WO2024029997A2

WO2024029997A2 - Computing system for providing exercise information to user, computing system operation method, and exercise information provision system comprising computing system

Info

Publication number: WO2024029997A2
Application number: PCT/KR2023/011519
Authority: WO
Inventors: 김진모; 최성훈; 이기범; 최재윤; 김재훈
Original assignee: 주식회사 뉴마핏
Priority date: 2022-08-05
Filing date: 2023-08-04
Publication date: 2024-02-08
Also published as: WO2024029997A3

Abstract

According to the present disclosure, provided is an operation method performed by at least one processor included in a computing device, comprising the steps of: acquiring first time-series data associated with a respiratory frequency (RF) by predicting the RF in a first time interval on the basis of first sensing data sensed according to the breathing of a user; acquiring second time-series data associated with minute ventilation (VE) by predicting the VE in the first time interval on the basis of the first sensing data; acquiring third time-series data associated with a heart rate (HR) by predicting the HR in the first time interval on the basis of second sensing data sensed according to the heartbeat of the user; and predicting fourth time-series data associated with oxygen intake in the first time interval on the basis of at least one from among the first time-series data, the second time-series data, and the third time-series data.

Description

A computing device for providing exercise information to a user, a method of operating the computing device, and an exercise information providing system including the computing device

This disclosure relates to a computing device for providing exercise information. More specifically, it relates to a system that provides information about a user's exercise ability by sensing the user's breathing and heart rate, and a computing device included therein.

In accurately analyzing exercise capacity, measuring breathing is very important. In particular, when sports athletes conduct medical tests, they essentially undergo a breathing-based exercise ability evaluation, and a representative evaluation method is a breathing analysis method through an exercise cardiopulmonary exercise test.

However, in the case of professional breathing testing devices such as the above, they are composed of very sensitive and expensive sensors, so it is close to impossible to analyze exercise ability in real time during actual exercise. For this reason, the above professional analysis equipment is only used by elite sports teams for medical testing purposes.

In order to provide exercise information to users by measuring exercise ability in real time during the user's exercise, a computing method is required to calculate indicators for exercise ability by processing sensing-based time series data received in real time.

One task of the present disclosure is to obtain an indicator representing exercise ability by processing time series data in order to analyze exercise ability in real time.

Meanwhile, the problem to be solved in this disclosure is not limited to the above-mentioned problems, and problems not mentioned are clear to those skilled in the art from this specification and the attached drawings. It will be understandable.

According to an embodiment of the present disclosure, acquiring biometric information of a user based on at least one sensing data sensed during a first time period by at least one processor included in a computing device; The step of acquiring the biometric information includes obtaining first time series data related to the breathing rate by predicting the breathing rate (RF) in the first time section based on the first sensing data detected according to the user's breathing. step; Obtaining second time series data related to the minute ventilation volume (VE) by predicting the minute ventilation volume (VE) in the first time period based on the first sensing data; and acquiring third time series data related to the heart rate by predicting the heart rate (HR) in the first time period based on second sensing data detected according to the user's heart rate. and a first time series associated with oxygen intake in the first time interval based on at least one of the first time series data, the second time series data, and the third time series data, using the learned first model. 4 Predicting time series data; An operation method including may be provided.

The means for solving the problem according to various embodiments are not limited to the above-mentioned solution means, and the solution methods not mentioned may be understood by those skilled in the art from this specification and the attached drawings. You will be able to understand it clearly.

According to an embodiment of the present disclosure, a computing device that provides accurate exercise information and exercise feedback by processing time series data measured during a user's exercise in real time can be provided.

The effects according to the embodiments included in the present disclosure are not limited to the above-mentioned effects, and effects not mentioned are clearly apparent to those skilled in the art from the present specification and the attached drawings. It will be understandable.

FIG. 1 is a diagram illustrating an example of implementation of an exercise information providing system according to various embodiments.

FIG. 2 is a block diagram illustrating a plurality of devices constituting an exercise information providing system according to various embodiments.

FIG. 3 is a diagram illustrating a method by which a computing device calculates oxygen intake data based on biometric information, according to various embodiments.

FIG. 4 is a diagram illustrating an example of an artificial intelligence model learning method included in a computing device, according to various embodiments.

FIG. 5 is a flowchart illustrating a method for a computing device to predict oxygen intake based on sensing data, according to various embodiments.

FIG. 6 is a diagram illustrating a method by which a computing device obtains time series data related to exercise ability based on sensing data, according to various embodiments.

Figure 7 is a diagram showing an example of pressure data obtained according to the respiratory sum of a user wearing a measuring device.

Figure 8 is a diagram showing an example of heart rate data acquired using a PPG sensor included in the measurement device.

FIG. 9 is a diagram illustrating examples of time series data related to athletic ability, according to various embodiments.

FIG. 10 is a diagram illustrating a method for a computing device to obtain data related to an exercise state, according to various embodiments.

FIG. 11 is a diagram illustrating an example of correlation data between oxygen intake and minute ventilation, according to various embodiments.

FIG. 12 is a diagram illustrating an example in which a computing device provides exercise feedback related to exercise state information, according to various embodiments.

FIG. 13 is a diagram illustrating an example in which a computing device provides exercise feedback related to exercise intensity information, according to various embodiments.

The embodiments described in this specification are intended to clearly explain the idea of the present invention to those skilled in the art to which the present invention pertains, and the present invention is not limited to the embodiments described in this specification, and the present invention is not limited to the embodiments described in this specification. The scope should be construed to include modifications or variations that do not depart from the spirit of the present invention.

