emission amount information corresponding to each of a plurality of subjects P from a predetermined detection device 61 via the network 15, generates training support information 51 for each subject P based on the acquired emission amount information, and transmits each generated training support information 51 to the terminal device 62 used by the corresponding subject P via the network 15.

[0075] The form of the detection device 61 (the device equipped with the skin gas sensor 11) is not particularly limited, but could be, for example, a dedicated device fixedly installed in a specific location, or a wearable device that can be worn by the subject P. The form of the terminal device 62 used by the subject P is not particularly limited, but could be, for example, a smartphone, a tablet device, a personal computer, or a dedicated device specifically designed for use with the training support information provision system 1.

[0076] As described above, the training support information providing device 12 according to the embodiment includes: an acquisition unit 101 that acquires emission amount information relating to the emission amounts of multiple types of skin gases emitted from the subject's skin; a vascular index value calculation unit 102 and a metabolic index value calculation unit 103, which are calculation units that calculate at least one objective index value indicating the ratio of the emission amount of a specific skin gas selected from multiple types of skin gases based on the emission amount information; a determination unit 104 that determines the subject's stress state based on at least one objective index value and determines the subject's suitability for training based on the determined stress state; a generation unit 105 that generates training support information relating to the subject based on the subject's suitability for training; and an output unit 106 that outputs the training support information.

[0077] Therefore, the training support information providing device 12 can accurately determine the stress state based on objective index values ​​calculated using the subject's skin gas, and perform a highly objective training suitability assessment based on the determined stress state. Furthermore, based on the highly objective training suitability assessment, it can present specific and appropriate training support information to the subject. The subject can quickly and easily obtain training support information simply by providing their skin gas, and can achieve effective training using this training support information.

[0078] Furthermore, the training support information includes at least one of the following: the temporal changes in the subject's stress state, training suitability classification information classified using the subject's subjective and objective indicator values, and management information based on the subject's training suitability.

[0079] Therefore, the training support information provision device 12 makes it possible to understand what specific stress tolerance level a subject belongs to. Furthermore, based on the management information derived from their training tolerance level, subjects can take specific measures to maximize the effectiveness of their training.

[0080] Furthermore, at least one index value includes at least one of a vascular index value and a metabolic index value.

[0081] Therefore, the training support information providing device 12 can determine training suitability based on at least one of the physical stress state and the mental stress state, obtain training support information based on the results, and take specific measures.

[0082] (Second Embodiment) Next, the training support information providing device 12 according to the second embodiment will be described. The training support information providing device 12 according to the second embodiment generates training suitability classification information based on subjective stress index values ​​and objective stress index values, and uses this to perform training suitability determination processing. Note that the following description will describe a configuration that differs from that of the first embodiment.

[0083] Here, the subjective stress index is a quantified index value based on the stress that the subject feels. The subjective stress index can be calculated, for example, by having the subject answer questions about a predetermined number of items and quantifying them using a predetermined method.

[0084] Furthermore, the objective stress index value is an index value calculated based on the chemical component analysis of skin gases. In this embodiment, for the sake of concrete explanation, we will use as an example the case where the objective stress index value is the vascular index value BV or the metabolic index value ME. However, the objective stress index value is not limited to the vascular index value BV or the metabolic index value ME, but may be other index values. In addition, new index values ​​calculated by arithmetic operations on index values ​​such as the vascular index value BV or the metabolic index value ME can also be used.

[0085] The memory unit 100 stores pre-calculated subjective stress index values ​​for each subject.

[0086] The determination unit 104 performs a training suitability determination process for the subject based on the subjective stress index value and the objective stress index value. Specifically, the determination unit 104 generates training suitability classification information for the subject using the vascular index value BV calculated by the vascular index value calculation unit 102 or the metabolic index value E calculated by the metabolic index value calculation unit 103 and the subjective stress index value stored in the memory unit 100.

[0087] Figure 13 shows an example of training suitability classification information according to the second embodiment. In the example of training suitability classification information shown in Figure 13, a two-dimensional coordinate system is used with subjective stress index values ​​on the vertical axis and objective stress index values ​​on the horizontal axis, and for example, regions R1 (a state with a high risk of overtraining syndrome), R2 (a state in which high performance can be achieved), and R3 (a state with a high risk of injury / malfunction) are defined. Point Pc indicates the coordinates of the subject (objective stress index value, subjective stress index value).

