Breastfeeding guidance method, device and its application

Abstract

A method for breastfeeding guidance includes capturing at least one image, displaying the at least one image, identifying whether a person's posture in the at least one image is correct according to a plurality of rules for breastfeeding, dynamically notifying the person to adjust the person's posture until each of the plurality of rules is satisfied, starting a timer to indicate that breastfeeding has begun, further identifying and notifying the person to adjust the person's posture according to the plurality of rules during breastfeeding, and ending and recording when breastfeeding has ended.

Description

[Technical Field]

[0001] The present invention relates to a breastfeeding guidance method, device and application thereof. [Background technology]

[0002]

[0002] After COVID-19, half of mothers intend to breastfeed for longer to provide their babies with the best immunity. However, only 29% of mothers continue breastfeeding for the first six months. During breastfeeding, 52% of mothers do not have enough breast milk, while 27% of mothers find breastfeeding painful. It is important to help resolve or at least alleviate these issues. Furthermore, not all mothers have a personal coach to teach them the correct way to breastfeed their babies, which may make it difficult for the baby to obtain milk and / or for the mother to supply milk. Therefore, there is a need for teaching methods, devices, and applications for correct breastfeeding positions for mothers and / or babies.

[0003]

[0003] The present invention helps pregnant or breastfeeding women learn and modify their breastfeeding position directly at home, thereby improving their breastfeeding experience. Summary of the Invention

[0004]

[0004] The present invention relates to a breastfeeding guidance method, device and application thereof.

[0005]

[0005] According to an embodiment of the present invention, a method for breastfeeding guidance includes capturing at least one image, displaying the at least one image, identifying whether a person's posture in the at least one image is correct according to a plurality of rules for breastfeeding, dynamically notifying the person to adjust their posture until each of the plurality of rules is satisfied, starting a timer, further identifying the person's posture and notifying the person to adjust their posture according to the plurality of rules during breastfeeding, and ending and recording the timer when breastfeeding is completed.

[0006] According to an embodiment of the present invention, an electronic device comprises a camera, a display, and a processor that performs the method of the present invention.

[0007] According to an embodiment of the present invention, a storage medium and a program / software are configured to store instructions that are executed by at least one processor to perform the method of the present invention. [Brief explanation of the drawings]

[0008]

[0008] The present invention will be discussed in more detail below with reference to the accompanying drawings. [Figure 1]

[0009] Figure 1 shows a method for breastfeeding instruction. [Figure 2]

[0010] FIG. 2 shows a method for feeding guidance when the baby is not identified. [Figure 3]

[0011] FIG. 3 shows a device for breastfeeding guidance. [Figure 4]

[0012] Figure 4 shows the guide outline in a seated breastfeeding position. [Figure 5]

[0013] Figure 5 shows the guide outline for the side-lying nursing position. DETAILED DESCRIPTION OF THE INVENTION

[0009]

[0014] Embodiments of the present disclosure are described below with reference to the accompanying drawings. However, the embodiments of the present disclosure are not limited to the particular embodiments, but should be construed to include all modifications, variations, equivalent devices and methods, and / or alternative embodiments of the present disclosure.

[0010]

[0015] As used herein, the terms "have," "may have," "include," and "may include" indicate the presence of the corresponding feature (e.g., a value, function, operation, or element such as a component) and do not exclude the presence of additional features.

[0011]

[0016] As used herein, the terms "A or B," "at least one of A or / and B," or "one or more of A or / and B" include all possible combinations of the items listed therewith. For example, "A or B," "at least one of A and B," or "at least one of A or B" means (1) including at least one A, (2) including at least one B, or (3) including both at least one A and at least one B.

[0012]

[0017] As used herein, terms such as "first" and "second" may modify various elements and do not limit the corresponding elements, regardless of the order and / or importance of the corresponding elements. These terms may be used to distinguish one element from another. For example, a first printed form and a second printed form may refer to different printed forms, regardless of the order or importance. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the present invention.

[0013]

[0018] When an element (e.g., a first element) is "operably or communicatively coupled" or "connected" to another element (e.g., a second element), it is understood that the element may be directly coupled to the other element, or there may be intervening elements (e.g., third elements) between the element and the other element. Conversely, when an element (e.g., a first element) is "directly coupled" or "directly connected" to another element (e.g., a second element), it is understood that there are no other intervening elements (e.g., third elements) between the element and the other element.

[0014]

[0019] As used herein, the phrase "configured to" may be used interchangeably with "suitable for," "capable of," "designed to," "adapted to," "made to," or "capable of," depending on the context. The term "configured to" does not necessarily mean "specially designed" at the hardware level. Instead, the phrase "an apparatus configured to..." may mean that the apparatus is "capable of..." in some context, together with other devices or parts.

[0015]

[0020] The terms used in describing various embodiments of the present disclosure are intended to describe specific embodiments and are not intended to limit the present disclosure. As used in this disclosure, the singular form is intended to include the plural form unless clearly indicated otherwise. All terms, including technical or scientific terms, used herein have the same meaning as commonly understood by those skilled in the art unless otherwise defined. Terms defined in commonly used dictionaries should be interpreted as having the same or similar meaning as in the context of the relevant art, and should not be interpreted as having an ideal or exaggerated meaning unless explicitly defined herein. In some cases, even terms defined in this disclosure should not be interpreted as excluding embodiments of the present disclosure.

[0016]

[0021] Figure 1 shows a method for breastfeeding instruction. Some steps shown in Figure 1 may be omitted, and the order of the steps may be different.

[0017]

[0022] In step 101, at least one image (used interchangeably herein as "image" and "images") is captured. This may be via a separate camera or an integrated camera in an electronic device, e.g., a mobile phone, tablet, laptop, desktop, TV, etc. Images may be captured continuously or at a predetermined interval (e.g., one per second).

[0018]

[0023] Prior to this step, a user (e.g., in this application, the user may be the mother or someone else assisting the mother) may start a breastfeeding instruction application (e.g., an app on a smartphone) installed (and / or stored) on an electronic device. The device may then identify (e.g., executed by at least one processor) whether there is an available camera. If no available camera is identified, the method may stop or may play at least one or more instructions (e.g., text, images, video, audio, animation, etc.) on the device to provide general instructions to the mother.

[0019]

[0024] If an available camera is detected, the user may be asked to consent to using the camera. For example, when the user provides input indicating consent to use the camera, the subsequent steps are performed, e.g., in Figures 1 and 2. Otherwise, the same steps are performed as if no camera was identified.