The terms used in this specification are general terms that are currently widely used as much as possible in consideration of their function in the present invention, but this may vary depending on the intention of those skilled in the art, precedents, or the emergence of new technology in the technical field to which the present invention belongs. You can. However, if a specific term is defined and used with an arbitrary meaning, the meaning of the term will be described separately. Therefore, the terms used in this specification should be interpreted based on the actual meaning of the term and the overall content of this specification, not just the name of the term.

The drawings attached to this specification are intended to easily explain the present invention, and the shapes shown in the drawings may be exaggerated as necessary to aid understanding of the present invention, so the present invention is not limited by the drawings.

As used herein, “A or B”, “at least one of A and B”, “at least one of A or B”, “A, B or C”, “at least one of A, B and C”, and “A Each of phrases such as “at least one of , B, or C” may include any one of the items listed together in the corresponding phrase, or any possible combination thereof.

In this specification, if it is determined that a detailed description of a known configuration or function related to the present invention may obscure the gist of the present invention, the detailed description thereof will be omitted as necessary. In addition, numbers (eg, first, second, etc.) used in the description of this specification are merely identifiers to distinguish one component from another component.

In addition, the suffixes "part" and "part" for components used in the following description are given or used interchangeably only considering the ease of writing the specification, and do not have distinct meanings or roles in themselves.

In other words, the embodiments of the present disclosure are provided to ensure that the present disclosure is complete and to inform those skilled in the art of the present disclosure of the scope of the present disclosure, and that the invention of the present disclosure is within the scope of the claims. It is only defined by Like reference numerals refer to like elements throughout the specification.

Terms such as “first” and/or “second” may be used to describe various components, but the components should not be limited by the terms. The terms refer to one component as referring to another component. For the sole purpose of distinguishing from the elements, for example, without departing from the scope of rights according to the concepts of the present disclosure, the first element may be referred to as the second element, and similarly the second element may be referred to as the first element. can also be named.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between. Other expressions that describe the relationship between components, such as "between" and "immediately between" or "neighboring" and "directly adjacent to" should be interpreted similarly.

In the drawings, each block of the processing flow diagrams and combinations of the flow diagram diagrams may be performed by computer program instructions. These computer program instructions can be mounted on a processor of a general-purpose computer, special-purpose computer, or other programmable data processing equipment, so that the instructions performed through the processor of the computer or other programmable data processing equipment are described in the flow chart block(s). It creates the means to perform functions. These computer program instructions may also be stored in computer-usable or computer-readable memory that can be directed to a computer or other programmable data processing equipment to implement a function in a particular manner, so that the computer-usable or computer-readable memory The instructions stored in may also be capable of producing manufactured items containing instruction means to perform the functions described in the flow diagram block(s). Computer program instructions can also be mounted on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a process that is executed by the computer, thereby generating a process that is executed by the computer or other programmable data processing equipment. Instructions that perform processing equipment may also provide steps for executing the functions described in the flow diagram block(s).

Additionally, device-readable storage media may be provided in the form of non-transitory storage media. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain signals (e.g. electromagnetic waves), and this term refers to cases where data is semi-permanently stored in the storage medium. There is no distinction between temporary storage cases.

Additionally, each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s). Additionally, it should be noted that in some alternative execution examples it is possible for the functions mentioned in the blocks to occur out of order. For example, it is possible for two blocks shown in succession to be performed substantially at the same time, or it is possible for the blocks to be performed in reverse order depending on the corresponding function. For example, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or One or more other operations may be added.

The term 'unit' used in this disclosure refers to software or hardware components such as FPGA (Field Programmable Gate Array) or ASIC (Application Specific Integrated Circuit). '~part' performs specific roles, but is not limited to software or hardware. The '~ part' may be configured to reside in an addressable storage medium and may be configured to reproduce on one or more processors. Therefore, according to some embodiments, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and processes. Includes scissors, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card. Additionally, according to various embodiments of the present disclosure, '˜unit' may include one or more processors.

Hereinafter, the operating principle of the present disclosure will be described in detail with reference to the attached drawings. In the following description of the present disclosure, if a detailed description of a related known function or configuration is determined to unnecessarily obscure the gist of the present disclosure, the detailed description will be omitted. In addition, the terms described below are terms defined in consideration of the functions in the present disclosure, and may vary depending on the intention or custom of the user or operator. Therefore, the definition should be made based on the contents throughout this specification.

It may further include obtaining first exercise information indicating a change in oxygen intake during the first time period and providing the first exercise information to the user device based on the fourth time series data.

calculating correlation data between oxygen intake and minute ventilation based on the second time series data and the fourth time series data; and determining at least one ventilation threshold based on the correlation data.

Using the learned second model, determining at least one ventilation threshold in the first time interval based on the first time series data, the second time series data, and the third time series data; further comprising; can do.

determining at least one ventilation threshold based on at least one of first time series data, the second time series data, the third time series data, and the fourth time series data; and obtaining second exercise information based on the at least one ventilation threshold and providing the second exercise information to the user device.

It may further include acquiring third exercise information indicating current oxygen intake compared to maximum oxygen intake based on pre-stored maximum oxygen intake information and the fourth time series data.

determining at least one ventilation threshold based on at least one of first time series data, the second time series data, the third time series data, and the fourth time series data; and acquiring fourth exercise information indicating a ventilation threshold relative to the maximum oxygen intake based on pre-stored maximum oxygen intake information and the at least one ventilation threshold.

