CN117653213A

CN117653213A - Menstrual cycle tracking using temperature measurements

Info

Publication number: CN117653213A
Application number: CN202311137003.5A
Authority: CN
Inventors: 张舒楠; C·L·库里; C·Y·张; 朴智贤; 王意恺
Original assignee: Apple Inc
Current assignee: Apple Inc
Priority date: 2022-09-06
Filing date: 2023-09-05
Publication date: 2024-03-08

Abstract

A menstrual cycle tracking using temperature measurements is provided. Embodiments relate to systems and methods for tracking menstrual cycles of a user. Embodiments may include obtaining a first set of temperature data at an electronic device, and determining a first probability of ovulation occurring during a first time period using the first set of temperature data in response to the first set of temperature data meeting a first criterion. In response to the first probability meeting a second criterion, embodiments may include determining a second set of probabilities including a probability of ovulation occurring daily in a first set of days during the first period of time. The second set of probabilities may be used to determine an estimated ovulation date and the electronic device may display an output indicative of the estimated ovulation date.

Description

Menstrual cycle tracking using temperature measurements

Cross Reference to Related Applications

This application is a non-provisional application of U.S. provisional patent application No. 63/403,937 filed on 6, 9, 2022, and claims the benefit of this U.S. provisional patent application in accordance with 35u.s.c.119 (e), the contents of which are incorporated herein by reference as if fully set forth herein.

Technical Field

The described embodiments relate generally to menstrual cycle tracking and prediction. More particularly, the present embodiments relate to estimating the date of ovulation, conception window, and/or date of menstrual onset based on biometric information of the user, such as temperature data.

Background

Many people who undergo the menstrual cycle plan activities around portions of their menstrual cycle, such as conception windows and/or menstrual periods. Menstrual cycles may be irregular, resulting in an inability to reliably plan activities. Furthermore, attempting to collect data that may be used to estimate or predict portions of the menstrual cycle may be difficult, invasive, and inaccurate.

Disclosure of Invention

Embodiments relate to a method for tracking menstrual cycles of a user. These methods may include: a first set of temperature data is obtained at the electronic device, and it is determined that the first set of temperature data meets a first criterion. In response to determining that the first set of temperature data meets the first criteria, the methods may include: a first probability of ovulation occurring during a first set of days is determined using the first set of temperature data. These methods may include: the first probability is determined to satisfy the second criterion, and the set of probabilities is determined in response to determining that the first probability satisfies the second criterion. These methods may include: the probability set is used to select an estimated ovulation date from a first set of days, and an output indicative of the estimated ovulation date is displayed on the electronic device. The second set of probabilities may include, for each day of the first set of days, the probability of ovulation occurring on that day.

Embodiments also relate to methods for estimating ovulation of a user. These methods may include: a start date of a first menstrual cycle of a user is determined at the electronic device, and a set of temperature data is obtained at the electronic device after the start date of the first menstrual cycle. These methods may include: determining a set of probabilities using the set of temperature data, the set of probabilities including, for each day of a set of days, a corresponding probability of ovulation occurring on that day; and using the set of probabilities to determine an estimated ovulation date for the first menstrual cycle. These methods may include: displaying a first output on the electronic device based on the estimated ovulation date; determining a start date of a second menstrual cycle subsequent to the first menstrual cycle; and determining an updated ovulation date of the first menstrual cycle using the updated start date of the second menstrual cycle. The methods may include displaying a second output on the electronic device based on the updated ovulation date.

Embodiments further relate to an electronic device for tracking a menstrual cycle of a user. The electronic device may include one or more temperature sensors to measure a temperature of a user, a display, and a processor configured to collect a set of temperature measurements using the one or more temperature sensors. The processor may be configured to operate in a first mode to determine that a first subset of the set of temperature measurements associated with a first set of days meets a first criterion, and to use the first set of operations to determine a first estimated ovulation date for the user using the first subset of the set of temperature measurements. The first set of operations may include an artificial neural network outputting a set of probabilities including a probability of ovulation occurring each day in a window of days. The processor may be configured to determine that a second subset of the set of temperature measurements associated with a second set of days meets a second criterion in a second mode and to use the second set of operations to determine a second estimated ovulation date using the second subset of the set of temperature measurements, a start date of a menstrual cycle, and an end date of the menstrual cycle.

Drawings

The present disclosure will be readily understood by the following detailed description in conjunction with the accompanying drawings, wherein like reference numerals designate like structural elements, and in which:

FIG. 1 shows an exemplary graph of temperature data during a menstrual cycle;

FIG. 2 illustrates a system architecture of an embodiment of a menstrual cycle estimator;

FIG. 3 illustrates an exemplary process flow for estimating the date of ovulation using temperature measurements;

FIGS. 4A and 4B illustrate exemplary user interfaces displaying estimated conception and ovulation information;

FIG. 5 illustrates an exemplary process flow for updating an estimated ovulation date and/or conception window based on additional menstrual cycle data;

FIG. 6 illustrates an exemplary process flow for estimating the date of ovulation by identifying a temperature transition using temperature data;

FIG. 7 illustrates an exemplary wearable device that may be used to track menstrual cycles using temperature measurements; and

fig. 8 shows exemplary components of the wearable device of fig. 7.

Detailed Description

Reference will now be made in detail to the exemplary embodiments illustrated in the drawings. It should be understood that the following description is not intended to limit the embodiments to one preferred embodiment. On the contrary, it is intended to cover alternatives, modifications and equivalents as may be included within the spirit and scope of the embodiments as defined by the appended claims.

Embodiments described herein generally take the form of techniques for estimating the date of various portions of the menstrual cycle, such as the date of ovulation, the conception window, and/or the date of onset of the menstrual period. These techniques use temperature data collected from the user, and in some instances, additional collected data (such as heart rate data and/or user input recording the start and stop of a given menstrual cycle) to track these portions of the menstrual cycle. Depending on the amount and type of data available, the mechanism may use different techniques to estimate the timing of portions of the menstrual cycle. Thus, as these mechanisms receive additional data, they may be able to refine these estimates (e.g., predicted ovulation date, conception window, and/or menstrual onset date).

In some embodiments, the techniques described herein are incorporated into a system that includes one or more temperature sensors that collect temperature data from a user. The system also includes a set of operational modules that perform the various steps described herein. In particular, the operating module comprises a cycle status module, a data processing module and an ovulation estimation module, which are commonly used to estimate the date of ovulation of the user (i.e. the day on which ovulation occurs) and/or the conception window of the user. In some examples, one or more temperature sensors and operating modules may be incorporated into a single device, such as a wearable device.

In other examples, the techniques described herein may be performed as a method. In some examples, the method may include receiving an initial estimate of a conception window of a current menstrual cycle and an initial estimate of a menstrual onset date of a subsequent menstrual cycle. The method may include receiving temperature data and determining whether the temperature data meets a data sufficiency criterion, which may represent a set of requirements for determining whether there is sufficient temperature data to accurately perform ovulation estimation. In the event that the temperature data meets data sufficiency criteria, the method may include using the temperature data to estimate the date of ovulation. In response to estimating the ovulation date, the conception window may be updated, and the ovulation date and/or the update to the conception window may be displayed to the user and electronically accessible to the user.

These and other embodiments are discussed below with reference to fig. 1-8. However, those skilled in the art will readily appreciate that the detailed description given herein with respect to these figures is for explanatory purposes only and should not be construed as limiting.

As used herein, the "menstrual cycle" extends from the beginning of the menstrual period to the day before the beginning of the next menstrual period, and generally includes the follicular phase, ovulation and luteal phase. The "conception window" is the portion of the menstrual cycle during which a person is most likely to become pregnant; it typically begins a few days (e.g., up to five days) before ovulation and typically ends on the day of ovulation. Follicular phase occurs after menstrual period and before ovulation, and luteal phase occurs after ovulation, lasting until the beginning of the next menstrual period. The techniques described herein may be used to estimate a date associated with a user's current menstrual cycle (referred to herein as an "ongoing cycle"). Additionally or alternatively, the techniques described herein may be used to estimate a date associated with an ending menstrual cycle (referred to herein as a "history cycle") or predict one or more dates of a menstrual cycle that has not yet started (referred to herein as a "future cycle").

