Method and device for providing menstrual-related information.

Abstract

According to various embodiments of the present disclosure, a method for providing menstruation-related information, performed by a computing device, is disclosed, which may include: acquiring physiological information including a predetermined plurality of electrocardiogram variable information, the plurality of electrocardiogram variable information including time series data; acquiring user questionnaire information corresponding to the plurality of electrocardiogram variable information; and generating menstrual cycle prediction information based on the physiological information and the user questionnaire information using an analytical model.

Description

Technical Field

[0001] The present invention relates to a method and apparatus for providing information using a computer, and more specifically, to a method and apparatus for providing menstrual cycle-related information using biological information including a plurality of electrocardiogram variable information and user questionnaire information.

Background Art

[0002] A generally known method for predicting the menstrual cycle is to predict the ovulation day (menstrual period) only based on a woman's body temperature, and the measurement accuracy is not high. Therefore, due to inaccurate prediction results, there is a problem that accurate menstrual cycle-related information such as information related to the fertile period, information related to the prevention and alleviation of menstrual disorders, etc. cannot be provided.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The present disclosure was devised in response to the aforementioned background art, and is for providing a method and apparatus for providing menstrual cycle-related information using biological information including a plurality of electrocardiogram variable information and user questionnaire information.

Means for Solving the Problems

[0005] To address the aforementioned challenges, a method for providing menstrual cycle-related information, performed by a computing device, is disclosed. The method may include: acquiring biological information including a predetermined set of electrocardiogram variable information - the set of electrocardiogram variable information includes time-series data; acquiring user question and answer information corresponding to the set of electrocardiogram variable information; and generating menstrual cycle prediction information based on the biological information and the user question and answer information using an analysis model. As an alternative, the above-mentioned electrocardiogram variable information can include at least one of the following: RRI (RR Intervals) information, HR (Heart Rate) information, RR (Respiration Rate) information, ST level information, SDNN (standard deviation of all NN intervals) information, RMSSD (square root of the mean of the sum of the squares of differences between adjacent NN intervals) information, NN50 (number of NN intervals differing by more than 50ms) information, pNN50 (ratio of NN50) information, and SDSD (standard deviation of differences between adjacent NN intervals) information.

[0006] As an alternative, the user Q&A information described above may include at least one of the following: Q&A information related to sleep disorders, Q&A information related to depressed mood, Q&A information related to anxiety, or Q&A information related to stress. As an alternative, the above analysis model may include an ensemble learning model that uses a combination of multiple predictor variables, each including at least a portion of the above electrocardiogram variable information and the above user Q&A information.

[0007] As an alternative, the above analysis model can be trained to generate information that predicts the transition from the follicular phase to the luteal phase when it identifies a decreasing trend in RRI information based on the above RRI information. As an alternative, the above analysis model can be trained to generate information predicting the transition from the menstrual phase to the follicular phase when it identifies a trend of maintenance or decrease in HR information, to generate information predicting the transition from the follicular phase to the fertile phase when it identifies a trend of increase in HR information, and to generate information predicting the transition to the luteal phase when it identifies a trend of peak levels in HR information.

[0008] As an alternative, the above analysis model can be trained to generate information predicting the transition from the menstrual phase to the follicular phase when it identifies a decreasing trend in the RR information, to generate information predicting the transition to the fertile period when it identifies a further decreasing trend in the RR information, and to generate information predicting the transition to the luteal phase when it identifies an increasing trend in the RR information. Alternatively, the above analysis model can be trained to generate information predicting the transition to the follicular phase when it identifies the trend of the maximum level of the ST level information, and to generate information predicting the transition to the luteal phase when it identifies the trend of the minimum level of the ST level information.

[0009] As an alternative, the above analysis model can be trained to generate information predicting the transition from the menstrual phase to the follicular phase when it identifies a maintenance trend in the above SDNN information, to generate information predicting the transition from the follicular phase to the fertile phase when it identifies a decrease trend in the above SDNN information, and to generate information predicting the transition to the luteal phase when it identifies a maximum decrease trend in the above SDNN information. As an alternative, the above analysis model can be trained to generate information that predicts the transition to the luteal phase when it identifies the maximum decreasing trend in the RMSSD information.

[0010] Alternatively, the above analysis model can be trained to generate information that predicts the transition from the follicular phase to the luteal phase when it identifies a decreasing trend in the NN50 information. Alternatively, the above analysis model can be trained to generate information that predicts the transition from the follicular phase to the luteal phase when it identifies a decreasing trend in the pNN50 information.

[0011] Alternatively, the above analysis model can be trained to generate information that predicts the transition from the menstrual phase to the follicular phase when it identifies a maintenance trend in the above SDSD information. Alternatively, the user Q&A information could include Q&A information related to sleep disorders, and the analysis model could be trained to generate information predicting the transition to the luteal phase when it identifies an increasing trend in the Q&A information related to sleep disorders.

[0012] As an alternative, the user Q&A information mentioned above could include Q&A information related to depression, and the analysis model could be trained to generate information predicting the transition to the luteal phase when it identifies an increasing trend in the Q&A information related to depression. Alternatively, the user Q&A information could include Q&A information related to anxiety, and the analysis model could be trained to generate information predicting the transition to the luteal phase when it identifies an increasing trend in the Q&A information related to anxiety.

[0013] Alternatively, the user Q&A information could include stress-related Q&A information, and the analysis model could be trained to generate information predicting ovulation delay when it identifies an increasing trend in the stress-related Q&A information. As an alternative, the step of acquiring user Q&A information corresponding to multiple electrocardiogram variable information may include: a step of providing a user interface that allows the user to input the above user Q&A information, corresponding to the point in time when multiple electrocardiogram variable information has been acquired.

[0014] As an alternative, the step of acquiring user Q&A information corresponding to multiple electrocardiogram variable information may include: providing a user interface that indicates whether or not the above user Q&A information corresponding to the point in time when multiple electrocardiogram variable information has been acquired has been entered; As an alternative, the above-mentioned multiple electrocardiogram variable information can include RRI information, HR information, RR information, ST level information, SDNN information, RMSSD information, NN50 information, pNN50 information, and SDSD information.

[0015] As an alternative, the user Q&A information mentioned above may include Q&A information related to sleep disorders, Q&A information related to depressed mood, Q&A information related to anxiety, and Q&A information related to stress. As an alternative, the above analysis model can utilize the random forest algorithm.

[0016] A computer program stored on a computer-readable medium is disclosed for solving the aforementioned problems. The computer program includes instructions for causing one or more processors to perform a method for providing menstrual-related information, the method may include: acquiring biological information including a predetermined set of electrocardiogram variable information - the set of electrocardiogram variable information including time-series data; acquiring user question and answer information corresponding to the set of electrocardiogram variable information; and generating menstrual cycle prediction information based on the biological information and the set of user question and answer information using an analysis model. A computing device is disclosed that executes a method for providing menstrual cycle-related information to solve the above-described problems. The computing device includes: a memory including computer-executable components; a processor that executes the following computer-executable components stored in the memory; and the processor obtains biological information including a plurality of predetermined electrocardiogram variable information - the plurality of electrocardiogram variable information includes time-series data -; obtains user questionnaire information corresponding to the plurality of electrocardiogram variable information, and can generate menstrual cycle prediction information based on the biological information and the plurality of user questionnaire information by an analysis model.

Advantages of the Invention

[0017] The present disclosure can provide a method and apparatus for providing menstrual cycle-related information using biological information including a plurality of electrocardiogram variable information and user questionnaire information.