Fourth time series data is set to be acquired in real time, and transmitting, by at least one processor, feedback related to exercise based on the fourth time series data acquired in real time to at least one of a user device or a measurement device; More may be included.

At least one piece of sensing data may be received from the measurement device based on a communication connection with the measurement device.

The first sensing data may be obtained by detecting the pressure value due to the user's breathing, and the second sensing data may be obtained by detecting PPG data from at least a portion of the user's body.

Obtaining fourth time series data includes inputting the biometric information and user information into the first model; and outputting the fourth time series data through at least one layer included in the first model.

Obtaining environmental information indicating at least one of temperature, humidity, or atmospheric pressure of the user's surrounding environment, further comprising acquiring the biometric information by considering the environmental information, or further using the environmental information to obtain the fourth time series. Data can be predicted.

The first model is LSTM (Long short-term memory), RNN (Recurrent Neural Network), GRU (Gated Recurrent Unit), DCRNN (Diffusion Convolution Recurrent Neural Network), ODE (Ordinary Differential Equation)-based model, and GCN (Graph Convolution Network). ), Transformer model, or multi-modal transformer model.

Below, a computing device for providing exercise information will be described.

In this specification, exercise information is a term that includes various information defined based on various indicators related to exercise ability. For example, exercise information includes basic information about exercise measured while the user is exercising (e.g. calories burned, distance, etc.), indicator information indicating the user's exercise ability (e.g. oxygen uptake, maximum oxygen uptake, ventilation threshold, etc.) , It is a concept that includes current exercise status information compared to the user's maximum exercise capacity or current exercise intensity information compared to the user's maximum exercise ability.

The exercise information providing system according to an embodiment of the present disclosure may be implemented to obtain exercise information based on the user's biometric information measured during the user's exercise and provide the exercise information to the user.

For example, referring to FIG. 1, the computing device 1 may calculate an index related to the user's exercise ability based on sensing data related to the user's breathing or heart rate detected by the measuring device 2. there is. Additionally, the computing device 1 may obtain exercise information based on indicators related to exercise ability and provide it to the user device 3. Additionally, in this case, the computing device 1 may acquire the user's exercise information in real time and transmit exercise feedback to at least one of the measurement device 2 or the user device 3.

The exercise information providing system may include a plurality of devices that are connected to each other for communication, as shown in the usage example shown in FIG. 1.

Referring to FIG. 2, the computing device 2000 according to an embodiment of the present disclosure may include a processor 2010, a memory 2020, and a communication circuit 2030, but is not limited thereto. It may further include configurations of a computing device. At this time, the computing device 2000 may include, but is not limited to, a server device.

The processor 2010 may include at least one processor, at least some of which are implemented to provide different functions. For example, software (e.g., a program) may be executed to control at least one other component (e.g., a hardware or software component) of a computing device connected to the processor 2010 and perform various data processing or operations. can do. According to one embodiment, as at least part of data processing or computation, the processor 2010 stores instructions or data received from other components in the memory 2020 (e.g., volatile memory), and stores the instructions or data stored in the volatile memory. Data can be processed and the resulting data can be stored in non-volatile memory. According to one embodiment, the processor 2010 is a main processor (e.g., a central processing unit or an application processor) or an auxiliary processor that can operate independently or together (e.g., a graphics processing unit, a neural processing unit (NPU)). , an image signal processor, a sensor hub processor, or a communication processor). For example, when a computing device includes a main processor and a secondary processor, the secondary processor may be set to use less power than the main processor or to specialize in a designated function. The auxiliary processor may be implemented separately from the main processor or as part of it. A coprocessor is a computing device, for example, on behalf of the main processor while the main processor is in an inactive (e.g., sleep) state, or in conjunction with the main processor while the main processor is in an active (e.g., application running) state. It is possible to control at least some of the functions or states related to at least one component (eg, the communication circuit 2030) among the components. According to one embodiment, an auxiliary processor (e.g., an image signal processor or a communication processor) may be implemented as part of another functionally related component (e.g., communication circuit 2030). According to one embodiment, an auxiliary processor (eg, neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. Artificial intelligence models can be created through machine learning. For example, this learning may be performed on the computing device itself on which the artificial intelligence model is performed, or may be performed through a separate server. Learning algorithms may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but It is not limited. An artificial intelligence model may include multiple artificial neural network layers. Artificial neural networks include deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), restricted boltzmann machine (RBM), belief deep network (DBN), bidirectional recurrent deep neural network (BRDNN), It may be one of deep Q-networks or a combination of two or more of the above, but is not limited to the examples described above. In addition to hardware structures, artificial intelligence models may additionally or alternatively include software structures. Meanwhile, the operation of the computing device described below may be understood as the operation of the processor 2010.

The memory 2020 may store various data output by at least one component of the computing device (e.g., the processor 2010). The data may be stored in, for example, software (e.g., a program) and instructions related thereto. It may include input data or output data. The memory 2020 may include volatile memory or non-volatile memory. The memory 2020 may include an operating system, middleware or application, and/or the aforementioned artificial intelligence model. It can be implemented to store .