[0088] The determination unit 104 uses the generated training suitability classification information to perform a training suitability determination process for the subject based on the positional relationship between point Pc and each region R1 to R3. For example, if point Pc is located within region R1, the determination unit 104 determines that the subject is currently in a state of high risk of overtraining syndrome. If point Pc is located within region R2, the determination unit 104 determines that the subject is currently in a state where they can perform at a high level. If point Pc is located within region R3, the determination unit 104 determines that the subject is currently in a state of high risk of injury or malfunction.

[0089] The generation unit 105 generates training support information about the subject based on the results of the training suitability determination process performed by the determination unit 104.

[0090] For example, if it is determined that the person is in a "high-risk state for overtraining syndrome," the generation unit 105 generates training support information, including management information indicating that the person is overtraining, in order to move the position of point Pc from region R1 to region R2.

[0091] Furthermore, if it is determined, for example, that the system is in a state where it can perform at a high level, the generation unit 105 generates training support information, including management information such as "there is no risk in continuing the current training," in order to ensure that the position of point Pc remains within region R2.

[0092] Furthermore, if it is determined, for example, that the "risk of injury or malfunction is high," the generation unit 105 generates training support information, including management information indicating a high risk of injury or malfunction, in order to move the position of point Pc from region R3 to region R2.

[0093] Furthermore, for example, if point Pc is not located in any of regions R1 to R3, as shown in Figure 13, training support information is generated that includes management information for moving point Pc from region R3 to region R2.

[0094] Furthermore, the training suitability classification information can be updated based on the subject's past stress levels over time. For example, as shown in Figure 13, areas R1 (high risk of overtraining syndrome), R2 (high performance), and R3 (high risk of injury) fluctuate along with the subject's training results. The judgment unit 104 can update the content of the training suitability classification information to be optimal for the current subject based on the past stress levels stored in the memory unit 107. The subject can then receive training support using training suitability classification information optimized according to the changes in their training results.

[0095] Furthermore, the training support information generation process performed by the training support information providing device 12 according to the second embodiment is substantially the same as the flowchart shown in Figure 11.

[0096] According to the configuration described above, training suitability classification information is generated based on subjective and objective stress index values, and this is used to perform training suitability determination processing. Then, based on the results of the training suitability determination processing, training support information is generated and provided to the subject.

[0097] Therefore, highly accurate training support information based on subjective and objective stress indicators can be provided quickly and easily.

[0098] (modified version) In the above embodiment, an example was given of determining the stress state using two indices, the vascular index BV and the metabolic index ME, and a stress state map. In contrast, it is also possible to determine the stress state using, for example, only one of the vascular index BV or the metabolic index ME.

[0099] Figure 14 shows an example of the relationship between the vascular index value BV and the stress value S. In Figure 14, line L1 illustrates the relationship between the vascular index value BV and the stress value S. The stress value S is a numerical representation of the intensity of mental stress based on a predetermined standard, and in this case, a higher value indicates greater stress.

[0100] Figure 14 shows that a relationship exists where the higher the stress value S, the lower the vascular index value BV. Here, if we define a subject as being in a stressed state when the stress value S is equal to or greater than the threshold S1, then a subject can be determined to be in a stressed state when the vascular index value BV is equal to or less than the threshold X1 corresponding to the threshold S1.

[0101] Figure 15 shows an example of the relationship between the metabolic index value ME and the physical stress value Sb. In Figure 15, line L2 illustrates the relationship between the metabolic index value ME and the physical stress value Sb. The physical stress value Sb is a numerical representation of the intensity of physical stress based on a predetermined standard, where a higher value indicates greater physical stress.

[0102] Figure 15 shows that a relationship exists where the higher the physical stress value Sb, the higher the metabolic index value ME. Here, if we define a subject as being in a state of physical stress when the physical stress value Sb is equal to or greater than the threshold Sb1, then a subject can be determined to be in a state of physical stress when the metabolic index value ME is equal to or greater than the threshold Y1 corresponding to the threshold Sb1.

[0103] The determination unit 104 can also determine the subject's stress state based on, for example, the relationship shown in Figure 14 or Figure 15, and perform a mental and physical state classification process based on the determined stress state.

[0104] According to the modified training support information provision device 12, the stress state is determined using either the vascular index value BV or the metabolic index value ME. Therefore, the computational load is reduced and the device can be simplified compared to the case where both the vascular index value BV and the metabolic index value ME are used.

