Method and apparatus for prescribing exercise on basis of hemodynamic information, and recording medium

Abstract

The present disclosure relates to a method and an apparatus for prescribing exercise on the basis of hemodynamic information, and a recording medium. The method for prescribing exercise on the basis of hemodynamic information, according to an embodiment of the present disclosure, comprises the steps of: obtaining optical signals detected after passing through a user's body tissue; calculating hemodynamic information on the basis of the optical signals; calculating, on the basis of the hemodynamic information, at least one of lactate information and fat burning information; and generating an exercise prescription for the user on the basis of at least one of the lactate information and the fat burning information.

Description

Method, device and recording medium for prescribing exercise based on hemodynamic information

[0001] The present disclosure relates to a method, device and recording medium for prescribing exercise based on hemodynamic information.

[0002] As physical activity levels decline in modern life, interest in exercise for health management is increasing. Recently, interest in aerobic exercise, such as walking, running, cycling, and swimming, has grown significantly.

[0003] Exercise that is too light may not be effective, while excessive exercise carries the risk of injury. Therefore, to promote health, appropriate exercise should be performed according to each individual's physical ability and condition.

[0004] However, accurately assessing one's physical abilities and condition is generally challenging. Consequently, most people find the right exercise level through trial and error. Even if professional facilities for assessing physical ability are available, it's unrealistic to utilize them every time you exercise. Furthermore, physical condition can fluctuate in real time, making it difficult to accurately determine the appropriate exercise intensity and duration each time.

[0005] Accordingly, there is a need for technology that can prescribe and evaluate exercise suitable for each individual for effective exercise even without complex and specialized facilities.

[0006] The present disclosure is intended to solve the problems of the above-described prior art, and its purpose is to provide a method and device for identifying a physical condition and prescribing appropriate exercise in a simple manner.

[0007] In addition, the present disclosure also aims to provide a method and device capable of evaluating individual exercise in real time.

[0008] A representative configuration of the present disclosure to achieve the above purpose is as follows.

[0009] A method for prescribing exercise based on hemodynamic information according to one embodiment of the present disclosure includes the steps of acquiring an optical signal detected by passing through a body tissue of a user, calculating hemodynamic information based on the optical signal, calculating at least one of lactate information and fat burning information based on the hemodynamic information, and generating an exercise prescription for the user based on at least one of lactate information and fat burning information.

[0010] According to one embodiment of the present disclosure, in the step of acquiring an optical signal, an optical signal detected by near-infrared light passing through the user's muscle tissue can be acquired.

[0011] According to one embodiment of the present disclosure, the hemodynamic information may include at least one of oxygenated hemoglobin concentration, non-oxygenated hemoglobin concentration, oxygen saturation, and blood flow variability.

[0012] According to one embodiment of the present disclosure, in the step of calculating at least one of lactate information and fat burning information, a change in blood lactate concentration may be calculated from oxygen saturation or a change in oxygen saturation included in the hemodynamic information using a lactate estimation model. Here, the lactate estimation model may be a machine-learned model based on data regarding oxygen saturation and blood lactate concentration acquired during exercise stress tests of multiple subjects.

[0013] According to one embodiment of the present disclosure, in the step of calculating at least one of lactate threshold information and fat burning rate information, the amount of fat burned can be calculated from the oxygen saturation or the change in oxygen saturation included in the hemodynamic information using a fat burning estimation model. Here, the fat burning estimation model may be a model generated based on the correlation between the amount of fat burned and the oxygen saturation estimated from data on oxygen consumption and carbon dioxide production acquired during exercise stress tests of multiple subjects.

[0014] A method for prescribing exercise based on hemodynamic information according to one embodiment of the present disclosure may further include a step of evaluating the user's exercise based on the user's exercise prescription.

[0015] According to one embodiment of the present disclosure, in the step of evaluating exercise, an exercise evaluation score based on the user's exercise prescription can be calculated by referring to hemodynamic information and exercise information.

[0016] A device for prescribing exercise based on hemodynamic information according to one embodiment of the present disclosure includes: an optical signal acquisition unit for acquiring an optical signal detected by passing through a user's body tissue; a hemodynamic calculation unit for calculating hemodynamic information based on the optical signal; a lactate calculation unit for calculating lactate information based on the hemodynamic information; a fat combustion calculation unit for calculating fat combustion information based on the hemodynamic information; and an exercise prescription unit for generating an exercise prescription for the user based on at least one of the lactate information and the fat combustion information.

[0017] A method for prescribing exercise based on hemodynamic information of a subject includes the steps of: acquiring an optical signal detected by passing through a body tissue of the subject; calculating hemodynamic information based on the optical signal; calculating at least one of lactate threshold information and fat burning rate information based on the hemodynamic information; and generating exercise prescription information of the subject based on at least one of the hemodynamic information, lactate threshold information, and fat burning rate information.

