Control Method, System and Storage Medium of Electric Breast Pump

Abstract

The present invention relates to the technical field of electric breast pump control, and discloses a control method, system and storage medium for an electric breast pump. The method includes obtaining an initial flow rate, an initial suction force, a real-time fitting degree and an accumulated flow rate; inputting the initial flow rate and the initial suction force into a preset suction force-flow rate correlation model to obtain a suction force parameter; adjusting the suction force of the breast pump according to the suction force parameter and outputting a suction force-flow rate curve; comparing the real-time fitting degree with a preset fitting degree threshold, and if the real-time fitting degree is lower than the fitting degree threshold, starting a preset breast shield adjustment mechanism, recording and outputting the pressure corresponding to the fitting degree to obtain a pressure-time curve; inputting the suction force-flow rate curve and the pressure-time curve into the suction force-flow rate correlation model for model update, and dynamically updating the accumulated flow rate. When the accumulated flow rate reaches a preset flow rate threshold, breast pumping is completed. This method can achieve intelligent adjustment of the breast pump.

Description

Technical Field

[0001] The present invention relates to the technical field of electric breast pump control, and particularly to a control method, system and storage medium for an electric breast pump. Background Art

[0002] At present, with the acceleration of the modern social life rhythm and the popularization of the concept of breastfeeding, electric breast pumps have become essential supplies for many lactating mothers. In recent years, the market demand for electric breast pumps has shown a continuous growth trend, especially in developed countries and some relatively economically developed regions, and the penetration rate of electric breast pumps has increased year by year.

[0003] In the prior art, most electric breast pumps adopt a fixed suction mode, which cannot meet the personalized needs of mothers. Even some high-end products, although they provide multiple gears of suction adjustment, still require manual operation by mothers, making it difficult to achieve real-time dynamic intelligent adjustment.

[0004] There is a problem that the existing electric breast pumps cannot be dynamically and intelligently adjusted during the breast milk pumping process. Summary of the Invention

[0005] The present invention provides a control method, system and storage medium for an electric breast pump to solve the problem that the existing electric breast pumps cannot be dynamically and intelligently adjusted during the breast milk pumping process.

[0006] In a first aspect, to solve the above technical problem, the present invention provides a control method for an electric breast pump, including: obtaining an initial flow rate, a real-time fitting degree and a cumulative flow rate; inputting the initial flow rate into a preset suction flow rate correlation model to obtain a suction parameter; adjusting the suction of the breast pump according to the suction parameter, monitoring the flow rate to obtain a real-time flow rate, and judging according to the real-time flow rate that if the flow rate increases, the suction intensity is increased, and if the flow rate decreases, the suction intensity is decreased, recording the changes in suction and flow rate and outputting to obtain a suction flow rate curve; comparing the real-time fitting degree with a preset fitting degree threshold, if the real-time fitting degree is lower than the fitting degree threshold, starting a preset breast shield adjustment mechanism, recording and outputting the real-time pressure; performing a regression analysis operation on the real-time pressure to obtain a pressure-suction relationship, obtaining a suction change curve through the pressure-suction relationship, and controlling the breast shield adjustment mechanism according to the suction change curve; inputting the suction flow rate curve into the suction flow rate correlation model for data adjustment, dynamically adjusting the breast milk pumping process according to the suction flow rate correlation model and the breast shield adjustment mechanism, and dynamically updating the cumulative flow rate, and when the cumulative flow rate reaches a preset flow rate threshold, the breast milk pumping is completed.

[0007] In an alternative embodiment, obtaining the initial flow rate, real-time fitting degree, and cumulative flow rate includes: obtaining the initial flow rate through a flow velocity and flow rate sensor and calculating the cumulative flow rate at the current moment; obtaining the pressure value of the contact surface between the breast shield and the breast through a pressure sensor; and obtaining the real-time fitting degree corresponding to the contact surface pressure value through a preset pressure fitting curve.

[0008] In an alternative embodiment, inputting the initial flow rate into a preset suction flow rate correlation model to obtain a suction parameter includes: calculating the suction parameter through the following formula: ; where is the suction parameter, is the quadratic coefficient, used to represent the influence of the square of the flow rate on the suction, is the linear coefficient, used to compensate for the linear effect at low flow rates, is the reference pressure difference, is the flow rate.