Menstrual cycle is tracked starting with a "first day" instantiation, which is the first day that a user initiates tracking by marking the first day of menstrual bleeding (i.e., "menstrual start date"). On the first day, the user is predicted a next menstrual period, which represents an estimate of the beginning of the next future period (and the end of the ongoing period). The conception window and/or the ovulation date of the ongoing cycle may also be estimated. During an ongoing period of the user, data collected by the systems, devices and methods described herein may allow for an estimate of whether ovulation has occurred. Accordingly, embodiments of the systems, devices, and methods described herein may update the date of ovulation, conception window, and/or initial predictions of the mid-date of the beginning of the next menstrual period based on the obtained data.

In particular, embodiments of the systems, devices, and methods described herein are configured to track a user's temperature over a plurality of days and analyze the temperature data to estimate the timing of various portions of the menstrual cycle. The body temperature of the user, in particular the basal body temperature of the user (or "BBT", i.e. the body temperature at rest), will change with the course of the ongoing menstrual cycle. For example, the BBT of a user will typically increase in response to ovulation and remain elevated during the luteal phase until the beginning of the next menstrual period. Thus, detecting an increase in the body temperature of the user may indicate that the user has ovulated. By detecting the ovulation date of a given menstrual cycle, the system, apparatus and method may update the initial estimate of the ovulation date, conception window (or, in the example of an ongoing cycle, the date of the beginning of the next menstrual cycle).

Fig. 1 shows an exemplary graph of a user's temperature during a menstrual cycle 100. For illustration purposes, each day is represented by a single temperature value (e.g., measurement of the BBT of the user). Each menstrual cycle 100 starts on the day 101 when the menstrual period starts and ends when the next menstrual period starts 103. The temperatures 102 during each menstrual cycle 100 generally exhibit a biphasic pattern, with these temperatures being lower prior to ovulation 104 and higher after ovulation 104. As shown in fig. 1, the body temperature 102 of the user typically increases at the time of ovulation 104 and remains elevated until near the beginning of the next menstrual cycle. Although the specific temperature values shown in fig. 1 are merely examples (and do not reflect the temperature values of any particular person), most people have similar correlations between body temperature and various portions of the menstrual cycle. This is especially true if the body temperature of the user is collected and averaged, smoothed, or otherwise algorithmically related across multiple menstrual cycles. Thus, the body temperature of the user may be used to estimate various portions of the menstrual cycle, or to improve the estimation of such portions of the menstrual cycle (such as the beginning and end of the conception window, the date of menstrual onset, and/or the date of ovulation).

In particular, the systems, methods and devices may use one or more techniques to estimate whether this ovulation-based temperature change (referred to herein as the "ovulation temperature transition") has occurred. The identification of the ovulation temperature transition may then be used to estimate the ovulation date of a given menstrual cycle (e.g., the ovulation date 104 of menstrual cycle 100 in fig. 1). Temperature information from the user may be used during an ongoing cycle to identify the ovulation temperature transition (and thus the ovulation date) during the ongoing cycle, or may be used retrospectively to identify the ovulation temperature transition (and thus the ovulation date) in a historical cycle. When retrospectively estimating the ovulation date in the history period, additional information such as the end date of the menstrual period (which may be determined, for example, when the user inputs a menstrual period indicating the start of the crescent menstrual period) may be used in performing retrospectively estimation.

In some instances, the estimated ovulation date for a given menstrual cycle may be used to estimate or predict the menstrual cycle or other aspects of the subsequent menstrual cycle. For example, the estimated ovulation date 104 determined for an ongoing menstrual cycle 100 may be used to calculate the conception window for that menstrual cycle. Additionally or alternatively, the estimated ovulation date 104 may be used to predict the start date of a subsequent menstrual cycle and/or the ovulation date of a subsequent menstrual cycle. In some cases, the menstrual cycle start date and/or ovulation may be tracked across multiple menstrual cycles 100, and the combined data may be used to predict menstrual events, such as menstrual cycle start date and/or ovulation date, for subsequent menstrual cycles 100.

As mentioned above, the devices, systems, and methods described herein involve the use of one or more temperature sensors to collect temperature data from a user. The temperature data may be collected by any suitable number or type of temperature sensors, which may be distributed across a plurality of individual devices. In instances where temperature data is collected from multiple temperature sensors, it may be desirable to calculate an adjustment amount for each temperature sensor to account for sensor-specific deviations in temperature readings. For example, two temperature sensors measuring the same subject may produce slightly different measurements, and adjusting for these differences may improve the accuracy of the ovulation date estimation techniques described herein. In other examples, the devices, systems, and methods described herein may utilize temperature data from a single temperature sensor (or from multiple temperature sensors of a single device) to estimate the date of ovulation even if temperature measurements from additional sensors and/or devices are available.

The devices, systems, and methods described herein may optionally collect additional user information that may be used to estimate the date of ovulation, conception window, and/or the beginning of the next menstrual period as described herein. In some examples, input received by a user (e.g., manually or in response to a prompt provided by one of the devices described herein) may be used to indicate a start date of a menstrual period indicating an end of a menstrual cycle and a start of a crescent menstrual cycle. The user may input (or the systems and devices described herein may be able to automatically determine) additional information such as user demographics (e.g., their age, body measurements), food and/or alcohol intake, current medication intake, sleep information, etc.

Additionally or alternatively, the devices, systems, and methods described herein may receive additional biometric data from one or more other sensors, such as heart rate information (e.g., heart rate of the user, resting heart rate, heart rate variability, etc.), respiratory rate, blood pressure, blood oxygen, etc. These additional sensors may be incorporated into the same device that includes the temperature sensor (or sensors) as discussed above, or may be part of a device that is separate from the one or more temperature sensors. For example, embodiments may take the form of a portable wearable device having one or more temperature sensors. The wearable device may also include one or more additional sensors, such as a photoplethysmograph sensor configured to measure and collect the additional biometric data.

Fig. 2 shows a system architecture 200 of an embodiment of a system as described herein configured to estimate the date of ovulation. Specifically, FIG. 2 generally illustrates an exemplary operational module that may perform the various techniques described herein. Thus, any operations described herein as being performed by each of the operational modules may be stored as instructions on a non-transitory computer-readable storage device such that the processor may utilize the instructions to perform the operations. Similarly, the systems and devices described herein include a memory and one or more processors operatively coupled to the memory. The one or more processors may receive instructions from the memory and are configured to execute the instructions to perform various operations of each of the operation modules. The system architecture 200 is configured to estimate the ovulation date of a given menstrual cycle and may further estimate the conception window of that menstrual cycle and/or the menstrual onset date of the subsequent menstrual cycle.

The operational modules of the system architecture 200 cooperate to perform these estimations. For example, the operational modules may include a cycle status module 202, a data processing module 206, an ovulation estimation module 208, and a conception window update module 216. The cycle status module 202 maintains information related to the user's menstrual cycle. The period status module 202 may contain user-entered data and/or estimates related to one or more historical periods, an ongoing period of the user, and/or one or more future periods. For example, for a given historical period, period status module 202 may store data including a menstrual period start date, a menstrual period end date, an ovulation date, and a conception window. Depending on the period, some or all of this data may be input by the user or may be estimated by the system architecture 200 when user input is not available. Similarly, an ongoing cycle may include a menstrual onset date, a menstrual ending date, an ovulation date (which may be an estimate of when ovulation has occurred or when ovulation will occur, depending on the location of the user in the ongoing cycle), and a conception window. Because future cycles must not have begun (e.g., a menstrual start date marks a new ongoing cycle), the cycle status module may maintain estimated predictions of menstrual start date, menstrual end date, ovulation date, and conception window.

