Method and device for providing menstruation-related information

Abstract

According to some embodiments of the present invention, a menstruation-related information providing method performed by a computing device is disclosed. The method comprises the following steps: acquiring biological information containing a plurality of pieces of preset electrocardiogram variable information, wherein the plurality of pieces of preset electrocardiogram variable information comprise time sequence data; acquiring user question and answer information corresponding to the multiple pieces of electrocardiogram variable information; and generating menstrual cycle prediction information based on the biological information and the user question and answer information through an analysis model.

Description

Technical Field

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

[0002] A common method for predicting the menstrual cycle is to predict the ovulation date (menstrual period) only using a woman's body temperature, and its measurement accuracy is not high. Therefore, due to inaccurate prediction results, there are problems such as inability to provide accurate menstrual cycle-related information such as fertile period information, menstrual disorder prevention and alleviation information.

[0003] Prior Art Documents

[0004] Patent Document 1: KR 10-2020-0026340A Summary of the Invention

[0005] Technical Problem

[0006] The present invention is proposed in response to the foregoing background art, and its object is to provide a method and apparatus for providing menstrual cycle-related information using biological information including a plurality of electrocardiogram variable information and user question-and-answer information.

[0007] Technical Solution

[0008] Disclosed is a method for providing menstrual cycle-related information executed by a computing device for implementing the above problem. The method may include the following steps: obtaining biological information including a predetermined plurality of electrocardiogram variable information, the plurality of electrocardiogram variable information including time series data; obtaining user question-and-answer information corresponding to the plurality of electrocardiogram variable information; and generating menstrual cycle prediction information based on the biological information and the user question-and-answer information through an analysis model.

[0009] Alternatively, the plurality of electrocardiogram variable information may include at least one of RR interval information, heart rate (HR) information, respiration rate information, ST segment level information, standard deviation of all NN intervals (SDNN) information, root mean square of successive differences between adjacent NN intervals (RMSSD) information, number of NN intervals differing by more than 50 ms information, ratio of NN50 (pNN50) information, and standard deviation of differences between adjacent NN intervals information.

[0010] Alternatively, the user Q&A information may include at least one of sleep disorder Q&A information, depression feeling Q&A information, anxiety feeling Q&A information, or stress Q&A information.

[0011] Alternatively, the analysis model may include an ensemble learning model that utilizes a combination of multiple predictors each including at least a portion of the plurality of electrocardiogram variable information and the user Q&A information.

[0012] Alternatively, the analysis model may be trained to generate information for predicting the transition from the follicular phase to the luteal phase when a downward trend of the RR interval information is identified based on the RR interval information.

[0013] Alternatively, the analysis model may be trained to: generate information for predicting the transition from the menstrual phase to the follicular phase when a sustained downward trend of the heart rate information is identified; generate information for predicting the transition from the follicular phase to the fertile phase when an upward trend of the heart rate information is identified; and generate information for predicting the transition to the luteal phase when a highest level trend of the heart rate information is identified.

[0014] Alternatively, the analysis model can be trained to generate information for predicting the transition from the menstrual phase to the follicular phase when a downward trend in the respiratory rate information is recognized; generate information for predicting the transition to the fertile period when a further downward trend in the respiratory rate information is recognized; and generate information for predicting the transition to the luteal phase when an upward trend in the respiratory rate information is recognized.

[0015] Alternatively, the analysis model can be trained to generate information for predicting the transition to the follicular phase when a highest-level trend in the ST segment level information is recognized; and generate information for predicting the transition to the luteal phase when a lowest-level trend in the ST segment level information is recognized.

[0016] Alternatively, the analysis model can be trained to generate information for predicting the transition from the menstrual phase to the follicular phase when a maintaining trend in the standard deviation information of all NN intervals is recognized; generate information for predicting the transition from the follicular phase to the fertile period when a downward trend in the standard deviation information of all NN intervals is recognized; and generate information for predicting the transition to the luteal phase when a maximum downward trend in the standard deviation information of all NN intervals is recognized.

[0017] Alternatively, the analysis model can be trained to generate information for predicting the transition to the luteal phase when a maximum downward trend in the root mean square of the differences between adjacent NN intervals information is recognized.

[0018] Alternatively, the analysis model can be trained to generate information for predicting the transition from the follicular phase to the luteal phase when a downward trend in the quantity information of NN intervals with a difference greater than 50 MS is recognized.

[0019] Alternatively, the analysis model can be trained to generate information for predicting the transition from the follicular phase to the luteal phase when a downward trend in the proportion information of the quantity of NN intervals with a difference greater than 50 MS is recognized.

[0020] Alternatively, the analysis model can be trained to generate information for predicting the transition from the menstrual phase to the follicular phase when a maintaining trend in the standard deviation information of the differences between adjacent NN intervals is recognized.

[0021] Alternatively, the user Q&A information can include sleep disorder Q&A information, and the analysis model can be trained to generate information for predicting the transition to the luteal phase when an upward trend in the sleep disorder Q&A information is recognized.

[0022] Alternatively, the user Q&A information may include depression-sensation Q&A information, and the analysis model may be trained to generate information for predicting the transition to the luteal phase when an upward trend in the depression-sensation Q&A information is recognized.

[0023] Alternatively, the user Q&A information may include anxiety-sensation Q&A information, and the analysis model may be trained to generate information for predicting the transition to the luteal phase when an upward trend in the anxiety-sensation Q&A information is recognized.

[0024] Alternatively, the user Q&A information may include stress Q&A information, and the analysis model may be trained to generate information for predicting ovulation delay when an upward trend in the stress Q&A information is recognized.

[0025] Alternatively, the step of obtaining user Q&A information corresponding to a plurality of electrocardiogram variable information may include the step of providing a user interface capable of inputting the user Q&A information at the acquisition time points corresponding to the plurality of electrocardiogram variable information.

[0026] Alternatively, the step of obtaining user Q&A information corresponding to a plurality of electrocardiogram variable information may include the step of providing a user interface for displaying whether the user Q&A information corresponding to the acquisition time points of the plurality of electrocardiogram variable information is input.

[0027] Alternatively, the plurality of electrocardiogram variable information may include RR interval information, heart rate information, respiratory rate information, ST segment level information, standard deviation information of all NN intervals, root mean square difference information of adjacent NN interphase differences, number information of NN intervals with a difference greater than 50 MS, ratio information of the number of NN intervals with a difference greater than 50 MS, and standard deviation information of the differences between adjacent NN intervals.

[0028] Alternatively, the user Q&A information may include sleep disorder Q&A information, depression-sensation Q&A information, anxiety-sensation Q&A information, and stress Q&A information.

[0029] Alternatively, the analysis model may use a random forest algorithm.

[0030] Disclosed is a computer program stored in a computer-readable medium for implementing the above-described problem. The computer program may include a plurality of instructions for causing one or more processors to execute a menstrual cycle-related information providing method, and the method may include the following steps: obtaining biological information including a predetermined plurality of electrocardiogram variable information, the plurality of electrocardiogram variable information including time series data; obtaining user Q&A information corresponding to the plurality of electrocardiogram variable information; and generating menstrual cycle prediction information based on the biological information and the plurality of user Q&A information through an analysis model.

[0031] Disclosed is a computing device that executes a menstrual cycle-related information providing method for implementing the problem described above. The computing device may include: a memory including a plurality of computer-executable components; and a processor for executing the following plurality of computer-executable components stored in the memory. The processor may perform the following steps: obtaining biological information including a predetermined plurality of electrocardiogram variable information, the plurality of electrocardiogram variable information including time-series data; obtaining user question-and-answer information corresponding to the plurality of electrocardiogram variable information; and generating menstrual cycle prediction information based on the biological information and the plurality of user question-and-answer information through an analysis model.

[0032] Effects of the Invention

[0033] The present invention can provide a method and apparatus for providing menstrual cycle-related information using biological information including a plurality of electrocardiogram variable information and user question-and-answer information. Brief Description of the Drawings

[0034] Figure 1 A diagram showing a menstrual cycle-related information providing system according to some embodiments of the present invention.

[0035] Figure 2 A block diagram of a computing device for executing a menstrual cycle-related information providing method according to some embodiments of the present invention.

