Infant feeding assessment visualization method, system, electronic device, and storage medium

Abstract

Embodiments of the present application provide a baby feeding evaluation visualization method, system, electronic device and storage medium, belonging to the technical field of medical treatment. The scheme obtains a facial waveform representing a sucking action of a baby, a neck waveform representing a swallowing action of the baby, and a chest and abdomen waveform representing a breathing action of the baby, respectively extracts waveform features of the facial waveform, the neck waveform and the chest and abdomen waveform, synthesizes the facial waveform, the neck waveform and the chest and abdomen waveform according to the waveform features of the facial waveform, the neck waveform and the chest and abdomen waveform, obtains a feeding waveform, evaluates the facial waveform, the neck waveform, the chest and abdomen waveform and the feeding waveform through an evaluation model, obtains a feeding evaluation result, and displays the facial waveform, the neck waveform, the chest and abdomen waveform, the feeding waveform and the feeding evaluation result through a preset interface. The baby feeding behavior can be monitored and tracked, the monitoring image and the evaluation result are output, the accuracy and comprehensiveness of the feeding evaluation identification are improved, and the professional requirement for personnel is reduced.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to a visualization method, system, electronic device and storage medium for infant feeding assessment. Background Technology

[0002] Breast milk is the most suitable natural food for infants. During breastfeeding, infants primarily complete this process through the coordinated actions of sucking, swallowing, and breathing. This coordinated movement is controlled by nerves and muscles and is a complex, dynamic process. When an infant's bodily functions are not yet fully developed, their sucking and swallowing abilities, as well as the coordination between these abilities and breathing, are not perfect. This can increase the risk of feeding difficulties such as choking, aspiration, and even suffocation. Therefore, assessing an infant's sucking, swallowing, and breathing processes is a prerequisite for identifying feeding difficulties and providing intervention.

[0003] Currently, the assessment of infant sucking-swallowing-breathing primarily employs imaging and scale-based methods. Imaging methods include swallowing contrast imaging, fiberoptic laryngoscopy for swallowing function assessment, ultrasound imaging, and high-resolution pharyngeal manometry. Scale-based methods include the Oral Feeding Assessment Scale for Premature Infants, the Neonatal Oral Motor Assessment Scale, and the Oral Feeding Skills Assessment Scale. However, these methods can only assess each stage independently and cannot provide a continuous evaluation of the entire sucking-swallowing-breathing process, making it difficult to directly and accurately identify feeding difficulties. Summary of the Invention

[0004] The main objective of this application is to propose a visualization method, system, electronic device, and storage medium for infant feeding assessment, which aims to continuously and dynamically monitor and track infant feeding behavior, output intuitive monitoring images and assessment results, improve the accuracy and comprehensiveness of feeding assessment identification, and reduce the professional requirements for personnel.

[0005] To achieve the above objectives, one aspect of this application proposes a visualization method for infant feeding assessment, the method comprising:

[0006] Acquire facial waveforms representing sucking movements, neck waveforms representing swallowing movements, and chest and abdominal waveforms representing breathing movements in infants;

[0007] Waveform features of the facial waveform, the neck waveform, and the chest and abdomen waveform are extracted respectively, wherein the waveform features include frequency, peaks, troughs, and amplitude;

[0008] The facial waveform, neck waveform, and chest and abdomen waveform are synthesized based on their waveform characteristics to obtain a feeding waveform;

[0009] The facial waveform, neck waveform, chest and abdominal waveform, and feeding waveform are evaluated using an evaluation model to obtain feeding evaluation results;

[0010] The facial waveform, neck waveform, chest and abdominal waveform, feeding waveform, and feeding assessment results are displayed through a preset interface.

[0011] In some embodiments, acquiring facial waveforms representing sucking movements, neck waveforms representing swallowing movements, and chest and abdominal waveforms representing breathing movements of an infant includes the following steps:

[0012] A facial waveform is obtained by monitoring the sucking motion of the baby's jaw by placing a first sensor on the face;

[0013] A second sensor placed in the neck monitors the swallowing motion of the infant's thyroid cartilage, which moves up and down, to obtain a neck waveform.

[0014] The breathing movements of an infant's chest and abdomen are monitored by a third sensor placed on the chest or abdomen, resulting in a waveform of the chest and abdomen.

[0015] In some embodiments, synthesizing the facial waveform, neck waveform, and chest / abdomen waveform based on the waveform features of the facial waveform, neck waveform, and chest / abdomen waveform to obtain a feeding waveform includes the following steps:

[0016] The facial waveform, the neck waveform, and the chest and abdomen waveform are time-aligned.

[0017] The infant's behavioral cycle is determined based on the waveform characteristics of the facial waveform, the neck waveform, and the chest and abdominal waveform, wherein the behavioral cycle includes a first stage, a second stage, and a third stage;

[0018] The facial waveform, neck waveform, and chest and abdominal waveform are divided into stages according to the behavioral cycle to obtain corresponding segmented waveforms;

[0019] The segmented waveforms of the face waveform, the neck waveform, and the chest and abdomen waveform that are in the same stage of the same behavioral cycle are synthesized to obtain the behavioral waveform.

[0020] The behavioral waveforms from different stages are spliced ​​together according to a preset order to obtain the feeding waveform.

[0021] In some embodiments, determining the infant's behavioral cycle based on the waveform characteristics includes the following steps:

[0022] The first stage of the infant's sucking and breathing alternation is determined based on the peaks and troughs of the facial waveform and the peaks and troughs of the chest and abdominal waveform.

[0023] The second stage of apnea during swallowing is determined based on the amplitude of the neck waveform and the amplitude of the chest and abdominal waveform.

[0024] The third stage of infant respiratory acceleration is determined based on the frequency of the chest and abdominal waveforms.

[0025] The first stage, the second stage, and the third stage are defined as the infant's behavioral cycle.

[0026] In some embodiments, the evaluation of the facial waveform, the neck waveform, the chest and abdominal waveform, and the feeding waveform using an evaluation model to obtain a feeding evaluation result includes the following steps:

[0027] The facial waveform is input into the evaluation model to obtain the sucking index;

[0028] The neck waveform is input into the evaluation model to obtain swallowing indicators;

[0029] The chest and abdominal waveforms are input into the evaluation model to obtain respiratory indicators;

[0030] The feeding waveform is input into the evaluation model to obtain the coordination index;

[0031] The sucking index, swallowing index, breathing index, and coordination index are compared with the preset benchmark parameters in the assessment model to obtain the feeding assessment results.

[0032] In some embodiments, the infant feeding assessment visualization method further includes the following steps:

[0033] The reference range of the benchmark parameter is determined by using a sampling statistical method based on historical data stored in the database.