[0020]

[0025] Before and / or during step 101, the user may be given some general guidance, such as "Please hold the camera / device at a distance (e.g., 0.5 to 3 meters, or 1 meter)", "The method will count down for 5 seconds before capturing the image", "Please relax and sit / lie down comfortably", etc.

[0021]

[0026] In step 102, the images are displayed on a screen / display of the device, for example on a separate display / monitor / screen or on an integrated display unit, for example on a mobile phone, tablet, laptop, etc. A single image or a video formed by the captured images may also be displayed, for example a live stream captured by a camera.

[0022]

[0027] The image may be displayed as a mirror image to help the mother easily adjust her and / or her baby's position.

[0023]

[0028] It should be noted that, as used herein, a "baby" may be a real baby or a fake baby, e.g., a doll, a roll of blanket, etc. A fake baby may be used by a mother to practice breastfeeding.

[0024]

[0029] In step 103, it is identified whether the posture of the person (e.g., mother) in one or more of the images is correct according to a number of rules for breastfeeding. The images may be images captured (and / or displayed) at the moment of performing step 103 or previous images. The person may be the mother or any other person (e.g., father) who wants to try the application. Optionally, the application may or may not identify the gender of the person. In this specification, the term "mother" is used interchangeably with the term "person."

[0025]

[0030] This step may include an initial step (which may be omitted) to identify whether a person (e.g., the mother) appears in the image and / or whether the person is in a typical breastfeeding position. The step of identifying whether a person appears in the image may be omitted, as may the step of identifying whether the person is in a typical breastfeeding position. If a person does not appear in the image (e.g., no body parts of the person are identified), the device may notify the user, for example, via at least one of audio, image, video, or any other notification method, to adjust the camera or the mother's position so that they are in the image.

[0026]

[0031] If a person is identified as appearing in the image (e.g., one or more of the person's parts are identified), the device may further identify whether the person (e.g., the mother) is in a common breastfeeding position. For example, guide outlines such as those shown in FIGS. 4 and 5 may be displayed, and the user may be prompted to enter a breastfeeding type. The breastfeeding type is a common breastfeeding position for the mother and / or baby, such as a seated breastfeeding position, a side-lying breastfeeding position, or any other breastfeeding position. For example, FIG. 4 shows a guide outline for a seated breastfeeding position, and FIG. 5 shows a guide outline for a side-lying breastfeeding position. Alternatively, the breastfeeding type may be identified automatically by analyzing the image. The mother may be notified by the device to position herself according to the guide outline (identified or selected / entered by the user) to meet the common breastfeeding position.

[0027]

[0032] Identifying that a common breastfeeding position is satisfied may include identifying that at least one of the basic filtering rules is satisfied by the position of the mother and / or baby.

[0028]

[0033] A rule may be considered satisfied if the associated posture complies with the rule for a predefined period of time or more, or for a threshold period of time within a predefined period of time or more. For example, a rule may be considered satisfied if the posture complies with the rule for a total of 5 seconds, or if the posture complies with the rule for 3 seconds or more out of a total of 5 seconds. Rules may include the following:

[0029]

[0034] 1. The mother's hips should be in the image. If not, the mother may be notified to adjust her position to include her hips in the image.

[0030]

[0035] 2. The mother's wrists, elbows, and shoulders should be in the image. The mother may be notified to adjust her position accordingly.

[0031]

[0036] 3. The mother is not too close to the camera and is not facing the camera. For example, if she is not showing her side in a sitting breastfeeding position, she is not facing the camera directly. This may be determined according to the mother's shoulder width and ear distance, and / or arm length in the image. For example, if the shoulder width in the image is shorter than 1.2 times the ear distance, the device determines that the mother is too close to the camera. The mother may be notified to face the camera and maintain a greater distance.

[0032]

[0037] 4. Do not place the camera too high or too low. For example, in a seated breastfeeding position, the device determines this according to the mother's shoulder and hip widths in the image. For example, if the shoulder width is greater than 1.2 times the hip width, the camera is too high, and / or if the hip width is greater than 1.5 times the shoulder width, the camera is too low. The mother may be notified to place the camera higher or lower.

[0033]

[0038] 5. Ensure that at least one or both of the mother's elbows are not too close to the camera, not too high, and / or not too far from the mother's body. This may be determined in a similar manner to 4, depending on the shoulder width as a reference distance in the image.

[0034]

[0039] The above-mentioned mother's body parts may be recognized and abstracted as key points and / or key areas. The key points may be positions on the center points of the relevant body parts, positions on the side points of the relevant body parts, or random positions on the relevant body parts. For example, the key points may include at least one of the right hand, right wrist, right elbow, right shoulder, nose, left palm, left wrist, left elbow, left shoulder, left breast, right breast, left nipple, right nipple, etc. The recognition / identification of the body key points may be via artificial intelligence and / or image reorganization technology. The key areas may be areas of the relevant body parts, such as the back area, head area, right hand area, right wrist area, right elbow area, right shoulder area, nose area, left palm area, left wrist area, left elbow area, left shoulder area, left breast area, right breast area, left nipple area, right nipple area, etc.

[0035]

[0040] The hand key point may be the center point of the back of the hand, the wrist key point may be the midpoint of the line between the hand and the forearm, the elbow key point may be the junction of the forearm and the upper arm, the shoulder key point may be the junction of the upper arm and the shoulder, the head key point may be the nose (e.g., in the case of a mother) or the ear drop (e.g., in the case of a baby), the chest key point may be the nipple position and / or may be estimated according to the mother's shoulder width and upper height, the waist key point may be the midpoint or one of the two edge points of the hip bones, and the neck key point may be the junction of the upper body and the head.

[0036]

[0041] In the first step, the breast being breastfed (e.g., left or right breast) may also be identified, for example, via user input and / or analysis of the image. For example, the breast being breastfed may be determined according to the recognized baby's head direction (e.g., the breast being breastfed is on the same side of the baby's head). In this case, the guide outlines shown in Figures 4 and 5 may be adjusted accordingly, for example, reflected according to the identified breastfed breast. Note that the baby may be a real baby or a fake baby (e.g., a doll).

[0037]

[0042] During the initial step, when the mother adjusts her posture and / or the baby's posture according to the guide outline and the basic filtering rules are satisfied, the later steps may be executed. The first step may be omitted, and the device may directly execute step 103 after step 102.