The information from the cycle status module 202 may be used to generate a user interface that depicts information about the user's menstrual cycle, such as discussed below with respect to fig. 4A and 4B. These user interfaces may be generated according to the user's requirements or in response to certain predetermined criteria.

In certain embodiments, at the beginning of an ongoing cycle, the cycle status module 202 may provide an initial (or "zeroth day") estimate of either or both of the conception window and menstrual period of the next menstrual cycle. More specifically, the period status module 202 may provide a range of dates in which the next menstrual period may begin and end, classifying some of these dates as likely start or end dates, and classifying other dates as more likely start or end dates. The periodic status module 202 may do the same for the conception window, but in some embodiments, the calendar may not present the unlikely date of the conception window to the user. For future cycles, the calendar may provide an estimate of the first day of the menstrual cycle, the conception window within the menstrual cycle, and an estimate of the start date of the next menstrual cycle. This information may be provided to the user by a calendar or other application executed by the computing device so that the user may plan future activities accordingly. This information may be used to plan an attempt to become pregnant or, conversely, for contraception, travel, etc.

The system architecture also includes a temperature sensor 204, which may include a single temperature sensor or multiple temperature sensors as previously described. The temperature sensor may periodically measure the body temperature of the user to obtain a set of temperature measurements. Individual temperature measurements may be made on demand (i.e., initiated by a user) or opportunistically, such as at predetermined intervals when a given temperature sensor is worn by a user. Each temperature measurement may include a temperature value and associated additional information such as the time of day the measurement was taken (e.g., day versus night), an indication of the user's sleep state (e.g., an indication of a deep sleep versus awake, or a particular sleep stage), a quality metric (e.g., the amount of device or user movement associated with the temperature measurement), combinations thereof, and the like. This associated additional information may facilitate the system architecture to select different subsets of these temperature measurements for analysis using the techniques described herein.

The data processing module 206 may receive calendar data and temperature data and place these data in a form to be used by the ovulation estimation module 208. In particular, the data processing module 206 may select a subset of the temperature measurements and use the subset of the temperature measurements to generate a set of temperature data. Thus, when the devices, systems, and methods described herein discuss "obtaining" data or measurements (e.g., temperature data or heart rate data), this includes selecting a subset of the available measurements. In some examples, the obtained data may be generated from a selected subset of available measurements.

As previously mentioned, the system architecture 200 may use different techniques to estimate the ovulation date based on certain characteristics of the temperature measurements received by the temperature sensor 204. In particular, the ovulation estimation module 208 may operate in a plurality of different modes, each mode using a different technique to estimate the ovulation date for a given menstrual cycle, and each mode may be associated with a different data sufficiency criterion. For a mode that uses temperature data to estimate the date of ovulation, the data sufficiency criteria may be based on having a minimum number of temperature measurements that meet certain criteria. For example, the data sufficiency criteria may require a predetermined number of days (e.g., twelve of the first fourteen days) within a time window, with a minimum number of temperature measurements per day or a minimum number of temperature measurements that meet certain criteria (e.g., temperature measurements obtained at night while the user sleeps, etc.).

For each mode and its associated ovulation estimation technique, the data processing module 206 may determine whether a subset of the temperature measurements meets the corresponding data sufficiency criteria. If the data sufficiency criteria are met for a given mode, the data processing module 206 may generate temperature data from a subset of the temperature measurements, which may be used by the ovulation estimation module 208 as described below. The temperature data may include, or may be derived from, some or all of the subset of temperature measurements. Because the number of temperature measurements collected may vary over time, it may be desirable for the data processing module 206 to generate temperature data in a generic form for use by the ovulation estimation module 208.

In some examples, the data processing module 206 determines that there are insufficient temperature measurements for the ovulation estimation module 208 to operate using a mode that utilizes temperature data. In these examples, the data processing module 206 may determine whether the data sufficiency criteria are met for the pattern using the heart rate data. In these examples, the data sufficiency criteria may be based on having a minimum number of heart rate measurements that meet a particular criteria.

The ovulation estimation module 208 is operable to estimate the ovulation date of a given menstrual cycle and may also be used to estimate the conception window of that menstrual cycle, or the menstrual start date of a subsequent menstrual cycle. The ovulation estimation module 208 may attempt to estimate the ovulation date of the menstrual cycle at one or more predetermined times. For example, for an ongoing cycle, the ovulation estimation module 208 may attempt to estimate the ovulation date of the ongoing cycle at predetermined intervals (e.g., once per day). Since temperature measurements may be collected on a continuous basis, each attempt to estimate the date of ovulation may utilize a different set of temperature data, but it should be appreciated that these different sets of temperature data may be selected or generated from some common temperature measurement.

In some of these examples, the ovulation estimation module 208 will not attempt to estimate the ovulation date of the ongoing cycle until a threshold amount of time (e.g., five days) has elapsed from the beginning date of the menstrual cycle, which prevents the ovulation estimation module 208 from prematurely estimating ovulation during certain portions of the menstrual cycle. Similarly, once the ovulation estimation module 208 estimates that ovulation has occurred during an ongoing cycle, the ovulation estimation module 208 may cease attempting to estimate the date of ovulation (either immediately or after a predetermined number of intervals after the date of ovulation is estimated). Although the ovulation estimation module 208 may have estimated that ovulation has occurred during an ongoing period, performing additional estimations using the ovulation estimation module 208 with additional temperature data may improve the estimation of the ovulation date and using the additional temperature data may improve the predicted starting date of the next menstrual period. In some variations, the ovulation estimation module 208 will perform an additional estimation of the ovulation date when the ongoing cycle ends (and thus becomes a historical cycle). In these examples, because the end date of the menstrual cycle is known (because a new menstrual cycle has already begun), the end date of the menstrual cycle can be used as an input to help improve the estimate of the ovulation date.

For a given attempt to estimate the ovulation date for a given cycle (e.g., an ongoing cycle or a historical cycle as outlined above), the ovulation estimation module 208 may operate in one or more modes, each mode utilizing a different technique to estimate the ovulation date. The ovulation estimation module 208 may include a plurality of modules, each module using a different technique to estimate menstrual events, and the ovulation estimation module 208 may utilize different modules depending on its mode of operation. Different modules may be selected based on the collected data and/or may be used at different times during the menstrual cycle. For example, some modules may require wearing a temperature sensor for a relatively long period of time during a certain set of days, other modules may be able to operate with intermittent temperature measurements, and/or other modules may not require any temperature measurements, but instead may utilize other types of data, such as heart rate measurements.

In some instances, for a given attempt to estimate the ovulation date of a given menstrual cycle, the ovulation estimation module 208 may select and operate in a single mode (and corresponding estimation technique). In these examples, the ovulation estimation module 208 may select a technique based on available temperature measurements. There may be a hierarchy of techniques such that the first technique (and corresponding modules of the ovulation estimation module 208) is used if the first data sufficiency criteria are met. If the first data sufficiency criteria is not met, but the second data sufficiency criteria for the second technology is met, the system architecture 200 may select the second technology. If neither of these criteria is met, but a third data sufficiency criterion associated with a third technique is met, system architecture 200 may select the third technique.

In other examples, for a given attempt to estimate the date of ovulation for a given menstrual cycle, the ovulation estimation module 208 may operate in a plurality of modes to estimate a plurality of estimates of the date of ovulation. For example, if the data sufficiency criteria for multiple modes are met, the ovulation estimation module 208 may attempt to use each of these modes to estimate the ovulation date. In these examples, different patterns may make different determinations regarding ovulation (e.g., different estimates regarding whether ovulation may not be uniform, or different ovulation dates may be estimated), and the ovulation estimation module 208 may use these determinations (e.g., using confidence information or other weighting factors) to estimate the ovulation date.

Returning to fig. 2, the ovulation estimation module 208 may include a machine learning module 210 that uses the trained data set and/or other classification and regression algorithms to estimate the date of ovulation using the measured temperature data. Generally, the machine learning module 210 includes two stages. The first stage estimates whether ovulation occurs within a set of days (also referred to herein as a window of days), and the second stage estimates the probability of ovulation occurring on that day for each day of the set of days. Together, these probabilities form a set of probabilities, and the machine learning module 210 selects one of the set of days as the estimated ovulation date. In other cases, the ovulation estimation module 208 may use additional or alternative time periods to output an estimate of the occurrence of ovulation. For example, the output may indicate a range of hours or other time division.