[0034] In some embodiments, the infant feeding assessment visualization method further includes the following steps:

[0035] Record the monitoring data of the facial waveform, the neck waveform, the chest and abdomen waveform, the feeding waveform, and the feeding assessment results;

[0036] The monitoring data is sent to a preset terminal.

[0037] To achieve the above objectives, another aspect of this application proposes an infant feeding assessment visualization system, the system comprising:

[0038] The first module is used to acquire facial waveforms representing sucking movements, neck waveforms representing swallowing movements, and chest and abdominal waveforms representing breathing movements in infants.

[0039] The second module is used to extract waveform features of the facial waveform, the neck waveform, and the chest and abdomen waveform, respectively, wherein the waveform features include frequency, peaks, troughs, and amplitude.

[0040] The third module is used to synthesize the facial waveform, the neck waveform, and the chest and abdomen waveform based on the waveform features of the facial waveform, the neck waveform, and the chest and abdomen waveform to obtain a feeding waveform;

[0041] The fourth module is used to evaluate the facial waveform, the neck waveform, the chest and abdomen waveform, and the feeding waveform using an evaluation model to obtain feeding evaluation results.

[0042] The fifth module is used to display the facial waveform, the neck waveform, the chest and abdomen waveform, the feeding waveform, and the feeding assessment results through a preset interface.

[0043] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0044] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0045] The embodiments of this application include at least the following beneficial effects: This application provides a visualization method, system, electronic device, and storage medium for infant feeding assessment. This solution continuously and dynamically monitors and tracks infant feeding behavior by acquiring facial waveforms representing sucking actions, neck waveforms representing swallowing actions, and chest and abdominal waveforms representing breathing actions. By extracting waveform features from the facial, neck, and chest / abdominal waveforms respectively, and synthesizing them based on these features, a feeding waveform is obtained. An assessment model is used to evaluate the facial, neck, chest / abdominal, and feeding waveforms to obtain feeding assessment results. The facial, neck, chest / abdominal, and feeding waveforms, along with the feeding assessment results, are displayed through a preset interface, providing intuitive monitoring images and assessment results. This improves the accuracy and comprehensiveness of feeding assessment identification and reduces the professional requirements for personnel. Attached Figure Description

[0046] Figure 1This is a flowchart of the infant feeding assessment visualization method provided in the embodiments of this application;

[0047] Figure 2 This is a schematic diagram of the waveform data collected according to an embodiment of this application;

[0048] Figure 3 This is a schematic diagram of the feeding waveform provided in an embodiment of this application;

[0049] Figure 4 This is a schematic diagram of a preset interface provided in an embodiment of this application;

[0050] Figure 5 This is a schematic diagram of the structure of the infant feeding assessment visualization device provided in the embodiments of this application;

[0051] Figure 6 This is a schematic diagram of the infant identification interface provided in an embodiment of this application;

[0052] Figure 7 This is a schematic diagram of the fixed sensor prompt box provided in an embodiment of this application;

[0053] Figure 8 This is a schematic diagram of the sensor inspection prompt box provided in an embodiment of this application;

[0054] Figure 9 This is a schematic diagram of the measurement interface provided in an embodiment of this application;

[0055] Figure 10 This is a schematic diagram of the data saving dialog box provided in an embodiment of this application;

[0056] Figure 11 This is a schematic diagram of the history record interface provided in an embodiment of this application;

[0057] Figure 12 This is a schematic diagram of the viewing interface provided in an embodiment of this application;

[0058] Figure 13 This is a schematic diagram of the transmission interface provided in an embodiment of this application;

[0059] Figure 14 This is a schematic diagram of the structure of the infant feeding assessment visualization system provided in the embodiments of this application;

[0060] Figure 15 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0062] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0063] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0065] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0066] (1) Suck-Swallow-Breathe (SSB): Suck-swallow-breath is a mechanism of infant feeding behavior. Specifically, the infant generates negative pressure in the mouth through the sucking action to draw milk from the breast. The milk is pushed to the pharynx by the action of the tongue. When there is enough milk in the pharynx, the swallowing action is triggered. During the swallowing process, breathing stops for about 0.5 seconds because the nasopharyngeal passage, pharynx and trachea passage are closed.

[0067] (2) Preterm Infant Oral Feeding Readiness Assessment (PIOFRA) Scale: The PIOFRA scale consists of 5 main categories and 18 items, including corrected gestational age, behavioral organization (wakefulness, overall posture, and muscle tone), oral posture (lip and teeth), oral reflexes (rooting reflex, sucking reflex, biting reflex, and gag reflex), and non-nutritive sucking (tongue movement, tongue wrapping, jaw movement, sucking strength, sucking and pausing, ability to maintain sucking / pausing, maintaining wakefulness, and signs of stress). Each item is scored from 0 to 2 points, with a maximum score of 36 points.

[0068] (3) Neonatal Oral Motor Assessment Scale (NOMAS): NOMAS includes six aspects: mandibular opening and closing rate, rhythm, consistency, and tongue movement direction, range, and rate, with a total of 28 items. It is divided into three categories: normal (10 items), disordered (8 items), and disordered (10 items). The total score for the normal category is 20 points, and the sucking function is directly proportional to the score. The total score for the disordered category is 8 points, and the total score for the disordered category is 10 points, and the sucking function is inversely proportional to the score.

[0069] (4) Oral Feeding Skills (OFS) Assessment Scale: The OFS scale is a 4-level (4-quadrant) data scale that does not require special monitoring equipment and will not interfere with infant feeding. It can assess the improvement effect of oral feeding in different infants. The main contents include total feeding amount, feeding rate, feeding proficiency, milk intake ratio, and clinical feeding rate.

[0070] (5) Radio Frequency Identification (RFID): Radio frequency identification technology, also known as wireless radio frequency identification, is an automatic identification technology that identifies specific targets and reads and writes relevant data through radio signals, thereby realizing non-contact two-way communication.

[0071] Next, the technical background or technical evolution of the embodiments of this application will be introduced.

[0072] Due to the high incidence of infant feeding difficulties, many studies have focused on assessing and quantifying the sucking, swallowing, and breathing functions of breastfed infants in order to evaluate whether they are experiencing feeding difficulties.

[0073] Early assessments of an infant's sucking ability rely primarily on the subjective judgment of healthcare professionals, who use gloved fingers to feel the sucking pressure inside the infant's mouth. However, this method lacks objectivity and quantitative standards.

[0074] As research has progressed, a series of scales have been developed to more systematically observe the sucking characteristics of infants during breastfeeding. Among them, the PIOFRA scale, as a standardized assessment tool, is used in clinical practice to determine whether an infant can be safely fed orally, providing a reference standard for the timing of intervention in rehabilitation treatment, thanks to its simplicity and efficiency. However, this scale is still limited by its strong subjectivity and the fact that it does not cover the assessment of swallowing and breathing patterns.