[0036] Figure 3 A schematic diagram for explaining a menstrual cycle-related information providing method according to some embodiments of the present invention.

[0037] Figure 4 A diagram for explaining electrocardiogram variable information according to some embodiments of the present invention.

[0038] Figure 5 A diagram for explaining user question-and-answer information according to some embodiments of the present invention.

[0039] Figure 6 An exemplary user application for obtaining user question-and-answer information according to some embodiments of the present invention.

[0040] Figure 7 A diagram for explaining the prediction performance of an analysis model according to some embodiments of the present invention.

[0041] Figure 8 Another diagram for explaining the prediction performance of an analysis model according to some embodiments of the present invention.

[0042] Figure 9 A flowchart of a menstrual cycle-related information providing method according to some embodiments of the present invention.

[0043] Figure 10 A schematic diagram showing a network function according to some embodiments of the present invention.

[0044] Figure 11 Block diagram of a computing device according to some embodiments of the present invention.

[0045] Figure 12 A chart showing the change patterns identified in the analyzed RR interval information for assigning labels related to the menstrual cycle. Detailed Description

[0046] Hereinafter, various embodiments will be described with reference to the accompanying drawings. In this specification, various descriptions are presented for understanding the present invention. However, it is obvious that these embodiments can be implemented even without these specific descriptions.

[0047] As used in this specification, terms such as "component", "module", "system", etc. refer to computer-related entities, hardware, firmware, software, and combinations of software and hardware or the operation of software. For example, a component can be a procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer, but is not limited thereto. For example, an application program running on a computing device and the computing device can both be components. At least one component can reside in a processor and / or an execution thread. A component can be localized in one computer. A component can be distributed among two or more computers. And these components can be executed by various computer-readable media storing various data structures therein. For example, a component can communicate through local and / or remote processing according to a signal having at least one data packet (e.g., data and / or signals from at least one component interacting with other components in a local system or a distributed system and transmitted between other systems via a network such as the Internet).

[0048] In addition, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless otherwise clearly stated or clearly indicated in the context, "X uses A or B" is intended to represent one of the natural inclusive alternatives. That is, in the case where X uses A; X uses B; or X uses A and B, any of these cases can apply to "X uses A or B". And the term "and / or" used in this specification refers to all possible combinations of one or more of the listed related items.

[0049] Also, the terms "comprise" and / or "include" should be understood to mean the presence of the feature and / or structural element. However, the terms "comprise" and / or "include" should be understood not to exclude the presence or addition of one or more other features, structural elements, and / or their combinations. And unless otherwise clearly stated or clearly indicated as singular in the context, singular expressions in this specification and the claims should generally be interpreted to mean "one or more".

[0050] Moreover, the term "at least one of A or B" should be construed to mean cases that "include only A", "include only B", and "consist of A and B".

[0051] Those skilled in the art should also recognize that the various exemplary logical blocks, structures, modules, circuits, means, logics, and algorithmic steps described in connection with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the various exemplary components, blocks, structures, means, logics, modules, circuits, and steps have been generally described above in terms of their functionality. Whether these functions are implemented in hardware or software depends on the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functions in various ways for each particular application. However, the determination of these implementations should not be construed as exceeding the scope of the present disclosure.

[0052] The description of the proposed embodiments is for those of ordinary skill in the art to which the present invention pertains to be able to use or practice the present invention. Various modifications to these embodiments will be readily apparent to those of ordinary skill in the art to which the present invention pertains. The general principles defined herein can be applied to other embodiments without departing from the scope of the present invention. Therefore, the present invention is not limited to the embodiments presented herein. The present invention should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

[0053] The present invention can provide a method for providing menstrual cycle-related information with high accuracy by using electrocardiogram variable information and user questionnaire information, rather than being limited to the temperature, which has been mainly used in the past as a variable for predicting the menstrual cycle. Specifically, the present invention can provide menstrual cycle-related information by identifying a temporal change pattern in the electrocardiogram variable information, where the temporal change pattern is temporal data continuously collected within a specified time. Moreover, the present invention can provide menstrual cycle-related information with higher accuracy by jointly using the electrocardiogram variable information and the user questionnaire information obtained from the user in the form of a questionnaire.

[0054] Figure 1 A diagram of a menstrual cycle-related information providing system 1000 showing some embodiments of the present invention.

[0055] Referring to Figure 1 , some embodiments of the menstrual cycle-related information providing system 1000 of the present invention may include a user terminal 1010, a bioinformation sensing device 1020, and a server 1030. Figure 1The configuration of the menstrual cycle-related information providing system 1000 shown is merely an example briefly illustrated. In some embodiments of the present invention, the menstrual cycle-related information providing system 1000 may include other additional configurations, or may be composed of only partially disclosed configurations to form the menstrual cycle-related information providing system 1000.

[0056] Communication between various entities included in the menstrual cycle-related information providing system 1000 may be performed through a wired / wireless network 1040. Among them, the wired / wireless network 1040 may refer to a connection structure through which each node can exchange information with each other, for example, between multiple terminals and a server. Some examples of such a network 1040 may include a local area network (LAN), a wide area network (WAN), the Internet (WWW), a wired or wireless data communication network, a telephone network, a wired or wireless television communication network, etc. Some examples of wireless data communication networks include, but are not limited to, 3G, 4G, 5G, the 3rd Generation Partnership Project (3GPP), the 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), a wireless network (Wi-Fi), the Internet, a local area network (LAN), a wireless local area network (Wireless LAN), a wide area network (WAN), a personal area network (PAN), radio frequency (RF), a Bluetooth network, a near-field communication (NFC) network, a satellite broadcast network, an analog broadcast network, a digital multimedia broadcast (DMB) network, etc.

[0057] The user terminal 1010 can be implemented as a computer that can access a remote server or terminal through a network. Among them, the user terminal 1010 can include at least one of a smartphone, a tablet personal computer, a mobile phone, a video phone, an e-book reader, a desktop personal computer, a laptop personal computer, a netbook computer, a workstation, a server, a personal digital assistant (PDA), a portable multimedia player (PMP), or a wearable device (e.g., smart glasses, a head-mounted device (HMD), electronic clothing, an electronic bracelet, an electronic necklace, an electronic accessory, a smart mirror, or a smart watch). However, this is not limited thereto, and the user terminal 1010 can be implemented as various computers.

[0058] According to some embodiments of the present invention, the user terminal 1010 can implement the menstrual-related information providing method of the present invention. For example, the user terminal 1010 can provide a user application for providing menstrual-related information. The user terminal 1010 can obtain menstrual-related user information for providing menstrual-related information through the user application. In some examples, the user terminal 1010 can operate the biometric information sensing device 1020 through the user application to obtain biometric information. In some examples, the user terminal 1010 can obtain biometric information stored in the server 1030. In some examples, the user terminal 1010 can obtain user Q&A information input through the user interface of the user application.

[0059] In some examples, the user terminal 1010 can use an analysis model implemented on the user terminal 1010 to generate menstrual-related user information. Alternatively, the user terminal 1010 can send the menstrual-related user information to the server 1030 to process the acquired data. In this case, the user terminal 1010 can receive menstrual-related information generated by processing the menstrual-related user information by using the analysis model provided by the server 1030. The user terminal 1010 can provide the received menstrual-related information to the user through the user application.

[0060] Menstruation-related information may include various information related to menstruation. For example, menstruation-related information may include predicted menstrual cycles (ovulation days, menstruation days, menstrual periods, fertile days, premenstrual syndrome, menopause, etc.), recommended diets, menstruation management guidance information (e.g., predicted menstrual disorders and music therapy and exercise therapy for relieving menstrual disorders, etc.), or recommended menstruation product and service information, etc. The types of menstruation-related information are not limited to the above examples and may include various information related to menstruation.

[0061] According to some embodiments of the present invention, the server 1030 may implement the menstruation-related information providing method of the present invention. For example, the server 1030 may use menstruation-related training data to train an analysis model. In some examples, the menstruation cycle-related training data may include various menstruation-related user information, including biological information and user Q&A information. The server 1030 may generate menstruation-related information by processing menstruation-related user information using the trained analysis model. As another example, the server 1030 may provide a user application program including the trained analysis model to the user terminal 1010. In this case, as described above, the user terminal 1010 may use the analysis model to process menstruation-related user information.