Specifically, for a given ovulation estimate, the machine learning module 210 receives a set of temperature data associated with a first set of days. The first stage uses the set of temperature data to determine whether ovulation occurred during the first set of days. It should be appreciated that the set of temperature data may include or be generated from a set of days that are greater than the first set of days. For example, the first stage may determine whether ovulation has occurred within a window of five days (e.g., five days prior to when an ovulation estimate was attempted), but may utilize temperature data based on temperature measurements collected over ten or more days (e.g., ten days prior to when an ovulation estimate was attempted) (e.g., select and/or generate the temperature data from these temperature measurements). The first set of days may be a subset of the days on which the data was analyzed. In some examples, the larger set of days may optionally include one or more days from a historical period prior to the ongoing period.

The first stage may include a classifier component configured to receive the temperature data and output a probability of ovulation occurring during the first set of days. The classifier can be trained using temperature data and a base true ovulation date. In some cases, the classifier component may include a random forest algorithm. The probability from the first stage may be compared to a probability threshold or other selection criteria to estimate whether ovulation has occurred. The probability threshold may be a static value or may be determined dynamically using information from the user's historical period.

In instances where the machine learning module 210 is used to estimate the ovulation date of an ongoing cycle, the machine learning module 210 may be run iteratively until the first stage determines that ovulation has occurred. Specifically, if the data processing module 206 determines that a set of temperature data meets the data sufficiency criteria of the machine learning module 210, the first stage will use the set of temperature data to determine a probability of ovulation occurring during the first set of days. If the determined probability does not meet the selection criteria, the machine learning module 210 will cease the current estimation. In response, additional temperature measurements may be collected, and the data processing module 206 obtains a second set of temperature data associated with a second set of days and meeting data sufficiency criteria. In some examples, heart rate data or other sensor measurements may also be input into the machine learning model. The first stage will use the second set of temperature data to determine the probability of ovulation occurring during a second set of days (which may partially overlap the first set of days) and determine whether the probability meets the selection criteria. Additional sets of temperature data associated with additional sets of days may be obtained and analyzed as needed until the results from the model meet the threshold criteria. When the first stage calculates the probability of meeting the selection criteria, the set of temperature data is passed to the second stage.

In instances where the machine learning module 210 is used to estimate the ovulation date of a historical cycle, the first stage of the machine learning module 210 may be run iteratively across multiple sets of days. The multiple sets of days may be selected based on one or more aspects of the historical period, such as the start date and/or end date of the period. In these examples, each of the plurality of sets of days is associated with a corresponding set of temperature data, and the first stage calculates a corresponding probability of ovulation occurring during the set of days. The machine learning module 210 may select a group of days from the plurality of groups of days having the highest corresponding probability. The selected set of days (and its corresponding set of temperature data) may then be passed to the second stage.

The second stage receives a set of temperature data associated with a set of days and uses the set of temperature data to determine a set of probabilities as previously discussed. For example, when the probability of ovulation occurring during the second set of days of the ongoing cycle meets the selection criteria discussed above, the second stage uses the second set of temperature data to determine that ovulation occurred on that day for each day of the second set of days. For example, the second stage may include a regression component that estimates the probability of ovulation occurring daily over the set of days. The ovulation estimation may estimate the ovulation date based on the output from the regression component. In some of these variations, the regression component may include a long-short-term memory (LSTM) artificial neural network.

As mentioned previously, the machine learning module 210 may be associated with corresponding data sufficiency criteria that may be used to determine whether to use the machine learning module 210 for a given ovulation date estimate. Depending on the configuration of the machine learning module 210, the machine learning module 210 may have relatively stringent data sufficiency criteria, which may require periodic measurement of temperature around the ovulation date. In instances where the temperature sensor is incorporated into a wearable device, this may require the user to wear the wearable device around the date of ovulation (e.g., when they sleep).

In addition to or in lieu of the machine learning module 210, the ovulation estimation module 208 may include a temperature transition detection module 212 that may use a different process and utilize different data sufficiency criteria to estimate ovulation data than the machine learning module 210. The temperature transition detection module 212 may be configured to detect an increase in temperature indicative of ovulation. The temperature transition detection module 212 may use an algorithm that compares the temperature from the first set of days to the temperature from the second set of days to estimate whether ovulation occurred on a particular day.

Specifically, to estimate whether ovulation occurs on a particular day, the temperature transition detection module 212 selects a first number of days before the day and a second number of days after the day (although it should be considered that the number of days may itself be included in either the first or the second number). The first number of days and the second number of days may have the same number of days or different numbers of days, as desired. The temperature transition detection module 212 determines one or more temperature metrics (e.g., average temperature, average basal body temperature, etc.) for each of the first number of days and the second number of days and determines whether a difference in the determined temperature metrics meets a difference criterion.

For example, the temperature transition detection module 212 may determine a difference between an average temperature for a first number of days (e.g., the first six days) and an average temperature for a second number of days (e.g., the last three days). When the temperature transition detection module 212 is used to estimate ovulation in an ongoing cycle, the temperature transition detection module 212 may determine whether the average temperature for a first number of days is lower than the average temperature for a second number of days by a threshold amount (e.g., 0.1 degrees celsius, 0.2 degrees celsius). If the average temperature has transitioned by a threshold amount, the temperature transition detection module 212 may estimate that ovulation occurred on that date. If the average temperature does not transition by a threshold amount, the temperature transition detection module 212 may make a subsequent attempt to estimate that ovulation occurred on another day (e.g., when additional temperature measurements are collected).

When the temperature transition detection module 212 is used to estimate ovulation in a history period, the temperature transition detection module 212 may select a window of days. For each day within the window of days, the temperature transition detection module 212 may calculate a corresponding temperature change between an average temperature for a first number of days before the day and an average temperature for a second number of days after the day. The temperature transition detection module 212 may use the determined temperature change to select a day from a window of days as the estimated ovulation date. For example, the temperature transition detection module 212 may select the day with the highest determined temperature change as the estimated ovulation date.

The window of days may be selected as a set of days that may include the date of ovulation. The number of days window may be selected using a menstrual cycle start date, menstrual cycle end date, information from previous historical cycles, other suitable information, combinations thereof, and the like. In some variations, when estimating the updated ovulation date of a history period, the temperature transition detection module 212 will use the starting date of the history period and the starting date of the next menstrual period.

Additionally or alternatively, the ovulation estimation module 208 may include a heart rate estimation module 214, which may be used to estimate the date of ovulation using heart rate. The sedentary heart rate of a user generally increases shortly before the start of the luteal phase of the user and steadily rises throughout ovulation, peaking near the start of the follicular phase shortly after ovulation. Thus, the sedentary heart rate of the user may be used to predict various portions of the menstrual cycle, or to improve the prediction of such portions of the menstrual cycle (such as the conception window, the menstrual period, and/or the onset and end of ovulation). As one non-limiting example, an increase in the heart rate of a person typically begins when the conception window is open, near-open, or shortly after opening.

For example, in the follicular phase, a person's sedentary (e.g., resting) heart rate begins to climb. The resting heart rate of a person continues to rise during most of the follicular phase of the menstrual cycle, usually (but not necessarily) in a fairly steady manner. As a person approaches ovulation, the rate of change of heart rate generally decreases, but the heart rate itself continues to increase. The conception window is typically opened during an increase in heart rate. In many cases, the rise in the heart rate of a person during the follicular phase (which extends from the beginning of the cycle to ovulation) is fairly rapid, and for many people the rise rate may be 1.5 to 2 heartbeats per minute. For most people, the follicular phase has no menstrual luteal phase law, and thus tracking the change in heart rate (and rate of change in heart rate) can provide the ability to accurately track the duration of the follicular phase and predict the onset of ovulation.