Communication circuitry 2030 may support establishing a direct (e.g., wired) or wireless communication channel between the computing device and an external electronic device (e.g., a measurement device or user device), and conducting communication through the established communication channel. . Communication circuitry 2030 operates independently of processor 2010 (e.g., a program processor) and may include one or more communication processors (e.g., communication chips) that support direct (e.g., wired) communication or wireless communication. . According to one embodiment, the communication circuit 2030 is a wireless communication module (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (e.g., a local area network (LAN) ) may include a communication module, or a power line communication module). Among these communication modules, the corresponding communication module is a first network (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (e.g., a legacy cellular network, 5G network, It may communicate with an external computing device (e.g., a mobile device, a wearable device, or a server device) through a next-generation communication network, the Internet, or a telecommunication network such as a computer network (e.g., a LAN or WAN). These various types of communication modules may be integrated into one component (e.g., a single chip) or may be implemented as a plurality of separate components (e.g., multiple chips). The wireless communication module may identify or authenticate the computing device within a communication network, such as a first network or a second network, using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module. The wireless communication module may support 5G networks after the 4G network and next-generation communication technologies, for example, NR access technology (new radio access technology). NR access technology provides high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and access to multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low latency). -latency communications)) can be supported. The wireless communication module may support high frequency bands (e.g., mmWave bands), for example, to achieve high data rates. Wireless communication modules use various technologies to secure performance in high frequency bands, such as beamforming, massive MIMO (multiple-input and multiple-output), and full-dimensional multiple input/output (FD). -It can support technologies such as full dimensional MIMO (MIMO), array antenna, analog beam-forming, or large scale antenna. According to one embodiment, the wireless communication module has Peak data rate (e.g., 20Gbps or more) for realizing eMBB, loss coverage (e.g., 164dB or less) for realizing mMTC, or U-plane latency (e.g., downtime) for realizing URLLC. Link (DL) and uplink (UL) each of 0.5 ms or less, or round trip 1 ms or less) can be supported.

Additionally, the measurement device 2001 according to an embodiment of the present disclosure may include at least one sensor, but is not limited thereto, and may further include computing components included in the computing device 2000.

At this time, at least one sensor may be provided to enable the measuring device to acquire various biometric data to analyze the user's exercise ability. Specifically, the measuring device may include a pressure sensor 2011 and a temperature sensor 2021 to analyze the user's breathing. It is not limited thereto, and at least one sensor may include a gas sensor (eg, a carbon dioxide sensor, an oxygen sensor, etc.). At this time, the pressure sensor 2011 may include, but is not limited to, an absolute pressure sensor, a gauge pressure sensor, or a differential pressure sensor.

Additionally, the measurement device may include a PPG sensor 2031 to analyze the user's heart rate and oxygen saturation. It is not limited thereto, and the at least one sensor may include a pulse oximeter, a heart rate monitor, a blood pressure sensor, a capnograph, or a sweat sensor.

Additionally, the measurement device may include an acceleration sensor 2041 to analyze the user's posture. It is not limited thereto, and the at least one sensor may include a gyroscope, an inertial sensor (IMU), a magnetometer, an inclinometer, a force sensor, a geomagnetic sensor, a strain gauge, or a piezoelectric sensor. Because the measuring device is mounted in the user's mouth, the acceleration sensor included in the electronic device can output data that accurately reflects the user's movements.

The measuring device 2001 may have at least one driving condition set in advance. For example, the PPG sensor 2031 may be set to detect the user's lips and drive the LED. Specifically, the PPG sensor can check whether lips are in contact based on IR data obtained by transmitting and receiving IR light, and can be implemented to emit an LED based on a data pattern indicating lip contact. Of course, the driving conditions of the sensor can be performed by the control operation of the processor described above.

Computing Devices (2000). The measuring device 2001 and the user device 2002 may configure an exercise information providing system based on communication connections between them.

The user device 2002 according to an embodiment of the present disclosure may include at least one input/output interface 2012, but is not limited thereto, and may further include computing components included in the computing device 2000.

The user device 2002 may be implemented to receive user input through the input/output interface 2012 or to output information related to exercise.

At this time, the user device 2002 may include a mobile device or a wearable device (eg, a smart watch, other wearable electronic devices).

The user device 2002 may store additional information needed to analyze the user's exercise ability. Specifically, the user device 2002 may store environmental information (eg, humidity, temperature, barometric pressure, etc.), GPS information, and user information (eg, height, weight, gender, age, etc.). This may be to provide information necessary for exercise ability analysis in addition to data obtained through the measuring device 2001. For example, the user device 2002 may provide information about the user by transmitting environmental information or user information to the computing device 2000, but is not limited to this.

The measurement device 2001 can acquire sensing data by detecting the user's biometric information using at least one sensor and transmit the sensing data to the computing device 2000. In this case, the measurement device 2001 may transmit sensing data to the computing device 2000 through a separate gateway (not shown), but is not limited to this. For example, the measurement device 2001 may transmit sensing data to the user device 2002, and the user device 2002 may transmit the sensing data to the computing device 2000, but the present invention is not limited to this.

Specifically, the measurement device 2001 can calculate sensing data including the user's breathing data, heart rate data, and acceleration data using at least one sensor, and transmit the calculated sensing data to the computing device 2000. there is.

The computing device 2000 may receive sensing data from the measurement device 2001.

The computing device 2000 may acquire exercise information based on sensing data. Specifically, the computing device 2000 can acquire biometric information during a user's exercise based on sensing data, and acquire exercise information based on the biometric information during exercise. At this time, the computing device 2000 may obtain exercise information by further using user information or environment information received from the user device 2002.

The computing device 2000 may receive environmental information from at least one of the measurement device 2001 or the user device 2002.

As an example, the computing device 2000 may display data (e.g., temperature, humidity, barometric pressure, etc.) related to the surrounding environment measured from at least one sensor (e.g., temperature sensor, humidity sensor, barometric pressure sensor, etc.) included in the measuring device 2001. etc.), environmental information can be obtained.