[0038]

[0043] Step 103 identifies whether the mother has a correct posture according to multiple rules for breastfeeding, for example, by analyzing the captured image or at least one displayed and / or a subset of the captured image, for example, only one image within each second of the captured and / or displayed video may be analyzed (e.g., displaying more images but analyzing only one image within each second).

[0039]

[0044] This step may include identifying the posture of the mother and / or baby through key points / areas on the mother and baby's bodies.

[0040]

[0045] The guide outline may still be displayed throughout this step and step 103. The identified key points / areas may or may not also be displayed. When displaying the key points / areas, the key points may be connected with the human anatomy and / or the key areas may be displayed with colored areas or boxes / circles / outlines of the key areas. The displayed guide outline and / or key points / areas can help the mother understand the relative positions of body parts and correct her (and / or the baby's) position in later steps. The outline and / or key points / areas may be displayed (e.g., mirrored) during the start of this step, throughout all steps, or until the end of the method.

[0041]

[0046] Furthermore, the mother's posture may also be classified into different feeding types, e.g., sitting or lying down. A mother can mainly breastfeed her baby in these two positions. The classification follows the identified key points / areas, for example, by comparing them with key point / area information in the sitting position and the lying down position. Alternatively, before step 101, or after step 101, before step 102, or after step 102 and before step 103, the method may include an additional step for receiving a user input for selecting a feeding type.

[0042]

[0047] The multiple rules may include key point / area information regarding the correct breastfeeding posture of the mother and / or baby. The multiple rules may include different rule sets based on key point / area information for different breastfeeding types. For example, a sitting breastfeeding position may have different rules than a side-lying breastfeeding position. The correct breastfeeding posture may be obtained via artificial intelligence after training with a large number of images with the correct breastfeeding posture, for example, by subtracting all key points / areas and obtaining relative position information (and / or within a tolerance range) of the key points / areas.

[0043]

[0048] In this step, the device may also identify whether a baby is present in at least one image. If a baby is not identified, the method may enter a feeding training mode in which an artificial baby may be displayed. For example, the artificial baby may be displayed between the mother's arms when the mother is in a sitting position, or in front of the mother's upper body when the mother is in a lying position. The artificial baby may be an animation, an image, a movie, or any other display object representing a baby.

[0044]

[0049] If a baby (e.g., a real baby or a fake baby) is identified, the baby's posture may also be identified in addition to the mother's posture. Identification of the baby's posture may be in a similar manner to that of the mother, for example, via identifying key points / areas on the baby's body. For example, the baby's key points / areas may include at least one of the head, (left / right) shoulders, back, waist, neck, (left / right) ears, mouth, nose, hands, face, etc. Recognition / identification of key points / areas on the body may be via artificial intelligence, for example, trained on images of babies breastfeeding.

[0045]

[0050] If a baby is identified (e.g., a real baby or a fake baby), a guide outline of the baby or identified key points / areas of the baby may be displayed as well. The displayed guide outline and / or key points / areas can help the mother understand the relative positions of the mother's and / or baby's body parts and correct the mother's and / or baby's posture accordingly, e.g., in a later step.

[0046]

[0051] The baby may be fully identified, for example, if all relevant keypoints / areas are identified or only some of the keypoints / areas are identified, or may be partially identified (e.g., real baby or fake baby). The keypoints / areas may be the keypoints / areas of the baby included in the rules for identifying whether the mother and baby are in the correct position.

[0047]

[0052] The (fully or partially) identified baby's pose may be determined to be correct according to the multiple rules mentioned above, for example, if the identified keypoints / areas of the baby have a certain relative distance / position to at least one of the other keypoints / areas of the baby and the mother's keypoints / areas, the baby's pose is correct (according to the rules).

[0048]

[0053] The rules may be different in different scenarios according to at least one of whether relevant key points / areas of the baby and / or mother are fully identified, left / right feeding, and feeding type (e.g., sitting or lying feeding position). The scenarios may include at least one of the following:

[0049]

[0054] 1. Sitting in left feeding position with baby and baby's key points / areas fully identified.

[0050]

[0055] 2. Sitting in the right feeding position with baby and baby's key points / areas fully identified.

[0051]

[0056] 3. Sitting in left breastfeeding position with baby and baby's key points / areas partially identified.

[0052]

[0057] 4. Sitting in right feeding position with baby and baby's key points / areas partially identified.

[0053]

[0058] 5. Sitting in left breastfeeding position without baby.

[0054]

[0059] 6. Sitting in right feeding position without baby.

[0055]

[0060] 7. Sleeping on your side in the left breastfeeding position with your baby and his / her key points / areas fully identified.

[0056]

[0061] 8. Sleeping on your side in the right feeding position with your baby and his / her key points / areas fully identified.

[0057]

[0062] 9. Lying on your side in the left breastfeeding position with your baby and key points / areas of your baby partially identified.

[0058]

[0063] 10. Lying on side in right feeding position with baby and key points / areas of baby partially identified.

[0059]

[0064] 11. Sleeping on your side in the left breastfeeding position without your baby.

[0060]

[0065] 12. Sleeping on your side in the right breastfeeding position without your baby.

[0061]

[0066] 13. The mother is not identified in the image.

[0062]

[0067] Some basic rules may include at least one of the following:

[0063]

[0068] 1. The mother's elbow needs to support the baby's neck.

[0064]

[0069] 2. The mother's forearms need to support the baby's back.

[0065]

[0070] 3. The relative positions of the mother's forearm, hand, and wrist should be appropriate (e.g., comfortable for the mother).

[0066]

[0071] 4. The baby's head should be higher than the baby's waist.

[0067]

[0072] 5. Your baby's head (or ears), shoulders, and hips should be in a straight line.

[0068]

[0073] 6. The baby's head faces the mother's breast, and the relative position between the baby's head and the breast is appropriate (e.g., not too far away so that the baby cannot reach the breast, and not too close so that the baby may not be able to breathe comfortably).

[0069]

[0074] The breast that the baby's head faces may be determined as the nursing breast.

[0070]

[0075] When there is no identified baby (e.g., a real baby or a fake baby), only some or all of the basic rules may be considered when identifying the correct breastfeeding position, for example, only rules 2, 3, and 6 may be included in the rules. A detailed example of the scenario when the baby is not identified is explained later with respect to FIG.