[0018] In addition, other methods for implementing the present disclosure, other devices, and recording media for recording a computer program for executing the method are further provided.

[0019] According to one embodiment of the present disclosure, exercise can be prescribed for an individual based on hemodynamic information obtained through an optical signal, thereby enabling an appropriate exercise to be prescribed for an individual in a simple manner even without specialized facilities.

[0020] Additionally, according to one embodiment of the present disclosure, an individual's exercise can be evaluated in real time based on an exercise prescription, thereby enabling effective exercise.

[0021] FIG. 1 is a schematic diagram illustrating a system environment for prescribing exercise based on hemodynamic information of a subject according to one embodiment of the present disclosure.

[0022] FIG. 2 is a functional block diagram schematically illustrating the functional configuration of an exercise prescription device according to one embodiment of the present disclosure.

[0023] FIG. 3 is a diagram exemplarily showing data for learning a lactate estimation model according to one embodiment of the present disclosure.

[0024] FIG. 4 is a diagram exemplarily showing the correlation between oxygen saturation and fat burning amount in a fat burning estimation model according to one embodiment of the present disclosure.

[0025] FIG. 5 is a diagram exemplarily showing how exercise information and exercise prescription are provided to a user terminal according to one embodiment of the present disclosure.

[0026] FIG. 6 is a diagram exemplarily showing how exercise evaluation scores are provided to a user terminal according to one embodiment of the present disclosure.

[0027] FIG. 7 is a flowchart illustrating a process of prescribing exercise based on hemodynamic information according to one embodiment of the present disclosure.

[0028] [Explanation of symbols]

[0029] 100: Exercise Prescription System

[0030] 110: Measuring device

[0031] 120: Exercise prescription device

[0032] 130: Communications network

[0033] 201: Optical signal acquisition unit

[0034] 203: Hemodynamics calculation unit

[0035] 205: Lactic acid production unit

[0036] 207: Fat Burning Output Unit

[0037] 209: Exercise Prescription

[0038] 211: Communications Department

[0039] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings. Hereinafter, specific descriptions of previously known functions and configurations will be omitted if deemed likely to unnecessarily obscure the gist of the present disclosure. Furthermore, it should be noted that the following description relates only to one embodiment of the present disclosure and that the present disclosure is not limited thereto.

[0040] The terminology used in this disclosure is merely used to describe specific embodiments and is not intended to be limiting of the present disclosure. For example, a component expressed in the singular should be understood to include plural components unless the context clearly indicates only a singular meaning. The term "and / or" used in this disclosure should be understood to encompass any and all possible combinations of one or more of the listed items. The terms "comprises," "has," and the like used in this disclosure are intended to specify the presence of a feature, number, step, operation, component, part, or combination thereof described in this disclosure, but the use of such terms does not exclude the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0041] In the embodiments of the present disclosure, a "module" or "part" refers to a functional component that performs at least one function or operation, and may be implemented as hardware or software, or as a combination of hardware and software. Furthermore, a plurality of "modules" or "parts" may be integrated into at least one software module and implemented by at least one processor, excluding any "modules" or "parts" that need to be implemented as specific hardware.

[0042] Additionally, unless otherwise defined, all terms used in this disclosure, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which this disclosure pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the contextual meaning of the relevant technology, and should not be interpreted in an unduly limiting or expansive manner unless explicitly defined otherwise in this disclosure.

[0043] FIG. 1 is a schematic diagram illustrating a system environment for prescribing exercise based on hemodynamic information according to one embodiment of the present disclosure.

[0044] Referring to FIG. 1, a system (100) for prescribing exercise based on hemodynamic information according to one embodiment of the present disclosure may include a measuring device (110), an exercise prescription device (120), and a communication network (130).

[0045] A measuring device (110) according to one embodiment of the present disclosure may be worn on a body part of a user (e.g., a leg, an arm, etc.) and may perform a function of measuring a predetermined signal from the body part of the user. The signal measured by the measuring device (110) may be processed or analyzed by an exercise prescription device (120), as described below, and may be utilized to monitor activities occurring in the corresponding body part of the user (e.g., hemodynamic changes occurring in a muscle, etc.). For this purpose, the measuring device (110) may be configured in the form of a patch that can be attached to a body part of the user, as illustrated.

[0046] In one embodiment, the measuring device (110) may include at least one light source that emits near-infrared light and at least one light receiver (detector) that detects near-infrared light.

[0047] The light-emitting unit of the measuring device (110) may perform a function of irradiating near-infrared rays to body tissue located in a user's body part. The light-emitting unit may include a light source that emits near-infrared light, such as a laser or LED. For example, the body tissue to which at least one light-emitting unit irradiates near-infrared rays may be a muscle in a leg or arm area.