By measuring sedentary heart rate, for example by periodic sampling while wearing a wearable device incorporating a heart rate monitor, changes in heart rate (and slope or rate of such changes) can be determined and used to predict various aspects of the future menstrual cycle, including the conception window and the likely or approximate start and end dates of menstrual period, as well as the start and end dates of ovulation.

Accordingly, the heart rate estimation module 214 may be configured to obtain a set of heart rate data from the user and use the heart rate data to estimate the date of ovulation, and may use any known technique as will be appreciated by one of ordinary skill in the art to estimate the date of ovulation. Because heart rate estimation module 214 utilizes heart rate data, ovulation estimation module 208 may use heart rate estimation module 214 in instances where there is insufficient temperature data to utilize machine learning module 210 or temperature transition detection module 212 as previously described. As discussed above, the heart rate estimation module 214 may have its own data sufficiency criteria.

When the ovulation estimation module 208 estimates the ovulation date of a given menstrual cycle, the system architecture may also use the ovulation date to estimate one or more additional aspects of the cycle. For example, when the ovulation estimation module 208 estimates the ovulation date of an ongoing cycle, the ovulation estimation module 208 may use the estimated ovulation date to estimate the start date of the next menstrual period (and thus the end of the ongoing cycle). In an example where the next menstrual period start date is predicted as part of the instantiation of the first day, the next menstrual period start date may replace the original prediction.

Additionally or alternatively, the estimated ovulation date determined by the ovulation estimation module 208 may be provided to the conception window updating module 216. The conception window update module 216 updates the estimated conception window based on the determined estimated ovulation date. The estimated ovulation date may be determined from the measured temperature and/or heart rate data, depending on which module or modules of the ovulation estimation module 208 are used to determine the date.

The ovulation estimation module 208 and the conception window update module 216 may provide any of their estimated dates (e.g., estimated ovulation date, estimated conception window, and/or estimated next menstrual period start date) to the cycle status module 202. The period status module 202 may then use these estimated dates in generating the user interface. In some examples, the cycle status module 202 may be configured to display a modified user interface with new information in response to receiving an update date from the ovulation estimation module 208 and/or the conception window update module 216.

Fig. 3 shows an exemplary process flow 300 for estimating the date of ovulation using temperature measurements. The process flow 300 may be performed by a device described herein, including devices having the system architecture 200 described with reference to fig. 2.

At operation 302, the process 300 may include obtaining, at an electronic device, a set of temperature data. The temperature data may be based on temperature measurements made by one or more temperature sensors, which may be integrated into the electronic device and/or a portion of a separate device. The temperature of the user may be measured at different times throughout the user's menstrual cycle (including during the previous menstrual cycle), and these temperature values (along with any associated additional information as discussed above) or information derived therefrom may be stored at the electronic device and/or remotely (e.g., at a database).

The electronic device may obtain a subset of the stored temperature data for use in performing a particular ovulation estimate. As previously discussed, the electronic device may not attempt to perform ovulation estimation (and thus obtain a subset of temperature data) for a given menstrual cycle until certain criteria are met. For example, at operation 302, the electronic device may begin to obtain temperature data for analysis a particular number of days after the start of a user's menstrual cycle (e.g., the period it is proceeding with). When the user records the beginning of an ongoing cycle, the electronic device may determine that a threshold amount of time has elapsed since the beginning date of the menstrual cycle and obtain a subset of temperature data in response to determining that the threshold amount of time has elapsed.

At operation 304, the process 300 may include determining whether the obtained temperature data meets one or more criteria (e.g., data sufficiency criteria as discussed above with respect to the machine learning module 210 of fig. 2). The electronic device may continue to obtain temperature data until one or more criteria are met. The criteria may be configured to ensure that the date of ovulation and/or other menstrual events may be determined with sufficient accuracy depending on the mode in which the electronic device is operating.

At operation 306, the process 300 may include using the obtained set of temperature data to determine whether ovulation occurred during a set of days. For example, the determination may be performed using the first stage of the machine learning module 210 described above with respect to fig. 2. The set of days may be determined based on a time period associated with the contained temperature data. In some cases, the set of days may correspond to a day in a time period in which the temperature data is obtained. In other cases, the set of days may be a subset of the time period associated with the obtained temperature data. For example, the obtained temperature data may correspond to a period of time that begins at the beginning of a menstrual cycle and ends after an initially predicted conception window. In this example, the set of days may exclude an initial portion of the menstrual cycle (e.g., menstrual period) where ovulation does not occur. To this end, the set of days may begin a later day of the menstrual cycle (e.g., day 5) and include data from each day until operation 306 determines that ovulation has occurred. Temperature data obtained from the entire time period can be used to determine whether ovulation occurs within a subset of days within the time period.

The obtained temperature data may be input into a classification model, and the classification model may output a probability of ovulation occurring during the set of days. If the probability meets the threshold, the process may determine that ovulation occurred during the set of days. In response to the probability meeting the threshold, the process 300 may proceed to additional operations that may analyze the obtained set of temperature data to estimate the date of ovulation from the set of days.

If the probability output by the classification model does not meet the threshold, additional temperature data (e.g., over additional days) may be collected and used to generate updated temperature data. Updated temperature data may be input into the classification model. Operation 306 may continue iteratively collecting and inputting additional temperature data into the classification model until the output probability meets a threshold. In some cases, operation 306 may be performed at a plurality of points over a period of time (e.g., corresponding to a likely ovulation date), and if the probability output by the classification does not meet a threshold, process 300 may determine that ovulation is not detected. In these cases, the electronic device may use other techniques (e.g., temperature transition detection and/or heart rate measurement to attempt to estimate the ovulation date and/or conception window).

At operation 308, the process 300 may include determining a set of probabilities including a probability of ovulation occurring daily in the set of days. The obtained temperature data and/or a subset of the obtained temperature data (e.g., associated with the set of days) may be input into a second model that determines a probability of ovulation occurring daily in the set of days. The second model may be a regression model, such as an LSTM, other artificial neural network model, or other suitable statistical or machine learning model.

At operation 310, the process 300 may include determining an estimated ovulation date using the set of probabilities determined at operation 308. In some cases, the day with the highest probability may be estimated as the ovulation date. In other cases, the probabilities may be analyzed as a set to determine an estimated ovulation date. For example, the mean, median, mode, and/or other statistical measures may be used to identify an estimated ovulation date from a set of probabilities.

The estimated ovulation date may be used to determine the conception window of the user. For example, the conception window may be estimated to include one or more days before the estimated date of ovulation and one or more days after the estimated date of ovulation. In the case where an initial conception window is predicted at the beginning of the menstrual period of the ongoing menstrual cycle, the conception window determined from the temperature data may be compared with the initial conception window. If the initial conception window is different from the newly estimated conception window (i.e., a conception window based on temperature data from an ongoing menstrual cycle), the initial conception window may be updated.

An indication of the date of ovulation and/or the conception window may be output to the user using an electronic device. The interface shown in fig. 4B may be used to display the date of ovulation and/or a conception window to the user. In some cases, the electronic device may send a warning, tactile, audible, or other warning to the user indicating that the date of ovulation has been determined and/or that the conception window has been determined or updated.

Fig. 4A and 4B illustrate an exemplary user interface 400 displaying estimated conception and ovulation information. The initial user interface 400a (shown in fig. 4A) may display initial estimates of the menstrual cycle start day 402 and conception window 404, which may be determined using user-entered information such as the start of menstrual period and/or tracking information received from the cycle status module 202. The initial interface 400a may be generated at the beginning of an ongoing menstrual cycle and may be generated in response to a user indicating that his menstrual period has begun. Initial user interface 400a may display initial conception window 404.

Visual effects may be used to display the menstrual period start date 402 and/or the initial conception window 404 to indicate these events. For example, the menstrual onset date 402 and/or the initial conception window 404 may include highlighting, different text, fonts, and/or other effects in the first user interface 400a to indicate the estimated date of these events.