[0009] In an alternative embodiment, the training process of the suction flow rate correlation model includes: obtaining flow rate samples obtained under different suctions, analyzing the flow rate range based on the flow rate samples; the flow rate samples include historical suction parameters and historical flow rate data; combining a machine learning algorithm to establish a matching relationship between different suctions and the corresponding flow rate ranges to obtain a basic matching model; dividing the flow rate samples into a training set, a validation set, and a test set to train the basic matching model to obtain trained model parameters, and obtaining a suction flow rate correlation model when the trained model parameters pass model verification.

[0010] In an alternative embodiment, adjusting the suction of the breast pump according to the suction parameter and monitoring the flow velocity to obtain the real-time flow velocity, and judging according to the real-time flow velocity. If the flow velocity increases, the suction intensity is increased; if the flow velocity decreases, the suction intensity is decreased. Recording the changes in suction and flow rate and outputting to obtain a suction flow rate curve includes: calculating the force difference between the collected real-time suction and the suction parameter; dividing the force difference into steps to obtain the adjustment step size; adjusting the suction of the breast pump according to the adjustment step size; during the suction adjustment process, monitoring the milk flow rate in real time to obtain the real-time flow velocity; judging and adjusting the force based on the real-time flow velocity. If the flow velocity increases, the suction intensity is increased; if the flow velocity decreases, the suction intensity is decreased. Recording the flow rate and force to obtain a suction flow rate curve.

[0011] In an alternative embodiment, the real - time fitting degree is compared with a preset fitting degree threshold. If the real - time fitting degree is lower than the fitting degree threshold, a preset breast pump adjustment mechanism is activated, and the real - time pressure is recorded and output, including: according to the preset breast pump adjustment mechanism, when the fitting degree decreases, by adjusting the fitting surface between the breast pump and the breast, the pressure of the fitting surface is obtained, and the fitting degree is readjusted; the pressure of the fitting surface is recorded and output to obtain the real - time pressure.

[0012] In an alternative embodiment, a regression analysis operation is performed on the real - time pressure to obtain a pressure - suction relationship. A suction change curve is obtained through the pressure - suction relationship, and the breast pump adjustment mechanism is controlled according to the suction change curve, including: when the breast pump adjustment mechanism is activated, real - time monitoring is performed to obtain the real - time pressure and the real - time suction; a regression analysis is performed on the real - time pressure to obtain a pressure - suction relationship in which the change of the real - time suction is affected by the change of the real - time pressure; according to the pressure - suction relationship, the change of the suction after the breast pump adjustment mechanism is activated is observed to obtain a suction change curve; wherein, when the suction change curve tends to be stable, it is determined that the adjustment of the breast pump is completed, and then the breast pump adjustment mechanism is controlled to close.

[0013] In an alternative embodiment, the suction - flow curve is input into the suction - flow correlation model for data adjustment. The breast - milk pumping process is dynamically adjusted according to the suction - flow correlation model and the breast pump adjustment mechanism, and the cumulative flow is dynamically updated. When the cumulative flow reaches a preset flow threshold, the breast - milk pumping is completed, including: the suction data and the flow data are obtained through the analysis of the suction - flow curve and input into a pre - established suction - flow correlation model; the model parameters of the suction - flow correlation model are optimized by using the gradient - descent algorithm to obtain an updated suction - flow correlation model; according to the updated suction - flow correlation model and the current flow, the suction parameters are dynamically updated and the suction is dynamically adjusted; the position of the breast pump is dynamically adjusted according to the breast pump adjustment mechanism; the cumulative flow at the current moment is calculated again. When the cumulative flow is greater than or equal to the preset flow threshold, it is determined that the breast - milk pumping is completed, and the electric breast pump is controlled to stop running.