[0062] The biological information sensing device 1020 may include various devices capable of measuring biological information. For example, the biological information sensing device 1020 may be a device capable of measuring the user's body temperature, blood pressure, pulse, skin conductivity, electrocardiogram, blood oxygen saturation, and respiratory rate, etc. The biological information sensing device 1020 may send the measured biological information to the user terminal 1010 or the server 1030. The biological information sensing device 1020 may include a portable device or a fixed device. In some examples, the biological information sensing device 1020 may include a wearable device capable of measuring electrocardiogram (e.g., a patch-type Tel ECG). In some examples, the biological information sensing device 1020 can be modularly arranged in the user terminal 1010.

[0063] Hereinafter, according to some embodiments of the present invention, a computer device for implementing the menstruation-related information providing method of the present invention, the computer device being the user terminal 1010 or the server 1030.

[0064] Figure 2 It is a block diagram of a computing device for performing the menstruation-related information providing method of some embodiments of the present invention.

[0065] As Figure 2 shown, the computing device 100 may include a processor 110, a memory 130, and a network unit 120. Figure 2The configuration of the computing device 100 shown is merely a simplified illustrative example. In some embodiments of the present invention, the computing device 100 may include other configurations for executing the computing environment of the computing device 100, and only the partially disclosed configurations constitute the computing device 100.

[0066] The processor 110 of the computing device may be composed of more than one core and may include processors for data analysis and processing, and deep training, such as a central processing unit (CPU) of the computing device, a general-purpose graphics processing unit (GPGPU), a tensor processing unit (TPU), etc. The processor 110 may execute data conversion, operation, generation, etc. for providing menstruation-related information in some embodiments of the present invention by reading a computer program stored in the memory 130. For example, the processor 110 may execute multiple steps for executing the following menstruation-related information providing method. And, according to some embodiments of the present invention, the processor 110 may perform operations for neural network training using training data to execute the menstruation-related information providing method. For example, the processor 110 may use the training data to generate / train an analysis model. The processor 110 may execute calculations for neural network training, such as processing input data trained in deep learning (DL), extracting features from the input data, calculating errors, and updating the weights of the neural network using backpropagation. At least one of the central processing unit, general-purpose graphics processing unit, and tensor processing unit of the processor 110 may process operations for the menstruation-related information providing method. For example, the central processing unit and the general-purpose graphics processing unit may jointly process operations for the menstruation-related information providing method. And, in some embodiments of the present invention, the processors of multiple computing devices may be jointly used to process data conversion, operation, generation, training of network functions, and data classification using network functions for the menstruation-related information providing method. And, the computer program executed in the computing device in some embodiments of the present invention may be a program executable by the central processing unit, general-purpose graphics processing unit, and tensor processing unit.

[0067] According to some embodiments of the present invention, the memory 130 may 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 may store data generated during the execution of the menstrual-related information providing method by the processor 110. And the memory 130 may store data received from the outside during the execution of the menstrual-related information providing method by the processor 110. However, it is not limited thereto, and the memory 130 may store various information for executing the menstrual-related information providing method of some embodiments of the present invention.

[0068] According to some embodiments of the present invention, the memory 130 may include at least one storage medium such as flash memory type, hard disk type, multimedia card micro type, card memory (e.g., SD or XD memory, etc.), 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 association with a web storage that executes the storage function of the memory 130 on the internet. The description of the above memory is only an example, and the present invention is not limited thereto.

[0069] The network unit 120 of some embodiments of the present invention may use any form of known wired or wireless communication system.

[0070] The network unit 120 may send and receive information, user interfaces, etc. processed by the processor 110 by communicating with other terminals. For example, the network unit 120 may provide the user interface generated by the processor 110 to a client (e.g., a user terminal). And the network unit 120 may receive an external input of a user applied to the client and pass it to the processor 110. In this case, the processor 110 may process operations such as output, modification, change, addition, etc. of the information provided through the user interface based on the external input of the user received from the network unit 120.

[0071] Specific examples are as follows: The network unit 120 can send or receive various information for implementing the menstrual cycle-related information providing method of some embodiments of the present invention. For example, the network unit 120 can send or receive biological information and user Q&A information stored in the database. Also, the network unit 120 can transfer some data generated during the execution of the following menstrual cycle-related information providing method to the outside for storage in the database.

[0072] On the other hand, the computing device 100 of some embodiments of the present invention can include a server 1030 as a computing system that sends or receives information by communicating with a client. In this case, the client can be any form of terminal capable of accessing the server. For example, the computing device 100 as a server can generate a single information processing result corresponding to a query by receiving the query from a user terminal. In this case, the computing device 100 as a server can provide a user interface including the processing result to the user terminal. In this case, the user terminal outputs the user interface received from the computing device 100 as a server and can receive or process information through interaction with the user.

[0073] In an additional embodiment, the computing device 100 can further include any form of user terminal 1010 that receives data resources generated from any server and performs additional information processing.

[0074] Figure 3 A schematic diagram for illustrating the menstrual cycle-related information providing method of some embodiments of the present invention. Figure 4 A diagram for illustrating the electrocardiogram variable information of some embodiments of the present invention. Figure 5 A diagram for illustrating the user Q&A information of some embodiments of the present invention. Figure 6 An exemplary user application for obtaining user Q&A information of some embodiments of the present invention is shown.

[0075] Reference will be made to Figures 3 to 6 to specifically describe the exemplary embodiments of some embodiments of the present invention.

[0076] The processor 110 can obtain biological information including a predetermined plurality of electrocardiogram variable information. Among them, the plurality of electrocardiogram variable information can include time series data.

[0077] Specifically, it is described as follows: The processor 110 can obtain biological information 10 that can be used to predict the menstrual cycle. For example, the biological information can include age, height, weight, body temperature, blood pressure, respiratory rate, menstrual day, menstrual period, pulse, skin conductivity, electrocardiogram, and blood oxygen saturation, etc. However, the biological information 10 is not limited to the above examples and can include various information related to the user.

[0078] In some examples, the biological information 10 may include information generated by more than one biological information sensing device 1020 (e.g., body temperature, blood pressure, respiratory rate, pulse, electrocardiogram, etc.). Also, the biological information 10 may include information input by the user (e.g., age, height, weight, etc.).

[0079] In some examples, the biological information 10 may include multiple electrocardiogram variable information. For example, the electrocardiogram variable information may be the time series data of an electrocardiogram (EKG or ECG) measured by an electrocardiogram device such as a Holter electrocardiograph. The electrocardiogram variable information may be time series data obtained by continuously measuring the electrocardiogram rather than cross-sectional measurement values.

[0080] According to some embodiments of the present invention, the multiple electrocardiogram variable information may include at least one of RR interval (RR Intervals) information, heart rate information, respiration rate information, ST segment level (ST level) information, standard deviation of all NN intervals information, square root of the mean of the sum of the squares of differences between adjacent NN intervals information, number of NN intervals differing by more than 50ms information, ratio of NN50 (ratio of NN intervals differing by more than 50ms) information, standard deviation of differences between adjacent NN intervals information.

[0081] Refer to Figure 4 , which shows exemplary electrocardiogram variable information obtained by a Holter electrocardiograph. Among them, the prediction factors for processing menstrual cycle prediction information through the analysis model may include RR interval information, heart rate information, respiration rate information, ST segment level information, standard deviation of all NN intervals information, square root of the mean of the sum of the squares of differences between adjacent NN intervals information, number of NN intervals differing by more than 50ms information, ratio of NN50 (ratio of NN intervals differing by more than 50ms) information, standard deviation of differences between adjacent NN intervals information, which are analyzed to have a high correlation with menstrual cycle prediction. The electrocardiogram variable information is not limited to the above examples and may include various information related to the electrocardiogram.

[0082] The multiple electrocardiogram variable information may be information obtained according to a predetermined period. For example, the multiple electrocardiogram variable information may be one of the information measured in the morning and afternoon every day. In this case, the analysis model can improve the prediction accuracy by generating menstrual cycle prediction information in each predetermined period. However, it is not limited thereto, and the multiple electrocardiogram variable information may be information obtained in various periods.