Brief Description of the Drawings

[0018] [Figure 1] A drawing showing a menstrual cycle-related information providing system based on multiple embodiments of the present disclosure. [Figure 2] A block configuration diagram of a computing device for executing a method for providing menstrual cycle-related information based on multiple embodiments of the present disclosure. [Figure 3] A schematic diagram for explaining a method for providing menstrual cycle-related information based on multiple embodiments of the present disclosure. [Figure 4] A drawing for explaining electrocardiogram variable information based on multiple embodiments of the present disclosure. [Figure 5] A drawing for explaining user questionnaire information based on multiple embodiments of the present disclosure. [Figure 6] A drawing showing an example of a user application for obtaining user questionnaire information based on multiple embodiments of the present disclosure. [Figure 7] A drawing for explaining the prediction performance of an analysis model based on multiple embodiments of the present disclosure. [Figure 8] This is another diagram illustrating the predictive performance of the analysis model based on several embodiments of the present disclosure. [Figure 9] This is a flowchart of a method for providing menstrual-related information based on several embodiments of the present disclosure. [Figure 10] This is a schematic diagram showing a network function based on several embodiments of the present disclosure. [Figure 11] This is a block diagram of a computing device based on several embodiments of the present disclosure. [Modes for carrying out the invention]

[0019] Various embodiments will be described below with reference to the drawings. Various explanations are provided in this specification to facilitate understanding of the disclosure. However, it will be obvious that such embodiments can be carried out without such specific explanations. In this specification, terms such as “component,” “module,” and “system” refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or software execution. For example, a component may be, but is not limited to, a processing procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer. For example, both an application running on a computing device and the computing device itself can be components. One or more components can reside in a processor and / or an execution thread. A single component can be localized within a single computer. A single component can be distributed across two or more computers. Furthermore, such components can run on a variety of computer-readable media having diverse data structures stored within them. Components can communicate locally and / or remotely using signals, for example, one or more data packets (e.g., data and / or signals from one component interacting with other components in a local or distributed system, and data transmitted over a network such as the Internet).

[0020] Furthermore, the terms “or,” “or else,” and “or else” shall mean “or,” “or else,” and “or else” in an implicational sense, rather than in an exclusive sense. That is, unless specifically specified and not clear from the context, “X uses A or B” shall mean one of the natural implicational substitutions. In other words, if X uses A; X uses B; or X uses both A and B, “X uses A or (or else) B” can apply to any of these. Also, the term “and / or” as used herein refers to and includes all possible combinations of one or more of the multiple related items discussed. Furthermore, the term “includes” as a predicate and / or as a modifier should be understood to mean that the feature and / or component in question exists. However, the term “includes” as a predicate and / or as a modifier should be understood not to exclude the presence or addition of one or more other further features, components and / or groups thereof. Also, where the number is not specifically identified or where it is not clear from the context to indicate a singular form, the singular in this specification and claims should generally be interpreted to mean “one or more.”

[0021] Furthermore, the phrase "at least one of A or B" should be interpreted as meaning "including only A," "including only B," or "a combination of A and B." Those skilled in the art should further recognize that the various exemplary logical blocks, configurations, modules, circuits, means, logic, and algorithmic stages described herein as relating to the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interoperability between hardware and software, various exemplary components, blocks, configurations, means, logic, modules, circuits, and stages have been generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and design constraints of the overall system. Skilled technicians can implement the described functionality in various ways for individual specific applications; however, such decisions on implementation should not be construed as departing from the scope of this disclosure.

[0022] The descriptions relating to the embodiments presented herein are provided so that a person with ordinary skill in the art of this disclosure may utilize or practice the invention. Various modifications to such embodiments will be readily apparent to a person with ordinary skill in the art of this disclosure. The general principles defined herein can be applied to other embodiments without departing from the scope of this disclosure. Accordingly, the invention is not limited to the embodiments presented herein. The invention should be interpreted in the broadest sense, consistent with the principles and novel features presented herein. This disclosure provides a method for providing highly accurate menstrual cycle-related information by using electrocardiogram (ECG) variable information and user Q&A information, rather than being limited to body temperature, which has been the primary variable used to predict the menstrual cycle. Specifically, this disclosure can provide menstrual cycle-related information by identifying patterns of time-series changes in ECG variable information, which is time-series data collected continuously over a certain period of time. Furthermore, this disclosure can provide even more accurate menstrual cycle-related information by using user Q&A information obtained from users in a question-and-answer format, along with ECG variable information.

[0023] Figure 1 is a diagram showing a menstrual cycle-related information provision system (1000) based on several embodiments of the present disclosure. Referring to Figure 1, in several embodiments of this disclosure, the menstrual information provision system (1000) may include a user terminal (1010), a biometric information sensing device (1020), and a server (1030). The configuration of the menstrual information provision system (1000) shown in Figure 1 is merely a simplified example. In several embodiments of this disclosure, other configurations can be added to the menstrual information provision system (1000), and it is also possible to configure the menstrual information provision system (1000) with only a part of the disclosed configuration.

[0024] Communication between various entities included in the menstrual cycle information provision system (1000) can be conducted via a wired / wireless network (1040). Here, the wired / wireless network (1040) can mean a connection structure that enables information exchange between nodes, such as multiple terminals and servers. Multiple examples of such a network (1040) can include local area networks (LANs), wide area networks (WANs), the internet (WWW), wired and wireless data communication networks, telephone communication networks, wired and wireless television communication networks, etc. Some examples of wireless data communication networks include 3G, 4G, 5G, and 3GPP. (Registered trademark) This includes, but is not limited to, the 3rd Generation Partnership Project, 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WiMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth (registered trademark) networks, NFC (Near-Field Communication) networks, satellite broadcasting networks, analog broadcasting networks, DMB (Digital Multimedia Broadcasting) networks, etc. The user terminal (1010) can be embodied as a computer that can connect to remote servers or terminals via a network. Here, the user terminal (1010) can include at least one of the following: smartphone, tablet PC (tablet personal computer), mobile phone, video phone, e-book reader, desktop PC (desktop personal computer), laptop PC (laptop personal computer), netbook computer, workstation, server, PDA (personal digital assistant), PMP (portable multimedia player), or wearable device (e.g., smart glasses, head-mounted device (HMD)), smart wear, electronic bracelet, electronic necklace, electronic accessory, smart mirror, or smart watch). However, the user terminal (1010) is not limited to these and can be embodied as a variety of computers.

[0025] Based on several embodiments of this disclosure, a user terminal (1010) can embody a method for providing menstrual-related information as described in this disclosure. For example, a user terminal (1010) can provide a user application for providing menstrual-related information. Through the user application, the user terminal (1010) can acquire menstrual-related user information necessary for providing menstrual-related information. In several examples, the user terminal (1010) can acquire biometric information by operating a biometric information sensing device (1020) using the user application. In several examples, the user terminal (1010) can acquire biometric information stored on a server (1030). In several examples, the user terminal (1010) can acquire user question and answer information entered through the user interface of the user application. In several examples, the user terminal (1010) can generate menstrual-related user information using an analysis model implemented on the user terminal (1010). The user terminal (1010) can also send the menstrual-related user information to the server (1030) for processing. In this case, the user terminal (1010) can receive the generated menstrual-related information by processing the menstrual-related user information using an analysis model provided by the server (1030). The user terminal (1010) can then provide the received menstrual-related information to the user via a user application.

[0026] Menstrual cycle-related information can include a variety of information related to menstruation. For example, it can include predictions of the menstrual cycle (ovulation date, menstruation date, menstrual period, fertile days, premenstrual syndrome, menopause, etc.), recommended diets, guidance information for menstrual management (e.g., predicted menstrual disorders and music therapy or exercise therapy to alleviate menstrual disorders), or information on recommended menstrual cycle-related products and services. The types of menstrual cycle-related information are not limited to the examples given above and can include a variety of information related to menstruation. In several embodiments of this disclosure, the server (1030) can embody a method for providing menstrual-related information based on this disclosure. For example, the server (1030) can train an analysis model using training data related to menstruation. In several examples, the training data related to the menstrual cycle can include a variety of information, including biometric information and user Q&A information, as user information related to menstruation. The server (1030) can generate menstrual-related information by processing the user information related to menstruation using the trained analysis model. In another example, the server (1030) can provide a user application containing the trained analysis model to a user terminal (1010). In this case, as described above, the user terminal (1010) can process the user information related to menstruation using the analysis model.