[0048] The light receiving unit of the measuring device (110) can perform a function of detecting near-infrared rays that are reflected, scattered, or transmitted from a user's body part after being emitted from the light emitting unit. The light receiving unit can be composed of a module comprising a photo detector (PD) that collects light that has passed through the user's body tissue and a circuit that drives the photo detector.

[0049] According to one embodiment of the present disclosure, light emitted from at least one light-emitting unit may pass through body tissue and be received by at least one light-receiving unit and converted into an electrical signal, which may be transmitted to an exercise prescription device (120) described below.

[0050] According to one embodiment of the present disclosure, by using light of a predetermined frequency (e.g., near-infrared light) in a measurement device (110), hemodynamic information can be obtained from a measured signal. In one embodiment, a measurement circuit gain of at least one light-receiving unit is dynamically controlled according to a time interval set based on a time division method applied to at least one light-emitting unit, or an optical signal detected by at least one light-receiving unit is modulated based on a frequency division method applied to at least one light-emitting unit, so that at least one light-receiving unit can detect an optical signal generated by at least one light-emitting unit by distinguishing it according to the optical signal. Accordingly, hemodynamic information of multiple regions of a user's body tissue can be obtained without mutual interference from the optical signal measured by the measurement device (110).

[0051] A communication network (130) according to one embodiment of the present disclosure may include any wired or wireless communication network, such as a TCP / IP communication network. According to one embodiment of the present disclosure, the communication network (130) may be configured as a Local Area Network (LAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), the Internet, etc., but the present disclosure is not limited thereto. For example, the communication network (130) may be a wireless data communication network that implements, at least in part, a conventional communication method such as WiFi communication, WiFi-Direct communication, Long Term Evolution (LTE) communication, 5G communication, Bluetooth communication (including Bluetooth Low Energy (BLE) communication), infrared communication, ultrasonic communication, etc. As another example, the communication network (130) may be an optical communication network that implements, at least in part, a conventional communication method such as LiFi (Light Fidelity).

[0052] An exercise prescription device (120) according to one embodiment of the present disclosure can perform a function of calculating hemodynamic information based on an optical signal obtained from a measurement device (110) and generating an exercise prescription based on the hemodynamic information.

[0053] The exercise prescription device (120) may be a server system capable of communicating with the measurement device (110) and / or the user terminal. The server may be an independent physical server or a virtual server such as a cloud server. In FIG. 1, the exercise prescription device (120) is illustrated as communicating with the measurement device (110) via a communication network (130), but the present disclosure is not limited thereto, and the measurement device (110) may be implemented in a form in which the user terminal (not shown) communicates with the exercise prescription device (120) using short-range communication, and the user terminal and the exercise prescription device (120) communicate with each other.

[0054] Alternatively, the exercise prescription device (120) may be implemented as a user terminal. That is, all components and functions of the exercise prescription device (120) may be included and implemented in the user terminal. Alternatively, at least some of the components or functions of the exercise prescription device (120) may be realized within the measuring device (110) or included within the measuring device (110). In some cases, all functions and all components of the exercise prescription device (120) may be fully executed within the measuring device (110) or included within the measuring device (110).

[0055] FIG. 2 is a functional block diagram schematically illustrating the functional configuration of an exercise prescription device according to one embodiment of the present disclosure.

[0056] Referring to FIG. 2, an exercise prescription device (120) according to one embodiment of the present disclosure may include an optical signal acquisition unit (201), a hemodynamic calculation unit (203), a lactate calculation unit (205), a fat burning calculation unit (207), an exercise prescription unit (209), and a communication unit (211).

[0057] According to one embodiment of the present disclosure, the optical signal acquisition unit (201), the hemodynamic calculation unit (203), the lactate calculation unit (205), the fat burning calculation unit (207), the exercise prescription unit (209), and the communication unit (211) may be program modules, at least some of which communicate with an external system (not shown). These program modules may be included in the exercise prescription device (120) in the form of an operating system, an application program module, and other program modules, and may be physically stored on various known memory devices. In addition, these program modules may be stored in a remote memory device that can communicate with the exercise prescription device (120). Meanwhile, these program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types to be described later according to the present disclosure.

[0058] The optical signal acquisition unit (201) of the exercise prescription device (120) according to one embodiment of the present disclosure may perform a function of acquiring an optical signal detected by passing through the user's body tissue. The optical signal acquisition unit (210) may acquire an optical signal measured by the above-described measurement device (110). Specifically, the optical signal may be a signal detected by at least one light-receiving unit after near-infrared light emitted from at least one light-emitting unit of the measurement device (110) passes through, scatters, or reflects through the user's body tissue (e.g., muscle tissue). In one embodiment, the optical signal acquired through the measurement device (110) may be an optical density (OD) signal based on near-infrared spectroscopy.