[0071]

[0076] The identifying step 103 (and / or any other identifying step in the present invention) may be performed in the same device that performs the other steps, or may be performed by an external device, for example, a server. In this case, the device can send at least one captured image to the external device via a communication unit, and after receiving at least one image, the server can perform the identifying step and then send the identification result back to the device. When the device receives the result, it performs the remaining steps.

[0072]

[0077] In step 104, the device dynamically notifies the mother to adjust her (and / or the baby's) position until all of the multiple rules are met.

[0073]

[0078] For example, in step 103, the posture of the mother and / or baby may be identified by rules according to the priority of the rules, e.g., the rule with the highest priority may be identified first and the rule with the lowest priority may be identified last. Alternatively, if the rule with the highest priority is identified as not satisfied, the identification step may stop and the mother may be notified of the unsatisfied rule.

[0074]

[0079] A rule may be considered satisfied if a posture complies with the rule for a predefined period of time or more, or if the posture complies with the rule for a threshold period of time or more within a predefined period of time. For example, a rule may be considered satisfied if a posture complies with the rule for a total of five seconds, or if a posture complies with the rule for three or more seconds out of a total of five seconds.

[0075]

[0080] If a rule is identified as not being met, a notification to the mother may be output, for example, via at least one of audio, text, image, animation, and video. Only the rule with the highest unmet priority is notified, or all unmet rules are notified to the mother one by one according to high to low priority. Optionally, if one of the multiple rules is still not met after a certain period and / or a predefined number of notifications, the unmet rule is ignored (e.g., in both identification and notification).

[0076]

[0081] Notifications may be generated based on rules, e.g.

[0077]

[0082] 1. Follow basic rule number 1: "Support your baby's neck with your elbow."

[0078]

[0083] 2. Follow basic rule 2: "Support the baby's back with your front arms."

[0079]

[0084] 3. Follow basic rule 3: "Front arm up," "Front arm down," "Lower arm up," and / or "Lower arm down."

[0080]

[0085] 4. Follow cardinal rule 4: "Keep baby's head higher than baby's hips," "Keep baby's head higher," or "Keep baby's hips lower."

[0081]

[0086] 5. Follow cardinal rule 5: "Keep baby's head (or ears), shoulders, and hips in a straight line," "Keep baby's neck high," "Keep baby's shoulders low," or similar notices.

[0082]

[0087] 6. Rule 6: "Turn baby's head toward breast," "Turn baby's head to the right," "Keep baby's head closer (or farther) from breast," or similar notice.

[0083]

[0088] The mother may be expected to adjust her and / or her baby's position according to the notification. Thus, steps 101, 102, 103, and 104 may be performed iteratively (e.g., once for every step over a period of time, e.g., every 5 seconds) until all (or some predefined number of) rules are met and the breastfeeding position can be determined to be correct.

[0084]

[0089] For example, every predefined period (e.g., 1 second, or depending on the duration of the notification), an image is captured (101), displayed (102), identified (103), and a notification is output (104).

[0085]

[0090] For example, the notification in step 104 may include only the notification according to the highest unsatisfied rule, and then a new image is captured (101), displayed (102), and identified (103). These steps are repeated until all rules are satisfied. Alternatively, the output notification in step 104 may include all notifications based on unsatisfied rules (e.g., in order of rule priority), and then a new image is captured (101), displayed (102), and identified (103). These steps are repeated until all rules are satisfied.

[0086]

[0091] After all rules are satisfied, steps 101, 102, and 103 may still be performed for a certain period of time to ensure that the mother and / or baby are in a stable, correct state. The certain period of time may be a continuous period during which all rules are satisfied. For example, the certain period of time may be three consecutive seconds during which no errors are identified. Alternatively, the certain period of time may be a predefined number of consecutive repetitions of steps 101, 102, and 103 during which no errors are identified (i.e., all rules are satisfied).

[0087]

[0092] If an unsatisfied rule has been signaled a certain number of times and the stance according to this rule is still not satisfied, this rule may be skipped in some or all subsequent steps (e.g., always considered correct), or this rule may be skipped for a certain period of time (e.g., considered correct during this certain period of time) and reconsidered after the certain period of time.

[0088]

[0093] If all rules (e.g., all rules that can be identified as being met) are met, a timer is started to indicate that breastfeeding should begin in step 105. The timer may start after the correct position of the mother and / or baby in step 104 has been continuously identified for a period of time during which all rules are met.

[0089]

[0094] The timer is advantageous because it generates a record of the duration of breastfeeding. The duration of breastfeeding may be compared, for example, according to the baby's age and / or historical data, thus monitoring the baby's growth and / or health. This also encourages the mother to maintain correct posture for as long as possible. The timer is also an indication of correct posture. The time, when compared with other babies or historical data, can also indicate whether the baby is adequately fed. If no baby was identified in steps 103 and / or 104, the timer may be omitted.

[0090]

[0095] For example, if it is not possible to determine whether some rules are satisfied because it is not possible to identify the relevant key points / areas, all these rules may be notified to the mother one by one (before or after starting the timer) to make sure that the mother receives all the information. Some other information may also be output, for example some relaxation tips / suggestions, or a piece of relaxing music, or speech with a suitable voice. This can help the mother and baby to relax.

[0091]

[0096] In step 106, the mother is dynamically notified to adjust her (and / or her baby's) posture according to multiple rules for breastfeeding during the breastfeeding period. This step is the same as step 104, and steps 101, 102, 103, and 104 may be repeated in the same manner. The only difference is that a timer may be displayed. Another difference is that the notification may only be output without using sound to avoid disturbing the baby. For example, the notification may be output via text, image, animation, or video without sound.

[0092]

[0097] The timer may be stopped and recorded when breastfeeding ends. A breastfeeding may be determined to have ended if the mother stops the timer or manually closes the application, or if the mother leaves the image (e.g., partially or completely out of the captured image for a period of time), or if the distance between the baby's head and the breastfeeding breast is greater than a predetermined distance for at least a period of time.

[0093]

[0098] During the breastfeeding period, the mother may use the device for other functions (e.g., watching news / videos, sending emails, etc.), so the application may run in the background (not closed) where the timer can still operate. If the application is closed while running in the background, the user may be reminded when the application is next opened / started, for example, informing the user that the timer ended abnormally and / or requesting the user to edit / enter the last breastfeeding time.

[0094]

[0099] FIG. 2 illustrates an example of the method of FIG. 1, a method for feeding guidance when the baby is not identified (eg, neither real nor fake baby is identified).