[0027] The biometric information sensing device (1020) can include various devices capable of measuring biometric information. For example, the biometric information sensing device (1020) can be a device capable of measuring a user's body temperature, blood pressure, pulse rate, skin conductivity, electrocardiogram, oxygen saturation, respiratory rate, etc. The biometric information sensing device (1020) can transmit the measured biometric information to a user terminal (1010) or a server (1030). The biometric information sensing device (1020) can include portable or stationary devices. In several examples, the biometric information sensing device (1020) can include a wearable device capable of measuring an electrocardiogram (e.g., a patch-type Holter electrocardiogram). In several examples, the biometric information sensing device (1020) can be provided as a module on a user terminal (1010). In the following, a computer device that performs the method for providing menstrual-related information as described herein, which is a user terminal (1010) or server (1030), will be described based on several embodiments of the present disclosure.

[0028] Figure 2 is a block diagram of a computing device for performing a method for providing menstrual-related information, based on several embodiments of the present disclosure. As shown in Figure 2, the computing device (100) may include a processor (110), memory (130), and a network unit (120). The configuration of the computing device (100) shown in Figure 2 is merely a simplified example. In several embodiments of this disclosure, the computing device (100) may include other configurations for implementing the computing environment of the computing device (100), and it is also possible to configure the computing device (100) using only some of the disclosed configurations.

[0029] The processor (110) can consist of one or more cores and may include processors for data analysis and processing, and deep learning, such as a central processing unit (CPU), a general-purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. The processor (110) can read computer programs stored in memory (130) and perform data transformation, calculations, generation, etc., to provide menstrual-related information in several embodiments of this disclosure. For example, the processor (110) can perform steps to carry out a method for providing menstrual-related information as described below. Furthermore, based on several embodiments of this disclosure, the processor (110) can use training data to perform calculations for learning a neural network in order to carry out a method for providing menstrual-related information. For example, the processor (110) can use training data to generate / train an analysis model. The processor (110) is capable of performing calculations for learning a neural network, such as processing input data for training in deep learning (DL), extracting feature values ​​from input data, calculating errors, and updating weights in the neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (110) is capable of processing calculations for a method to provide menstrual-related information. For example, both the CPU and GPGPU can process calculations related to a method to provide menstrual-related information. Furthermore, in several embodiments of this disclosure, it is possible to use the processors of multiple computing devices together to process data transformation, calculations, generation, network function training, and data classification using network functions related to a method to provide menstrual-related information. In addition, the programs executed in the computing devices in several embodiments of this disclosure can be programs that can be executed on the GPU, GPGPU, and TPU. In one embodiment of the present disclosure, the memory (130) can store any form of information generated or determined by the processor (110) and any form of information received by the network unit (120). For example, the memory (130) can store data generated in the process of the processor (110) performing a method for providing menstrual-related information. The memory (130) can also store data received from an external source in the process of the processor (110) performing a method for providing menstrual-related information. However, the memory (130) can store any information for performing a method for providing menstrual-related information based on multiple embodiments of the present disclosure.

[0030] In several embodiments of this disclosure, the memory (130) may include at least one type of storage medium from among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory), Random Access Memory (RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), magnetic memory, magnetic disk, and optical disk. The computing device (100) may also operate in conjunction with web storage that performs the storage function of the memory (130) over the internet. The foregoing descriptions of memory are illustrative, and this disclosure is not limited thereto. In some embodiments of this disclosure, the network unit (120) can be any known wired or wireless communication system of any form.

[0031] The network unit (120) can send and receive information and user interfaces processed by the processor (110) through communication with other terminals. For example, the network unit (120) can provide a user interface generated by the processor (110) to a client (e.g., a user terminal). The network unit (120) can also receive external input from the user to the client and forward it to the processor (110). At this time, the processor (110) can process operations such as outputting, modifying, changing, and adding information provided via the user interface based on the external input from the user received from the network unit (120). Specifically, the network unit (120) can send and receive various information for performing a method for providing menstrual-related information based on multiple embodiments of this disclosure. For example, the network unit (120) can send and receive biometric information and user question and answer information stored in a database. The network unit (120) can also transmit multiple data generated in the process of performing the method for providing menstrual-related information described below to an external source for storage in a database.

[0032] On the other hand, a computing device (100) based on multiple embodiments of this disclosure may include a server (1030) as a computing system that sends and receives information through communication with a client. In this case, the client can be any form of terminal that can access the server. For example, the computing device (100) which is a server can receive a query from a user terminal and generate a single information processing result corresponding to the query. In this case, the computing device (100) which is a server can provide the user terminal with a user interface including the processing result. In this case, the user terminal can output the user interface received from the computing device (100) which is a server and receive and process information through interaction with the user. In additional embodiments, the computing device (100) may also include any form of user terminal (1010) that receives data resources generated on any server and performs additional information processing.

[0033] Figure 3 is a schematic diagram illustrating a method for providing menstrual cycle-related information based on several embodiments of the present disclosure. Figure 4 is a diagram illustrating electrocardiogram variable information based on several embodiments of the present disclosure. Figure 5 is a diagram illustrating user question and answer information based on several embodiments of the present disclosure. Figure 6 is a diagram showing an example of a user application for obtaining user question and answer information based on several embodiments of the present disclosure. Exemplary embodiments based on multiple embodiments of this disclosure will be specifically described with reference to Figures 3 to 6.

[0034] The processor (110) is capable of acquiring biological information, including a predetermined set of electrocardiogram variable information. Here, the set of electrocardiogram variable information can include time-series data. Specifically, the processor (110) can acquire biometric information (10) that can be used to predict the menstrual cycle. For example, the biometric information may include age, height, weight, body temperature, blood pressure, respiratory rate, menstrual day, menstrual period, pulse rate, skin conductivity, electrocardiogram, and oxygen saturation. However, the biometric information (10) is not limited to the examples given above and can include various other information related to the user.

[0035] In several examples, the biometric information (10) may include information generated by one or more biometric sensing devices (1020) (e.g., body temperature, blood pressure, respiratory rate, pulse rate, electrocardiogram, etc.). The biometric information (10) may also include information entered by the user (e.g., age, height, weight, etc.). In several cases, the biological information (10) can include multiple electrocardiogram variable information. For example, the electrocardiogram variable information can be time-series data of an electrocardiogram (EKG or ECG) measured by an electrocardiogram device such as a Holter monitor. The electrocardiogram variable information can be time-series data obtained by a method of continuously measuring the electrocardiogram, rather than cross-sectional measurements.

[0036] Based on multiple embodiments of this disclosure, the multiple electrocardiogram variable information may include at least one of the following: RRI (RR Intervals) information, HR (Heart Rate) information, RR (Respiration Rate) information, ST level information, SDNN (standard deviation of all NN intervals) information, RMSSD (square root of the mean of the sum of the squares of differences between adjacent NN intervals) information, NN50 (number of NN intervals differing by more than 50ms) information, pNN50 (ratio of NN50) information, and SDSD (standard deviation of differences between adjacent NN intervals) information. Figure 4 shows an example of electrocardiogram (ECG) variable information obtained by a Holter ECG. Among these, the predictors processed by the analysis model to generate menstrual cycle prediction information can include RRI information, HR information, RR information, ST level information, SDNN information, RMSSD information, NN50 information, pNN50 information, and SDSD information, which have been analyzed to have a high correlation with menstrual cycle prediction. The ECG variable information is not limited to the examples described above and can include various types of information related to the ECG.