An updated user interface 400B (shown in fig. 4B) may be generated in response to determining an estimated ovulation date for an ongoing or previous menstrual cycle, as described herein. The update user interface 400b may indicate an estimated ovulation date 406 and an updated conception window 408, which may be determined from the obtained temperature data as described herein. Although the last day of updating conception window 408 is shown in fig. 4B as coinciding with estimated ovulation date 406, in other variations, updating conception window 408 may be selected such that updating conception window 408 extends beyond estimated ovulation date 406 (e.g., one day beyond estimated ovulation date 406).

Some embodiments may provide a warning to the user when the ovulation date or conception window is updated. For example, the electronic device (whether the device that calculates the estimate or another associated device) may provide an audible, visual, and/or tactile alert to the user to capture their attention and indicate that an update has occurred. As another example, some embodiments may automatically open and display a calendar with updated information. The frequency of these warnings may be limited in some implementations, as discussed above.

Fig. 5 illustrates an exemplary process 500 flow for updating an estimated ovulation date and/or conception window based on additional menstrual cycle data. Process flow 500 may be performed by a device described herein, including devices having system architecture 200 described with reference to fig. 2.

At operation 502, the process 500 may include obtaining, at an electronic device, temperature data of a user. In some cases, obtaining the temperature data may be initiated in response to a start of a menstrual cycle, which may be indicated by user input to the electronic device and/or a physiological parameter determined at the electronic device. The temperature data may be based on temperature measurements made by one or more temperature sensors. The temperature data may be obtained based on recorded and/or detected menstrual events and include data measured during an ongoing menstrual cycle (and in some instances, a portion of a historical period preceding the ongoing menstrual cycle). Temperature data may be obtained using a process as previously described, such as operation 302 from process 300.

At operation 504, the process 500 may include determining an estimated date of ovulation using the obtained set of temperature data. In some cases, the ovulation date may be determined using a machine learning process (e.g., using machine learning module 210 described above with respect to fig. 2), which may include operations from process 300 described herein. The estimated ovulation date may be determined during an ongoing cycle, for example shortly after ovulation and when the machine learning process is able to output an estimate of ovulation meeting the first criterion (e.g. the output estimated ovulation date is associated with a threshold probability). In other cases, the estimated ovulation date may be output using a temperature transition detection process as described herein and/or using heart rate data.

At operation 506, the process 500 may include identifying an end of an ongoing menstrual cycle. In some cases, the end of the menstrual cycle may be determined from user input to the electronic device, such as user input indicating the start of the menstrual period of the next menstrual cycle. The end of an ongoing menstrual cycle may be identified as the day before the beginning day of the next menstrual cycle.

At operation 508, the process 500 may include using the ending day of the menstrual cycle to determine an updated ovulation date for the menstrual cycle (which has transitioned from an ongoing cycle to a historical cycle). The end date of this historical menstrual cycle (alone or in combination with the beginning date of the menstrual cycle) can be used to identify a set of days on which ovulation may have occurred. In some cases, the set of days may be identified as including days that are defined days from the end of menstrual cycle. For example, the first day of the set of days may be a defined number of days from the identified end of menstrual cycle day, and the set of days may span the defined number of days.

The estimated ovulation date may be determined from the set of days using a temperature transition process (such as described above with respect to the temperature transition detection module 212 of fig. 2) that compares temperature information from a first day (or first set of days) with temperature information from a second day (or second set of days). In one example, six to three processes may be used, wherein the average temperature from the first six days is compared to the average temperature from the last three days for each day of the set of days. The estimated ovulation date may be designated as the day on which the increase in average temperature from the first six days to the second three days increases by a defined threshold. Six to three processes are given as one example, and other sets of days may be used.

The ovulation date determined using the end of menstrual cycle information may be used to update a previously determined ovulation date that may have been determined at the beginning of the menstrual cycle and/or during the menstrual cycle (e.g., using the machine learning process described herein). Updating the ovulation date may also be used to update the conception window, as described herein. In some cases, updates to the ovulation date and/or conception window based on the end of menstrual cycle date may be used to update the user interface and/or alert the user that the ovulation date has been updated.

Fig. 6 shows an exemplary process flow 600 for selecting an ovulation estimation process based on temperature data that has been obtained by an electronic device. Different ovulation estimation processes may have different data sufficiency requirements (e.g., the data sufficiency criteria previously discussed) to be able to estimate the date of ovulation with a desired level of accuracy. For example, when temperature data is captured over a longer period of time (which may include capturing multiple measurements daily/evening), the machine learning process described herein may output results with greater accuracy. For example, the machine learning process may perform well on wearable electronic devices that include temperature sensors and are worn by the user throughout the menstrual cycle. The temperature transition process may be able to use fewer temperature values per day and/or temperature values for several days (which may be associated with intermittent wear of one or more temperature sensors) to estimate the date of ovulation. If no or limited temperature data is available, other physiological measurements including heart rate data as described herein may be used to estimate the date of ovulation and/or the conception window.

At operation 602, process 600 may include collecting temperature data, which may include a temperature collection process described herein. The temperature data may be generated from a temperature sensor worn by the user, e.g., a temperature sensor integrated into the wearable electronic device. Thus, the amount and duration of available temperature data may be based on the duration of time that the user wears the watch during an ongoing menstrual cycle.

At operation 604, the process 600 may include determining whether the first subset of temperature data meets a first criterion. The first criteria may be configured to determine whether there is sufficient temperature data for the machine learning process to output accurate results. The first criteria may include a minimum temperature data threshold that may include temperature measurements from a minimum number of days in a menstrual cycle and/or a minimum number of temperature measurements per day. Additionally or alternatively, the first criteria may include parameters such as movement parameters, time or days, sleep/awake state, minimum duration of each measurement, etc.

At operation 606, the process 600 may include determining an estimated ovulation date using a machine learning process in response to the temperature data meeting a first criterion. The machine learning process may include the processes described herein, such as process 300 described with reference to fig. 3. The electronic device may be configured to operate in a first mode to determine whether a first subset of temperature data (or any subsequent subset of temperature data) meets a first criterion and to use the first subset of temperature data to determine an estimated ovulation date.

At operation 608, the process 600 may include determining whether the second subset of temperature data meets a second criterion. Operation 608 may be performed in lieu of, or in addition to, operation 606. For example, if the temperature data does not meet the first criteria at operation 604, the process 600 may perform operation 608. In other cases, the process 600 may include determining a first estimated date of ovulation using operation 606, and then determining whether a second estimated date of ovulation may be determined at operation 608.

The second criterion may include a second minimum data threshold based on a second data processing algorithm, such as the temperature transition detection process described herein. In some cases, the second data processing algorithm may require less data than the machine learning process. For example, the temperature transition detection module may require a single temperature measurement from each day. Thus, the second criterion may define a minimum data threshold that requires fewer overall temperature measurements than the first criterion.

At operation 610, the process 600 may include determining an estimated ovulation date using a temperature transition process in response to the temperature data meeting a second criterion. The temperature transition process may include the process described herein. In some cases, the temperature transition process may be based on an end-of-menstrual cycle date, such as process 500 described with reference to fig. 5. The electronic device may be configured to operate in a second mode to determine whether a second subset of temperature data (or any subsequent subset of temperature data) meets a second criterion and to use the second subset of temperature data to determine the estimated date of ovulation.

At operation 612, the process 600 may include using the heart rate data to determine an estimated ovulation date, as described herein. In some cases, operation 612 may be performed if neither the first nor second criteria are met for a given subset of temperature data (e.g., a third subset of temperature data). In other cases, operation 612 may be performed in addition to operation 606 and/or operation 610. In the case of determining the date of ovulation using a plurality of different processes, the method may be configured to use the date of ovulation from each process to determine an estimated date of ovulation. In some cases, the output of some processes may be weighted higher (e.g., the output from the machine learning process is weighted higher than the output from the heart rate process) using the estimated ovulation date of the output from a plurality of different processes. Additionally or alternatively, the outputs from these processes may be averaged or otherwise analyzed to generate an estimated ovulation date. The electronic device may be configured to operate in a third mode to determine whether a third subset of temperature data (or any subsequent subset of temperature data) fails to meet the first criteria and the second criteria and to use the third subset of temperature data to determine the estimated ovulation date.