[0083] The processor 110 may obtain user Q&A information corresponding to the multiple electrocardiogram variable information.

[0084] Specifically, the processor 110 may obtain the multiple electrocardiogram variable information and the user Q&A information processed by the analysis model. The user Q&A information may include information related to menstrual symptoms. For example, the user Q&A information may be information input by the user regarding physical changes, mental changes, and changes in dysmenorrhea / breast pain / headache.

[0085] According to some embodiments of the present invention, the user Q&A information may include at least one of sleep disorder Q&A information, depressive feeling Q&A information, anxiety feeling Q&A information, and stress Q&A information.

[0086] Figure 5 Exemplary user Q&A information is shown. As Figure 5 shown, the user Q&A information may be information input in a categorical or numerical manner for various items such as physical changes, mental changes, and changes in dysmenorrhea / breast pain / headache. Among them, the user Q&A information for processing menstrual cycle prediction information by the analysis model may include sleep disorder Q&A information, depressive feeling Q&A information, and anxiety feeling Q&A information with a high correlation analyzed with the menstrual cycle prediction. However, it is not limited thereto, and the user Q&A information may include various information regarding menstrual symptoms obtained from the user.

[0087] According to some embodiments of the present invention, when obtaining the user Q&A information corresponding to the multiple electrocardiogram variable information, the processor 110 may provide a user interface that can input multiple user Q&A information corresponding to the acquisition time point of the multiple electrocardiogram variable information.

[0088] As described above, the processor 110 may provide a user interface capable of inputting user Q&A information through a user application. Generally, in order to reduce the amount of data processing, the analysis model uses information obtained at several time points instead of information obtained 24 hours a day to generate prediction results. Therefore, it is necessary to process the electrocardiogram variable information and user Q&A information obtained during the same period together. For example, multiple electrocardiogram variable information measured this morning can be matched with the user Q&A information input for the user's menstrual symptoms this morning. In addition, the analysis model can generate menstrual cycle prediction information by jointly processing the matched multiple electrocardiogram variable information and user Q&A information. Therefore, in order to be able to jointly process with multiple electrocardiogram variable information, user Q&A information can be obtained according to the period of obtaining multiple electrocardiogram variable information. For example, when multiple electrocardiogram variable information is obtained every morning and afternoon, the processor 110 can provide a user interface capable of inputting user Q&A information every morning and afternoon.

[0089] Correspondingly, the processor 110 may provide a user interface that enables a user to input user Q&A information according to a predetermined period of obtaining multiple electrocardiogram variable information. Refer to Figure 6 , which shows an exemplary user interface capable of inputting user Q&A information in a user application provided through the user terminal 1010. In some examples, when the period of obtaining multiple electrocardiogram variable information is twice in the morning and afternoon, the user interface may display whether user Q&A information has been input in the morning and afternoon of each date on the calendar. When the user interface receives an input for selecting a date on which user Q&A information has not been input, it may provide an input window capable of inputting user Q&A information on that date. Refer to Figure 6 , when a user instruction to select a specific date on the calendar is recognized, the user interface may display whether the user Q&A information has been completed through tick marks for the morning and afternoon of that date.

[0090] In some examples, the user interface may provide a display capable of identifying the number of pieces of information that have been input among multiple user Q&A information. For example, refer to Figure 6 , the user interface may provide a graph for displaying the number of pieces of information that have been input among multiple user Q&A information for each date on the calendar. However, it is not limited to this, and the user interface can be provided in various forms.

[0091] According to some embodiments of the present invention, the processor 110 may generate menstrual cycle prediction information 30 based on the biological information 10 and user Q&A information 20 through an analysis model.

[0092] The analysis model 200 can generate menstrual cycle prediction information by processing biometric information containing multiple electrocardiogram variable information and multiple user Q&A information. The menstrual cycle can be formed as a cycle repeated by the luteal phase (the period before menstruation), the menstrual phase (the menstrual period), and the follicular phase (the period after menstruation). From a reproductive perspective, the fertile phase can refer to the period around "ovulation" that occurs approximately 14 days after menstruation. The analysis model can generate menstrual cycle prediction information 30 that can identify the luteal phase, the menstrual phase, the follicular phase, and the fertile phase by processing input data including biometric information and user Q&A information.

[0093] The processor 110 can use the generated menstrual cycle prediction information 30 to generate menstrual-related information. For example, the processor 110 can use the menstrual cycle prediction information 30 to appropriately provide the predicted menstrual cycle (ovulation day, menstrual day, menstrual period, fertile days, premenstrual syndrome, menopause, etc.), recommended diet, menstrual management guidance information (e.g., predicted menstrual disorders and music therapy and exercise therapy for relieving menstrual disorders), or recommended menstrual product and service information, etc. However, it is not limited to this, and the processor 110 can use the menstrual cycle prediction information 30 to provide various menstrual-related information.

[0094] According to some embodiments of the present invention, the analysis model 200 can include an ensemble learning model that uses a combination of multiple predictor variables including at least a part of the multiple electrocardiogram variable information and user Q&A information.

[0095] The specific description is as follows: As described above, the biological information 10 containing multiple electrocardiogram variable information and the user Q&A information 20 are multiple prediction variables. Therefore, the analysis model needs to be implemented as a suitable algorithm that can process multiple prediction variables as inputs. For example, the analysis model 200 can be an ensemble training model that can derive more accurate predictions by integrating and processing the prediction results of multiple sub-models 210 through a prediction information determination module 220. In some examples, the ensemble training model can be a model using voting, bagging, or boosting algorithms, which utilize multiple sub-models. Hereinafter, exemplary analysis models of some embodiments of the present invention implemented using the random forest algorithm, which is a type of bagging algorithm, will be described, but the present invention is not limited thereto. And hereinafter, an embodiment in which the combination of prediction variables of the analysis model only includes the electrocardiogram variable information in the biological information 10 will be described, but the combination of prediction variables of the analysis model can also include various biological information 10 other than the electrocardiogram variable information, such as respiratory rate, body temperature, etc.

[0096] The random forest algorithm can be an ensemble technique that improves training performance by applying training data to multiple decision trees. For example, the analysis model 200 can include n sub-models 210a to 210n trained by generating n pieces of training data extracted by resampling from the original training data. In this case, each sub-model can be trained using a combination of prediction variables composed of only a part of the multiple prediction variables. For example, the first sub-model 210a can be a model using a combination of prediction variables including RR interval information, heart rate information, and respiratory rate information in the multiple electrocardiogram variable information. The second sub-model 210b can be a model using a combination of prediction variables including RR interval information, ST segment level information, and sleep disorder Q&A information in the user Q&A information. The third sub-model 210c can be a model including a combination of prediction variables including the number information of NN intervals with a difference greater than 50 MS in the multiple electrocardiogram variable information, and sleep disorder Q&A information and anxiety feeling Q&A information in the user Q&A information. Among them, the combination of prediction variables used by each sub-model can be a randomly determined combination or a predetermined combination.

[0097] In the training data used for training the analysis model, the training data related to the electrocardiogram variable information can be generated by assigning a label related to the menstrual cycle to the change pattern identified in the electrocardiogram variable information as time series data. Figure 12 A chart for analyzing the change pattern identified in the RR interval information to assign information related to the menstrual cycle.

[0098] In some examples, the training data may include labels generated by analyzing the correlation between the change patterns identified in each of the multiple electrocardiogram variable information and the menstrual cycle. Hereinafter, according to some embodiments of the present invention, an exemplary analysis model 200 generated using the training data generated based on the analysis results of the correlation between the multiple electrocardiogram variable information and the menstrual cycle will be described. Hereinafter, when the analysis model 200 is an integrated training model, the training of the analysis model 200 may refer to the training of individual sub-models 210.

[0099] According to some embodiments of the present invention, for the RR interval information, when a downward trend of the RR interval information is identified based on the RR interval information, the analysis model 200 may be trained to generate information for predicting the transition from the follicular phase to the luteal phase. For example, the downward trend of the RR interval information may include a case where the RR interval decreases by about 0.15 hz to 0.40 hz in the luteal phase compared to the follicular phase.