[0037] Multiple electrocardiogram (ECG) variable information can be data acquired according to a predetermined cycle. For example, multiple ECG variable information can be one of several measurements taken in the morning and afternoon each day. In this case, the analysis model can improve the accuracy of the prediction by generating menstrual cycle prediction information at predetermined cycle intervals. However, this is not the only example; multiple ECG variable information can be data acquired at various cycle intervals. The processor (110) is capable of acquiring user question and answer information corresponding to multiple electrocardiogram variable information.

[0038] Specifically, the processor (110) can acquire user question information, which is processed by the analysis model along with multiple electrocardiogram variable information. User question information can include information related to menstrual symptoms. For example, user question information can be information entered by the user regarding physical changes, mental changes, and changes in menstrual pain / breast pain / headaches. In some embodiments of this disclosure, the user question and answer information may include at least one of the following: question and answer information relating to sleep disorders, question and answer information relating to depression, question and answer information relating to anxiety, and question and answer information relating to stress.

[0039] Figure 5 shows an example of user question and answer information. As shown in Figure 5, user question and answer information can be entered as categorical or numerical data based on a variety of items related to physical changes, mental changes, and changes in menstrual pain / breast pain / headaches. Among these, the user question and answer information processed by the analysis model to generate menstrual cycle prediction information can include question and answer information related to sleep disorders, depressed mood, and anxiety, which have been analyzed to have a high correlation with menstrual cycle prediction. However, it is not limited to this, and user question and answer information can include various information about menstrual symptoms obtained from the user. In the embodiments of this disclosure, when acquiring user question and answer information corresponding to multiple electrocardiogram variable information, the processor (110) can provide a user interface that allows the input of multiple user question and answer information corresponding to the time when the multiple electrocardiogram variable information has been acquired.

[0040] As described above, the processor (110) can provide a user interface that allows user Q&A information to be entered via a user application. Generally, in order to reduce the amount of data to be processed, the analysis model generates prediction results using information acquired at several points in time, rather than information acquired over a 24-hour period. Therefore, electrocardiogram variable information and user Q&A information must be processed together with information acquired during the same period. For example, multiple electrocardiogram variable information measured this morning can be linked with user Q&A information entered this morning regarding the user's menstrual symptoms. The analysis model can then generate menstrual cycle prediction information by processing the matched multiple electrocardiogram variable information and user Q&A information together. Therefore, user Q&A information can be acquired in accordance with the cycle in which multiple electrocardiogram variable information is acquired, so that it can be processed together with multiple electrocardiogram variable information. For example, if multiple electrocardiogram variable information is acquired in the morning and afternoon each day, the processor (110) can provide a user interface that allows user Q&A information to be entered in the morning and afternoon each day. In this case, the processor (110) can provide a user interface that allows the user to input user question information in accordance with a predetermined cycle in which multiple electrocardiogram variable information is acquired. Figure 6 shows an example of a user interface in which user question information can be input in a user application provided by a user terminal (1010). In several examples, if there are two cycles each for acquiring multiple electrocardiogram variable information in the morning and afternoon, the user interface can display whether or not user question information has been entered for the morning and afternoon of each date on the calendar. When the user interface receives input to select a date for which user question information has not been entered, it can provide an input window for which user question information can be entered for that date. Referring to Figure 6, when the user interface identifies a user command to select a specific date on the calendar, it can display whether or not user question information has been completed using check marks for the morning and afternoon of that date.

[0041] In several examples, the user interface can provide a display that identifies how many of the user questions have been entered. For example, as shown in Figure 6, the user interface can display an icon for each date on the calendar indicating the number of user questions that have been completed. However, the user interface is not limited to this and can be provided in a variety of forms. Based on several embodiments of this disclosure, the processor (110) can generate menstrual cycle prediction information (30) based on biological information (10) and user question and answer information (20) using an analysis model.

[0042] The analysis model (200) can generate menstrual cycle prediction information by processing biometric information including multiple electrocardiogram variables and multiple user question and answer information. The menstrual cycle can be formed by a cycle in which the luteal phase (the period before the start of menstruation), the menstrual phase (the period during menstruation), and the follicular phase (the period after the end of menstruation) are repeated. The fertile phase can refer to the period around 14 days after menstruation, when ovulation occurs reproductively. The analysis model can generate menstrual cycle prediction information (30) that can identify the luteal phase, menstrual phase, follicular phase, and fertile phase by processing input data including biometric information and user question and answer information. The processor (110) can generate menstrual cycle prediction information (30) to produce menstrual cycle-related information. For example, the processor (110) can use the menstrual cycle prediction information (30) to provide, at an appropriate time, menstrual cycle predictions (ovulation day, menstruation day, menstrual period, fertile days, premenstrual syndrome, menopause, etc.), recommended diets, guidance information for menstrual management (e.g., predicted menstrual disorders and music therapy or exercise therapy to alleviate menstrual disorders), or information on recommended menstrual cycle-related products and services. However, it is not limited to this, and the processor (110) can use the menstrual cycle prediction information (30) to provide a variety of menstrual cycle-related information.

[0043] Based on several embodiments of this disclosure, the analysis model (200) may include an ensemble learning model that uses a combination of multiple predictor variables, including at least a portion of multiple electrocardiogram variable information and user question and answer information. To explain in more detail, since the biometric information (10) containing multiple electrocardiogram variables and the user question and answer information (20) are multiple predictor variables as described above, the analysis model needs to be implemented with an appropriate algorithm that can process multiple predictor variables as input. For example, the analysis model (200) can be an ensemble learning model that can derive more accurate predictions by integrally processing the prediction results of multiple submodels (210) with a predictive information decision module (220). In several examples, the ensemble learning model can be a model that uses voting, bagging, or boosting algorithms that use multiple submodels. Below, exemplary analysis models based on several embodiments of this disclosure will be described using a model implemented with a random forest algorithm, which is a type of bagging algorithm, but this disclosure is not limited thereto. Furthermore, although the following description explains an example in which the combination of predictor variables in the analysis model includes only electrocardiogram variable information from the biological information (10), the combination of predictor variables in the analysis model can also include various other biological information (10) such as respiratory rate and body temperature.

[0044] The Random Forest algorithm can be an ensemble method that improves learning performance by applying training data to multiple decision trees. For example, the analysis model (200) can include n submodels (210a to 210n) trained on n training data generated by sampling with replacement from the original training data. In this case, each submodel can be trained using a combination of predictor variables that combines only a portion of multiple predictor variables. For example, the first submodel (210a) can be a model that uses a combination of predictor variables that include RRI information, HR information, and RR information from among multiple electrocardiogram variable information. The second submodel (210b) can be a model that uses a combination of predictor variables that include RRI information, ST level information, and sleep disorder-related question and answer information from among user question and answer information from among multiple electrocardiogram variable information. The third submodel (210c) can be a model that uses a combination of predictor variables that include NN50 information from among multiple electrocardiogram variable information, and question and answer information related to sleep disorder and anxiety from among user question and answer information. Here, the combination of predictor variables used by each submodel can be either a randomly determined combination or a predetermined combination. Among the training data used to train the analysis model, the training data related to electrocardiogram (ECG) variable information can be generated by assigning labels related to the menstrual cycle to the patterns of change identified from the time-series ECG variable information. Table 1 below is a graph showing the analysis of patterns of change identified from RRI information in order to assign information related to the menstrual cycle.

[0045] [Table 1]

[0046] In several examples, the training data may include labels generated by analyzing the correlation between patterns of change identified from each of several electrocardiogram variable information and the menstrual cycle. Below, an example of an analysis model (200) generated using training data generated based on the results of an analysis of the correlation between several electrocardiogram variable information and the menstrual cycle is described based on several embodiments of the present disclosure. Below, if the analysis model (200) is an ensemble learning model, training of the analysis model (200) may mean training of individual submodels (210). Based on several embodiments of this disclosure, with respect to RRI information, the analysis model (200) can be trained to generate information that predicts the transition from the follicular phase to the luteal phase when it identifies a decreasing trend in RRI information based on the RRI information. For example, the decreasing trend in RRI information may include a decrease of approximately 0.15 to 0.40 Hz in the luteal phase compared to the follicular phase.