Fig. 7 illustrates an example wearable device 700 that may perform the methods described herein and/or various modules in conjunction with fig. 2. Here, the wearable device 700 takes the form of a smart watch, but other embodiments may be instantiated in other wearable devices, such as glasses, headphones, earphones, jewelry, clothing, and the like. Some embodiments may be portable electronic devices, such as smartcomputers, tablet computers, laptop computers, etc., which are not necessarily wearable.

In the example of fig. 7, the wearable device 700 includes a housing 710 coupled to a display 715. The display 715 may show a user interface, such as the user interface 400b discussed previously, to provide information to the user regarding menstrual cycle estimation. Such information may include estimates of conception windows, menstrual periods, ovulation, etc. The display may be touch sensitive, force sensitive, or otherwise used as user input. In this way, the display 715 may accept user data, such as for menstrual period tracking, and the like.

The wearable device 700 may include one or more other user interfaces, such as a rotatable crown 725, buttons 730, and the like. The user may rotate the crown, press or slide buttons, or otherwise interact with these devices to provide input. As discussed herein, such inputs may be used to establish an initial zero day menstrual/conception window prediction, interact with a module such as cycle status module 202, or otherwise provide or request information related to menstrual cycle tracking.

The strap 720 may couple the wearable device 700 to a user. This may be particularly useful where the heart rate sensor is integrated into or extends through a portion of the housing 710 (e.g., the rear of the housing). The strap 720 may hold the wearable device in a position relative to the user that allows the heart rate sensor to operate unobtrusively. As one example, the belt may position the wearable device such that the heart rate sensor remains in continuous or near continuous contact or proximity with the user. This may allow the heart rate sensor to collect heart rate data without any prompting of the user.

As yet another option, the heart rate sensor may be integrated into the crown 725, the button 730, the display 715, or the band 720.

Fig. 8 is an exemplary block diagram of an ovulation monitoring system 800 which may take the form of any of the devices as described with respect to fig. 1 to 7. The ovulation monitoring system 800 may include a processor 802, an input/output (I/O) mechanism 804 (e.g., a wired or wireless communication interface), a display 806, a memory 808, sensors 810 (e.g., physiological sensors such as those described herein), and a power source 812 (e.g., a rechargeable battery). The processor 802 may control some or all of the operations of the ovulation monitoring system 800. The processor 802 may be in communication with some or all of the components of the ovulation monitoring system 800, either directly or indirectly. For example, a system bus or other communication mechanism 814 may provide for communication between the processor 802, the I/O mechanism 804, the memory 808, the sensor 810, and the power supply 812.

The processor 802 may be implemented as any electronic device capable of processing, receiving, or transmitting data or instructions. For example, the processor 802 may be a microprocessor, a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), or a combination of such devices. As described herein, the term "processor" is intended to encompass a single processor or processing unit, multiple processors, multiple processing units, or one or more other suitable computing elements. The processing unit may be programmed to perform various aspects of the systems described herein.

It should be noted that the components of the ovulation monitoring system 800 may be controlled by a plurality of processors. For example, selected components of the ovulation monitoring system 800 (e.g., the sensor 810) may be controlled by a first processor, and other components of the ovulation monitoring system 800 (e.g., the I/O804) may be controlled by a second processor, wherein the first processor and the second processor may or may not be in communication with each other.

The I/O device 804 may transmit data to and/or receive data from a user or another electronic device. The I/O devices may transmit electrical signals via a communication network such as a wireless and/or wired network connection. Examples of wireless and wired network connections include, but are not limited to, cellular networks, wi-Fi, bluetooth, IR, and ethernet connections. In some cases, the I/O device 804 may communicate with an external electronic device, such as a smart phone, electronic device, or other portable electronic device, as described herein.

The ovulation monitoring system may optionally include a display 806, such as a Liquid Crystal Display (LCD), an Organic Light Emitting Diode (OLED) display, a Light Emitting Diode (LED) display, or the like. If the display 806 is an LCD, the display 806 may also include a backlight component that can be controlled to provide a variable display brightness level. If the display 806 is an OLED or LED display, the brightness of the display 806 may be controlled by modifying the electrical signal provided to the display element. Display 806 may correspond to any of the displays shown or described herein.

The memory 808 may store electronic data that may be used by the ovulation monitoring system 800. For example, memory 808 may store electrical data or content such as, for example, audio and video files, documents and applications, device settings and user preferences, timing signals, control signals, and data structures or databases. Memory 808 may be configured as any type of memory. By way of example only, the memory 808 may be implemented as random access memory, read only memory, flash memory, removable memory, other types of storage elements, or a combination of such devices.

The ovulation monitoring system 800 may also include one or more sensors 810 positioned substantially anywhere on the ovulation monitoring system 800. The sensor 810 may be configured to sense one or more types of parameters such as, but not limited to, pressure, light, touch, heat, movement, relative motion, biometric data (e.g., a biometric parameter), and the like. For example, the sensors 810 may include thermal sensors, position sensors, light or optical sensors, accelerometers, pressure transducers, gyroscopes, magnetometers, health monitoring sensors, and the like. Further, the one or more sensors 810 may utilize any suitable sensing technology including, but not limited to, capacitive, ultrasonic, resistive, optical, ultrasonic, piezoelectric, and thermal sensing technologies.

The power supply 812 may be implemented with any device capable of providing power to the ovulation monitoring system 800. For example, the power source 812 may be one or more batteries or rechargeable batteries. Additionally or alternatively, the power source 812 may be a power connector or power cord that connects the ovulation monitoring system 800 to another power source, such as a wall outlet.

As described above, one aspect of the present technology is to monitor and manage a physiological condition of a user, such as tracking menstrual cycles, and the like. The present disclosure contemplates that in some examples, such collected data may include personal information data that uniquely identifies or may be used to contact or locate a particular person. Such personal information data may include demographic data, location-based data, telephone numbers, email addresses, twitter IDs (or other social media aliases or treatments), home addresses, data or records related to the user's health or fitness level (e.g., vital sign measurements, medication information, exercise information), date of birth, or any other identifying information or personal information.

The present disclosure recognizes that the use of such personal information data in the present technology may be used to benefit users. For example, personal information data may be used to provide user-customized haptic or audiovisual output. In addition, the present disclosure contemplates other uses for personal information data that are beneficial to the user. For example, health and fitness data may be used to provide insight into the overall health of a user, or may be used as positive feedback to individuals using technology to pursue health goals.

The present disclosure contemplates that entities responsible for collecting, analyzing, disclosing, transmitting, storing, or otherwise using such personal information data will adhere to established privacy policies and/or privacy practices. In particular, such entities should implement and adhere to privacy policies and practices that are recognized as meeting or exceeding industry or government requirements for maintaining the privacy and security of personal information data. Such policies may be readily accessed by a user and should be updated as the collection and/or use of data changes. Personal information from users should be collected for legal and reasonable use by entities and not shared or sold outside of these legal uses. In addition, such collection/sharing should be performed after informed consent is received from the user. In addition, such entities should consider taking any necessary steps to defend and secure access to such personal information data and to ensure that others who have access to personal information data adhere to their privacy policies and procedures. In addition, such entities may subject themselves to third party evaluations to prove compliance with widely accepted privacy policies and practices. In addition, policies and practices should be adjusted to collect and/or access particular types of personal information data and modified to suit applicable laws and standards including specific considerations of jurisdiction. For example, in the united states, the collection or acquisition of certain health data may be governed by federal and/or state law, such as the health insurance flow and liability act (HIPAA); while health data in other countries may be subject to other regulations and policies and should be processed accordingly. Thus, different privacy practices should be maintained for different personal data types in each country.