[0095]

[0100] Steps 201 and 202 are the same as steps 101 and 102, including all alternatives. For example, a user (e.g., a mother) may start a breastfeeding instruction application installed (or stored) on the electronic device before step 201 and then select a feeding type, e.g., in a seated or side-lying breastfeeding position. Alternatively, the feeding type may be detected and determined by the device (or an external device as described with respect to FIG. 1) by analyzing a captured image. Additional optional steps in FIG. 1 may also apply to FIG. 2 and will not be described in detail here.

[0096]

[0101] In step 203, it is identified that the baby does not appear in the image. Steps 201 to 203 may be performed repeatedly, for example, once for both steps every second. If the baby is still not identified after a certain period of time, it is determined that the application is to run in a "baby-free" mode (e.g., "feeding guidance mode"). The certain period may be a fixed time period (e.g., 3 seconds) or a number of consecutively captured and analyzed images (e.g., 5 or 10). After entering the "baby-free" mode, the mother may be notified via audio, text, video, animation, or any other method that the application is now operating in the "baby-free" mode. The application may also directly receive input from the user (i.e., the mother) to operate in the "baby-free" mode, in which case the identification step in step 203 may be omitted.

[0097]

[0102] In step 204, the artificial baby may be displayed over the displayed image of the mother. The artificial baby may be an animation, an image, a movie, or any other displayed object representing a baby. Prior to displaying the artificial baby, key points / areas and / or guide outlines of the mother may be identified. The location of displaying the artificial baby may follow the identified key points / areas and / or guide outlines of the mother.

[0098]

[0103] The baby may be displayed in a breastfeeding position within the image. For example, the artificial baby may be displayed in front of the mother's chest. The left or right breastfeeding position may be initially determined, for example, according to user input or by analyzing at least one image. For example, if the mother's left elbow is higher, it may be determined that the artificial baby's head may be supported by the left elbow, and therefore, the baby may be breastfed by the mother's left breast. Thus, the artificial baby's head may be displayed above the mother's left elbow, the edge of the baby's head may be attached to the mother's elbow, and the baby's body may be displayed along the mother's forearm.

[0099]

[0104] The position of the artificial baby may be displayed according to the feeding type, for example, sitting in a side-lying position with the mother. For example, the above example may be applied to a sitting feeding type. When the mother is in a side-lying position, it may be determined that the baby is intended to be fed by the breast closest to the bed (e.g., the lower breast in the image). For example, when the mother is lying on her left side, it may be determined that the baby is intended to be fed by the left breast. The artificial baby's head may then be displayed in the position of the mother's left breast, and the baby's body may be displayed in the same side-lying orientation as the mother (e.g., with the mother and artificial baby's heads facing the same direction). In a side-lying feeding position, the artificial baby may also be displayed lying on the bed (i.e., not in the mother's arms).

[0100]

[0105] The size of the displayed artificial baby may be determined according to identified key points / areas of the mother, such as the mother's arm length, head width, and / or shoulder width. For example, the artificial baby may have a length that is approximately 0.8 to 1.5 times the mother's shoulder width.

[0101]

[0106] The displayed artificial baby may be dynamically adjusted / adapted according to each captured and / or displayed image. Alternatively, once the baby's position and size have been determined, the artificial baby may be displayed in the same position for at least some period of time.

[0102]

[0107] After the baby is displayed, in step 204, the mother's posture is monitored and corrected, ie, dynamically identifying and notifying whether the mother's posture is correct according to multiple rules for breastfeeding.

[0103]

[0108] Before step 204, a notification may be output to indicate that the correction step is about to begin.

[0104]

[0109] Step 204 is performed in the same way as steps 103 and / or 104, except that an artificial baby is displayed. Rules relating only to key points / areas of the baby may be omitted, and only rules relating to key points / areas of the mother (or both the baby and the mother) are included in the multiple rules.

[0105]

[0110] In all examples of the present invention, for example in all diagrams, the rules for different feeding types may be different.

[0106]

[0111] For example, rules for a seated breastfeeding position may include and be prioritized in the following order (eg, lower numbers with higher priority or different priority orders):

[0107]

[0112] 1. One or both arms of the mother are within a certain area / range. For example, whether the relative position of one of the mother's arms compared to other key points / areas is within a range. The output notification to the mother may include "Please raise (and / or lower) your left arm (and / or right arm) and / or left hand (and / or right hand)" if this rule is not met.

[0108]

[0113] 2. The mother's elbow supports the baby's neck, which can be directly identified or calculated according to the key points / areas of the baby's head and shoulders.

[0109]

[0114] 3. The baby's head is higher than the baby's waist.

[0110]

[0115] 4. Your baby's head (or ears), shoulders, and hips are in a straight line.

[0111]

[0116] 5. The mother's front arm is placed on the baby's back. For example, if the mother's left elbow is supposed to support the baby's neck, the mother's left front arm can be placed on the baby's back to comfort / support the baby, and at the same time, the mother's left arm is in a comfortable position.

[0112]

[0117] 6. The baby's head faces the mother's breast, and the relative position between the baby's head and the breast is appropriate.

[0113]

[0118]

[0114]

[0119] Rules for side-lying nursing positions may include and be prioritized in the following order (higher priority with a lower number, or a different priority order):

[0115]

[0120] 1. The mother should lie on one side and face the camera.

[0116]

[0121] 2. The mother should sleep flat on her side (e.g., not support herself with her elbows or hands; this is not comfortable for the mother if continued for longer than a certain period).

[0117]

[0122] 3. The mother's forearm is on the baby's back. For example, if the mother is sleeping on her left side, she may intend to breastfeed the baby on the left breast, so it is comfortable for the mother to place her right hand on the baby's back area, which also makes the baby comfortable.

[0118]

[0123] 4. The baby's head is not held by the mother's hands. The baby may not feel comfortable when supported by one or both of the mother's hands.

[0119]

[0124] 5. Your baby's head (or ears), shoulders, and hips are in a straight line.

[0120]

[0125] 6. The baby's head faces the mother's breast, and the relative position between the baby's head and the breast is appropriate.