[0100] According to some embodiments of the present invention, for the heart rate information, when a sustained downward trend of the heart rate information is identified, the analysis model 200 may be trained to generate information for predicting the transition from the menstrual phase to the follicular phase. For example, the sustained downward trend of the heart rate information may include a case where the heart rate has a similar value or decreases by about 1.36 bpm in the follicular phase compared to the menstrual phase.

[0101] Moreover, when an upward trend of the heart rate information is identified, the analysis model 200 may be trained to generate information for predicting the transition from the follicular phase to the fertile phase. For example, the upward trend of the heart rate information may include a case where the heart rate increases by about 0.61 bpm in the fertile phase compared to the follicular phase.

[0102] Moreover, when a highest level trend of the heart rate information is identified, the analysis model 200 may be trained to generate information for predicting the transition to the luteal phase. The highest level trend of the heart rate information may include a case where the heart rate increases by about 2.33 bpm in the luteal phase compared to the follicular phase, a case where the heart rate increases by about 1.84 bpm in the luteal phase compared to the fertile phase, and a case where the heart rate increases by about 2.31 bpm in the luteal phase compared to the menstrual phase.

[0103] According to some embodiments of the present invention, for the respiratory rate information, when a downward trend of the respiratory rate information is identified, the analysis model 200 may be trained to generate information for predicting the transition from the menstrual phase to the follicular phase. For example, the downward trend of the respiratory rate information may include a case where the respiratory rate decreases by about 0.29 breath / min in the follicular phase compared to the menstrual phase.

[0104] Also, when a further downward trend in the respiratory rate information is recognized, the analysis model 200 can be trained to generate information for predicting the transition to the fertile period. For example, the further downward trend in the respiratory rate information may include a situation where the respiratory rate during the fertile period decreases by about 0.46 breath / min compared to the menstrual period.

[0105] Also, when an upward trend in the respiratory rate information is recognized, the analysis model 200 can be trained to generate information for predicting the transition from the menstrual period to the luteal phase. The upward trend in the respiratory rate information may include a situation where the respiratory rate during the luteal phase increases by about 0.18 breath / min compared to the menstrual period.

[0106] According to some embodiments of the present invention, for the ST segment level information, when a highest level trend in the ST segment level information is recognized, the analysis model 200 can be trained to generate information for predicting the transition to the follicular phase. For example, the highest level trend in the ST segment level information may include a situation where the value represents the maximum value among the values of the ST segment level information.

[0107] Also, when a lowest level trend in the ST segment level information is recognized, the analysis model 200 can be trained to generate information for predicting the transition to the luteal phase. For example, the highest level trend in the ST segment level information may include a situation where the value represents the maximum value among the values of the ST segment level information.

[0108] According to some embodiments of the present invention, for the standard deviation information of all NN intervals, when a maintaining trend in the standard deviation information of all NN intervals is recognized, the analysis model 200 can be trained to generate information for predicting the transition from the menstrual period to the follicular phase.

[0109] Also, when a downward trend in the standard deviation information of all NN intervals is recognized, the analysis model 200 can be trained to generate information for predicting the transition from the follicular phase to the fertile period. For example, the downward trend in the standard deviation information of all NN intervals may include a situation where the standard deviation during the fertile period decreases by about 0.04 compared to the follicular phase.

[0110] Also, when a maximum downward trend in the standard deviation information of all NN intervals is recognized, the analysis model 200 can be trained to generate information for predicting the transition to the luteal phase. For example, the maximum downward trend in the standard deviation information of all NN intervals may include a situation where the value represents the minimum value among the values of the standard deviation information of all NN intervals.

[0111] According to some embodiments of the present invention, for the root mean square information of the difference between adjacent NN intervals, when the maximum downward trend of the root mean square information of the difference between adjacent NN intervals is recognized, the analysis model 200 can be trained to generate information for predicting the transition to the luteal phase. For example, the maximum downward trend of the root mean square information of the difference between adjacent NN intervals can include the case of the minimum value among the values representing the root mean square information of the difference between adjacent NN intervals.

[0112] According to some embodiments of the present invention, for the quantity information of NN intervals with a difference greater than 50 MS, when the downward trend of the quantity information of NN intervals with a difference greater than 50 MS is recognized, the analysis model 200 can be trained to generate information for predicting the transition from the follicular phase to the luteal phase.

[0113] According to some embodiments of the present invention, for the proportional information of the quantity of NN intervals with a difference greater than 50 MS, when the downward trend of the proportional information of the quantity of NN intervals with a difference greater than 50 MS is recognized, the analysis model 200 can be trained to generate information for predicting the transition from the follicular phase to the luteal phase.

[0114] According to some embodiments of the present invention, for the standard deviation information of the difference between adjacent NN intervals, when the maintaining trend of the standard deviation information of the difference between adjacent NN intervals is recognized, the analysis model 200 can be trained to generate information for predicting the transition from the menstrual phase to the follicular phase.

[0115] In some examples, the training data may further include data generated by analyzing the correlation between the change patterns identified in each user's Q&A information and the menstrual cycle. Hereinafter, according to some embodiments of the present invention, the operation of the exemplary analysis model 200 generated using the training data generated based on the analysis results of the correlation between the user's Q&A information and the menstrual cycle will be described. Hereinafter, when the analysis model 200 is an integrated training model, the training of the analysis model 200 may refer to the training of the sub-model 210.

[0116] According to some embodiments of the present invention, for the sleep disorder Q&A information, when the upward trend of the sleep disorder Q&A information is recognized, the analysis model 200 can be trained to generate information for predicting the transition to the luteal phase.

[0117] According to some embodiments of the present invention, for the depressive feeling Q&A information, when the upward trend of the depressive feeling Q&A information is recognized, the analysis model 200 can be trained to generate information for predicting the transition to the luteal phase.

[0118] According to some embodiments of the present invention, for anxiety-related Q&A information, when an upward trend of the anxiety-related Q&A information is recognized, the analysis model 200 may be trained to generate information for predicting the transition to the luteal phase.

[0119] According to some embodiments of the present invention, for stress-related Q&A information, when an upward trend of the stress-related Q&A information is recognized, the analysis model 200 may be trained to generate information for predicting ovulation delay.

[0120] Figure 7 A graph for illustrating the prediction performance of the analysis model according to some embodiments of the present invention.

[0121] Figure 7 Illustrates the prediction performance of the analysis model generated by combining electrocardiogram variable information and user Q&A information. Refer to Figure 7 , Figure 7 Illustrates that the "Random Forest Model 2" implemented by jointly using electrocardiogram variable information and user Q&A information has higher prediction performance compared to the "Random Forest Model 1" implemented by only using electrocardiogram variable information. The specific observations are as follows: The prediction performance (test_ecg) value of the "Random Forest Model 1" is lower than the prediction performance (test_ecg_cli) value of the "Random Forest Model 2". Therefore, it can be known that by jointly using electrocardiogram variable information and user Q&A information as prediction factors, the prediction performance of the analysis model of the present invention is further improved.

[0122] Figure 8 Another graph for illustrating the prediction performance of the analysis model according to some embodiments of the present invention.

[0123] Figure 8 Illustrates the prediction performance generated by combining sleep problem variables (e.g., sleep disorder Q&A information) and mental health variables (e.g., depression-related Q&A information, anxiety-related Q&A information, and stress-related Q&A information) in user Q&A information. Refer to Figure 8 ,the value of the prediction performance result (RandomForest-AUC 1) of jointly using only the sleep problem variables in user Q&A information and electrocardiogram variable information is lower than the value of the prediction performance result (RandomForest-AUC 2) of jointly using the sleep problem variables and mental health variables in user Q&A information and electrocardiogram variable information. Therefore, it can be known that as user Q&A information, by jointly using sleep problem variables and mental health variables as prediction factors, the prediction performance of the analysis model of the present invention is further improved.

[0124] Figure 9 A flowchart of a method for providing menstrual-related information according to some embodiments of the present invention.

[0125] According to some embodiments of the present invention, a method for providing menstrual-related information may include step s100 of obtaining biological information including a predetermined plurality of electrocardiogram variable information. Among them, the plurality of electrocardiogram variable information may include time series data.

[0126] According to some embodiments of the present invention, a method for providing menstrual-related information may include step s200 of obtaining user Q&A information corresponding to the plurality of electrocardiogram variable information.