[0014] Second aspect, the present invention provides a control system for an electric breast pump, including: a data acquisition module, configured to acquire an initial flow rate, a real-time fitting degree, and an accumulated flow rate; a suction force calculation module, configured to input the initial flow rate into a preset suction force-flow rate correlation model to obtain a suction force parameter; a flow rate adjustment module, configured to adjust the suction force of the breast pump according to the suction force parameter, monitor the flow rate to obtain a real-time flow rate, and judge according to the real-time flow rate that if the flow rate increases, the suction force intensity is increased, and if the flow rate decreases, the suction force intensity is decreased, record the changes in suction force and flow rate and output them to obtain a suction force-flow rate curve; a fitting degree adjustment module, configured to compare the real-time fitting degree with a preset fitting degree threshold, and if the real-time fitting degree is lower than the fitting degree threshold, start a preset breast shield adjustment mechanism, record and output the real-time pressure; a pressure analysis module, configured to perform a regression analysis operation on the real-time pressure to obtain a pressure-suction force relationship, obtain a suction force change curve through the pressure-suction force relationship, and control the breast shield adjustment mechanism according to the suction force change curve; a data feedback module, configured to input the suction force-flow rate curve into the suction force-flow rate correlation model for data adjustment, dynamically adjust the breast pumping process according to the suction force-flow rate correlation model and the breast shield adjustment mechanism, and dynamically update the accumulated flow rate. When the accumulated flow rate reaches a preset flow rate threshold, the breast pumping is completed.

[0015] Third aspect, the present invention further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the control method of the electric breast pump described in any one of the above.

[0016] Fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the control method of the electric breast pump described in any one of the above.

[0017] Compared with the prior art, the present invention has the following beneficial effects:

[0018] (1) The present invention obtains the suction force parameter based on the suction force-flow rate correlation model for suction force adjustment, and performs fusion analysis on the new data and the existing historical data of the model. By adjusting the parameters of the model, the model can fit the new input data, realize the update of the model, and adapt to the actual situations of different users and breast pumping stages; through the dynamic update of the suction force-flow rate model and the cyclic monitoring of the current flow rate, the dynamic update of the suction force parameter and the dynamic adjustment of the suction force are carried out, forming a closed-loop control to continuously optimize the breast pumping effect; at the same time, since the parameter adjustment is based on objective data and scientific algorithms, it avoids the subjectivity and uncertainty of human judgment and provides a more scientific and comfortable breastfeeding experience for mothers.

[0019] (2) The present invention adjusts the suction force of the breast pump according to the adjustment step length. During the suction force adjustment process, if the real-time flow rate increases, the suction force intensity is increased according to the preset intensity adjustment step length; if the real-time flow rate decreases, the suction force intensity is decreased according to the preset intensity adjustment step length. By such setting, in the initial stage of breast milk pumping, the milk flow rate may be slow, and the system will maintain a low suction force intensity and frequency. As the lactation reflex is fully stimulated and the milk flow rate increases, the system will gradually increase the intensity and frequency. After the lactation peak, as the flow rate begins to decline, the system will correspondingly reduce the parameters to ensure comfort and high efficiency throughout the process. The advantage of this dynamic adjustment mechanism is that it can adapt to the lactation characteristics of each mother in a personalized manner, improving both the breast milk pumping efficiency and ensuring the comfort of use.

[0020] (3) The present invention monitors the fit between the breast shield and the breast in real time through a pressure sensor, triggers the adjustment of the breast shield position through a fit judgment threshold, performs a regression analysis operation on the real-time pressure to obtain a pressure-suction force relationship, obtains a suction force change curve through the pressure-suction force relationship, and controls the breast shield adjustment mechanism according to the suction force change curve. That is, it incorporates the stability of the suction force value into the position adjustment of the breast shield, achieving an optimal dynamic adjustment of the breast shield position, which can not only improve the breast milk pumping efficiency but also adapt to the individual differences of different users. Description of the Drawings

[0021] Figure 1 is a schematic flow chart of the control method of the electric breast pump provided by the first embodiment of the present invention;

[0022] Figure 2 is a schematic structural diagram of the control system of the electric breast pump provided by the second embodiment of the present invention. Detailed Embodiments

[0023] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0024] Refer to Figure 1 , the first embodiment of the present invention provides a control method for an electric breast pump, including the following steps:

[0025] S11, obtaining the initial flow rate, real-time fit degree, and cumulative flow rate;

[0026] S12, inputting the initial flow rate into a preset suction force-flow rate correlation model to obtain suction force parameters;

[0027] S13. Adjust the suction of the breast pump according to the suction parameter, monitor the flow rate to obtain the real-time flow rate, and judge according to the real-time flow rate. If the flow rate increases, increase the suction intensity; if the flow rate decreases, decrease the suction intensity. Record the changes in suction and flow rate and output them to obtain the suction-flow curve.

[0028] S14. Compare the real-time fit with a preset fit threshold. If the real-time fit is lower than the fit threshold, activate a preset breast shield adjustment mechanism, and record and output the real-time pressure.