[0121]

[0126] In all examples, e.g., in all figures, in this description, the scenario may be determined according to whether the baby is fully or partially identified or not, which feeding type is used, and whether it is left-feeding or right-feeding. A fully identified baby mode may be a mode in which all relevant key points / areas of the baby, such as the baby's head, shoulders, and waist, can be identified. However, in real life, a baby may not be fully grown and may be wearing a lot of clothes or under a blanket, making it difficult to identify all relevant key points / areas. For example, the baby's waist may be difficult to identify under a blanket. A partially identified baby mode is a mode in which some, but not all, relevant key points / areas of the baby (e.g., including the most important key points / areas) may be identified. For example, only the baby's head can be identified. A non-identified baby mode (i.e., a no-baby mode or a feeding guidance mode) is a mode in which all key points / areas or the most important key points / areas may not be identified. For example, if the most important key point / area (eg, the baby's head) may not be identified, then none of the baby's relevant head, shoulders, and waist can be identified.

[0122]

[0127] The set of rules taken into account may be different in different scenarios: for example, in a full identification mode (of baby's key points / areas), all example rules may be included for all posture identification steps in the present invention (listed above for sitting and lying down positions), in a partial identification mode, only rules 1 and 6 for sitting down breastfeeding positions may be considered, and / or only rules 1, 2, 4 and 6 for lying down breastfeeding positions may be considered, in a non-identification mode, the example of Fig. 2 may be applied, where rules relating to only the baby may be ignored and rules relating to both the mother's posture and / or the mother's and baby's posture may be considered.

[0123]

[0128] When identifying whether a rule is satisfied in any step of the present invention, the relative positions of the mother's and / or baby's key points / areas are analyzed. For example, the vertical distance between the mother's shoulder and breast key points / areas (on the same side) or the length of the mother's upper body may be used as a reference for the vertical position of other key points / areas, and / or the distance between the mother's breast key points / areas or the width of the mother's shoulder key point / area may be used as a reference for the horizontal position of other key points / areas.

[0124]

[0129] For example, in a left-side breastfeeding position (e.g., either a sitting position or a lying position), the distance between the key points / areas of the mother's left shoulder and left breast may be used as the vertical reference distance. Typically, the exact height of the breastfeeding elbow (in this case, the left elbow) should be approximately the same height as the breastfeeding breast (and / or may be within a predetermined range). For example, the height of the breastfeeding elbow should be within a range of c+0.5d, where c is the height of the breastfeeding breast and d is the distance between the key points / areas of the mother's left shoulder and left breast. Therefore, depending on the breastfeeding elbow identification result, it can be determined whether to raise or lower the breastfeeding front arm (i.e., if the breastfeeding elbow is higher than c+0.5d, lower the breastfeeding front arm; otherwise, raise the breastfeeding front arm). The nursing-side wrist position may be identified in a similar manner, for example, whether it is c+0.2d or c-0.8d (e.g., if higher than c+0.2d, lower the nursing-side hand, otherwise raise the nursing-side hand).

[0125]

[0130] In the present invention, key locations on the non-nursing breast side can be identified in the same way as on the nursing breast side, e.g., as described above. However, some locations of key points / areas on the non-nursing side, e.g., the mother's wrist, which is not the nursing side, may be skipped (e.g., always considered correct).

[0126]

[0131] For example, when identifying whether a baby's head is facing the nursing breast, the keypoint / area of ​​the baby's head has a position (x,y) in the x / y axis position system on the image, and the keypoint / area of ​​the mother's nursing breast has a position (u,v). In that case, x should be in the range of u-0.5e and u+0.5e, and y should be in the range of v-0.5d and v+0.5d, where e is the distance between the keypoints / areas of the mother's left and right breasts. If x or y are out of range, the mother is notified to adjust her baby's head to face the nursing breast.

[0127]

[0132] Similarly, whether the mother's elbow is supporting the baby's neck may be determined by whether the distance between the key point / area of ​​the nursing-side elbow and the baby's shoulder is within a predetermined range, and whether the mother's forearm is on the baby's back may be determined by meeting at least one of the following conditions: a) whether the key point / area of ​​the hand from the relevant forearm is in the baby's back area; b) whether the key point / area of ​​the wrist from the relevant forearm is in the baby's back area; and c) whether the line connecting the wrist and elbow on the same side of the relevant forearm crosses the baby's back area.

[0128]

[0133] For example, when identifying whether the baby's head is being held by the mother's hands, the length of the baby may be used as a reference distance (e.g., k), and then it is identified whether the key points / areas of any of the mother's hands are within a certain area range, for example, within an area with the key points / areas of the baby's head as the center point and a radius of 0.1k. If they are within this area, it is determined that the mother is holding the baby's head, and the mother is notified to stop doing so.

[0129]

[0134] For example, when identifying whether a mother is facing the camera, it may be determined according to whether some or all key points / areas on the mother's face, such as the mother's two eyes and nose (and / or mouth), can be identified. For example, if all are identified, the mother is identified as facing the camera.

[0130]

[0135] The scenario may change between a fully identified baby, a partially identified baby, or an unidentified baby, or between feeding types or breastfeeding positions, e.g., from a scenario with a baby to a scenario without a baby. However, the rules and / or displayed information may change with a delay depending on the scenario change. For example, when the previous scenario changes to the changed scenario, the rule set is not changed immediately, but only after the changed scenario has been continuously identified for a certain period of time (e.g., 5 seconds or more). Similarly, the displayed user interface and / or notifications still follow the previous scenario for some time before the change. This is particularly advantageous for improving the user experience, e.g., avoiding too frequent switching of rules and user interfaces due to some short / transient events. For example, if a mother simply wants to stretch out one arm and quickly return to the correct feeding position, there is no need to change the rules at all.

[0131]

[0136] In the present example, after the mother is in the correct breastfeeding position (e.g., after steps 104 and 204), any rules that were identified as not satisfied in at least one of the previous scenarios (if the scenarios have changed) may be notified to the mother again, even if the rules no longer apply to the current scenario, to ensure that the mother gets all important instructions and rules.

[0132]

[0137] 1 and 2, the user may be able to actively turn the camera on and off. For example, during step 106, the user may turn the camera off because the pose has already been corrected. In this way, no dynamic correction may be performed in step 106.

[0133]

[0138] FIG. 3 shows a device 300 for implementing the present invention, such as a mobile phone, tablet, laptop, desktop, smartwatch, TV, etc.

[0134]

[0139] The device 300 may comprise a processor 301 , a display 302 , a communication unit 303 , a memory 305 , a camera 306 and other input / output units 307 .

[0135]

[0140] The processor 301 is configured to execute programs / instructions stored in the memory 305, for example, via controlling other components such as a display 302, a communication unit 303, a memory 305, a camera 306, and other input / output units 307.

[0136]

[0141] The display 302 may be controlled by the processor 301 to perform all display functions (and input functions if it is a touch screen) in the present invention, such as steps 102, 105, 202, etc.