[0127] Alternatively, step s200 of obtaining user Q&A information corresponding to the plurality of electrocardiogram variable information may include the step of providing a user interface for displaying whether to input user Q&A information corresponding to the acquisition time point of the plurality of electrocardiogram variable information.

[0128] Alternatively, step s200 of obtaining user Q&A information corresponding to the plurality of electrocardiogram variable information may include the step of providing a user interface for displaying whether to input user Q&A information corresponding to the acquisition time point of the plurality of electrocardiogram variable information.

[0129] According to some embodiments of the present invention, a method for providing menstrual-related information may include step s300 of generating menstrual cycle prediction information based on the biological information and the user Q&A information through an analysis model.

[0130] The steps of the above method for providing menstrual-related information are only proposed for illustration, and some steps may be omitted or additional steps may be added. And the above steps may be executed in any order.

[0131] Figure 10 A simplified diagram of a network function showing multiple embodiments of the present invention.

[0132] In this specification, network model, operation model, neural network, network function, and neural network can be used interchangeably. A neural network can be composed of a set of interconnected computing units commonly called nodes. The above nodes can also be called neurons. A neural network includes more than one node. The multiple nodes (or neurons) constituting the neural network can be connected by more than one link.

[0133] In a neural network, more than one node connected by a link can form a relative relationship between an input node and an output node. As relative concepts, for any node in an output node relationship relative to one node, it may be in an input node relationship with another node, and vice versa. As described above, the relationship between the input node and the output node can be generated around the link. More than one output node can be connected to one input node through a link, and vice versa.

[0134] In the relationship between an input node and an output node connected by a link, the data of the output node depends on the data of the input node, and its value can be determined based on the data input to the input node. Among them, the link that connects the input node and the output node can have a weight value. The weight value can be variable and can be changed by the user or an algorithm to perform the functions expected by the neural network. For example, when an input node is connected to an output node through various links, the output node can determine the output node value based on multiple values input to the input nodes connected to the above output node and the weight values set for the links corresponding to each input node.

[0135] As described above, a neural network can form the relationship between an input node and an output node in a neural network where more than one node is connected by more than one link. The characteristics of the neural network can be determined based on the number of nodes in the neural network, the number of links, the correlation between the nodes and the links, and the weight values assigned to each link. For example, when there are two neural networks with the same number of nodes and links but different link weight values, they can be recognized as two different neural networks.

[0136] A neural network can be composed of a set of more than one node. A partial set of the multiple nodes that make up the neural network can form a layer. A part of the multiple nodes that make up the neural network can form a layer based on the distance from the initial input node. For example, the set of nodes at a distance of n from the initial input node can form the nth layer. The distance from the initial input node can depend on the minimum number of links required to reach the corresponding node from the initial input node. However, this layer definition is only a temporary definition for illustration purposes, and the number of layers in the neural network can be defined based on a different method from the above. For example, the layer of nodes can also be defined based on the distance from the final output node.

[0137] Among the multiple nodes in a neural network, the initial input node refers to more than one node that directly inputs data without passing through a link in the relationship with other nodes. Or, in the relationship between nodes based on links in the neural network, it refers to a node that does not include other input nodes connected by a link. Similarly, among the multiple nodes in a neural network, the final output node refers to more than one node other than the output node in the relationship with other nodes. And the hidden node refers to the nodes that make up the neural network except for the initial input node and the final output node.

[0138] According to an embodiment of the present invention, in a neural network, the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes in the neural network may decrease and then increase again as the process progresses from the input layer to the hidden layer. Also, according to another embodiment of the present invention, in a neural network, the number of nodes in the input layer may be less than the number of nodes in the output layer, and the number of nodes in the neural network may decrease as the process progresses from the input layer to the hidden layer. Further, according to another embodiment of the present invention, in a neural network, the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes in the neural network may increase as the process progresses from the input layer to the hidden layer. According to still another embodiment of the present invention, the neural network may be a neural network composed of the above neural networks.

[0139] A deep neural network (DNN) refers to a neural network including an input layer, an output layer, and multiple hidden layers. If a deep neural network is used, the latent structures of data can be recognized. That is, the latent structures of photos, texts, videos, voices, and music can be recognized (for example, the objects existing in a photo, the content and emotion of a text, the content and emotion of a voice, etc.). The deep neural network may include a convolutional neural network (CNN), a recurrent neural network (RNN), an autoencoder, a generative adversarial network (GAN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a Q-network, a U-network, a siamese network, a generative adversarial network (GAN), a transformer, etc. The above deep neural networks are only examples, and the present invention is not limited thereto.

[0140] The neural network may use at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. The learning of the neural network may be a process of applying knowledge that enables the neural network to perform a specific task.

[0141] A neural network can learn in a way that minimizes output errors. In the learning of a neural network, learning data is repeatedly input into the neural network, the output of the neural network and the target error are calculated for the learning data, and the error of the neural network is backpropagated from the output layer of the neural network to the input layer in the direction of reducing the error to update the weighted values of each node in the neural network. In the case of supervised learning, learning data marked with the correct answer (i.e., labeled learning data) is used for each learning data. In the case of unsupervised learning, each learning data may not be marked with the correct answer. That is, for example, in the case of supervised learning related to data classification, the learning data can be data where each learning data is marked with a category. As the labeled learning data is input into the neural network, the input (category) of the neural network can be compared with the label of the learning data to calculate the error. As another example, in the case of unsupervised learning related to data classification, the input learning data can be compared with the neural network output to calculate the error. The calculated error is backpropagated from the neural network (i.e., in the direction from the output layer to the input layer), and the connection weighted values of each node in each layer of the neural network can be updated through backpropagation. The change amount of the updated connection weighted value of each node can be determined according to the learning rate. The calculation of the neural network for the input data and the backpropagation of the error can form a learning cycle (epoch). Different learning rates can be applied according to the number of repetitions of the learning cycle of the neural network. For example, in the initial stage of the learning of the neural network, a high learning rate can be applied to enable the neural network to quickly ensure a specified level of performance to provide efficiency. In the later stage of learning, a low learning rate can be applied to improve the accuracy.

[0142] To increase the amount of learning data used by the neural network for learning, various data augmentation methods can be used. For example, data augmentation can be performed through two-dimensional transformations such as rotation, scale, shearing, reflection, and translation. Also, data augmentation can be performed by applying noise insertion, color, and brightness changes.

[0143] Generally, in the learning of a neural network, the training data can be a partial set of actual data (i.e., the data processed using the learned neural network). Therefore, there can be a learning loop as follows: although the error of the learning data decreases, the error of the actual data increases. Overfitting refers to the phenomenon where the error of the actual data increases due to overlearning of the learning data as described above. Overfitting can be a cause of increasing the error of machine learning algorithms. Various optimization methods can be used to prevent this overfitting. To prevent overfitting, methods such as increasing the learning data, regularization, dropout (not activating some nodes in the network during learning), and applying a batch normalization layer can be adopted.

[0144] Figure 11 Block diagram of a computing device according to some embodiments of the present invention.

[0145] Figure 11 Simplified diagram for briefly showing an exemplary computing environment that can be implemented by embodiments of the present invention.

[0146] In this specification, although the present invention is generally described in terms of how it is implemented by a computing device, those of ordinary skill in the art to which the present invention pertains should understand that the present invention can be implemented through a combination of computer-executable instructions that can be executed on one or more computers and / or other program modules and / or a combination of hardware and software.

[0147] Generally, program modules can include routines, programs, instructions, data structures, and others that perform specific tasks or implement specific abstract data types. And those of ordinary skill in the art to which the present invention pertains should understand that the methods of the present invention can be implemented by other computer system architectures, such as single-processor or multi-processor computer systems, minicomputers, mainframe computers, personal computers, handheld computing devices, microprocessor-based or programmable household appliances, etc. (each of which can work by connecting one or more related devices).

[0148] Multiple embodiments disclosed in the present invention can be implemented in a distributed computing environment, where some tasks are executed by remote processing devices linked through a communication network. In a distributed computing environment, program modules can be located in storage devices such as local and remote memories.