[0075] Similarly, NOMAS, as the most widely used assessment scale, can sensitively reflect the developmental changes in the sucking function of premature infants in clinical practice and provide targeted assessments of oral motor function and sucking-swallowing behavior. However, it also faces the problems of strong subjectivity and lack of assessment of breathing patterns.

[0076] The OFS scale, because it does not require special equipment, can assess the effectiveness of different interventions in improving infant oral feeding in clinical practice. However, it also suffers from strong subjectivity and lacks assessment of swallowing and breathing patterns.

[0077] The above scales have played a positive role in promoting the assessment of infant feeding ability, but they still have problems such as lack of objective numerical support, too much subjective judgment, and incomplete assessment scope. At the same time, it requires personnel to have certain medical knowledge and infant care knowledge, and to master assessment skills and methods.

[0078] Since the sucking-swallowing-breathing mechanism is a complex and dynamic process, the above methods can only be used to assess a single step independently, making it difficult to evaluate the entire process continuously. Therefore, there is currently a lack of a method to intuitively assess the overall coordination of the SSB mechanism during breastfeeding.

[0079] In view of this, this application provides a visualization method, system, electronic device, and storage medium for infant feeding assessment. This method acquires facial waveforms representing sucking actions, neck waveforms representing swallowing actions, and chest and abdominal waveforms representing breathing actions. Waveform features of these waveforms are extracted, and the facial, neck, and chest / abdominal waveforms are synthesized based on these features to obtain a feeding waveform. An assessment model evaluates the facial, neck, chest / abdominal, and feeding waveforms to obtain a feeding assessment result. The facial, neck, chest / abdominal, and feeding waveforms, along with the feeding assessment result, are displayed through a preset interface. This method can monitor and track infant feeding behavior, output monitoring images and assessment results, improve the accuracy and comprehensiveness of feeding assessment identification, and reduce the professional requirements for personnel.

[0080] The infant feeding assessment visualization method provided in this application relates to the field of medical technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smartwatch, etc., but is not limited thereto; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application implementing the infant feeding assessment visualization method, but is not limited to the above forms.

[0081] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0082] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0083] Figure 1 This is an optional flowchart of the infant feeding assessment visualization method provided in the embodiments of this application. Figure 1The method may include, but is not limited to, steps S101 to S105.

[0084] Step S101: Obtain facial waveforms representing sucking movements, neck waveforms representing swallowing movements, and chest and abdominal waveforms representing breathing movements of the infant.

[0085] Step S102: Extract waveform features from the facial waveform, neck waveform, and chest and abdomen waveform, respectively. The waveform features include frequency, peaks, troughs, and amplitude.

[0086] Step S103: Based on the waveform characteristics of the facial waveform, neck waveform, and chest and abdomen waveform, synthesize the facial waveform, neck waveform, and chest and abdomen waveform to obtain the feeding waveform.

[0087] Step S104: The facial waveform, neck waveform, chest and abdominal waveform, and feeding waveform are evaluated using an evaluation model to obtain feeding evaluation results.

[0088] Step S105: Display facial waveforms, neck waveforms, chest and abdominal waveforms, feeding waveforms, and feeding assessment results through a preset interface.

[0089] In this embodiment, firstly, facial waveforms representing sucking movements, neck waveforms representing swallowing movements, and chest and abdominal waveforms representing breathing movements are acquired, such as... Figure 2 As shown, Figure 2 This is a schematic diagram of the waveform data collected from the face, neck, and chest / abdomen.

[0090] For example, considering that imaging methods such as swallowing contrast examination, fiberoptic laryngoscopy swallowing function assessment, and ultrasound imaging examination involve radiation or invasive procedures, in order to reduce infant discomfort and improve safety, a non-invasive monitoring method is adopted. The sensor is fixed to the infant's body to acquire facial waveforms representing sucking actions, neck waveforms representing swallowing actions, and chest and abdominal waveforms representing breathing actions, so as to continuously and dynamically monitor and track the infant's feeding behavior.

[0091] Subsequently, waveform features were extracted from the facial, neck, and chest / abdomen waveforms, respectively. These waveform features included frequency, peaks, troughs, and amplitude. Specifically, the frequency, peaks, troughs, and amplitude of the facial, neck, and chest / abdomen waveforms were extracted to obtain the waveform features for each waveform.

[0092] For example, spectral analysis is performed on facial waveforms, neck waveforms, and chest and abdominal waveforms to calculate the number of waveform repetitions within a specific period in each waveform to obtain the frequency. Peaks and troughs are determined based on the local maximum and minimum values ​​in the waveforms, and the amplitude is obtained based on the difference between the peaks and troughs.

[0093] It should be noted that the waveforms corresponding to sucking, swallowing, and breathing movements usually have different characteristics. For example, facial waveforms have a faster frequency and smaller amplitude, chest and abdominal waveforms have a slower frequency and larger amplitude, while neck waveforms have more obvious peaks and troughs.

[0094] After obtaining the waveform features, the facial, neck, and chest / abdominal waveforms are synthesized based on their characteristics to obtain the feeding waveform. Specifically, refer to... Figure 3 The facial, neck, and chest / abdomen waveforms are synthesized based on their frequencies, peaks, troughs, and amplitudes, and then combined into a single feeding waveform.

[0095] Furthermore, the facial, neck, chest and abdominal, and feeding waveforms are evaluated using an assessment model to obtain feeding assessment results. The assessment model can extract assessment indicators from the facial, neck, chest and abdominal, and feeding waveforms and compare them with preset benchmark parameters to obtain feeding assessment results. These results may include whether feeding difficulties occur during sucking, swallowing, and breathing, and whether the sucking-swallowing-breathing mechanism is coordinated.

[0096] Finally, a preset interface displays facial, neck, chest / abdomen, feeding waveforms, and feeding assessment results. Specifically, the preset interface outputs these waveforms in graphical form, providing an intuitive visual interface that allows non-professionals to quickly understand the infant's activity during feeding, improving readability and reducing the need for specialized personnel. Simultaneously, displaying feeding assessment results through the preset interface enhances the accuracy and comprehensiveness of feeding assessment identification.

[0097] For example, refer to Figure 4 The default interface, from left to right, consists of an operation button bar, a waveform display bar, and a waveform indicator bar. The waveform display bar includes four display boxes, used to show the facial, neck, chest / abdomen, and feeding waveforms of the infant during feeding. The upper left corner of each display box is labeled with the waveform name: "Su," "Sw," "B," and "SSB," corresponding to sucking, swallowing, breathing, and sucking-swallowing-breathing. The waveform indicator bar displays the corresponding indicator data for each waveform.