As another example, the computing device 2000 may obtain environmental information by receiving weather data about the surrounding environment from the user device 2002. Specifically, environmental information can be obtained by receiving information measured by a nearby meteorological office based on GPS information of the user device 2002.

The computing device 2000 may provide the acquired exercise information to the user device 2002. Specifically, the computing device 2000 may provide exercise information through the input/output interface 2012 included in the user device.

The computing device 2000 may determine exercise feedback based on exercise information obtained by analyzing the user's exercise ability in real time and provide the exercise feedback to at least one of the measurement device 2001 or the user device 2002.

For example, the computing device 2000 may provide an alarm indicating a change in exercise information, or provide exercise feedback through a predetermined feedback mechanism (e.g., vibration of the measurement device 2001 or voice transmission through a speaker). However, it is not limited to this.

Referring to FIG. 3, the computing device 2000 according to an embodiment of the present disclosure may acquire exercise information using at least one trained model (2300). At this time, the learned model 2300 may be an artificial intelligence model learned according to a predetermined standard based on learning data. A specific method by which the computing device 2000 learns the learned model 2300 will be described in the description of FIG. 4 .

Specifically, the computing device 2000 may input biometric information 2310 obtained based on sensing data obtained from the measurement device 2001 into the learned model 2300. In this case, the learned model 2300 may output oxygen intake data 2350 based on the input biometric information 2310.

Additionally, the computing device 2000 may input at least one of user information 2320 or environmental information 2330 along with biometric information 2310 into the learned model 2300. The computing device 2000 may selectively input user information 2320 or environment information 2330 into the learned model 2300. In this case, the learned model 2300 may output oxygen intake data 2350 based on biometric information 2310, user information 2320, and environmental information 2330.

The computing device 2000 may correct the sensing data obtained from the measurement device 2001 using the environmental information 2330. Specifically, the computing device 2000 may correct pressure data obtained from at least one pressure sensor included in the measuring device 2001 using environmental information (eg, temperature, atmospheric pressure, humidity, etc.). For example, the computing device 2000 may calculate ventilation volume data per minute by correcting the sensing data using the environmental information 2330, but is not limited to this.

Additionally, the computing device 2000 may determine exercise information by considering the environmental information 2330. Specifically, the computing device 2000 may determine exercise information by considering differences in exercise intensity according to environmental information 2330.

That is, the computing device 2000 can utilize the environment information 2330 for a plurality of calculation operations with different purposes.

The computing device 2000 may provide oxygen intake data obtained using the learned model 2300 to the user device 2002 as exercise information. Here, the oxygen intake data may be data representing exercise intensity.

The computing device 2000 can obtain oxygen intake data in real time during the user's exercise using the above-described technical means and provide information about the intensity of the exercise to the user.

The computing device may learn a neural network model to predict at least one time series data representing exercise intensity based on at least one time series data representing exercise ability.

For example, artificial intelligence neural network models include LSTM (Long short-term memory), RNN (Recurrent Neural Network), GRU (Gated Recurrent Unit), DCRNN (Diffusion Convolution Recurrent Neural Network), ODE (Ordinary Differential Equation)-based models, It may include, but is not limited to, GCN (Graph Convolution Network), Transformer model, multi-modal transformer model, etc.

In particular, the computing device may include an artificial intelligence model capable of calculating time series data by processing data having multiple modalities. For example, a computing device may be set to produce time series data by processing data with different modalities using a multi-modal transformer.

Exemplarily, the computing device may train an artificial intelligence model to output time series data related to oxygen intake based on user information of the first modality, biometric information of the second modality, and environmental information of the third modality. At this time, the computing device learns correlations based on feature values obtained by embedding biometric information and environmental information composed of time series data and feature values obtained by encoding user information (e.g., multi-head self attention mechanism). Time series data related to oxygen intake can be output.

In this case, the computing device may learn an artificial intelligence model by configuring a learning data set based on the above-mentioned input data and oxygen intake data obtained using an oxygen intake measurement device in the same usage environment, but is not limited to this. .

Referring to FIG. 5, the computing device may receive at least one sensing data in a first time period from the measurement device (S2501). Specifically, the computing device may obtain sensing data obtained by measuring the user's breathing or heart rate during a time including the first time period.

The computing device calculates the respiratory rate (or respiratory rate or Respiratory Frequency, RF) in the first time interval based on the first sensing data detected during the first time interval, and calculates the respiratory rate in the first time interval. As a basis, first time series data can be obtained (S2503). At this time, the first sensing data may be pressure data. Specifically, the computing device may calculate the breathing rate in the first time section based on pressure data defined as a pressure value over time due to the user's breathing, and obtain first time series data based on this.

The computing device calculates minute ventilation (VE) in the first time interval based on the first sensing data detected during the first time interval, and calculates second time series data based on the minute ventilation in the first time interval. can be obtained (S2505). Specifically, the computing device may calculate the ventilation amount per minute in the first time period based on pressure data defined as the pressure value over time due to the user's breathing, and obtain second time series data based on this.

The computing device calculates the heart rate (HR) in the first time interval based on the second sensing data detected during the first time interval, and acquires third time series data based on the heart rate in the first time interval. You can (S2507). At this time, the second sensing data may be PPG data (pulse wave data). Specifically, the computing device may acquire PPG data for a part of the user's body (e.g., lips), calculate the heart rate in a first time period based on the PPG data, and obtain third time series data based on this. can do.