[0047] Based on several embodiments of this disclosure, with respect to HR information, the analysis model (200) can be trained to generate information that predicts the transition from menstruation to the follicular phase when it identifies a maintenance-decrease trend in HR information. For example, the maintenance-decrease trend in HR information may include cases where the follicular phase is close to the same value as the menstrual phase or decreases by approximately 1.36 bpm compared to the menstrual phase. Furthermore, the analysis model (200) can be trained to generate information that predicts the transition from the follicular phase to the fertile phase when it identifies an increasing trend in HR information. For example, the increasing trend in HR information may include an increase of approximately 0.61 bpm in the fertile phase compared to the follicular phase.

[0048] Furthermore, the analysis model (200) can be trained to generate information that predicts the transition to the luteal phase when it identifies the highest level trends in HR information. The highest level trends in HR information can include an increase of approximately 2.33 bpm in the luteal phase compared to ovulation, an increase of approximately 1.84 bpm in the luteal phase compared to the fertile period, and an increase of approximately 2.31 bpm in the luteal phase compared to menstruation. Based on several embodiments of this disclosure, with respect to RR information, the analytical model (200) can be trained to generate information that predicts the transition from menstruation to the follicular phase when it identifies a decreasing trend in RR information. For example, a decreasing trend in RR information may include a decrease of approximately 0.29 breath / min in the follicular phase compared to the menstrual phase.

[0049] Furthermore, the analytical model (200) can be trained to generate information predicting the transition to the fertile period if it identifies a further decreasing trend in RR information. For example, a further decreasing trend in RR information may include a decrease of approximately 0.46 breath / min during the fertile period compared to the menstrual period. Furthermore, the analysis model (200) can be trained to generate information that predicts the transition from the menstrual phase to the luteal phase when it identifies an increasing trend in RR information. The increasing trend in RR information may include cases where the luteal phase increases by approximately 0.18 breath / min compared to the menstrual phase.

[0050] Based on several embodiments of this disclosure, with respect to ST level information, the analysis model (200) can be trained to generate information that predicts the transition to the follicular phase when it identifies a trend of the maximum level of ST level information. For example, the trend of the maximum level of ST level information may include the highest value among the values ​​of ST level information. Furthermore, the analysis model (200) can be trained to generate information that predicts the transition to the luteal phase when it identifies a trend in the minimum level of ST level information. For example, the trend in the minimum level of ST level information may include the lowest value among the ST level information values.

[0051] Based on several embodiments of this disclosure, with respect to SDNN information, the analysis model (200) can be trained to generate information that predicts the transition from the menstrual phase to the follicular phase when it identifies a maintenance trend in the SDNN information. Furthermore, the analysis model (200) can be trained to generate information that predicts the transition from the follicular phase to the fertile phase when it identifies a decreasing trend in SDNN information. For example, the decreasing trend in SDNN information may include a decrease of approximately 0.04 in the fertile phase compared to the follicular phase.

[0052] Furthermore, the analysis model (200) can be trained to generate information predicting the transition to the luteal phase when it identifies the trend of the maximum decrease in SDNN information. For example, the trend of the maximum decrease in SDNN information may include the lowest value among the SDNN information values. Based on several embodiments of this disclosure, with respect to RMSSD information, the analysis model (200) can be trained to generate information predicting the transition to the luteal phase when it identifies a trend of maximum decrease in RMSSD information. For example, the trend of maximum decrease in RMSSD information may include the lowest value among the RMSSD information values.

[0053] Based on several embodiments of this disclosure, with respect to NN50 information, the analysis model (200) can be trained to generate information that predicts the transition from the follicular phase to the luteal phase when it identifies a decreasing trend in NN50 information. Based on several embodiments of this disclosure, with respect to pNN50 information, the analysis model (200) can be trained to generate information that predicts the transition from the follicular phase to the luteal phase when it identifies a decreasing trend in the pNN50 information.

[0054] Based on several embodiments of this disclosure, with respect to SDSD information, the analysis model (200) can be trained to generate information that predicts the transition from the menstrual phase to the follicular phase when it identifies a maintenance trend in the SDSD information. In several examples, the training data may further include data generated by analyzing the correlation between patterns of change identified from each user question and answer piece of information and the menstrual cycle. Below, an example of an analysis model (200) generated using training data generated based on the results of the analysis of the correlation between user question and answer information and the menstrual cycle is described based on several embodiments of the present disclosure. Below, if the analysis model (200) is an ensemble learning model, training of the analysis model (200) may mean training of the submodel (210).

[0055] Based on several embodiments of this disclosure, with respect to question-and-answer information related to sleep disorders, the analysis model (200) can be trained to generate information that predicts the transition to the luteal phase when it identifies an increasing trend in question-and-answer information related to sleep disorders. Based on several embodiments of this disclosure, with respect to question-and-answer information related to depressed mood, the analysis model (200) can be trained to generate information that predicts the transition to the luteal phase when it identifies an increasing trend in question-and-answer information related to depressed mood.

[0056] Based on several embodiments of this disclosure, with respect to question-and-answer information related to anxiety, the analysis model (200) can be trained to generate information that predicts the transition to the luteal phase when it identifies an increasing trend in question-and-answer information related to anxiety. Based on several embodiments of this disclosure, with respect to stress-related Q&A information, the analysis model (200) can be trained to generate information that predicts ovulation delay when it identifies an increasing trend in stress-related Q&A information.

[0057] Figure 7 is a diagram illustrating the predictive performance of an analytical model based on several embodiments of this disclosure. Figure 7 shows the predictive performance of the analysis model based on a combination of electrocardiogram variable information and user question information. Referring to Figure 7, it is shown that "Random Forest Model 2," which is implemented using both electrocardiogram variable information and user question information, has higher predictive performance than "Random Forest Model 1," which is implemented using only electrocardiogram variable information. Specifically, the predictive performance of "Random Forest Model 1" (test_ecg) is lower than that of "Random Forest Model 2" (test_ecg_cli). Therefore, it can be seen that the predictive performance of the analysis model in this disclosure is further improved by using both electrocardiogram variable information and user question information as predictors.

[0058] Figure 8 is another diagram illustrating the predictive performance of the analysis model based on several embodiments of this disclosure. Figure 8 shows the predictive performance of combinations of sleep problem variables (e.g., Q&A information related to sleep disorders) and mental health variables (e.g., Q&A information related to depressed mood, Q&A information related to anxiety, and Q&A information related to stress) from user Q&A information. Referring to Figure 8, the predictive performance result (RandomForest-AUC1) using only sleep problem variables from user Q&A information together with electrocardiogram variable information is lower than the predictive performance result (RandomForest-AUC2) using both sleep problem variables and mental health variables from user Q&A information together with electrocardiogram variable information. Therefore, it can be seen that the predictive performance of the analysis model disclosed in this disclosure can be further improved by using both sleep problem variables and mental health variables as predictors in the user Q&A information.

[0059] Figure 9 is a flowchart of a method for providing menstrual-related information based on several embodiments of the present disclosure. Based on several embodiments of this disclosure, a method for providing menstrual-related information may include a step (s100) of acquiring biological information including a predetermined set of electrocardiogram variable information. Here, the set of electrocardiogram variable information may include time-series data.

[0060] Based on several embodiments of this disclosure, a method for providing menstrual-related information may include a step (s200) of acquiring user question and answer information corresponding to multiple electrocardiogram variable information. As an alternative, the step of acquiring user question and answer information corresponding to multiple electrocardiogram variable information (s200) may include a step of providing a user interface that indicates whether or not user question and answer information corresponding to the acquisition of multiple electrocardiogram variable information has been entered.