[0098] In some embodiments, step S101 may include, but is not limited to, steps S201 to S203.

[0099] Step S201: The first sensor set on the face monitors the sucking motion of the baby's jaw moving up and down, and obtains the facial waveform.

[0100] Step S202: The swallowing motion of the infant's thyroid cartilage moving up and down is monitored by a second sensor placed in the neck to obtain a neck waveform.

[0101] Step S203: Monitor the infant's breathing movements by the rise and fall of the chest and abdomen using a third sensor located on the chest or abdomen to obtain chest and abdominal waveforms.

[0102] Specifically, refer to Figure 2 The first sensor is fixed to the face to capture data on the baby's sucking movements, the second sensor is fixed to the neck to capture data on the baby's swallowing movements, and the third sensor is fixed to the chest and abdomen to capture data on the baby's breathing movements. The collected data undergoes preprocessing steps such as noise reduction and filtering to obtain the corresponding waveforms.

[0103] In step S201 of some embodiments, a facial waveform is obtained by monitoring the sucking motion of the infant's jaw as it moves up and down, using a first sensor placed on the face. Specifically, a pressure sensor or strain sensor is fixed to the infant's face to capture the up-and-down movement of the infant's jaw during feeding caused by the sucking motion, and converts it into an electrical signal to obtain the facial waveform.

[0104] For example, when an infant suckles, a negative pressure environment needs to be created in the mouth. To achieve this, the infant's jaw moves downwards to contact the breast, creating a relatively sealed environment. Then, through muscle contraction and relaxation, negative pressure is generated to draw milk from the breast into the mouth. As the suckling action continues, the jaw moves upwards to adjust the negative pressure state in the mouth. Therefore, when the sensor detects downward movement of the jaw, an upward waveform is generated; when the sensor detects upward movement of the jaw, a downward waveform is generated. Figure 2 As shown, each rise and fall of the facial waveform corresponds to a complete sucking action, and the frequency of the waveform directly reflects the frequency or speed of the baby's sucking.

[0105] In step S202 of some embodiments, a neck waveform is obtained by monitoring the swallowing motion of the infant's thyroid cartilage by a second sensor placed in the neck. Specifically, a pressure sensor or strain sensor is fixed to the infant's neck to capture the up-and-down movement of the infant's thyroid cartilage during swallowing and convert it into an electrical signal.

[0106] For example, when sufficient milk accumulates during sucking, a swallowing action is triggered. Swallowing is a complex physiological process involving the coordinated action of multiple parts of the neck, including the mouth, pharynx, larynx, esophagus, and trachea. When milk is swallowed, the thyroid cartilage, as part of the larynx, moves upward as the larynx rises to close the laryngeal opening and prevent milk from entering the trachea. Therefore, when the sensor detects upward movement of the thyroid cartilage, a rising waveform is generated; when the sensor detects downward movement of the thyroid cartilage, a falling waveform is generated. Figure 2 As shown, each rise and fall of the neck waveform corresponds to a complete swallowing action.

[0107] In step S203 of some embodiments, the infant's breathing movements, including the rise and fall of the chest and abdomen, are monitored by a third sensor located on the chest or abdomen to obtain a chest and abdominal waveform. Specifically, a pressure sensor or strain sensor is fixed to the infant's chest or abdomen to capture the rise and fall of the infant's chest or abdomen due to breathing during feeding, and converts it into an electrical signal to obtain a chest and abdominal waveform.

[0108] For example, during breathing, the chest and abdomen rise and fall with the expansion and contraction of the lungs to complete inhalation and exhalation. When inhaling, the sensor detects that the chest and abdomen expand with the lungs, thus generating a descending waveform; when exhaling, the sensor detects that the chest and abdomen contract with the lungs, thus generating an ascending waveform. Figure 2 As shown, each rise and fall of the chest and abdominal waveform corresponds to a complete breathing action, and the frequency of the waveform directly reflects the frequency or speed of the infant's breathing.

[0109] This application embodiment obtains corresponding waveforms by collecting physiological movements of the infant's jaw, thyroid cartilage, chest, and abdomen. It can perform multi-dimensional assessment of the infant's sucking-swallowing-breathing physiological process, continuously and dynamically monitor and track the infant's feeding behavior, and quantify the feeding process through waveform data so that subsequent calculations can be performed based on the data, providing an objective basis for infant feeding assessment.

[0110] In some embodiments, step S103 may include, but is not limited to, steps S301 to S305.

[0111] Step S301: Time alignment of the facial waveform, neck waveform, and chest and abdominal waveform.

[0112] Step S302: Determine the infant's behavioral cycle based on the waveform characteristics of the facial waveform, neck waveform, and chest and abdominal waveform, wherein the behavioral cycle includes a first stage, a second stage, and a third stage.

[0113] Step S303: Divide the facial waveform, neck waveform, and chest and abdomen waveform into stages according to the behavioral cycle to obtain the corresponding segmented waveforms.

[0114] Step S304: Combine the segmented waveforms of the face, neck, and chest / abdomen that are in the same stage of the same behavioral cycle to obtain the behavioral waveform.

[0115] Step S305: The behavioral waveforms of different stages are spliced ​​together according to a preset order to obtain the feeding waveform.

[0116] In this embodiment, the facial waveform, neck waveform, and chest / abdomen waveform are first time-aligned. Optionally, the facial waveform, neck waveform, and chest / abdomen waveform are time-aligned using timestamps or synchronization signals to ensure that the timing of each waveform is synchronized during subsequent waveform synthesis.

[0117] Next, the infant's behavioral cycle is determined based on the waveform characteristics of the face, neck, and chest / abdomen, referring to... Figure 2 In this embodiment, a single sucking-swallowing-breathing sequence is considered a behavioral cycle. Within a cycle, sucking and breathing initially alternate. When the infant sucks a certain amount of milk, a swallowing action is triggered, and breathing pauses during swallowing. After swallowing, there is an interval before the next sucking. To compensate for the interruption of oxygen supply during respiratory arrest, the body increases its respiratory rate. Therefore, this embodiment further divides the behavioral cycle into three stages: Stage I, Stage II, and Stage III. Stage I involves alternating sucking and breathing; Stage II involves respiratory arrest during swallowing; and Stage III involves accelerated breathing. Because each stage has unique characteristics, to identify the infant's behavioral cycle, the current stage can be determined based on the time-aligned facial, neck, and chest / abdominal waveforms, according to the waveform characteristics within the same time period.

[0118] After determining the behavioral cycle, the facial, neck, and chest / abdomen waveforms are divided into stages according to the behavioral cycle, resulting in corresponding segmented waveforms. Specifically, the feeding process is segmented, and the facial, neck, and chest / abdomen waveforms are divided according to the start and end points of each stage in the behavioral cycle, with each segmented waveform corresponding to one stage.