The temporal order in which the computing device acquires the first to third time series data is not limited to the order of operations S2503 to S2507 shown in FIG. 5, and may be operated differently from the order shown in FIG. 5, or They can also be operated simultaneously. A specific method by which a computing device acquires time series data based on sensing data in operations S2503 to S2507 will be described in the description of FIG. 6 .

The computing device may use the learned artificial intelligence model to obtain fourth time series data related to oxygen intake based on biometric information including at least one of first time series data, second time series data, and third time series data. There is (S2509). In this case, the computing device may obtain fourth time series data by further using user information or environment information. Specifically, the computing device may output fourth time series data including at least one value related to oxygen intake through at least one layer included in the learned artificial intelligence model.

Figure 7 is a diagram showing an example of pressure data obtained according to the respiratory sum of a user wearing a measuring device. Figure 8 is a diagram showing an example of heart rate data acquired using a PPG sensor included in the measurement device. FIG. 9 is a diagram illustrating examples of time series data related to athletic ability, according to various embodiments.

Referring to FIG. 6, the computing device 2000 may receive pressure data and PPG data from the measurement device 2001.

For example, referring to FIG. 7 , the measuring device may obtain pressure data 2700 by measuring the pressure value caused by the user's breathing. Here, at least one section of the pressure data 2700 represents the flow direction and flow rate (flow rate) of air according to the breathing direction.

For example, the first window 2710 of pressure data can confirm that the air pressure measured by the pressure sensor is lower than atmospheric pressure, which represents the pressure section due to inhalation. Also, for example, the second window 2720 of pressure data can confirm that the air pressure measured by the pressure sensor is higher than atmospheric pressure, which represents the pressure section due to exhalation. Additionally, for example, when a differential pressure sensor is used, the sign of the pressure is determined depending on the flow direction, and the magnitude of the pressure has a one-to-one functional relationship with the respiratory flow rate (flow rate). Specifically, when the magnitude of the pressure measured using the differential pressure sensor is a negative number, the direction of breathing is determined to be “inhalation”, and when the magnitude of the pressure is a positive number, the direction of breathing is determined to be “exhalation.” Additionally, the flow rate and flow rate of respiration are determined depending on the size of the measured pressure. In the above-described example, the direction of breathing according to the sign of pressure (negative and positive) may be set in the opposite direction.

In addition, for example, through the experimental data shown in FIG. 8, the accuracy of calculation of time series data related to heart rate through the measuring device of the present disclosure can be confirmed. To determine the accuracy of the PPG measurement method, the ECG measurement method using a polar chest belt that can accurately measure the electrocardiogram can be used as a reference.

Specifically, Figure 8 (a) is heart rate data according to an ECG measurement method based on electrocardiogram measurement as the amount of exercise changes, and Figure 8 (b) is heart rate data measured using a PPG sensor as the amount of exercise changes. Referring to (c) of FIG. 8, it can be seen that the heart rate data measured using the PPG sensor perfectly follows the heart rate data measured by the ECG.

As verified through a heart rate measurement experiment, it was confirmed that the heart rate data measured by ECG was perfectly tracked as the amount of exercise changed. (Because the ECG measurement method measures the electrocardiogram, it is used as a reference to determine the accuracy of the PPG measurement method.)

Referring again to FIG. 6 , the computing device may input pressure data into a pre-trained first model 2610 and a pre-trained second model 2620.

At this time, the first model 2610 may be a neural network model learned to predict respiration rate (or respiration rate) based on pressure data.

The computing device 2000 may be configured to input pressure data into the input layer of the first model 2610 and output respiratory rate data through at least one layer of the first model 2610. For example, (a) of FIG. 9 shows respiratory rate data 2910 during a first time period.

The second model 2620 may be a neural network model learned to predict ventilation per minute based on pressure data.

The computing device 2000 may be set to input pressure data into the input layer of the second model 2620 and output per minute ventilation data through at least one layer of the second model 2620. For example, (b) of FIG. 9 shows minute ventilation data 2920 during the first time period.

Additionally, the computing device may input PPG data into a pre-trained third model 2630.

The third model 2630 may be a neural network model learned to predict heart rate based on PPG data.

The computing device 2000 may be configured to input PPG data into the input layer of the third model 2630 and output heart rate data through at least one layer of the third model 2630. For example, (c) of FIG. 9 shows heart rate data 2930 during a first time period.

According to one embodiment of the present disclosure, the computing device may identify the user's exercise intensity by estimating the user's oxygen intake during exercise. In other words, the oxygen intake predicted by the computing device is proportional to the user's exercise intensity.

Generally, ventilation increases proportionally to oxygen intake (exercise intensity). However, as the exercise intensity becomes stronger, a point occurs where the respiratory volume (ventilation volume) rapidly increases, and this point is called the ventilatory threshold (or lactate threshold, VT). In addition, the term "ventilation threshold" used throughout this specification refers to the exercise intensity including the point where the ventilation threshold occurs, and may also mean a value corresponding to the ventilation threshold, and an exercise intensity section including the value. It may mean. Alternatively, the term "ventilation threshold" refers to the oxygen intake including the point where the ventilation threshold occurs, and may mean the oxygen intake value corresponding to the ventilation threshold, or may mean the oxygen intake section including the corresponding value. It may be possible. A computing device according to an embodiment of the present disclosure may estimate at least one ventilation threshold by identifying the ventilation threshold based on at least one time series data related to exercise ability.

As an example, a computing device according to an embodiment of the present disclosure may predict at least one ventilation threshold based on oxygen intake and minute ventilation.