[0061] Based on several embodiments of this disclosure, a method for providing menstrual-related information may include a step (s300) in which an analytical model generates menstrual cycle prediction information based on biological information and user question and answer information. The steps outlined above for providing menstrual-related information are merely illustrative; some steps may be omitted, and others may be added. Furthermore, the steps can be performed in any order.

[0062] Figure 9 is a schematic diagram showing a network function based on several embodiments of this disclosure. Throughout this specification, the terms network model, computation model, neural network, network function, and neural network can be used interchangeably. A neural network can be composed of a set of interconnected computational units, generally called nodes. Such nodes may also be referred to as neurons. A neural network consists of at least one node. The nodes (or neurons) that make up a neural network can be interconnected by one or more links.

[0063] In a neural network, one or more nodes connected by links can, relatively speaking, be in an input-output node relationship. The concepts of input and output nodes are relative; any node that is an output node to one node can be an input node to another node, and vice versa. As mentioned above, the relationship between input and output nodes can be established around links. One input node can be connected to one or more output nodes via links, and vice versa.

[0064] In a relationship between input and output nodes connected via a single link, the output node's data can be determined based on the data input to the input node. In this case, the link connecting the input and output nodes can have weights. These weights can be variable, but they can be adjusted according to the user or algorithm to perform the function required by the neural network. For example, if one or more input nodes are interconnected to one output node by their respective links, the output node can determine its value based on the values ​​input to the input nodes connected to it and the weights set for the links corresponding to each input node.

[0065] As mentioned above, a neural network consists of one or more nodes interconnected via one or more links, forming an input-output node relationship within the network. In a neural network, the characteristics of the network can be determined by the number of nodes and links, the correlation between nodes and links, and the weight values ​​assigned to each link. For example, if there are two neural networks with the same number of nodes and links but different link weight values, these two neural networks can be recognized as distinct.

[0066] A neural network can consist of a set of one or more nodes. A subset of nodes constituting a neural network can form a layer. Some of the nodes constituting a neural network can form a layer based on their distance from a first input node. For example, a set of nodes that are n in distance from a first input node can form an n-th layer. The distance from the first input node can be defined based on the minimum number of links that must be traversed to reach that node from the first input node. However, this definition of a layer is arbitrary for the sake of explanation, and the position of a layer in a neural network can be defined in a way different from the above explanation. For example, the layer of nodes can be defined based on their distance from the final output node.

[0067] The first input node can refer to one or more nodes in a neural network that receive data directly without going through links in relation to other nodes. Alternatively, it can refer to a node in a neural network that does not have other input nodes connected via links in relation to other nodes based on links. Similarly, the final output node can refer to one or more nodes in a neural network that do not have an output node in relation to other nodes. Furthermore, a hidden node can refer to a node that is neither a first input node nor a final output node, but is part of the neural network.

[0068] In one embodiment of the present disclosure, the neural network may be such that the number of nodes in the input layer is equal to the number of nodes in the output layer, and the number of nodes decreases once before increasing again as one progresses from the input layer to the hidden layer. In another embodiment of the present disclosure, the neural network may be such that the number of nodes in the input layer is less than the number of nodes in the output layer, and the number of nodes decreases as one progresses from the input layer to the hidden layer. Furthermore, in another embodiment of the present disclosure, the neural network may be such that the number of nodes in the input layer is greater than the number of nodes in the output layer, and the number of nodes increases as one progresses from the input layer to the hidden layer. In another embodiment of the present disclosure, the neural network may be a combination of the neural networks described above.

[0069] A deep neural network (DNN) can refer to a neural network that includes multiple hidden layers in addition to the input and output layers. By using deep neural networks, it is possible to grasp the latent structures of data. In other words, it is possible to grasp the latent structures of photographs, texts, videos, audio, and music (for example, what is depicted in a photograph, what is the content and emotion of a text, what is the content and emotion of an audio, etc.). Deep neural networks can include convolutional neural networks (CNNs), recurrent neural networks (RNNs), autoencoders, Generative Adversarial Networks (GANs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), Q networks, U networks, Siam networks, Generative Adversarial Networks (GANs), and transformers. The deep neural networks mentioned above are merely examples, and this disclosure is not limited to them.

[0070] Neural networks can be trained using at least one of the following methods: supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Learning a neural network can be the process of applying knowledge to the neural network to enable it to perform specific actions.

[0071] Neural networks can be trained to minimize the error in their output. During neural network training, training data is repeatedly input into the network, the network's output and target error for the training data are calculated, and the error is backpropagated from the output layer to the input layer to update the weights of each node in the neural network, in order to reduce the error. In supervised learning, training data with the correct answer labeled is used (i.e., labeled training data), while in unsupervised learning, training data without the correct answer labeled can be used. For example, in supervised learning for data classification, the training data could be data with each data point labeled with a category. The labeled training data is input into the neural network, and the error can be calculated by comparing the neural network's output (category) with the labels of the training data. As another example, in unsupervised learning for data classification, the error can be calculated by comparing the input training data with the output of the neural network. The calculated error is backpropagated in the neural network in the reverse direction (i.e., from the output layer to the input layer), and through backpropagation, the connection weights of each node in each layer of the neural network can be updated. The amount of change in the connection weights of each node that are updated can be determined by the learning rate. The calculation of the neural network on the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied in different ways depending on the number of iterations of the neural network's learning cycle. For example, in the early stages of learning the neural network, a high learning rate can be used to increase efficiency by enabling the neural network to quickly achieve a certain level of performance, while in the later stages of learning, a low learning rate can be used to improve accuracy.

[0072] In neural networks, various data augmentation methods can be used to increase the amount of training data available for learning. For example, data augmentation can be performed through 2D transformations such as rotation, scaling, shearing, reflection, and translation. Furthermore, data augmentation can be achieved by utilizing noise insertion, color and brightness changes, and other techniques.

[0073] In neural network training, training data is often a subset of real-world data (i.e., data that the trained neural network intends to process). As a result, there can be training cycles where errors related to training data decrease, but errors related to real-world data increase. Overfitting is a phenomenon where errors increase on real-world data due to excessive training on the training data. Overfitting can cause errors in machine learning algorithms. Various optimization methods can be used to prevent such overfitting. Methods that can be applied to prevent overfitting include increasing the amount of training data, regularization, dropout (deactivating some of the network nodes during the training process), and the use of a batch normalization layer.

[0074] Figure 11 is a block diagram of a computing device based on several embodiments of the present disclosure. Figure 11 is a simplified and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure can be realized.

[0075] While it has been stated that this disclosure can generally be embodied by computing devices, those skilled in the art will understand that this disclosure can also be embodied in combination with computer executable instructions and / or other program modules that can be run on one or more computers, and / or as a combination of hardware and software. Generally, modules as defined herein include routines, programs, components, data structures, and so on, that perform a specific task or implement a specific abstract data type. Furthermore, those skilled in the art will understand that the methods disclosed herein can be implemented in configurations of other computer systems, including single-processor or multi-processor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor boards, or programmable consumer electronics, and so on (each of which can operate in conjunction with one or more associated devices).

[0076] The embodiments described herein can further be implemented in a distributed computing environment in which a task is performed by remote processing units connected via a communication network. In a distributed computing environment, program modules can reside in both local and remote memory storage devices. Computers include a variety of computer-readable media. Any media accessible by a computer can be computer-readable, but such computer-readable media include volatile and non-volatile media, transient and non-transitory media, and portable and non-portable media. By example, rather than by limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media include volatile and non-volatile media, transient and non-transitory media, portable and non-portable media implemented by any method or technique for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, DVD (digital video disk) or other optical disk storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other media that can be accessed by a computer and used to store information.