[0119] Then, the segmented waveforms of the face, neck, and chest / abdomen that are in the same stage of the same behavioral cycle are synthesized to obtain the behavioral waveform. Then, the behavioral waveforms of different stages are spliced ​​together according to a preset order to obtain the feeding waveform.

[0120] Specifically, the behavioral waveforms can be synthesized by superposition, where segmented waveforms from the same stage are superimposed to obtain the behavioral waveforms for the corresponding stage. Then, based on the temporal relationship of each stage, the behavioral waveforms are sequentially spliced ​​together in the order of the first, second, and third stages to generate a continuous curve of the entire feeding process, thus obtaining the feeding waveform.

[0121] For example, according to Figure 2 It can be seen that the neck waveform remains unchanged in the first stage, meaning there are only sucking and breathing movements. Since one rise and fall of the waveform corresponds to one complete movement, the segmented waveforms of the face, neck, and chest / abdomen in the first stage are synthesized by superposition. (Refer to...) Figure 3 This can be understood as superimposing facial and chest / abdominal waveforms according to one sucking action and one breathing action to obtain the first stage of behavioral waveforms. Similarly, in synthesizing the second and third stage behavioral waveforms, since only neck waveforms are present in the second stage and only chest / abdominal waveforms are present in the third stage, the superimposed second stage behavioral waveform is consistent with the neck waveform of the second stage, and the superimposed third stage behavioral waveform is consistent with the chest / abdominal waveform of the third stage. The second and third stage behavioral waveforms are extracted and sequentially spliced ​​with the first stage behavioral waveform. Through this waveform synthesis method, a continuous curve of the feeding waveform is obtained, such as... Figure 4 The “SSB” display box is shown in the middle.

[0122] It should be noted that the behavioral waveforms of each stage can be smoothly connected through appropriate transitions.

[0123] In some embodiments, step S302 may include, but is not limited to, steps S401 to S404.

[0124] Step S401: Determine the first stage of the infant's sucking and breathing alternation based on the peaks and troughs of the facial waveform and the peaks and troughs of the chest and abdominal waveform.

[0125] Step S402: Based on the amplitude of the neck waveform and the amplitude of the chest and abdomen waveform, determine the second stage of the infant's apnea during swallowing.

[0126] Step S403: Determine the third stage of infant respiratory acceleration based on the frequency of the chest and abdominal waveforms.

[0127] Step S404: The first stage, the second stage, and the third stage are defined as the infant's behavioral cycle.

[0128] In step S401 of some embodiments, the first stage of the infant's sucking and breathing alternation is determined based on the peaks and troughs of the facial waveform and the peaks and troughs of the chest and abdominal waveform. (See also...) Figure 2 The facial and chest / abdominal waveforms exhibit a clear periodic pattern over specific time periods. This periodicity is primarily manifested in the fact that the facial waveform reaches its peak while the chest / abdominal waveform reaches its trough, and vice versa. The peaks and troughs of the facial and chest / abdominal waveforms always appear relative to each other. Therefore, the start and end points of the sucking-breathing alternation phase in the feeding process can be determined based on the peaks and troughs of both the facial and chest / abdominal waveforms, thus defining the first phase.

[0129] In step S402 of some embodiments, a second stage of apnea during swallowing is determined based on the amplitude of the neck waveform and the amplitude of the chest and abdominal waveform. (See also...) Figure 2 When a significant change in the amplitude of the neck waveform occurs, it indicates that the infant is swallowing. Since swallowing temporarily blocks the airway, the amplitude of the chest and abdominal waveforms no longer changes. Therefore, the start and end points of the apnea phase during swallowing can be determined based on the amplitudes of the neck and chest / abdominal waveforms, thus identifying the second phase.

[0130] In step S403 of some embodiments, the third stage of infant respiratory acceleration is determined based on the frequency of the chest and abdominal waveforms. (See also...) Figure 2 Before and after swallowing, the frequency of the chest and abdominal waveforms changes significantly. This is because the body accelerates its respiratory rate after swallowing to compensate for the interruption of oxygen supply during apnea. Therefore, the start and end points of this accelerated breathing phase during feeding can be determined based on the frequency of the chest and abdominal waveforms, thus identifying the third stage.

[0131] In step S404 of some embodiments, the first stage, the second stage, and the third stage are defined as the infant's behavioral cycle. After steps S401 to S403, the feeding process is divided into several first, second, and third stages. The first, second, and third stages together constitute a complete sucking-swallowing-breathing behavior of the infant. Therefore, the first, second, and third stages are defined as the infant's behavioral cycle so that the sucking-swallowing-breathing pattern can be evaluated according to the behavioral cycle and the physiological changes during the feeding process can be analyzed.

[0132] In some embodiments, step S104 may include, but is not limited to, steps S501 to S505.

[0133] Step S501: Input the facial waveform into the evaluation model to obtain the sucking index.

[0134] Step S502: Input the neck waveform into the evaluation model to obtain swallowing indices.

[0135] Step S503: Input the chest and abdominal waveforms into the evaluation model to obtain respiratory indicators.

[0136] Step S504: Input the feeding waveform into the evaluation model to obtain the coordination index.

[0137] Step S505: Compare the sucking index, swallowing index, breathing index, and coordination index with the preset benchmark parameters in the assessment model to obtain the feeding assessment results.

[0138] In this embodiment, facial waveforms are input into the evaluation model to obtain sucking indices, neck waveforms are input into the evaluation model to obtain swallowing indices, chest and abdominal waveforms are input into the evaluation model to obtain breathing indices, and feeding waveforms are input into the evaluation model to obtain coordination indices. The sucking indices include sucking force and sucking frequency, the swallowing indices include swallowing force and swallowing frequency, and the breathing indices include breathing force and breathing frequency.

[0139] For example, waveform analysis of facial waveforms is performed using an evaluation model, and the sucking force is obtained by calculating the average of the amplitude or energy based on amplitude or energy. Waveform analysis of neck waveforms is performed using an evaluation model, and the swallowing force is obtained by calculating the average of the amplitude or energy based on amplitude or energy. Waveform analysis of chest and abdominal waveforms is performed using an evaluation model, and the breathing force is obtained by calculating the average of the amplitude or energy based on amplitude or energy.

[0140] Next, the feeding waveform is processed and analyzed by the evaluation model. The composite waveform (i.e. the feeding waveform) is decomposed by Fourier transform or fast Fourier transform, the signal is converted from the time domain to the frequency domain, the components are analyzed, and the average value of the frequency of each component or the frequency of the main component is used as the frequency value to obtain the sucking frequency, swallowing frequency and breathing frequency.