[0029] S15. Perform a regression analysis operation on the real-time pressure to obtain the pressure-suction relationship, obtain the suction change curve through the pressure-suction relationship, and control the breast shield adjustment mechanism according to the suction change curve.

[0030] S16. Input the suction-flow curve into the suction-flow correlation model for data adjustment, and dynamically adjust the breast pumping process according to the suction-flow correlation model and the breast shield adjustment mechanism. When the cumulative flow rate reaches the preset flow rate threshold, dynamically update the cumulative flow rate to complete breast pumping.

[0031] In step S11, obtain the initial flow rate, real-time fit, and cumulative flow rate.

[0032] Obtain the initial flow rate through a flow rate sensor and calculate the cumulative flow rate at the current moment; obtain the pressure value of the contact surface between the breast shield and the breast through a pressure sensor; obtain the real-time fit corresponding to the contact surface pressure value through a preset pressure-fit curve.

[0033] It should be noted that the initial flow rate is obtained through a flow rate sensor. This involves using a sensor to measure the speed and volume of milk flowing through the breast pump to calculate the initial flow rate. For example, the sensor can be a pressure sensor in an electric breast pump, which can detect the suction volume on the air path to infer the initial flow rate. After obtaining the initial flow rate, it is necessary to calculate the cumulative flow rate at the current moment. This can be obtained by adding the initial flow rate to the previously measured flow rate. The calculation of the cumulative flow rate is crucial for monitoring the entire breast pumping process and ensuring the performance of the breast pump. The pressure value of the contact surface between the breast shield and the breast is obtained through a pressure sensor, and this pressure value reflects the degree of fit between the breast shield and the breast. For example, the pressure sensor can be set on the breast shield to detect the pressure change between the breast and the breast shield. Through a preset pressure-fit curve, the real-time fit corresponding to the contact surface pressure value can be obtained. This real-time fit is very important for adjusting the suction to ensure comfortable and effective breast pumping.

[0034] In step S12, input the initial flow rate into a preset suction-flow correlation model to obtain the suction parameter.

[0035] Calculate the suction parameter through the following formula: ; where is the suction parameter, is the quadratic coefficient, which is used to represent the influence of the square of the flow rate on the suction, is the linear coefficient, which is used to compensate for the linear effect at low flow rates, is the reference pressure difference, is the flow rate.

[0036] It should be noted that is the initial flow rate, which is obtained by the flow sensor and transmitted to the data storage end. The purpose of the suction parameter calculation formula is to find the optimal suction value at the initial flow rate.

[0037] The training process of the suction-flow correlation model includes: obtaining flow samples obtained under different suctions, analyzing the flow range according to the flow samples; the flow samples include historical suction parameters and historical flow data; combining machine learning algorithms to establish a matching relationship between different suctions and the corresponding flow ranges to obtain a basic matching model; dividing the flow samples into a training set, a validation set and a test set to train the basic matching model to obtain the trained model parameters, and obtaining the suction-flow correlation model when the trained model parameters pass the model verification.

[0038] It should be noted that, from the database or file stored locally in the device, read the suction data and flow data recorded during multiple previous milk suction processes in chronological order. Connect the device to the cloud, or through a network request, use a specific API to obtain these historical data from the cloud server, check the data integrity. For missing values, if the missing ratio is small, fill them with the mean or median; if the missing ratio is large, delete the corresponding samples. Use statistical methods to identify and remove outliers to ensure the data quality. Apply the principal component analysis (PCA) algorithm to find the main feature direction of the data, retain the principal components that can explain most of the data variance, and convert the high-dimensional data into low-dimensional suction-flow dimensionality-reduced data to reduce data redundancy and computational complexity.

[0039] Specifically, the principal components of the suction flow dimensionality reduction data are used as coordinate axes. For example, the first principal component suction is used as the x-axis, and the second principal component flow is used as the y-axis. Considering the preset correlation model, the distribution pattern of data points in the coordinate system is determined. Each sample point in the suction flow dimensionality reduction data is mapped to the corresponding position in the correlation coordinate system according to its value on the principal component, completing the mapping of the data points. After receiving the data, the model first preprocesses the newly input curve data, including data cleaning, removing outliers and noise interference, to ensure the accuracy and reliability of the data. Then, using the update algorithm inside the model, the new data is fused and analyzed with the existing historical data of the model. By adjusting the parameters of the model, such as the weight coefficient, bias value, etc., the model can fit the newly input data, realizing the update of the model to adapt to the actual situations of different users and breast pumping stages.