[0059] The hemodynamic calculation unit (203) of the exercise prescription device (120) according to one embodiment of the present disclosure may perform a function of calculating hemodynamic information based on an optical signal. In one embodiment, the hemodynamic calculation unit (203) may calculate hemodynamic information by analyzing an optical density signal acquired by the optical signal acquisition unit (201). In one embodiment, the hemodynamic information calculated by the hemodynamic calculation unit (203) may be at least one of an oxygenated hemoglobin concentration, a non-oxygenated hemoglobin concentration, oxygen saturation, and a blood flow change amount. Here, the oxygen saturation may be the ratio of oxygenated hemoglobin to the total hemoglobin. In one embodiment, the hemodynamic information may be hemodynamic information for a muscle (e.g., muscle oxygen saturation).

[0060] In one embodiment, the hemodynamic information produced by the hemodynamic calculation unit (203) may further include at least one of pulse and heart rate. For example, the hemodynamic calculation unit (203) may calculate a blood flow change amount based on an optical signal, and may calculate the pulse and / or heart rate from the calculated amount. In another example, the hemodynamic calculation unit (203) may receive a related signal from a separate device that measures pulse and / or heart rate and calculate the pulse and / or heart rate.

[0061] The lactate calculation unit (205) of the exercise prescription device (120) according to one embodiment of the present disclosure may perform a function of calculating lactate information based on hemodynamic information. Lactate is a byproduct of glycolysis, an anaerobic metabolism, and is typically used as an indicator of exercise load. In the present embodiment, lactate information may be utilized to prescribe an exercise suitable for the user.

[0062] In one embodiment, the lactate calculation unit (205) can calculate the change (increase) in blood lactate concentration from the oxygen saturation or change in oxygen saturation calculated by the hemodynamic calculation unit (203) using a lactate estimation model. Here, the lactate estimation model may be a machine-learned model based on blood lactate concentration and oxygen saturation.

[0063] For example, a lactate estimation model can be a machine-learned model based on data on oxygen saturation and blood lactate concentration obtained during an exercise stress test for multiple subjects. The exercise stress test can be performed with a predetermined time (e.g., 5 minutes) as a stage, with a predetermined rest period (e.g., 30 seconds) between each stage, and the subject's running speed can be increased for each stage. In other words, each stage represents a specific exercise intensity, and the exercise intensity increases as the stage progresses. A lactate concentration meter can be used to measure the subject's blood lactate concentration during the rest period between each stage, and the subject's oxygen saturation can be measured at each stage. Based on the acquired stage-by-stage blood lactate concentration and oxygen saturation data, the correlation between the change in oxygen saturation and the increase in lactate can be estimated through ensemble learning. The model generated through this ensemble learning is a model that takes the change in oxygen saturation as an input value and the increase in lactate concentration as an output value, and can be used as a lactate estimation model.

[0064] Although this embodiment describes estimating lactate from oxygen saturation or changes in oxygen saturation, it is also possible to estimate lactate from other hemodynamic information (e.g., blood flow changes, pulse, heart rate, etc.) or to estimate lactate by reflecting other hemodynamic information together. Furthermore, in addition to hemodynamic information, it may be possible to use a model that estimates lactate from exercise information such as exercise speed or to reflect these together to estimate lactate.

[0065] For example, when training data for creating a lactate estimation model, in addition to the blood lactate concentration and oxygen saturation data acquired for each stage during an exercise load test, exercise speed for each stage can be provided as an additional input value for training. In this way, by training the lactate estimation model using exercise speed as an additional input value, errors that may occur when estimating lactate concentration based on either oxygen saturation or exercise speed can be corrected, thereby improving the accuracy of the lactate estimation model.

[0066] According to one embodiment of the present disclosure, the lactate production unit (205) can estimate the lactate threshold using a lactate estimation model. The lactate threshold is the point at which the concentration of blood lactate increases, and may refer to the exercise intensity at which lactate begins to accumulate.

[0067] In one embodiment, the lactate calculation unit (205) can obtain a change in lactate concentration from the change in oxygen saturation or oxygen saturation using a lactate estimation model, and can calculate a cumulative lactate concentration by accumulating the change in lactate concentration. It can be determined whether the cumulative lactate concentration calculated in this way exceeds a preset value (e.g., 2 mmol, 4 mmol, etc.), which can serve as a standard for exercise prescription and / or evaluation described below.