[0141] Furthermore, based on the calculated sucking frequency, swallowing frequency, and breathing frequency, the ratio of the three frequencies is determined to obtain a coordination index. As an important factor in assessing the coordination of an infant's sucking-swallowing-breathing mechanism, the coordination index should maintain a relatively stable frequency ratio during normal infant feeding. Abnormalities in the coordination index indicate a lack of coordination in the infant's sucking-swallowing-breathing process.

[0142] Finally, the sucking, swallowing, breathing, and coordination indicators are compared with the preset baseline parameters in the assessment model to obtain the feeding assessment results. It should be noted that each indicator has a corresponding baseline parameter, which is a statistically determined upper and lower limit threshold for the normal range, based on feeding data from a large number of healthy infants. If the value of any indicator exceeds the reference range of the baseline parameter (i.e., greater than the upper threshold or less than the lower threshold), it indicates an abnormality in infant feeding. Specifically, the sucking, swallowing, breathing, and coordination indicators are compared item by item with the preset baseline parameters in the assessment model, and all comparison results are summarized to obtain the feeding assessment results.

[0143] For example, the presence of sucking difficulties is determined based on sucking indicators and corresponding benchmark parameters; the presence of swallowing difficulties is determined based on swallowing indicators and corresponding benchmark parameters; the presence of breathing difficulties is determined based on breathing indicators and corresponding benchmark parameters; and the overall coordination is comprehensively assessed based on sucking indicators, swallowing indicators, breathing indicators, and coordination indicators to determine whether there is any incoordination. When incoordination is found, the incoordination process is further confirmed.

[0144] This application embodiment uses an evaluation model to analyze facial waveforms, neck waveforms, chest and abdominal waveforms, and feeding waveforms. Based on sucking indicators, swallowing indicators, breathing indicators, coordination indicators, and benchmark parameters, it evaluates the coordination of each stage and the entire feeding process of the infant. This can promptly identify feeding difficulties during the feeding process and improve the accuracy and comprehensiveness of feeding assessment and identification.

[0145] In some embodiments, the infant feeding assessment visualization method may also include, but is not limited to, step S601.

[0146] Step S601: Using sampling statistics, determine the reference range of the benchmark parameters based on the historical data stored in the database.

[0147] In this embodiment, a sampling statistical method is used to determine the reference range of the benchmark parameters based on historical data stored in the database. Specifically, data collection is first performed by retrieving historical data related to the benchmark parameters from the database. To ensure the completeness and accuracy of the historical data, data cleaning is conducted to remove missing or abnormal data, thereby improving the reliability of the benchmark parameters.

[0148] Optionally, a suitable sampling method can be selected based on the total amount of data and requirements, such as random sampling or systematic sampling, to extract historical data from the database. Statistical analysis is then performed on the extracted historical data to calculate statistical measures such as the mean and standard deviation of the baseline parameters.

[0149] Based on statistics, the reference range can be determined by adding or subtracting the standard deviation from the mean. For example, the upper and lower limits of the normal range can be defined by adding or subtracting one or two standard deviations from the mean, thereby determining the reference range of the benchmark parameter.

[0150] It should be noted that the reference range of the benchmark parameters can be set not only by sampling and statistically analyzing historical data, but also based on the results of medical research. This application does not impose any specific limitations on the embodiments.

[0151] In some embodiments, the infant feeding assessment visualization method may also include, but is not limited to, steps S701 to S702.

[0152] Step S701: Record monitoring data of facial waveform, neck waveform, chest and abdominal waveform, feeding waveform, and feeding assessment results.

[0153] Step S702: Send the monitoring data to the preset terminal.

[0154] In this embodiment, monitoring data including facial waveforms, neck waveforms, chest and abdominal waveforms, feeding waveforms, and feeding assessment results are recorded and sent to a preset terminal. Optionally, the facial waveforms, neck waveforms, chest and abdominal waveforms, feeding waveforms, and feeding assessment results can be transmitted to a cloud database to upload the currently collected monitoring data.

[0155] After collecting monitoring data, in response to user commands, the monitoring data is sent to a preset terminal for viewing. The preset terminal can be a device or system, pre-configured to receive monitoring data from a cloud database. Specifically, it can be a smartphone, tablet, or medical system platform—a terminal that can assist doctors in remote diagnosis and treatment, thereby helping multiple medical teams and parents make collaborative decisions.

[0156] The following is a detailed description and explanation of the solutions in the embodiments of this application, with reference to specific application examples.

[0157] To assist institutions such as hospital rooming-in wards, breastfeeding clinics, postpartum care centers, and rehabilitation centers in assessing and diagnosing the feeding of newborns, premature infants, and neurological infants, and to provide a reference for treatment, this application provides an infant feeding assessment device. Medical staff and parents can use this device to continuously and dynamically monitor and track infant feeding behavior. By analyzing the graphical data and indicators of the infant's sucking, swallowing, and breathing, feeding problems can be identified, and this data can be shared with multiple medical centers to jointly provide scientific and effective interventions for the infant.

[0158] Reference Figure 5The device includes swallowing monitoring sensors, sucking monitoring sensors, breathing monitoring sensors, an ARM processor, memory, an OLED display, and a cloud platform.

[0159] Each sensor via I 2 The C bus is connected to the ARM processor, where I 2 The C-bus includes a serial data line (SDA) and a serial clock line (SCL), which connect to the corresponding pins and clock pins of the ARM processor, respectively. After the device starts, the ARM processor sends commands to three sensors monitoring sucking, swallowing, and breathing. Each sensor collects waveform data during these actions according to the ARM processor's commands and transmits the waveform data back to the ARM processor. The ARM processor processes the waveform data collected by each sensor to ensure the accuracy of the facial, neck, and chest / abdominal waveforms, then combines these waveforms and provides corresponding indicators.

[0160] The ARM processor's SPI output line is connected to the corresponding input line of the OLED display. Specifically, the ARM processor sends commands and data to the OLED display via the SPI interface. For example, it sends control commands to set the display's operating mode, and sends image data to display images on the screen. The ARM processor can periodically send update commands and data to the OLED display to update and refresh the displayed content. Simultaneously, the ARM processor can also receive response data from the OLED display.

[0161] ARM processors connect to memory via a data bus to achieve data storage.

[0162] ARM processors connect to cloud platforms via network communication methods such as Ethernet, Wi-Fi, or cellular networks (such as 4G / 5G), and then communicate with the cloud platform through network protocols (such as TCP / IP) to achieve data sharing.

[0163] It should be noted that the device is equipped with an application that uses the infant feeding assessment visualization method provided in the embodiments of this application.

[0164] When the user launches the application and clicks the "Start / Stop" button, it enters the following... Figure 6 The infant identification interface shown uses an RFID device to scan the QR code on the infant's wristband to identify the infant's name and hospital number. After verification, click the "Confirm" button to complete the identification process.