In spite of the foregoing, the present disclosure also contemplates embodiments in which a user selectively prevents use or access to personal information data. That is, the present disclosure contemplates that hardware elements and/or software elements may be provided to prevent or block access to such personal information data. For example, in terms of determining spatial parameters, the present technology may be configured to allow a user to choose to "opt-in" or "opt-out" to participate in the collection of personal information data during or at any time after registration with a service. In addition to providing the "opt-in" and "opt-out" options, the present disclosure also contemplates providing notifications related to accessing or using personal information. For example, the user may be notified that his personal information data will be accessed when the application is downloaded, and then be reminded again just before the personal information data is accessed by the application.

Further, it is an object of the present disclosure that personal information data should be managed and processed to minimize the risk of inadvertent or unauthorized access or use. Once the data is no longer needed, risk can be minimized by limiting the data collection and deleting the data. In addition, and when applicable, included in certain health-related applications, the data de-identification may be used to protect the privacy of the user. De-identification may be facilitated by removing a particular identifier (e.g., date of birth, etc.), controlling the amount or characteristics of data stored (e.g., collecting location data at a city level rather than an address level), controlling the manner in which data is stored (e.g., aggregating data among users), and/or other methods, where appropriate.

Thus, while the present disclosure broadly covers the use of personal information data to implement one or more of the various disclosed embodiments, the present disclosure also contemplates that the various embodiments may be implemented without accessing such personal information data. That is, various embodiments of the present technology do not fail to function properly due to the lack of all or a portion of such personal information data. For example, the haptic output may be provided based on non-personal information data or an absolute minimum of personal information (such as events or status at a device associated with the user, other non-personal information, or publicly available information).

For purposes of explanation, the foregoing descriptions use specific nomenclature to provide a thorough understanding of the embodiments. However, it will be apparent to one skilled in the art that the specific details are not required in order to practice the embodiments. Thus, the foregoing descriptions of specific embodiments described herein are presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the embodiments to the precise forms disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art in light of the above teachings.

Claims

1. A method for tracking menstrual cycles of a user, the method comprising:

obtaining, at an electronic device, a first set of temperature data;

determining that the first set of temperature data meets a first criterion;

in response to determining that the first set of temperature data meets the first criteria, determining a first probability of ovulation occurring during a first set of days using the first set of temperature data;

determining that the first probability meets a second criterion;

in response to determining that the first probability meets the second criterion, determining a set of probabilities;

selecting an estimated ovulation date from the first set of days using the set of probabilities; and

displaying an output on the electronic device indicating the estimated ovulation date, wherein:

the probability set includes the probability of ovulation occurring daily in the first set of days.

2. The method of claim 1, further comprising:

obtaining, at the electronic device, a second set of temperature data;

determining that the second set of temperature data meets the first criterion;

in response to determining that the first set of temperature data meets the first criteria, determining a second probability of ovulation occurring during a second set of days using the second set of temperature data; and

Determining that the second probability does not meet the second criterion,

wherein:

obtaining the first set of temperature data at the electronic device includes obtaining the first set of temperature data in response to determining that the second probability does not meet the second criterion.

3. The method of claim 1, further comprising:

determining, at the electronic device, a duration of the menstrual cycle of the user after selecting the estimated ovulation date; and

an updated estimated ovulation date is determined using the determined duration of the menstrual cycle.

4. The method of claim 3, wherein determining the updated estimated ovulation date comprises:

identifying a second set of days using the duration of the menstrual cycle;

identifying a third set of days using the duration of the menstrual cycle; and

an increase in temperature of the user from the second set of days to the third set of days is determined.

5. The method according to claim 1, wherein:

determining the first probability includes inputting the first set of temperature data into a classification algorithm; and

determining the set of probabilities includes inputting the first set of temperature data into an artificial neural network.

6. The method according to claim 5, wherein:

the classification algorithm comprises a random forest classification model; and

the artificial neural network comprises a long-term and short-term memory artificial neural network.

7. The method of claim 1, further comprising:

determining a start date of the menstrual cycle prior to obtaining the first set of temperature data;

estimating a conception window based on the determined start of the menstrual cycle; and

updating the conception window using the estimated ovulation date.

8. The method of claim 7, further comprising: in response to updating the conception window, causing the electronic device to output a notification to the user indicating the updated conception window.

9. The method of claim 1, further comprising: the estimated ovulation date is used to predict the end of menstrual cycle date.

10. A method for estimating ovulation of a user, the method comprising:

determining, at an electronic device, a start date of a first menstrual cycle of the user;

obtaining a set of temperature data at the electronic device after the start date of the first menstrual cycle;

determining a set of probabilities using the set of temperature data, the set of probabilities including corresponding probabilities of ovulation occurring daily in the set of days;

Determining an estimated ovulation date of the first menstrual cycle using the set of probabilities;

displaying a first output on the electronic device based on the estimated ovulation date;

determining a start date of a second menstrual cycle subsequent to the first menstrual cycle;

determining an updated ovulation date for the first menstrual cycle using the start date of the second menstrual cycle; and

a second output is displayed on the electronic device based on the updated ovulation date.

11. The method of claim 10, further comprising:

displaying the first output includes displaying a first indication of a conception window selected using the estimated ovulation date.

12. The method of claim 10, wherein determining the updated ovulation date comprises:

identifying, at the electronic device, a window of days using the start date of the first menstrual cycle and the start date of the second menstrual cycle;

for each day in the window of days, comparing a first average temperature for a first number of days before the day with a second average temperature for a second number of days after the day to determine a corresponding temperature change; and

A day of the window of days is selected as the updated ovulation date using the corresponding temperature change determined for the window of days.

13. The method of claim 10, comprising:

inputting the set of temperature data into a classification algorithm; and

an output from the classification algorithm is received indicating that ovulation occurred within the set of days.

14. The method of claim 13, wherein determining the set of probabilities comprises:

in response to receiving the output indicating that ovulation has occurred, the set of temperature data is input into an artificial neural network to generate the set of probabilities.

15. The method of claim 10, further comprising:

determining that a threshold amount of time has elapsed since the start date of the first menstrual cycle; wherein:

the set of temperature data is obtained in response to determining that the threshold amount of time has elapsed.

16. An electronic device for tracking a menstrual cycle of a user, comprising:

one or more temperature sensors that measure a temperature of the user;

a display; and

a processor configured to collect a set of temperature measurements using the one or more temperature sensors, wherein:

The processor is configured to operate in a first mode to:

determining that a first subset of the set of temperature measurements associated with a first set of days meets a first criterion;

determining a first estimated ovulation date for the user using the first subset of the set of temperature measurements using a first set of operations, the first set of operations comprising an artificial neural network outputting a set of probabilities, the set of probabilities comprising probabilities of ovulation occurring daily in a window of days; and

the processor is configured to operate in a second mode to:

determining that a second subset of the set of temperature measurements associated with a second set of days meets a second criterion; and

a second set of operations is used to determine a second estimated ovulation date using the second subset of the set of temperature measurements, a start date of a menstrual cycle, and an end date of the menstrual cycle.

17. The electronic device of claim 16, further comprising:

a heart rate sensor; and

the processor is configured to operate in a third mode to:

determining that a third subset of the set of temperature measurements associated with a third set of days fails to meet the first criteria and the second criteria;

Responsive to determining that the third subset of the set of temperature measurements fails to meet the first criteria and the second criteria, obtaining a set of heart rate data received from the heart rate sensor; and

the third estimated ovulation date is determined using the set of heart rate data.

18. The electronic device of claim 16, wherein:

determining that the second subset of the set of temperature measurements meets the second criterion includes determining that the second subset of the set of temperature measurements does not meet the first criterion.

19. The electronic device of claim 16, wherein the processor is configured to, when operating in the first mode:

inputting the first subset of the set of temperature measurements into a classification algorithm; and

an output from the classification algorithm is received indicating ovulation occurred within the window of days.

20. The electronic device of claim 19, wherein the processor is configured to, when operating in the first mode:

in response to receiving the output indicative of ovulation occurring, inputting the first subset of the set of temperature measurements into the artificial neural network.