[0149] Generally, a computer includes various computer-readable media. Media accessible by a computer can be any type of computer-readable media, including volatile media and non-volatile media, transitory media and non-transitory media, removable media and non-removable media. As a non-limiting example, computer-readable media can include computer-readable storage media and computer-readable transmission media. Computer-readable storage media can include any method or technology-implemented volatile media and non-volatile media, transitory media and non-transitory media, removable media and non-removable media for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media can include random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), high-density digital video disc (DVD, digital video disk) or other optical disc storage devices, cassette tapes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any type of media accessible by a computer and used to store the required information, but is not limited thereto.

[0150] Generally, computer-readable transmission media include all information transmission media for implementing computer-readable instructions, data structures, program modules, or other data to a carrier wave or other transport mechanism such as a modulated data signal. The term "modulated data signal" refers to a signal that encodes information in a signal by setting or changing more than one of various signal characteristics. As a non-limiting example, computer-readable transmission media can include wired media such as a wired network or a direct-wired connection, and wireless media such as sound, radio frequency (RF), infrared, and other wireless media. Any combination of the above media can also fall within the scope of computer-readable transmission media.

[0151] An exemplary environment 1100 of multiple embodiments of the present invention includes a computer 1102, which includes a processing device 1104, a system memory 1106, and a system bus 1108. The system bus 1108 connects system instructions including the system memory 1106 (not limited thereto) to the processing device 1104. The processing device 1104 can be any of a variety of commonly used processors. Dual processors and other multi-processor architectures can also be used as the processing device 1104.

[0152] The system bus 1108 can be any one of a variety of types of bus structures and can be connected to a local bus that uses any one of a memory bus, a peripheral device bus, and a variety of commercial bus frameworks. The system memory 1106 includes a read-only memory 1110 and a random access memory 1112. The basic input / output system (BIOS) is stored in a non-volatile memory 1110 such as a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. This basic input / output system includes basic routines for enabling information transmission between multiple structural elements within the computer 1102 during operation. The random access memory 1112 may include a high-speed random access memory for caching data, for example, a static random access memory.

[0153] The computer 1102 includes a built-in hard disk drive (HDD) 1114 (e.g., EIDE, SATA), and this built-in hard disk drive 1114 can also be used for external use in a suitable chassis (not shown), a magnetic floppy disk drive (FDD) 1116 (e.g., for reading and recording on a removable floppy disk 1118), and an optical disc drive 1120 for reading (e.g., for reading a read-only optical disc 1122 or other high-capacity optical media such as a high-density digital video disc (DVD) for reading or recording). The hard disk drive 1114, the disk drive 1116, and the optical disc drive 1120 can be respectively connected to the system bus 1108 through a hard disk drive interface 1124, a disk drive interface 1126, and an optical disc drive interface 1128. The interface 1124 for implementing an external drive can include at least one of the universal serial bus (USB, Universal Serial Bus) and the IEEE 1394 interface technology or both.

[0154] Such a drive and its associated computer-readable medium implement non-volatile storage of data, data structures, computer-executable instructions, etc. In the case of the computer 1102, the drive and the medium are equivalent to a device for storing any data in an appropriate digital form. In the above content, although the computer-readable medium is a hard disk drive, a removable disk, and a removable optical medium such as a CD or DVD, those of ordinary skill in the art to which the present invention pertains should understand that different types of computer-readable media such as a zip drive, a cassette tape, a flash memory card, a magnetic tape, etc. can also be used in an exemplary operating environment, and any such medium may include computer-executable instructions for performing the method of the present invention.

[0155] A variety of program modules such as 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 random access memory 1112. The operating system, applications, modules, and / or all or a part of the data can also be cached in the random access memory 1112. It should be understood that the present invention can be implemented by a variety of commercial operating systems or combinations of operating systems.

[0156] A user can input instructions and information into the computer 1102 through one or more wired / wireless input devices. For example, pointing devices such as a keyboard 1138 and a mouse 1140. Other input devices (not shown) can be a microphone, an IR remote control, a joystick, a gamepad, a stylus, a touch screen, etc. Although such other input devices can be connected to the processing device 1104 through an input device interface 1142 connected to the system bus 1108, they can also be connected through other interfaces such as a parallel interface, an IEEE 1394 serial interface, a game interface, a USB interface, an IR interface, etc.

[0157] 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, a computer generally includes other peripheral output devices (not shown) such as speakers, printers, etc.

[0158] The computer 1102 can work in a network environment by logically connecting to one or more remote computers such as a remote computer 1148 through wired and / or wireless communication. The remote computer 1148 can be a workstation, a computing device computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other common network nodes, and generally includes many or all of the multiple structural elements of the computer 1102, but only a memory storage device 1150 is shown for simplicity of illustration. The shown logical connection includes a wired / wireless connection in a local area network (LAN) 1152 and / or a larger network, such as a wide area network (WAN) 1154. Such a local area network and wide area network network environment is usually used in offices and companies and simplifies an enterprise-wide computer network, all of which can be connected to a global computer network, such as the Internet.

[0159] When using a local area network (LAN) network environment, the computer 1102 can be connected to the local network 1152 through a wired and / or wireless communication network interface or adapter 1156. The adapter 1156 can simplify the wired or wireless communication with the LAN 1152. Moreover, such a LAN 1152 can include a wireless access interface provided therein for communicating with the wireless adapter 1156. When using a wide area network (WAN) network environment, the computer 1102 can include a modem 1158, or can include other devices for connecting to communication computing devices on the WAN 1154 or for establishing communication through the Internet or the like or through the WAN 1154. The modem 1158 can be an internal or external, wired or wireless device, and is connected to the system bus 1108 through a direct connection interface 1142. In a networked environment, program modules of the computer 1102 or a part thereof can be stored in the remote memory / storage device 1150. It should be understood that the illustrated network connections are only examples, and other devices for establishing communication links between computers can be used.

[0160] The computer 1102 is configured for wireless communication to communicate with any wireless device or object, such as a printer, scanner, desktop and / or portable computer, personal data assistant (PDA), communication satellite, any device or location associated with a wirelessly detectable tag, and telephone. It includes wireless network communication technologies (Wi-Fi) and Bluetooth wireless technology. Thus, the communication can be a predefined structure in an existing network or an ad hoc communication between at least two devices.

[0161] Wireless network communication technology (Wi-Fi, Wireless Fidelity) is used to achieve a wireless connection to the Internet or the like. As a wireless technology, the wireless network communication technology enables a computer to send and receive data both indoors and outdoors, that is, enables a digital cellular mobile phone to send and receive data anywhere within the coverage area of a base station. The Wi-Fi network uses wireless technologies called IEEE 802.11 (a, b, g, etc.) to provide a secure, reliable, and high-speed wireless connection. Wi-Fi can be used for interconnecting computers, connecting to the Internet, and connecting to a wired network (using IEEE 802.3 or Ethernet). The Wi-Fi network can be used in the unlicensed 2.4 GHz wireless band and 5 GHz wireless band, for example, operating at a data rate of 11 Mbps (802.11a) or 54 Mbps (802.11b), or operating in products including dual bands.

[0162] Those of ordinary skill in the art to which the present invention pertains should understand that information and signals can be represented by any of a variety of different technologies and processes. For example, they can be expressed by referring to the data, instructions, commands, information, signals, bits, symbols, and chip voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof described above.

[0163] Those of ordinary skill in the art to which the present invention pertains should understand that the various illustrative logical blocks, modules, processors, devices, circuits, and algorithmic steps in the embodiments and related descriptions disclosed herein can be implemented by electronic hardware (for convenience in the description, referred to herein as software), various forms of programs or design codes, or a combination thereof. In the above, various illustrative instructions, blocks, modules, circuits, and steps have been generally described according to their functions to clearly illustrate the interchangeability of hardware and software. Whether such functions are implemented by hardware or software depends on the design constraints imposed on a particular application and the overall system. Although those of ordinary skill in the art to which the present invention pertains can implement the functions of each particular application in various ways, such implementation decisions should not be construed in a manner that departs from the scope of the present invention.

[0164] The various embodiments disclosed herein can be implemented by a manufactured article using methods, devices, or standard programming and / or engineering techniques. The term "manufactured article" includes computer programs, carriers, or media that can be accessed by any computer-readable storage device. For example, computer-readable storage media include 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, memory cards, memory sticks, key drives, etc.), but are not limited thereto. Also, the various storage media disclosed herein can include more than one device for storing information and / or other machine-readable media.