[0105] The program that causes a computer to execute the calculation and control functions of the training support information provider described above can be provided as an installable or executable file recorded on a computer-readable recording medium such as a CD (Compact Disc)-ROM, flexible disk (FD), CD-R (Recordable), or DVD (Digital Versatile Disk). Furthermore, this program may be provided or distributed via a network such as the Internet.

[0106] Although embodiments of the present invention have been described above, the embodiments and their modifications described herein are merely examples and are not intended to limit the scope of the invention. The novel embodiments and modifications described herein can be implemented in various forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and modifications described herein are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents.

[0107] [Summary of this embodiment] This embodiment comprises at least the following configurations.

[0108] The training support information providing device (12) according to the embodiment includes: an acquisition unit (101) that acquires emission amount information relating to the emission amounts of multiple types of skin gases emitted from the subject's skin; a calculation unit (102, 103) that calculates at least one objective index value indicating the ratio of the emission amount of a specific skin gas selected from the multiple types of skin gases based on the emission amount information; a determination unit (104) that determines the subject's stress state based on at least one objective index value and determines the subject's suitability for training based on the determined stress state; a generation unit (105) that generates training support information relating to the subject based on the subject's suitability for training; and an output unit (106) that outputs the training support information.

[0109] Therefore, the training support information providing device (12) can correctly determine the stress state based on objective index values ​​calculated using the subject's skin gas, and perform a highly objective training suitability assessment based on the determined stress state. Furthermore, based on the highly objective training suitability assessment, it can present specific and appropriate training support information to the subject. The subject can quickly and easily obtain training support information simply by providing their skin gas, and can achieve effective training using the training support information.

[0110] Furthermore, the training support information includes at least one of the following: the temporal changes in the subject's stress state, training suitability classification information classified using the subject's subjective and objective indicator values, and management information based on the subject's training suitability.

[0111] Therefore, the training support information provision device (12) makes it possible to understand which specific stress appropriateness classification a subject belongs to. Furthermore, the subject can take specific countermeasures to maximize the effectiveness of the training based on the management information derived from the training appropriateness classification.

[0112] Furthermore, training suitability classification information is updated based on the subject's past stress levels over time.

[0113] Therefore, participants can receive training support using training suitability classification information optimized according to the fluctuations in their own training results.

[0114] Furthermore, at least one index value includes at least one of a vascular index value and a metabolic index value.

[0115] Therefore, the training support information providing device 12 can determine training suitability using at least one of the physical stress state and the mental stress state, obtain training support information based on the results, and take specific countermeasures.

[0116] Although embodiments of the present invention have been illustrated above, these embodiments and modifications are merely examples and are not intended to limit the scope of the invention. The above embodiments and modifications can be implemented in various other forms, and various omissions, substitutions, combinations, and changes can be made without departing from the spirit of the invention. Furthermore, the configurations and shapes of each embodiment and modification can be partially replaced. [Explanation of Symbols]

[0117] 1...Training support information provision system, 11...Skin gas sensor, 12...Training support information provision device, 15...Network, 21...CPU, 22...RAM, 23...ROM, 24...Storage, 25...Communication I / F, 26...User I / F, 51...Training support information, 61...Detection device, 62...Terminal device, 101...Acquisition unit, 102...Vascular index value calculation unit, 103...Metabolic index value calculation unit, 104...Determination unit, 105...Generation unit, 106...Output unit

Claims

1. An acquisition unit that acquires emission amount information regarding the emission amounts of multiple types of skin gases emitted from the subject's skin, A calculation unit that calculates at least one objective index value indicating the proportion of the emission amount of a specific skin gas selected from the multiple types of skin gases based on the emission amount information, A determination unit that determines the stress state of the subject based on at least one of the objective indicator values, and determines the suitability of the subject for training based on the determined stress state, A generation unit that generates training support information relating to the subject based on the subject's training suitability, An output unit that outputs the aforementioned training support information, A training support information provision device equipped with the following features.

2. The training support information includes at least one of the following: the temporal changes in the subject's stress state, training suitability classification information classified using the subject's subjective indicator values ​​and the subject's objective indicator values, and management information based on the subject's training suitability. The training support information providing device according to claim 1.

3. The aforementioned training suitability classification information is updated based on the subject's past stress levels over time. The training support information providing device according to claim 2.

4. At least one of the aforementioned index values ​​includes at least one of a vascular index value and a metabolic index value. A training support information providing device according to any one of claims 1 to 3.

Images