Referring to (a) of FIG. 10, after acquiring the fourth time series data in operation S2509, the computing device calculates correlation data between the fourth time series data related to oxygen intake and the second time series data related to minute ventilation amount. You can do it (S3001).

Additionally, the computing device may determine at least one ventilation threshold based on the correlation data (S3003). Specifically, the computing device may determine at least one ventilation threshold by extracting at least one inflection point of the correlation data. The computing device may determine at least one ventilation threshold by identifying a section (or point) where the increase in ventilation volume as oxygen intake increases rapidly changes.

Referring to FIG. 11, it can be seen that correlation data 3110 is defined based on the correlation of minute ventilation (VE) with oxygen intake (VO2).

In this case, the computing device according to an embodiment of the present disclosure may determine at least one ventilation threshold (VT) based on correlation data 3110 of oxygen intake and minute ventilation.

Additionally, referring again to (a) of FIG. 10, the computing device may provide exercise state information based on at least one ventilation threshold (S3005). Specifically, the computing device may provide exercise status information by comparing real-time oxygen uptake and ventilation threshold. For example, if the real-time oxygen intake is above the ventilation threshold, the computing device may determine that it is in a high-intensity exercise state (e.g., an exercise state in which lactate production is active), and if the real-time oxygen intake is below the ventilation threshold, it may be determined that the computing device is in a low-intensity exercise state. It can be judged that

Additionally, the computing device may set training intensity based on at least one ventilatory threshold. Specifically, the computing device may guide training to achieve an oxygen uptake above at least one ventilatory threshold for high-intensity training.

Such training through a computing device can be achieved through real-time exercise feedback, and the training method through exercise feedback is described in the description of FIGS. 12 and 13.

As another example, a computing device according to an embodiment of the present disclosure may predict at least one ventilation threshold based on breathing and heart rate data.

Referring to (b) of FIG. 10, the computing device acquires first to third time series data according to operation S2507, and then uses the learned artificial intelligence model to obtain first time series data, second time series data, and At least one ventilation threshold may be determined based on at least one of the third time series data (S3007). At this time, the artificial intelligence model may be trained to output a value corresponding to at least one ventilation threshold based on breathing and heart rate data.

Specifically, the computing device may input first time series data related to respiratory rate, second time series data related to minute ventilation, and third time series data related to heart rate into the learned artificial intelligence model. Additionally, the computing device may be set to output a value corresponding to at least one ventilation threshold through at least one layer of the learned artificial intelligence model. Additionally, in this case, the computing device may be further configured to output fourth time series data related to real-time oxygen intake through at least one layer of the learned artificial intelligence model.

Additionally, the computing device may provide exercise state information based on at least one ventilation threshold (S3009).

FIG. 12 is a diagram illustrating an example in which a computing device provides exercise feedback related to exercise capability information, according to various embodiments.

Referring to FIG. 12, the measuring device and/or the user device may be set to the first exercise mode (S3201). At this time, the first exercise mode in the present disclosure may mean an operation mode of at least one electronic device for providing information about the exercise state to the user. For example, as the measuring device or user device is set to the first exercise mode, the user may receive an alarm about a change in exercise state, etc. through the measuring device or user device.

Additionally, the measuring device can measure the user's breathing and heart rate (S3203). Additionally, the measuring device may transmit sensing data obtained by measuring breathing and heart rate to the computing device (S3205).

The computing device can predict oxygen intake data based on sensing data (S3207). In this case, the computing device may obtain exercise state information based on at least one determined ventilation threshold. For example, the computing device may change the exercise state from low-intensity exercise to high-intensity exercise if the user's oxygen intake during exercise reaches the ventilatory threshold.

Maximum oxygen intake during exercise may be an indicator of the user's aerobic exercise capacity. Additionally, the intensity of ventilation threshold compared to maximum oxygen intake during exercise can indicate the user's exercise capacity. Specifically, if the ventilation threshold relative to maximum oxygen intake is formed at a high intensity, the user's exercise capacity can be evaluated as high.

Accordingly, the computing device may obtain exercise capacity information by comparing the pre-stored maximum oxygen intake information and at least one determined ventilation threshold (S3211). Here, maximum oxygen intake information can be obtained by extracting the maximum value based on oxygen intake data measured during the user's exercise. At this time, maximum oxygen intake information may be obtained according to a predetermined exercise protocol and stored in advance in memory.

For example, the computing device may obtain exercise capacity information based on the ratio between ventilatory threshold to maximum oxygen uptake.

Accordingly, the computing device may calculate and provide an indicator indicating exercise capacity based on the ratio between maximum oxygen intake and ventilation threshold. For example, the computing device may be set to calculate an index of the user's high exercise capacity when the ratio of the ventilation threshold to the maximum oxygen intake is greater than a predetermined ratio.

Additionally, the computing device may transmit exercise feedback related to exercise capability information to the measurement device or user device according to a preset training program (S3213). For example, but not limited to, the computing device may transmit feedback to exercise at an exercise intensity corresponding to the ventilatory threshold.

At this time, the feedback may include, but is not limited to, voice feedback through at least one speaker included in the measurement device, haptic feedback through a user device, etc.

Additionally, the computing device may score based on the degree of matching between the training information presented in the training program and the user's exercise state information. Specifically, the computing device may compare the exercise state according to the preset training program and the actual exercise state, calculate and provide a score for training performance.

Additionally, the computing device may provide an exercise graph during a first time period in which the exercise is performed. Specifically, the computing device may provide an exercise graph indicating exercise intensity information (oxygen uptake data), ventilation threshold information, exercise state information according to the time section, maximum oxygen uptake information, etc. according to the first time section. It is not limited.