[0165] It should be understood that the specific order or hierarchical structure of the disclosed processing steps is merely an example of illustrative access. The specific order or hierarchical structure of the processing steps within the scope of the present invention can be rearranged based on design priorities. The appended claims provide the elements of the various steps in a sample order, but this does not mean that they are limited to a specific order or hierarchical structure.

[0166] The related descriptions of the disclosed embodiments are only for enabling those of ordinary skill in the art to which the present invention pertains to easily utilize or implement the present invention. For those of ordinary skill in the art to which the present invention pertains, various modifications of such illustrative embodiments are obvious, and without departing from the scope of the present invention, the general principles defined herein can be applied to other embodiments. Therefore, the present invention is not limited to the embodiments disclosed herein and should be construed as the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for providing menstrual-related information, which is executed by a computing device, characterized in that, Comprising the following steps: Obtain biometric information including a predetermined plurality of electrocardiogram variable information, the plurality of electrocardiogram variable information including timing data; Obtain user Q&A information corresponding to the plurality of electrocardiogram variable information; And Generate menstrual cycle prediction information based on the biometric information and the user Q&A information through an analysis model.

2. The method for providing menstrual-related information according to claim 1, wherein The plurality of electrocardiogram variable information includes at least one of RR interval information, heart rate information, respiratory rate information, ST segment level information, standard deviation information of all NN intervals, root mean square difference information of adjacent NN intervals, number information of NN intervals with a difference greater than 50MS, ratio information of the number of NN intervals with a difference greater than 50MS, and standard deviation information of the difference between adjacent NN intervals.

3. The method for providing menstrual-related information according to claim 1 or 2, wherein The user Q&A information includes at least one of sleep disorder Q&A information, depression feeling Q&A information, anxiety feeling Q&A information, or stress Q&A information.

4. The method for providing menstrual-related information according to claim 2, wherein The analysis model includes an integrated training model, and the integrated training model utilizes combinations of a plurality of predictor variables respectively including at least a part of the plurality of electrocardiogram variable information and the user Q&A information.

5. The method for providing menstrual-related information according to claim 1 or 4, characterized in that, The analysis model is trained to generate information for predicting the transition from the follicular phase to the luteal phase when a downward trend of the RR interval information is identified based on the RR interval information.

6. The method for providing menstrual-related information according to claim 1 or 4, characterized in that, The analysis model is trained as follows: When a sustained downward trend of the heart rate information is identified, generate information for predicting the transition from the menstrual phase to the follicular phase; When an upward trend of the heart rate information is identified, generate information for predicting the transition from the follicular phase to the fertile phase; and When a highest level trend of the heart rate information is identified, generate information for predicting the transition to the luteal phase.

7. The method for providing menstrual-related information according to claim 1 or 4, characterized in that, The analysis model is trained as follows: When a downward trend of the respiratory rate information is identified, generate information for predicting the transition from the menstrual phase to the follicular phase; When a further downward trend of the respiratory rate information is identified, generate information for predicting the transition to the fertile phase; And When an upward trend of the respiratory rate information is identified, generate information for predicting the transition to the luteal phase.

8. The method for providing menstrual-related information according to claim 1 or 4, characterized in that, The analysis model is trained as follows: When a highest level trend of the ST segment level information is identified, generate information for predicting the transition to the follicular phase; and When a lowest level trend of the ST segment level information is identified, generate information for predicting the transition to the luteal phase.

9. The method for providing menstrual-related information according to claim 1 or 4, characterized in that, The analysis model is trained as follows: When a sustained trend of the standard deviation information of all NN intervals is identified, generate information for predicting the transition from the menstrual phase to the follicular phase; When a downward trend of the standard deviation information of all NN intervals is identified, generate information for predicting the transition from the follicular phase to the fertile phase; And When a maximum downward trend of the standard deviation information of all NN intervals is identified, generate information for predicting the transition to the luteal phase.

10. The method for providing menstrual-related information according to claim 1 or 4, characterized in that The analysis model is trained to generate information for predicting the transition to the luteal phase when a maximum downward trend of the root mean square difference information of adjacent NN intervals is identified.

11. The method for providing menstrual-related information according to claim 1 or 4, characterized in that, The analysis model is trained to generate information for predicting the transition from the follicular phase to the luteal phase when a downward trend in the quantity information of the NN intervals with a difference greater than 50 MS is recognized.

12. The method for providing menstrual-related information according to claim 1 or 4, characterized in that, The analysis model is trained to generate information for predicting the transition from the follicular phase to the luteal phase when a downward trend in the proportional information of the quantity of the NN intervals with a difference greater than 50 MS is recognized.

13. The method for providing menstrual-related information according to claim 1 or 4, characterized in that, The analysis model is trained to generate information for predicting the transition from the menstrual phase to the follicular phase when a maintaining trend in the standard deviation information of the differences between adjacent NN intervals is recognized.

14. The method for providing menstrual-related information according to claim 1 or 4, wherein the user Q&A information includes sleep disorder Q&A information, the analysis model is trained to generate information for predicting the transition to the luteal phase when an upward trend in the sleep disorder Q&A information is recognized.

15. The method for providing menstrual-related information according to claim 1 or 4, wherein the user Q&A information includes depression feeling Q&A information, the analysis model is trained to generate information for predicting the transition to the luteal phase when an upward trend in the depression feeling Q&A information is recognized.

16. The method for providing menstrual-related information according to claim 1 or 4, wherein the user Q&A information includes anxiety feeling Q&A information, the analysis model is trained to generate information for predicting the transition to the luteal phase when an upward trend in the anxiety feeling Q&A information is recognized.

17. The method for providing menstrual-related information according to claim 1 or 4, wherein the user Q&A information includes stress Q&A information, the analysis model is trained to generate information for predicting ovulation delay when an upward trend in the stress Q&A information is recognized.

18. The method for providing menstrual-related information according to claim 1 or 4, wherein the step of obtaining user Q&A information corresponding to multiple electrocardiogram variable information includes: the step of providing a user interface capable of inputting the user Q&A information at the acquisition time points corresponding to multiple electrocardiogram variable information.

19. The method for providing menstrual-related information according to claim 18, wherein the step of obtaining user Q&A information corresponding to multiple electrocardiogram variable information includes: the step of providing a user interface for displaying whether the user Q&A information corresponding to the acquisition time points of multiple electrocardiogram variable information is input.

20. The method for providing menstrual-related information according to claim 1, wherein The multiple electrocardiogram variable information includes RR interval information, heart rate information, respiratory rate information, ST segment level information, standard deviation information of all NN intervals, root mean square of differences between adjacent NN intervals, quantity information of NN intervals with a difference greater than 50 MS, proportional information of the quantity of NN intervals with a difference greater than 50 MS, and standard deviation information of differences between adjacent NN intervals.

21. The method for providing menstrual-related information according to claim 20, characterized in that, The user Q&A information includes sleep disorder Q&A information, depression feeling Q&A information, anxiety feeling Q&A information, and stress Q&A information.

22. The method for providing menstrual-related information according to claim 4, wherein The analysis model uses a random forest algorithm.

23. A computer program stored in a computer-readable medium, wherein The computer program includes multiple instructions for causing one or more processors to execute a method for providing menstrual-related information, and the method includes the following steps: Obtain biological information including a predetermined plurality of electrocardiogram variable information, where the plurality of electrocardiogram variable information includes timing data; Obtain user Q&A information corresponding to the plurality of electrocardiogram variable information; And Generate menstrual cycle prediction information based on the biological information and the plurality of user Q&A information through an analysis model.

24. A computing device for executing a method for providing menstrual-related information, characterized in that The computing device includes: A memory including a plurality of computer-executable components; and A processor for executing the following plurality of computer-executable components stored in the memory, The processor executes the following steps: Obtain biological information including a predetermined plurality of electrocardiogram variable information, where the plurality of electrocardiogram variable information includes timing data; Obtain user Q&A information corresponding to the plurality of electrocardiogram variable information; and Generate menstrual cycle prediction information based on the biological information and the plurality of user Q&A information through an analysis model.

Images