[0077] Computer-readable transmission media typically include all information transmission media that implement computer-readable instructions, data structures, program modules, or other data on a modulated data signal, such as a carrier wave or other transport mechanism. The term modulated data signal means a signal in which one or more of its characteristics have been set or modified to encode information within the signal. By example, rather than by limitation, computer-readable transmission media include wired media such as wired networks or direct-wired connections, and wireless media such as acoustic, RF, infrared, and other wireless media. Any combination of any of the aforementioned media is also included in the scope of computer-readable transmission media.

[0078] An exemplary environment (1100) is shown that realizes various aspects of this disclosure, including a computer (1102), the computer (1102) including a processor (1104), system memory (1106), and a system bus (1108). The system bus (1108) connects system components, including (but not limited to) system memory (1106), to the processor (1104). The processor (1104) can be any processor from a variety of commercial processors. Dual processors and other multiprocessor architectures can also be used as the processor (1104). The system bus (1108) can be one of several types of bus structures that can be further interconnected to a local bus using any of the following: a memory bus, a peripheral bus, and various commercial bus architectures. System memory (1106) includes read-only memory (ROM) (1110) and random access memory (RAM) (1112). The basic input / output system (BIOS) is stored in non-volatile memory (1110) such as ROM, EPROM, or EEPROM, and this BIOS includes basic routines that support the exchange of information between multiple components within the computer (1102) during startup, etc. RAM (1112) may also include high-speed RAM such as static RAM for caching data.

[0079] The computer (1102) also includes an internal hard disk drive (HDD) (1114) (e.g., EIDE, SATA)—this internal hard disk drive (1114) can also be configured for external use in a suitable chassis (not shown), a magnetic floppy disk drive (FDD) (1116) (e.g., for reading from and writing to a portable diskette (1118)), and an optical disk drive (1120) (e.g., for reading CD-ROM disks (1122) or for reading from and writing to other high-capacity optical media such as DVDs). The hard disk drive (1114), magnetic disk drive (1116), and optical disk drive (1120) can be connected to the system bus (1108) by a hard disk drive interface (1124), a magnetic disk drive interface (1126), and an optical drive interface (1128), respectively. The interface (1124) for implementing external drives includes, for example, at least one or both of the following: USB (Universal Serial Bus) or IEEE 1394 interface technology. These drives and computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and so on. In the case of a computer (1102), the drives and media correspond to storing any data in a suitable digital format. While the above description of computer-readable storage media refers to HDDs, portable magnetic disks, and portable optical media such as CDs or DVDs, those skilled in the art will understand that other types of computer-readable storage media, such as zip drives, magnetic cassettes, flash memory cards, cartridges, and so on, can also be used in exemplary operating environments, and that any of these media may contain computer-executable instructions for performing the methods of the present disclosure.

[0080] Numerous program modules, including an operating system (1130), one or more application programs (1132), other program modules (1134), and program data (1136), can be stored in the drive and RAM (1112). All or part of the operating system, applications, modules, and / or data can also be cached in RAM (1112). It will be understood that this disclosure can be implemented by various commercially available operating systems or combinations of operating systems. The user can input commands and information to the computer (1102) through one or more wired or wireless input devices, such as a keyboard (1138) and a pointing device such as a mouse (1140). Other input devices (not shown in the diagram) may include a microphone, IR remote control, joystick, gamepad, stylus pen, touchscreen, and so on. These and other input devices are often connected to the processing unit (1104) through an input device interface (1142) connected to the system bus (1108), but they can also be connected through other interfaces such as parallel ports, IEEE1394 serial ports, game ports, USB ports, IR interfaces, and so on.

[0081] A monitor (1144) or other type of display device is also connected to the system bus (1108) through an interface such as a video adapter (1146). In addition to the monitor (1144), the computer generally includes other peripheral output devices such as speakers, printers, and so on (not shown in the illustration). A computer (1102) can operate in a networked environment by utilizing logical connections to one or more remote computers (1148), such as multiple remote computers (1148), via wired and / or wireless communication. The multiple remote computers (1148) can be workstations, server computers, routers, personal computers, portable computers, microprocessor-based entertainment devices, peer devices, or other typical network nodes, and generally include many or all of the components described for a computer (1102), although for simplification only a memory storage device (1150) is illustrated. The illustrated logical connections include wired and wireless connections in a short-range network (LAN) (1152) and / or a larger network, such as a long-range network (WAN) (1154). Such LAN and WAN networking environments are common in offices and companies, facilitating enterprise-wide computer networks such as intranets, all of which can connect to global computer networks, such as the Internet.

[0082] When used in a LAN networking environment, the computer (1102) connects to the local network (1152) via a wired and / or wireless network interface, or via an adapter (1156). The adapter (1156) facilitates wired or wireless communication to the LAN (1152), which also includes a wireless access point installed therein to communicate with the wireless adapter (1156). When used in a WAN networking environment, the computer (1102) may include a modem (1158), connect to a communication server on the WAN (1154), or have other means of establishing communication through the WAN (1154), such as via the Internet. The modem (1158), which can be internal or external, and wired or wireless, connects to the system bus (1108) via a serial port interface (1142). In a networked environment, a program module or part thereof described for a computer (1102) can be stored in a remote memory / storage device (1150). While the illustrated network connection is illustrative, it is readily apparent that other means of establishing communication links between multiple computers may be used. The computer (1102) operates to communicate with any wireless device or unit that is arranged and operates wirelessly, such as a printer, scanner, desktop and / or portable computer, PDA (portable data assistant), communication satellite, any equipment or location relating to a wirelessly discoverable tag, and a telephone. This includes at least Wi-Fi and Bluetooth® wireless technologies. Thus, the communication may be a predefined structure like a conventional network, or simply ad hoc communication between at least two devices.

[0083] Wi-Fi (Wireless Fidelity) enables internet access and other connectivity without a wired connection. Wi-Fi is a wireless technology, similar to cell phones, that allows devices like computers to send and receive data indoors and outdoors, i.e., anywhere within the range of a base station. Wi-Fi networks use IEEE 802.11 (a, b, g, etc.) wireless technology to provide secure, reliable, and high-speed wireless connectivity. Wi-Fi can be used to connect computers to each other, to the internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in unlicensed 2.4 and 5 GHz wireless bands at data rates such as 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band).

[0084] A person with ordinary skill in the art of this disclosure will understand that information and signals can be represented using any variety of different techniques and methods. For example, the data, instructions, commands, information, signals, bits, symbols and chips referenced in the foregoing description can be represented by voltage, current, electromagnetic waves, magnetic fields, etc. or particles, optical fields, etc. or particles, or any combination thereof. A person with ordinary skill in the art of this disclosure will understand that the various exemplary logic blocks, modules, processors, means, circuits, and algorithmic stages described herein can be implemented by electronic hardware, various forms of programs or design code (referred to herein for convenience as “software”), or a combination of all of these. To illustrate this interoperability of hardware and software, various exemplary components, blocks, modules, circuits, and stages have been generally described above with respect to their functions. Whether such functions are implemented in hardware or software depends on the design constraints imposed on a particular application and the overall system. A person with ordinary skill in the art of this disclosure can implement the functions described in various ways for individual specific applications, but such decisions should not be construed as departing from the scope of this disclosure.

[0085] The various embodiments described herein can be realized by methods, apparatus, or manufactured articles using standard programming and / or engineering techniques. The term “manufactured article” includes computer programs, carriers, or media accessible from any computer-readable device. For example, computer-readable storage media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). The various storage media described herein also include one or more devices and / or other machine-readable media for storing information. It should be understood that the specific order or hierarchical structure of the multiple stages in the presented process is an example of an exemplary approach. It should be understood that, based on design priorities, the specific order or hierarchical structure of the stages in the process can be rearranged within the scope of this disclosure. The appended method claims provide a variety of stage elements in sample order, but are not limited to the specific order or hierarchical structure shown.