[0165] It should be noted that the name and hospital number can also be obtained by manually entering the information using the input method.

[0166] After confirming the identity information is correct, the application will display a prompt box saying "Please fix the sensor in the corresponding position on the baby," such as... Figure 7 As shown in the image, users can follow the prompts to attach the sucking sensor to the baby's face to detect the up-and-down movement of the jaw during sucking, attach the swallowing sensor to the baby's neck to capture the up-and-down movement of the thyroid cartilage during swallowing, and attach the breathing sensor to the baby's abdomen to detect the rise and fall of the abdomen during breathing. After attaching the sensors in the appropriate positions, users can click the "I have attached the sensors, start measurement" button to begin the measurement.

[0167] It should be noted that if the sensor is not properly secured, a prompt box will pop up again saying "Please check if the sensor is properly secured" to remind the user to make adjustments. Figure 8 As shown. After the user has adjusted the sensor, they can click the "I have adjusted the sensor, start measurement" button to perform the measurement.

[0168] After the sensor is fixed and the measurement phase begins, the application will redirect to the measurement interface, such as... Figure 9 As shown, clicking the "Start / Stop" button will begin collecting the sucking waveform (i.e., facial waveform), swallowing waveform (i.e., neck waveform), and breathing waveform (i.e., chest and abdomen waveform) during the infant feeding process. The three waveforms collected will be combined into a single feeding waveform, and all waveform graphics and corresponding evaluation indicators will be displayed on the measurement interface.

[0169] It should be noted that during feeding, infants may experience problems in one or more stages of the sucking-swallowing-breathing process, which will manifest as abnormal waveforms on the graph, specifically abnormalities in the amplitude and frequency of the waveform. Common feeding problems and possible waveform abnormalities include sucking difficulties, swallowing difficulties, breathing difficulties, and sucking-swallowing-breathing incoordination. Sucking-swallowing-breathing incoordination can be further divided into breathing difficulties during sucking, breathing difficulties during swallowing, and breathing difficulties throughout the feeding process.

[0170] (1) Sucking difficulty: manifested as weak sucking force and lack of rhythm. When analyzing the graph, the sucking waveform may show that the corresponding waveform amplitude is too low or too high, irregular, and the duration of a single waveform is too short or too long.

[0171] (2) Difficulty swallowing: During graphical analysis, the swallowing waveform may show that the corresponding waveform amplitude is too low or too high, or the duration of a single waveform is too short or too long.

[0172] (3) Breathing difficulties: The infant’s breathing becomes shallow or deep, the frequency is too slow or too fast, the rhythm is abnormal, and during graphical analysis, the breathing waveform may show that the corresponding waveform amplitude is too low or too high, irregular, and the duration of a single waveform is too short or too long.

[0173] (4) Difficulty breathing during sucking: If a baby experiences difficulty breathing while sucking, it may indicate a problem with the coordination between sucking and breathing, which can lead to sucking difficulties. During graphical analysis, abnormal breathing waveforms may be observed, and the sucking waveform may also show abnormalities.

[0174] (5) Difficulty breathing during swallowing: If an infant experiences difficulty breathing while swallowing, it may indicate a problem with the coordination between swallowing and breathing, which could lead to swallowing difficulties or choking. Abnormal breathing waveforms may be visible during graphical analysis, and swallowing waveforms may also be abnormal.

[0175] (6) Difficulty breathing throughout feeding: If an infant experiences difficulty breathing throughout feeding, it may indicate a problem with the coordination between sucking, swallowing, and breathing, possibly due to obstruction in the mouth or throat. Abnormal breathing waveforms may be observed throughout feeding, and sucking and swallowing may also be abnormal after being affected.

[0176] Understandably, the application analyzes all waveforms through an evaluation model, assesses the coordination of the infant's sucking, swallowing, and breathing based on indicators such as the number of sucks, sucking force, swallowing frequency, and respiratory rate, identifies whether waveform abnormalities occur during feeding, obtains feeding evaluation results, and displays the identified abnormal results when feeding difficulties are detected.

[0177] The "Settings" button is used to set assessment parameters for the baby's normal sucking, swallowing, breathing, and coordination. Additionally, users can use this button to configure the display mode, such as whether a grid and ruler are needed for the waveform display.

[0178] The "Help" button is used to resolve problems encountered by users and to provide guidance.

[0179] If the sensor detaches during infant feeding, causes choking or suffocation, or exhibits significant waveform changes, a corresponding alarm will be triggered. Clicking the "Alarm" button will bring up a dialog box displaying the specific problem. Once the user has resolved the issue, the alarm can be deactivated, and measurements can continue. Additionally, clicking this button allows the user to view a history of all alarms.

[0180] After the data collection is complete, you can press the "Start / Stop" button again. A dialog box will then pop up, as shown below. Figure 10 As shown, clicking "Yes" will save the data, clicking "No" will not save the data, and clicking "Cancel" will continue data collection.

[0181] If the user has saved the data collection records, they can click the "History" button to jump to the history interface and view the data. Figure 11As shown. After selecting the target record, clicking the "Delete" button will remove the target record, and the deleted records can be viewed through the "Recycle Bin" button. The application can store the saved data in a database for long-term tracking of infant feeding behavior.

[0182] Clicking the "View" button will take you to the view interface to see the complete recorded waveform, such as... Figure 12 As shown. Clicking on any waveform will display the corresponding indicator in the waveform indicator bar. Clicking the "Print Report" button will print the recorded waveform curve as a paper report.

[0183] Clicking the "Data Transfer" button will take you to the data transfer interface, such as... Figure 13 As shown. Clicking the "Medical System" button uploads the infant's waveform recording to the electronic medical record. Clicking the "Mobile Terminal" button uploads the waveform recording to remote devices such as smartphones and tablets. After selecting the recipient, click the "Start Transfer" button to upload the data. To pause the process, press the "Stop Transfer" button. Remote data transmission via the cloud platform can assist doctors in remote diagnosis and treatment, and help multiple medical teams and parents make collaborative decisions.

[0184] Reference Figure 14 This application also provides an infant feeding assessment visualization system, which can implement the above-mentioned infant feeding assessment visualization method. The system includes:

[0185] The first module is used to acquire facial waveforms representing sucking movements, neck waveforms representing swallowing movements, and chest and abdominal waveforms representing breathing movements in infants.

[0186] The second module is used to extract waveform features of the facial waveform, neck waveform, and chest and abdomen waveform, respectively. The waveform features include frequency, peaks, troughs, and amplitude.

[0187] The third module is used to synthesize the facial waveform, neck waveform, and chest and abdomen waveform based on their waveform characteristics to obtain the feeding waveform.