[0068] Meanwhile, in one embodiment of the present disclosure, different lactate estimation models may be used depending on the user's physical characteristics or physical abilities. In one embodiment, the exercise prescription device (120) may be divided into a general user mode and an athlete mode, and different lactate estimation models may be used depending on each mode. For example, the lactate estimation model in the general user mode is a model learned based on data obtained from a subject with typical physical abilities, and may be generated by learning from data obtained from an exercise stress test performed by setting the running speed in the first stage to 3.6 km / h and increasing the running speed by 1.4 km / h per stage. In addition, the lactate estimation model in the athlete mode is a model learned based on data obtained from an athlete as a subject, and may be generated by learning from data obtained from an exercise stress test performed by setting the running speed in the first stage to 5 km / h and increasing the running speed by 1.8 km / h per stage.

[0069] FIG. 3 is a diagram exemplarily showing data for learning a lactate estimation model according to one embodiment of the present disclosure. Specifically, FIG. 3 (a) exemplarily shows learning data for a lactate estimation model in a general user mode, and FIG. 3 (b) exemplarily shows learning data for a lactate estimation model in an athlete mode. Referring to FIG. 3 , learning data for different models can be used depending on the physical characteristics or physical abilities of the subject, and by applying an appropriate lactate estimation model according to the user's physical abilities, etc., exercise prescription or evaluation described below can be effectively performed.

[0070] Meanwhile, in the illustrated embodiment, two learning data groups are exemplified and explained, but it is also possible to further segment an individual's physical characteristics or physical abilities, acquire learning data groups accordingly, and create more diverse lactate estimation models based on each learning data group.

[0071] The fat burning calculation unit (207) of the exercise prescription device (120) according to one embodiment of the present disclosure may perform a function of calculating fat burning information based on hemodynamic information. In one embodiment, the fat burning calculation unit (207) may calculate the amount of fat burning from the oxygen saturation or the change in oxygen saturation calculated by the hemodynamic calculation unit (203) using a fat burning estimation model.

[0072] During exercise stress testing, a respiratory gas analyzer can be used to obtain data on oxygen consumption (VO2) and carbon dioxide production (VCO2), from which fat burning rate (i.e., fat burning rate) can be estimated. For example, fat burning rate can be estimated using the following mathematical formula:

[0073] [Mathematical Formula 1]

[0074]

[0075] Here, f is the fat consumption rate (g / min), Vo2 is the oxygen consumption rate (l / min), Vco2 is the carbon dioxide production rate (l / min), and n is the urinary nitrogen excretion rate (g / min).

[0076] Additionally, the amount of fat burned can be estimated by multiplying the exercise time by the above fat consumption rate.

[0077] Based on the fat burning amount estimated as above and the oxygen saturation obtained during the exercise load test, a fat burning estimation model can be created that takes the oxygen saturation change amount as an input value and the fat burning amount as an output value. In this embodiment, the fat burning amount is described as being estimated from the oxygen saturation or the change amount of oxygen saturation, but it is also possible to estimate the fat burning amount from other hemodynamic information (e.g., blood flow change amount, pulse, heart rate, etc.) or to estimate the fat burning amount by reflecting other hemodynamic information together. In addition, a model that estimates the fat burning amount from exercise information such as exercise speed in addition to hemodynamic information or to estimate the fat burning amount by reflecting them together can be used.

[0078] According to one embodiment of the present disclosure, similar to the lactate estimation model, different fat burning estimation models may be utilized depending on the user's physical characteristics or abilities. For example, the exercise prescription device (120) may be divided into a general user mode and an athlete mode, and different fat burning estimation models may be utilized depending on each mode.

[0079] FIG. 4 is a diagram exemplarily showing the correlation between oxygen saturation and fat consumption in a fat burning estimation model according to one embodiment of the present disclosure. Specifically, FIG. 4 (a) exemplarily shows the correlation between oxygen saturation and fat consumption in a general user mode, and FIG. 4 (b) exemplarily shows the correlation between oxygen saturation and fat consumption in an athlete mode. In FIG. 4, the horizontal axis represents oxygen saturation, and the vertical axis represents fat consumption. Referring to FIG. 4, it generally shows a trend that fat consumption increases as oxygen saturation decreases, and as the stage increases (i.e., as the exercise intensity increases), the change (increase) in fat consumption tends to change gradually compared to the change (decrease) in oxygen saturation. In addition, it can be confirmed that this trend is different for the general user and the athlete. In this way, in the present embodiment, by applying a fat burning estimation model suitable for the user's physical ability, etc., the exercise prescription or evaluation described below can be effectively performed.

[0080] In another embodiment, the fat burning calculation unit (207) can calculate the amount of fat burned using the correlation between exercise speed and the amount of fat burned. For example, based on the amount of fat burned estimated from data acquired during an exercise load test and the exercise speed during the exercise load test, a fat burning estimation model that uses exercise speed as an input value and fat burning amount as an output value can be created, and the amount of fat burned can be calculated using this fat burning estimation model.