[0137]

[0142] The communication unit 303 may be controlled by the processor 301 to perform all communication functions in the present invention. For example, when an external device 310 (e.g., a server) is used to perform some or all of the identification functions in the present invention, e.g., steps 103, 106, 203 and 204, messages such as sending images and / or receiving identification results are communicated via the communication unit 303. Optionally, the images may not be stored in the external device 310 for privacy reasons, e.g., the images are immediately deleted in the external device 310 after each identification step.

[0138]

[0143] The memory 305 is configured to store breastfeeding application software and / or data, such as scenarios, basic rules, corresponding rules for each scenario, captured images, identified results, user profile, usage history, breastfeeding records, relaxation tips, and other guidance, etc. The application may provide at least one entry for the user to check / monitor these data, such as breastfeeding records, rules, relaxation tips, and other guidance, etc.

[0139]

[0144] Camera 306 is configured to capture images in the present invention, for example, in steps 101 and 201 .

[0140]

[0145] Other input / output unit 307 is configured to perform other input / output functions of the present invention, for example to output audio notifications in steps 106 and 204, or to receive user input regarding the baby's feeding type and / or mode (e.g., fully, partially, or not identified) and / or any other usage settings.

[0141]

[0146] In the present invention, at least a portion of a device (e.g., FIG. 3) or a method (e.g., FIGS. 1 and 2) may be implemented as instructions stored on a non-transitory computer-readable storage medium, for example, in the form of a program module, software, a mobile app, and / or other form. The instructions, when executed by a processor (e.g., processor 301), may enable the processor to perform corresponding functions according to the present invention. The non-transitory computer-readable medium may be, for example, memory 305.

[0142]

[0147] According to one embodiment of the present invention, a method for breastfeeding guidance includes capturing at least one image, displaying the at least one image, identifying whether a person's posture in the at least one image is correct according to a plurality of rules for breastfeeding, dynamically notifying the person to adjust their posture until each of the plurality of rules is satisfied, starting a timer, further identifying the person's posture and notifying the person to adjust their posture according to the plurality of rules during breastfeeding, and ending and recording when breastfeeding is completed.

[0143]

[0148] According to one embodiment of the present invention, the method may include receiving input to identify or indicate a feeding type, such as, for example, whether a person is in a seated or side-lying feeding position.

[0144]

[0149] According to one embodiment of the present invention, the method may further include sending at least one image to an external device, receiving an identification result of the person's posture from the external device, or identifying the person's posture is performed by the electronic device.

[0145]

[0150] According to one embodiment of the present invention, identifying a person's posture according to a plurality of rules may further include identifying according to a priority of the plurality of rules, and / or the plurality of rules may include both at least one standard posture of a person and at least one standard posture of a baby.

[0146]

[0151] According to one embodiment of the present invention, at least one of dynamically notifying the person to adjust their posture may further include notifying the person according to a priority of the plurality of rules that have not been met, and / or the notifying is via at least one of audio, text, image, animation, and video methods.

[0147]

[0152] According to one embodiment of the present invention, at least one of dynamically notifying the person to adjust their posture may further include identifying a rule having a highest priority among the unsatisfied rules, notifying the person only of the rule having the highest priority at a time, and / or ignoring the unsatisfied rule if one of the multiple rules remains unsatisfied after a certain period and / or a predefined number of notifications.

[0148]

[0153] According to one embodiment of the present invention, the method further comprises identifying whether a baby appears in the at least one image, and if the baby is not identified, displaying an artificial baby and entering a coaching mode, and if the baby is identified, entering a feeding mode, and / or in the coaching mode, no timer is started.

[0149]

[0154] According to one embodiment of the present invention, the method may further include identifying whether the posture of the baby in the at least one image is correct according to a plurality of rules.

[0150]

[0155] According to one embodiment of the present invention, identifying the posture of the person and / or baby may further include identifying at least one key point and / or at least one key area of ​​the person and / or baby, and comparing the position of the identified at least one key point and / or at least one key area with a plurality of rules, wherein the plurality of rules include key point and / or key area information of the person and / or baby in a correct breastfeeding state.

[0151]

[0156] According to one embodiment of the present invention, the method may further include identifying a feeding scenario depending on at least one of the feeding type, whether the feeding breast is left or right, and whether the baby is fully identified, partially identified or not identified, and / or the plurality of rules includes different rule sets in different scenarios.

[0152]

[0157] According to one embodiment of the present invention, when a previous scenario switches to a changed scenario, the set of rules according to the previous scenario may switch to the set of rules according to the changed scenario when the changed scenario is identified for longer than a certain period of time.

[0153]

[0158] According to one embodiment of the present invention, if a baby is partially identified when one or more key points and / or key areas of the baby are identified but not all key points and / or key areas are identified, the multiple rules may exclude rules related to the unidentified key points and / or key areas of the baby.

[0154]

[0159] According to one embodiment of the present invention, the method may further comprise displaying a guide outline of the person and / or baby on the display before and / or during identification of the person's posture and / or baby's posture.

[0155]

[0160] According to one embodiment of the present invention, the rules may be based on a vertical reference distance between the shoulder and breast on the same side of the person.

[0156]

[0161] According to one embodiment of the present invention, the rules may be based on a horizontal reference distance between a person's breasts or a horizontal reference distance between a person's shoulders.

[0157]

[0162] According to one embodiment of the present invention, an electronic device comprises a camera, a display, and a processor for performing the method of the present invention.