[0188] The fourth module is used to evaluate facial waveforms, neck waveforms, chest and abdominal waveforms, and feeding waveforms using an evaluation model to obtain feeding evaluation results.

[0189] The fifth module is used to display facial waveforms, neck waveforms, chest and abdominal waveforms, feeding waveforms, and feeding assessment results through a preset interface.

[0190] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0191] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described infant feeding assessment visualization method. This electronic device can be any smart terminal, including tablets and smartphones.

[0192] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0193] Reference Figure 15 , Figure 15 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0194] The processor 110 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0195] The memory 120 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 120 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 120 and is called and executed by the processor 110 using the infant feeding assessment visualization method of the embodiments of this application.

[0196] Input / output interface 130 is used to realize information input and output;

[0197] The communication interface 140 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0198] Bus 150 transmits information between various components of the device (e.g., processor 110, memory 120, input / output interface 130, and communication interface 140);

[0199] The processor 110, memory 120, input / output interface 130 and communication interface 140 are connected to each other within the device via bus 150.

[0200] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described infant feeding assessment visualization method.

[0201] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0202] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0203] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0204] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0205] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0206] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0207] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0208] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A visualization method for infant feeding assessment, characterized in that, The method includes the following steps: Acquire facial waveforms representing sucking movements, neck waveforms representing swallowing movements, and chest and abdominal waveforms representing breathing movements in infants; Waveform features of the facial waveform, the neck waveform, and the chest and abdomen waveform are extracted respectively, wherein the waveform features include frequency, peaks, troughs, and amplitude; The facial waveform, neck waveform, and chest and abdomen waveform are synthesized based on their waveform characteristics to obtain a feeding waveform; The facial waveform, neck waveform, chest and abdominal waveform, and feeding waveform are evaluated using an evaluation model to obtain feeding evaluation results; The facial waveform, neck waveform, chest and abdominal waveform, feeding waveform, and feeding assessment results are displayed through a preset interface. The step of synthesizing the facial waveform, neck waveform, and chest / abdomen waveform based on their waveform features to obtain a feeding waveform includes the following steps: The facial waveform, the neck waveform, and the chest and abdomen waveform are time-aligned. The infant's behavioral cycle is determined based on the waveform characteristics of the facial waveform, the neck waveform, and the chest and abdominal waveform, wherein the behavioral cycle includes a first stage, a second stage, and a third stage; The facial waveform, neck waveform, and chest and abdominal waveform are divided into stages according to the behavioral cycle to obtain corresponding segmented waveforms; The segmented waveforms of the face waveform, the neck waveform, and the chest and abdomen waveform that are in the same stage of the same behavioral cycle are synthesized to obtain the behavioral waveform. The behavioral waveforms from different stages are spliced ​​together according to a preset order to obtain the feeding waveform.

2. The method according to claim 1, characterized in that, The acquisition of facial waveforms representing sucking movements, neck waveforms representing swallowing movements, and chest and abdominal waveforms representing breathing movements in infants includes the following steps: A facial waveform is obtained by monitoring the sucking motion of the baby's jaw by placing a first sensor on the face; A second sensor placed in the neck monitors the swallowing motion of the infant's thyroid cartilage, which moves up and down, to obtain a neck waveform. The breathing movements of an infant's chest and abdomen are monitored by a third sensor placed on the chest or abdomen, resulting in a waveform of the chest and abdomen.

3. The method according to claim 1, characterized in that, Determining the infant's behavioral cycle based on the waveform characteristics includes the following steps: The first stage of the infant's sucking and breathing alternation is determined based on the peaks and troughs of the facial waveform and the peaks and troughs of the chest and abdominal waveform. The second stage of apnea during swallowing is determined based on the amplitude of the neck waveform and the amplitude of the chest and abdominal waveform. The third stage of infant respiratory acceleration is determined based on the frequency of the chest and abdominal waveforms. The first stage, the second stage, and the third stage are defined as the infant's behavioral cycle.

4. The method according to claim 3, characterized in that, The step of evaluating the facial waveform, neck waveform, chest and abdominal waveform, and feeding waveform using an evaluation model to obtain feeding evaluation results includes the following steps: The facial waveform is input into the evaluation model to obtain the sucking index; The neck waveform is input into the evaluation model to obtain swallowing indicators; The chest and abdominal waveforms are input into the evaluation model to obtain respiratory indicators; The feeding waveform is input into the evaluation model to obtain the coordination index; The sucking index, swallowing index, breathing index, and coordination index are compared with the preset benchmark parameters in the assessment model to obtain the feeding assessment results.

5. The method according to claim 4, characterized in that, The infant feeding assessment visualization method also includes the following steps: The reference range of the benchmark parameter is determined by using a sampling statistical method based on historical data stored in the database.

6. The method according to claim 1, characterized in that, The infant feeding assessment visualization method also includes the following steps: Record the monitoring data of the facial waveform, the neck waveform, the chest and abdomen waveform, the feeding waveform, and the feeding assessment results; The monitoring data is sent to a preset terminal.

7. A visualization system for infant feeding assessment, characterized in that, The system includes: The first module is used to acquire facial waveforms representing sucking movements, neck waveforms representing swallowing movements, and chest and abdominal waveforms representing breathing movements in infants. The second module is used to extract waveform features of the facial waveform, the neck waveform, and the chest and abdomen waveform, respectively, wherein the waveform features include frequency, peaks, troughs, and amplitude. The third module is used to synthesize the facial waveform, the neck waveform, and the chest and abdomen waveform based on the waveform features of the facial waveform, the neck waveform, and the chest and abdomen waveform to obtain a feeding waveform; The fourth module is used to evaluate the facial waveform, the neck waveform, the chest and abdomen waveform, and the feeding waveform using an evaluation model to obtain feeding evaluation results. The fifth module is used to display the facial waveform, the neck waveform, the chest and abdomen waveform, the feeding waveform, and the feeding assessment results through a preset interface; The step of synthesizing the facial waveform, neck waveform, and chest / abdomen waveform based on their waveform features to obtain a feeding waveform includes the following steps: The facial waveform, the neck waveform, and the chest and abdomen waveform are time-aligned. The infant's behavioral cycle is determined based on the waveform characteristics of the facial waveform, the neck waveform, and the chest and abdominal waveform, wherein the behavioral cycle includes a first stage, a second stage, and a third stage; The facial waveform, neck waveform, and chest and abdominal waveform are divided into stages according to the behavioral cycle to obtain corresponding segmented waveforms; The segmented waveforms of the face waveform, the neck waveform, and the chest and abdomen waveform that are in the same stage of the same behavioral cycle are synthesized to obtain the behavioral waveform. The behavioral waveforms from different stages are spliced ​​together according to a preset order to obtain the feeding waveform.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images