[0081] In another embodiment, the fat burning calculation unit (207) may estimate the amount of fat burned using the correlation between oxygen saturation and fat burning amount and the correlation between exercise speed and fat burning amount. For example, the fat burning calculation unit (207) may calculate an average value of the amount of fat burned estimated using the correlation between oxygen saturation and fat burning amount and the amount of fat burned estimated using the correlation between exercise speed and fat burning amount. This makes it possible to correct for errors in the amount of fat burned that may occur when estimating based on either oxygen saturation or exercise speed.

[0082] According to one embodiment of the present disclosure, the fat burning calculation unit (207) can calculate the ratio of fat burning to total calories consumed. Specifically, the fat burning calculation unit (207) can calculate the fat burning amount using a fat burning estimation model and calculate the ratio of fat burning to total calories consumed as a percentile. Here, the total calories burned can be calculated based on the subject's exercise information, body weight, METs (metabolic equivalent of task), etc., and the exercise information can include at least one of exercise intensity and exercise time.

[0083] Meanwhile, the exercise prescription unit (209) of the exercise prescription device (120) according to one embodiment of the present disclosure may perform a function of generating an exercise prescription for a user based on at least one of lactate information and fat burning information. The individual exercise prescription may include exercise intensity, exercise speed, exercise time, etc.

[0084] In one embodiment, the exercise prescription unit (209) may generate an exercise prescription for the user based on the lactate threshold calculated by the lactate calculation unit (205). For example, the exercise prescription unit (209) may generate an exercise prescription that includes at least one of an exercise intensity, an exercise speed, and an exercise time that does not cause the user to reach the lactate threshold by referring to the lactate threshold.

[0085] In one embodiment, the exercise prescription unit (209) may generate an exercise prescription for the user based on the fat burning rate calculated by the fat burning calculation unit (207). For example, the exercise prescription unit (209) may generate an exercise prescription that includes at least one of exercise intensity, exercise speed, and exercise time that achieve optimal fat burning.

[0086] According to one embodiment of the present disclosure, the exercise prescription unit (209) can evaluate the user's exercise based on the personal exercise prescription.

[0087] In one embodiment, the exercise prescription unit (209) may calculate an exercise assessment score based on a personalized exercise prescription by referencing the user's hemodynamic information and exercise information. Specifically, the exercise prescription unit (209) may calculate an exercise assessment score by referencing at least one of the user's oxygen saturation, exercise intensity, exercise speed, and exercise time.

[0088] The exercise prescription unit (209) can assign a score for oxygen saturation. The score for oxygen saturation can be determined from the average change in oxygen saturation (slope) over a specific time range compared to the baseline. At this time, the score for oxygen saturation can be assigned with reference to the exercise intensity. For example, the exercise intensity can be classified into low intensity, high intensity, interval, etc., and if the exercise intensity is low intensity, the smaller the change in oxygen saturation (slope), the higher the score can be assigned. If the exercise intensity is high intensity, the larger the change in oxygen saturation (slope), the higher the score can be assigned. In addition, if the exercise intensity is interval, the smaller the slope in the low-speed section, and the larger the slope in the high-speed section, the higher the score can be assigned.

[0089] The exercise prescription unit (209) can assign a score for exercise speed. The exercise prescription unit (209) can assign a score for actual exercise speed based on the exercise speed in the user's exercise prescription that was created.

[0090] The exercise prescription unit (209) can assign scores for exercise time. The exercise prescription unit (209) can assign scores based on the ratio of actual exercise time to exercise time in the generated personal exercise prescription.

[0091] The exercise prescription unit (209) may also assign scores for exercise speed and exercise time by considering both exercise speed and exercise time. For example, a personal exercise prescription generated by the exercise prescription unit (209) may include exercise time according to exercise speed, and a score may be assigned based on the ratio of the prescribed exercise time to the actual exercise time based on the user's exercise speed.

[0092] Meanwhile, exercise information such as exercise intensity and exercise speed can be acquired through a motion sensor. The motion sensor may include an accelerometer and a gyrometer, which may be incorporated into a measuring device (110) worn by the user during exercise.

[0093] According to one embodiment of the present disclosure, the exercise prescription unit (209) may calculate an evaluation score for the user's exercise by combining scores related to oxygen saturation, scores related to exercise speed, scores related to exercise time, etc. In one embodiment, the exercise prescription unit (209) may apply preset weights to scores related to oxygen saturation, scores related to exercise speed, scores related to exercise time, etc., and calculate an exercise evaluation score by summing them.

[0094] According to one embodiment of the present disclosure, the exercise prescription unit (209) may accumulate exercise evaluation scores over a predetermined period of time to calculate a period-specific exercise evaluation score. For example, the exercise prescription unit (209) may assign an exercise evaluation score out of 100 points for each session and accumulate the scores to calculate a weekly or monthly exercise evaluation score.