[0158]

[0163] According to one embodiment of the present invention, a storage medium is configured to store instructions that are executed by at least one processor to perform the method of the present invention. The following is a summary of the claims as originally filed: [C1] 1. A method for breastfeeding instruction, comprising: capturing at least one image; displaying said at least one image; identifying whether a posture of the person in the at least one image is correct according to a plurality of rules for breastfeeding; dynamically notifying the person to adjust their posture until each of the plurality of rules is satisfied; Starting a timer; further identifying a posture of the person and informing the person to adjust their posture according to the plurality of rules while breastfeeding; and ending and recording said timer when the feeding is completed. [C2] The method of C1, further comprising identifying a feeding type or receiving input indicating the feeding type, for example, whether the person is in a seated or side-lying feeding position. [C3] sending the at least one image to an external device; receiving an identification of the person's posture from the external device; or The method of claim C1, wherein identifying the person's posture is performed by an electronic device. [C4] Identifying the posture of the person according to the plurality of rules includes: and / or further comprising identifying the plurality of rules according to a priority order. The method of claim C1, wherein the plurality of rules includes both at least one standard posture of the person and at least one standard posture of a baby. [C5] At least one of dynamically informing the person to adjust the person's posture and / or further comprising notifying the person in order of priority of the plurality of rules that are not satisfied. The method of C3, wherein the notifying is performed via at least one of audio, text, image, animation, and video. [C6] At least one of dynamically informing the person to adjust the person's posture identifying a rule having a highest priority among the unsatisfied rules; notifying the person at one time of only the rules having the highest priority; and / or If one of the plurality of rules remains unsatisfied after a specific period and / or a predefined number of notifications, ignoring the unsatisfied rule. [C7] identifying whether a baby is present in the at least one image; If the baby is not identified, display an artificial baby and enter coaching mode; and / or, if the baby is identified, entering a feeding mode. The method of any one of C1 to C6, wherein in the coaching mode, a timer is not started. [C8] The method of any one of C1 to C7, further comprising identifying whether the baby's posture in the at least one image is correct according to the plurality of rules. [C9] Identifying the posture of the person and / or the baby includes: identifying at least one key point and / or at least one key area of ​​said person and / or said baby; comparing the location of the identified at least one key point and / or at least one key area with the plurality of rules; A method according to any one of C1 to 8, wherein the plurality of rules comprises key point and / or key area information of the person and / or baby in a correct feeding state. [C10] further comprising identifying a feeding scenario depending on at least one of the feeding type, whether the feeding breast is left or right, and whether the baby is fully identified, partially identified, or not identified; and / or 10. The method of any one of C1 to C9, wherein the plurality of rules comprises different sets of rules for different scenarios. [C11] The method according to C10, wherein when a previous scenario switches to a changed scenario, when the changed scenario is identified for a period longer than a certain period, the set of rules according to the previous scenario switches to the set of rules according to the changed scenario. [C12] The method of C10, wherein if the baby is partially identified when one or more key points and / or key areas of the baby are identified but not all of the key points and / or key areas are identified, the plurality of rules excludes rules related to the unidentified key points and / or key areas of the baby. [C13] A method according to any one of C1 to 12, further comprising displaying a guide outline of the person and / or the baby on a display before and / or during said identifying the posture of the person and / or the baby. [C14] 14. The method of any one of C1 to 13, wherein the plurality of rules are based on a vertical reference distance between the shoulder and breast on the same side of the person. [C15] The method of C14, wherein the plurality of rules are based on a horizontal reference distance between the person's breasts or a horizontal reference distance between the person's shoulders. [C16] An electronic device comprising a camera, a display, and a processor that performs the method of any one of C1 to C15. [C17] A storage medium configured to store instructions that are executed by at least one processor to perform the method of any one of C1 to C15.

Claims

1. A computer-implemented method for breastfeeding guidance, comprising: Capturing at least one image; displaying the at least one image; identifying whether a posture of the person in the at least one image is correct according to a plurality of rules for breastfeeding; dynamically notifying the person to adjust their posture until each of the plurality of rules is satisfied; Starting a timer; further identifying a posture of the person and informing the person to adjust their posture according to the plurality of rules while breastfeeding; and when the feeding is completed, ending the timer and recording the timer; The method, wherein the plurality of rules are based on one of a vertical reference distance between a shoulder and a breast on the same side of the person, a horizontal reference distance between the person's breasts, and a horizontal reference distance between the person's shoulders.

2. 10. The method of claim 1, further comprising identifying a feeding type or receiving input to indicate the feeding type, such as, for example, whether the person is in a seated or side-lying feeding position.

3. sending the at least one image to an external device; receiving an identification of the person's posture from the external device; or The method of claim 1 , wherein identifying the person's posture is performed by an electronic device.

4. Identifying the posture of the person according to the plurality of rules includes: and / or further comprising identifying the plurality of rules according to a priority order. The method of claim 1 , wherein the plurality of rules includes both at least one standard posture of the person and at least one standard posture of a baby.

5. At least one of dynamically informing the person to adjust the person's posture comprises: and / or notifying the person in order of priority of the plurality of rules that are not satisfied. The method of claim 3 , wherein the informing is via at least one of the following methods: audio, text, image, animation, and video.

6. At least one of dynamically informing the person to adjust the person's posture comprises: identifying a rule having a highest priority among the unsatisfied rules; notifying the person at one time of only the rules with the highest priority; and / or 6. The method of claim 5, further comprising: if one of the plurality of rules remains unsatisfied after a specific period and / or a predefined number of notifications, ignoring the unsatisfied rule.

7. identifying whether a baby is present in the at least one image; If the baby is not identified, display an artificial baby and enter coaching mode; and / or, if a baby is identified, entering a feeding mode.

7. The method of claim 1, wherein in the coaching mode, a timer is not started.

8. The method of claim 7 , further comprising identifying whether the baby is posed correctly in the at least one image according to the plurality of rules.

9. Identifying the posture of the person and / or the baby includes: identifying at least one key point and / or at least one key area of ​​said person and / or said baby; comparing the location of the identified at least one key point and / or at least one key area with the plurality of rules; The method of claim 8 , wherein the plurality of rules includes key point and / or key area information of the person and / or baby in a correct feeding state.

10. further comprising identifying a feeding scenario depending on at least one of the feeding type, whether the feeding breast is left or right, and whether the baby is fully identified, partially identified, or not identified; and The method of claim 1 , wherein the plurality of rules comprises different sets of rules for different breastfeeding scenarios.

11. The method of claim 10, wherein when a previous breastfeeding scenario switches to a changed breastfeeding scenario, the set of rules according to the previous breastfeeding scenario switches to the set of rules according to the changed breastfeeding scenario when the changed breastfeeding scenario is identified for longer than a certain period of time.

12. 11. The method of claim 10, wherein if the baby is partially identified when one or more key points and / or key areas of the baby are identified but not all of the key points and / or key areas are identified, the plurality of rules excludes rules related to the unidentified key points and / or key areas of the baby.

13. 10. The method of claim 9, further comprising displaying a guide outline of the person and / or the baby on a display before and / or during the identification of the person's and / or the baby's posture.

14. An electronic device comprising a camera, a display, and a processor for performing the method of any one of claims 1 to 13.

15. A storage medium configured to store instructions that are executed by at least one processor to perform the method of any one of claims 1 to 13.

Images