[0086] The descriptions relating to the embodiments provided herein are provided so that any person with ordinary skill in the art of the present disclosure may utilize or implement the present disclosure. Various variations of such embodiments are readily apparent to a person with ordinary skill in the art of the present disclosure, and the general principles defined herein can be applied to other embodiments without departing from the scope of the present disclosure. Accordingly, the present disclosure is not limited by the embodiments provided herein and should be interpreted in the broadest sense consistent with the principles and novel features provided herein.

Claims

1. A method for providing menstrual-related information, performed by a computing device, A step of acquiring biological information including a predetermined set of electrocardiogram variable information – the set of electrocardiogram variable information includes time-series data; A step of acquiring user question and answer information corresponding to the aforementioned plurality of electrocardiogram variable information; and A step in which an analysis model generates menstrual cycle prediction information based on the aforementioned biological information and the aforementioned user question and answer information; including, method.

2. In the method according to claim 1, The aforementioned multiple electrocardiogram variable information includes RRI (RR Intervals) information, HR (Heart Rate) information, RR (Respiration Rate) information, ST level information, SDNN (standard deviation of all NN intervals) information, RMSSD (square root of the mean of the sum of the squares of differences between adjusting NN intervals) information, and NN50 (number of NN intervals differing by more than) The information includes at least one of the following: 50ms information, pNN50 (ratio of NN50) information, and SDSD (standard deviation of differences between adjust NN intermediates) information. method.

3. In the method according to claim 1 or claim 2, The user Q&A information includes at least one of the following: Q&A information relating to sleep disorders, Q&A information relating to depressed mood, Q&A information relating to anxiety, or Q&A information relating to stress. method.

4. In the method of claim 2, The analysis model includes an ensemble learning model that uses a combination of multiple predictor variables, each including at least a portion of the multiple electrocardiogram variable information and the user question and answer information. method.

5. In the method according to claim 1 or claim 4, The aforementioned analysis model is, Based on RRI information, if a decreasing trend in RRI is identified, the system is trained to generate information that predicts the transition from the follicular phase to the luteal phase. method.

6. In the method according to claim 1 or claim 4, The aforementioned analysis model is, When a trend of maintenance or decrease in HR information is identified, the system is trained to generate information that predicts the transition from the menstrual phase to the follicular phase. When an increasing trend in the aforementioned HR information is identified, the system is learned to generate information that predicts the transition from the follicular phase to the fertile phase, and When the highest level trend in the aforementioned HR information is identified, the system is trained to generate information that predicts the transition to the luteal phase. method.

7. In the method according to claim 1 or claim 4, The aforementioned analysis model is, When a decreasing trend in RR information is identified, the system is trained to generate information that predicts the transition from the menstrual phase to the follicular phase. When a further decreasing trend in the aforementioned RR information is identified, the system is learned to generate information that predicts the transition to the fertile period, and When an increasing trend in the aforementioned RR information is identified, the system is trained to generate information that predicts the transition to the luteal phase. method.

8. In the method according to claim 1 or claim 4, The aforementioned analysis model is, When the trend at the highest level of ST level information is identified, it is learned to generate information that predicts the transition to the follicular phase, and When the trend of the minimum level of the aforementioned ST level information is identified, the system is trained to generate information that predicts the transition to the luteal phase. method.

9. In the method according to claim 1 or claim 4, The aforementioned analysis model is, When a maintenance trend is identified in SDNN information, it is learned to generate information that predicts the transition from the menstrual phase to the follicular phase. When a decreasing trend in the aforementioned SDNN information is identified, it is learned to generate information that predicts the transition from the follicular phase to the fertile phase, and When the maximum decreasing trend of the aforementioned SDNN information is identified, the system is trained to generate information that predicts the transition to the luteal phase. method.

10. In the method according to claim 1 or claim 4, The aforementioned analysis model is, When the maximum decreasing trend in RMSSD information is identified, the system is trained to generate information that predicts the transition to the luteal phase. method.

11. In the method according to claim 1 or claim 4, The aforementioned analysis model is, When a decreasing trend in NN50 information is identified, the system is trained to generate information that predicts the transition from the follicular phase to the luteal phase. method.

12. In the method according to claim 1 or claim 4, The aforementioned analysis model is, When a decreasing trend in pNN50 information is identified, the system is trained to generate information that predicts the transition from the follicular phase to the luteal phase. method.

13. In the method according to claim 1 or claim 4, The aforementioned analysis model is, When a maintenance trend in SDSD information is identified, the system is trained to generate information that predicts the transition from the menstrual phase to the follicular phase. method.

14. In the method according to claim 1 or claim 4, The user Q&A information includes Q&A information related to sleep disorders, The aforementioned analysis model is, When the system identifies an increasing trend in the degree to which individuals perceive sleep disorders in the aforementioned question-and-answer information related to sleep disorders, it is trained to generate information that predicts the transition to the luteal phase. method.

15. In the method according to claim 1 or claim 4, The aforementioned user Q&A information includes Q&A information related to depression, The aforementioned analysis model is, If the system identifies an increasing trend in the degree to which the user is aware of their depressed mood in the aforementioned question-and-answer information related to depressed mood, it will be trained to generate information that predicts the transition to the luteal phase. method.

16. In the method according to claim 1 or claim 4, The user Q&A information includes Q&A information related to feelings of anxiety, The aforementioned analysis model is, When the system identifies an increasing trend in the degree of anxiety perceived in the aforementioned question-and-answer information, it is trained to generate information that predicts the transition to the luteal phase. method.

17. In the method according to claim 1 or claim 4, The user Q&A information includes Q&A information related to stress, The aforementioned analysis model is, When the system identifies an increasing trend in the stress-related Q&A information, it is trained to generate information that predicts ovulation delay. method.

18. In the method according to claim 1 or claim 4, The steps to obtain user question information corresponding to multiple ECG variable information are: A step in which a user interface is provided that allows the user to input the aforementioned user question and answer information, corresponding to the point in time when multiple electrocardiogram variable information is acquired; including, method.

19. In the method according to claim 18, The steps to obtain user question information corresponding to multiple ECG variable information are: A step of providing a user interface that indicates whether or not user question and answer information corresponding to the point in time when multiple electrocardiogram variable information is acquired has been entered; including, method.

20. In the method according to claim 1, The aforementioned multiple electrocardiogram variable information includes RRI information, HR information, RR information, ST level information, SDNN information, RMSSD information, NN50 information, pNN50 information, and SDSD information. method.

21. In the method of claim 20, The user Q&A information includes Q&A information related to sleep disorders, Q&A information related to depressed mood, Q&A information related to anxiety, and Q&A information related to stress. method.

22. In the method according to claim 4, The aforementioned analysis model uses the random forest algorithm. method.

23. A computer program stored on a computer-readable medium, the computer program includes instructions for causing one or more processors to perform a method for providing menstrual-related information, the method being: A step of acquiring biological information including a predetermined set of electrocardiogram variable information – the set of electrocardiogram variable information includes time-series data; A step of acquiring user question and answer information corresponding to the aforementioned plurality of electrocardiogram variable information; and The analysis model includes the step of generating menstrual cycle prediction information based on the aforementioned biological information and the aforementioned user question and answer information; A computer program stored on a computer-readable medium.

24. A computing device that performs a method for providing menstrual-related information, wherein the computing device: Memory containing components that can be executed by a computer; A processor that runs the following computer-executable components stored in memory; The aforementioned processor, Obtain biological information including a predetermined set of electrocardiogram variables—these electrocardiogram variables include time-series data; The user question and answer information corresponding to the aforementioned multiple electrocardiogram variable information is obtained, and The analysis model generates menstrual cycle prediction information based on the aforementioned biological information and user question and answer information. Computing device.

Images