[0095] The communication unit (211) of the exercise prescription device (120) according to one embodiment of the present disclosure performs a function that enables the exercise prescription device (120) to communicate with an external device.

[0096] According to one embodiment of the present disclosure, exercise information, lactic acid information, fat burning information, exercise prescription, exercise evaluation score, etc. generated by an exercise prescription device (120) may be provided to a user terminal. The information may be provided through a dedicated application installed on the user terminal.

[0097] FIG. 5 is a diagram exemplarily illustrating how exercise information and a personalized exercise prescription are provided to a user terminal according to one embodiment of the present disclosure. As illustrated in (a) of FIG. 5, exercise information, including exercise time and exercise speed, along with information such as oxygen saturation, lactate, and lactate threshold, may be provided via the user terminal. Furthermore, a user's exercise prescription (e.g., exercise speed) may be provided based on lactate information and / or fat burning information. Furthermore, as illustrated in (b) of FIG. 5, fat burning amount and fat burning rate may also be provided via the user terminal.

[0098] FIG. 6 is a diagram exemplarily illustrating how an exercise evaluation score is provided to a user terminal according to one embodiment of the present disclosure. As illustrated in (a) of FIG. 6, the exercise evaluation score may be provided along with exercise information, including oxygen saturation information, exercise intensity, etc. In this case, the exercise information may be provided by time zone. In addition, as illustrated in (b) of FIG. 6, a weekly exercise evaluation score, which is an accumulation of exercise evaluation scores over a week, may be provided, along with changes in the exercise evaluation score compared to the previous week.

[0099] In addition to what is illustrated in FIG. 6, feedback regarding improvements in exercise capacity may also be provided via the user terminal. In one embodiment, feedback regarding whether exercise capacity has improved and the degree of improvement may be provided by referencing exercise assessment scores when performing exercise of the same intensity. For example, an exercise assessment score may be calculated based on hemodynamic information (e.g., oxygen saturation, etc.), lactate information, and / or fat burning information during the same low-intensity exercise, and feedback regarding whether exercise capacity has improved and the degree of improvement may be provided based on this score. Such feedback regarding improvements in exercise capacity may be provided during or after exercise is completed.

[0100] Figure 7 is a flowchart illustrating a process for prescribing exercise based on a subject's hemodynamic information according to one embodiment of the present disclosure. Each step of the exercise prescription method according to this embodiment does not necessarily have to be performed in the order shown, nor does it imply that each step is necessarily essential. In other words, it should be understood that each step of the exercise prescription method according to this embodiment may be performed in a different order than shown, and some steps may be omitted or other steps may be added.

[0101] In step (S701), an optical signal detected by passing through the user's body tissue is acquired. In one embodiment, the exercise prescription device (120) may obtain the optical signal from the measurement device (110), and the optical signal may be a near-infrared ray detected by passing through the user's muscle tissue. For example, the optical signal may be an optical density (OD) signal based on near-infrared spectroscopy.

[0102] In step (S703), hemodynamic information is calculated based on the optical signal. In one embodiment, the exercise prescription device (120) can calculate hemodynamic information based on the optical signal acquired from the measurement device (110). The hemodynamic information may include at least one of oxygenated hemoglobin concentration, non-oxygenated hemoglobin concentration, oxygen saturation, and blood flow change amount. For example, the hemodynamic information may be hemodynamic information for a muscle (e.g., muscle oxygen saturation).

[0103] In step (S705), at least one of lactate information and fat burning information is generated based on hemodynamic information.

[0104] According to one embodiment of the present disclosure, the exercise prescription device (120) can calculate the amount of change (increase) in blood lactate concentration and the accumulated lactate concentration from the amount of change in oxygen saturation or oxygen saturation using a lactate estimation model, and can estimate a lactate threshold. The lactate estimation model may be a machine-learned model based on blood lactate concentration and oxygen saturation.

[0105] According to one embodiment of the present disclosure, the exercise prescription device (120) can calculate fat burning amount from oxygen saturation or changes in oxygen saturation using a fat burning estimation model. The fat burning estimation model can be generated based on the correlation between the fat burning rate estimated through data on oxygen consumption and carbon dioxide production and oxygen saturation.

[0106] In one embodiment, the exercise prescription device (120) may have multiple modes, such as a general mode and an athlete mode, and a lactate estimation model and / or a fat burning estimation model generated based on different groups of subjects may be used according to each mode.

[0107] In step (S707), an exercise prescription for the user is generated based on at least one of lactate information and fat burning information. In one embodiment, the exercise prescription device (120) may generate an exercise prescription including exercise intensity, exercise speed, exercise time, etc. that do not reach the lactate threshold of the user by referring to the lactate threshold. In another embodiment, the exercise prescription device (120) may generate an exercise prescription including exercise intensity, exercise speed, exercise time, etc. that achieve optimal fat burning by referring to the fat burning information.