Referring to FIG. 13, the measuring device and/or the user device may be set to the second exercise mode (S3301). At this time, the second exercise mode in the present disclosure may refer to an operation mode of at least one electronic device for providing information about exercise intensity to the user. For example, as the measuring device or user device is set to the second exercise mode, the user may receive an alarm about a change in exercise intensity, etc. through the measuring device or user device.

Additionally, the measuring device can measure the user's breathing and heart rate (S333). Additionally, the measuring device may transmit sensing data obtained by measuring breathing and heart rate to the computing device (S335).

The computing device can predict oxygen intake data based on sensing data (S3307).

Additionally, the computing device may obtain exercise intensity information by comparing the pre-stored maximum oxygen intake information and the predicted oxygen intake (S3309). Specifically, the computing device can obtain real-time exercise intensity information by comparing real-time oxygen intake with maximum oxygen intake and calculating an index indicating current exercise intensity compared to maximum intensity.

Additionally, the computing device may transmit feedback related to exercise intensity information to the measurement device or user device (S3311). In this case, the computing device may transmit feedback related to exercise intensity information according to a preset training program.

As described above, although the embodiments have been described with limited examples and drawings, various modifications and variations can be made by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims

In a method of operating a computing device,

By at least one processor included in the computing device,

Obtaining biometric information of a user based on at least one piece of sensing data detected during a first time period; The step of acquiring the biometric information is,

Obtaining first time series data related to the respiratory rate by predicting the respiratory rate (RF) in the first time period based on first sensing data detected according to the user's breathing;

Obtaining second time series data related to the minute ventilation volume (VE) by predicting the minute ventilation volume (VE) in the first time period based on the first sensing data; and

Obtaining third time series data related to the heart rate by predicting the heart rate (HR) in the first time period based on second sensing data detected according to the user's heart rate; Includes, and

Using the learned first model, predict fourth time series data related to oxygen intake in the first time period based on at least one of the first time series data, the second time series data, or the third time series data. steps; An operation method comprising:
According to paragraph 1,

Based on the fourth time series data, obtaining first exercise information indicating a change in oxygen intake during the first time period and providing the first exercise information to the user device.
According to paragraph 1,

calculating correlation data between oxygen intake and minute ventilation based on the second time series data and the fourth time series data; and

A method of operation further comprising: determining at least one ventilation threshold based on the correlation data.
According to paragraph 1,

Using the learned second model, determining at least one ventilation threshold in the first time interval based on the first time series data, the second time series data, and the third time series data; further comprising; How to operate.
According to paragraph 1,

determining at least one ventilation threshold based on at least one of the first time series data, the second time series data, the third time series data, and the fourth time series data; and

An operating method further comprising obtaining second exercise information based on the at least one ventilation threshold and providing the second exercise information to a user device.
According to paragraph 1,

An operating method further comprising acquiring third exercise information indicating current oxygen intake compared to maximum oxygen intake based on pre-stored maximum oxygen intake information and the fourth time series data.
According to paragraph 1,

determining at least one ventilation threshold based on at least one of the first time series data, the second time series data, the third time series data, and the fourth time series data; and

An operation method further comprising: acquiring fourth exercise information indicating a ventilation threshold relative to the maximum oxygen intake based on pre-stored maximum oxygen intake information and the at least one ventilation threshold.
According to paragraph 1,

The fourth time series data is set to be acquired in real time,

An operation method further comprising transmitting, by the at least one processor, feedback related to exercise to at least one of a user device or a measurement device based on the fourth time series data acquired in real time.
According to paragraph 1,

An operating method, characterized in that the at least one sensing data is received from the measurement device based on a communication connection with the measurement device.
According to paragraph 1,

The first sensing data is obtained by detecting a pressure value due to the user's breathing, and the second sensing data is obtained by detecting PPG data from at least a portion of the user's body.
According to paragraph 1,

The step of acquiring the fourth time series data is,

Inputting the biometric information and user information into the first model; and

An operating method comprising: outputting the fourth time series data through at least one layer included in the first model.
According to paragraph 1,

Further comprising: obtaining environmental information indicating at least one of temperature, humidity, or atmospheric pressure of the user's surrounding environment,

An operation method characterized by acquiring the biometric information by considering the environmental information, or predicting the fourth time series data by further using the environmental information.
According to clause 11,

The first model is Long short-term memory (LSTM), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), Diffusion Convolution Recurrent Neural Network (DCRNN), Ordinary Differential Equation (ODE)-based model, and Graph Convolution (GCN). An operation method that includes at least one of a Network), a Transformer model, or a multi-modal transformer model.
As a computing device,

Memory; and

At least one processor electronically connected to the memory,

The at least one processor,

Obtain first time series data related to the respiratory rate by predicting the respiratory rate (RF) in the first time period based on the first sensing data detected according to the user's breathing,

Obtaining second time series data related to the minute ventilation volume (VE) by predicting the minute ventilation volume (VE) in the first time period based on the first sensing data,

Obtaining third time series data related to the heart rate by predicting the heart rate (HR) in the first time period based on the second sensing data detected according to the user's heart rate, and

Using the learned first model, set to predict fourth time series data related to oxygen intake in the first time interval based on the first time series data, the second time series data, and the third time series data. Computing device.
According to clause 14,

The at least one processor

Based on the fourth time series data, the computing device is further set to obtain first exercise information indicating a change in oxygen intake during the first time period and provide the first exercise information to the user device.