[0108] A method according to one embodiment of the present disclosure may include a step (not shown) of evaluating a user's exercise based on the user's exercise prescription. In one embodiment, the step of evaluating the exercise may calculate an exercise evaluation score by referring to at least one of the user's oxygen saturation, exercise intensity, exercise speed, and exercise time. For example, the exercise prescription device (120) may assign a score for oxygen saturation, a score for exercise speed, and a score for exercise time, respectively, and may calculate an exercise evaluation score by combining these scores. In addition, the exercise prescription device (120) may also calculate an exercise evaluation score for each period by accumulating exercise evaluation scores over a predetermined period.

[0109] Although the present disclosure has been described above with specific details such as specific components and limited examples and drawings, these are provided only to help a more general understanding of the present disclosure, and the present disclosure is not limited to the above examples, and a person having ordinary knowledge in the technical field to which the present disclosure belongs can make various modifications and variations from this description.

[0110] Meanwhile, the embodiments according to the present disclosure described above may be implemented in the form of program commands that can be executed through various computer components and recorded on a computer-readable recording medium. The recording medium may include program commands, data files, data structures, etc., singly or in combination. The program commands recorded on the recording medium may be those specially designed and configured for the present disclosure or may be those known and available to those skilled in the art of computer software. Examples of the recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The hardware devices may be configured to operate as one or more software modules to perform processing according to the present disclosure, and vice versa.

[0111] In this way, the idea of ​​the present disclosure should not be limited to the embodiments described above, and all things that are modified equally or equivalently to the claims described below as well as the claims are considered to fall within the scope of the idea of ​​the present disclosure.

Claims

1. A method for prescribing exercise based on hemodynamic information, A step of acquiring an optical signal detected by passing through the user's body tissue; A step of calculating hemodynamic information based on the above optical signal; A step of calculating at least one of lactate information and fat burning information based on the hemodynamic information; and A step of generating an exercise prescription for a user based on at least one of the lactic acid information and the fat burning information; How to include.

2. In paragraph 1, In the step of acquiring the above optical signal, a method of acquiring an optical signal detected by passing near-infrared light through the user's muscle tissue.

3. In paragraph 1, A method wherein the hemodynamic information comprises at least one of oxygenated hemoglobin concentration, non-oxygenated hemoglobin concentration, oxygen saturation, and blood flow variability.

4. In paragraph 1, A method in which, in the step of calculating at least one of the above lactate information and fat burning information, the amount of change in blood lactate concentration is calculated from at least one of oxygen saturation, amount of change in oxygen saturation, and pulse included in the above hemodynamic information using a lactate estimation model.

5. In paragraph 4, The above lactate estimation model is a machine-learned model based on data on oxygen saturation and blood lactate concentration obtained during exercise stress tests of multiple subjects.

6. In paragraph 5, The above lactate estimation model is a machine-learned model that uses data on exercise speed acquired during exercise load tests of multiple subjects as additional input values.

7. In paragraph 1, A method in which, in the step of calculating at least one of the above lactate threshold information and fat burning rate information, the amount of fat burning is calculated from at least one of the oxygen saturation, the change in oxygen saturation, and the pulse included in the hemodynamic information using a fat burning estimation model.

8. In paragraph 7, The above fat burning estimation model is a method in which the fat burning amount is estimated from data on oxygen consumption and carbon dioxide production obtained during exercise load tests of multiple subjects and the correlation between the fat burning amount and oxygen saturation is generated based on the correlation between the fat burning amount and oxygen saturation.

9. In paragraph 7, The above fat burning estimation model is a method in which the fat burning amount is estimated from data on oxygen consumption and carbon dioxide production obtained during exercise load tests of multiple subjects and the correlation between the fat burning amount and exercise speed is generated.

10. In paragraph 1, A method further comprising the step of evaluating the user's exercise based on the user's exercise prescription.

11. In paragraph 10, In the step of evaluating the above exercise, a method for calculating an exercise evaluation score based on the user's exercise prescription by referring to the hemodynamic information and exercise information.

12. A recording medium recording a computer program for executing the method according to paragraph 1.

13. A device that prescribes exercise based on hemodynamic information, An optical signal acquisition unit that acquires an optical signal detected by passing through the user's body tissue; A hemodynamic calculation unit that calculates hemodynamic information based on the above optical signal; A lactate calculation unit that calculates lactate information based on the above hemodynamic information; A fat burning calculation unit that calculates fat burning information based on the above hemodynamic information; and An exercise prescription unit that generates an exercise prescription for a user based on at least one of the lactic acid information and the fat burning information; A device comprising:

Images