[0040] Specifically, the actual suction and flow data are processed according to the steps of the previous data preprocessing to make them match the data dimensions and ranges in the correlation coordinate system. In the correlation coordinate system, using a fitting algorithm (such as the least squares method), a curve or surface that can best fit all data points (the mapped pressure flow dimensionality reduction data points and the transformed suction flow data points) is found. If the data shows a linear relationship, a straight line is fitted by linear regression; if it is a non-linear relationship, non-linear models such as polynomial regression or neural networks are used for fitting. The mathematical model represented by this fitted curve or surface is the suction flow correlation model, which is used to predict the flow based on the suction or vice versa later, providing a basis for the suction adjustment of the breast pump. After fitting, the flow samples are divided into a training set, a validation set, and a test set to train the basic matching model, obtaining the trained model parameters. When the trained model parameters pass the model verification, the suction flow correlation model is obtained. Exemplarily, a minimum loss threshold or a maximum number of training times can be set. When the loss value of the model is less than the minimum loss threshold or the number of training times is greater than the maximum number of training times, it is determined that the model verification is passed.

[0041] In step S13, the suction of the breast pump is adjusted according to the suction parameter, and the real-time flow rate is monitored to obtain the real-time flow rate. According to the real-time flow rate judgment, if the flow rate increases, the suction intensity is increased; if the flow rate decreases, the suction intensity is decreased. The changes in suction and flow are recorded and output to obtain the suction flow curve.

[0042] Calculate the force difference between the collected real-time suction and the suction parameter; divide the force difference into steps to obtain the adjustment step size; adjust the suction of the breast pump according to the adjustment step size; during the suction adjustment process, monitor the milk flow rate in real time to obtain the real-time flow rate; judge and adjust the force based on the real-time flow rate. If the flow rate increases, the suction intensity is increased; if the flow rate decreases, the suction intensity is decreased. Record the flow and force to obtain the suction flow curve.

[0043] Specifically, obtain the suction parameters output by the model, calculate the force difference between the collected real-time suction and the suction parameters, and perform step division on the force difference to obtain the adjustment step size.

[0044] Next, adjust the suction force of the breast pump according to the adjustment step size. During the suction force adjustment process, the real-time flow rate is monitored in real time through a sensor to determine whether the flow rate increases or decreases. If the real-time flow rate increases, the suction force intensity is increased according to the preset intensity adjustment step size. If the real-time flow rate decreases, the suction force intensity is decreased according to the preset intensity adjustment step size. While adjusting the suction force intensity, the suction force frequency is dynamically adjusted according to the preset frequency adjustment step size to match the current milk secretion rhythm. Input the adjusted suction force intensity and frequency parameters into the control module to perform the dynamic adjustment operation. By continuously monitoring the real-time flow rate and dynamically adjusting the suction parameters in a loop, a closed-loop control is formed to continuously optimize the matching effect of the suction force intensity and frequency.

[0045] Exemplarily, obtain the suction parameters output by the model, which are obtained based on a large amount of historical data and machine learning algorithms. For example, the model may suggest an initial suction force intensity of 50 kPa and a frequency of 60 times per minute. Combining the preset adjustable range and adjustment step size, the system will set the intensity range to 30 - 70 kPa with a step size of 5 kPa; the frequency range is 40 - 80 times per minute with a step size of 5 times per minute. Real-time monitoring of the real-time flow rate is the basis for dynamic adjustment. Assume that an optoelectronic sensor is used to measure the volume of milk flowing through per unit time, and the initial flow rate is 10 ml / min. If the detected flow rate increases to 12 ml / min, the system will increase the suction force intensity according to the preset step size, such as from 50 kPa to 55 kPa. This enhancement can more effectively stimulate the mammary gland and promote milk secretion. On the contrary, if the flow rate decreases to 8 ml / min, the system will reduce the intensity to 45 kPa to avoid discomfort or damage to the breast. At the same time, adjusting the suction force frequency is also important, which needs to match the natural milk secretion rhythm of the mother. For example, if it is detected that the milk flow rate increases while the lactation interval shortens, the system may increase the frequency from 60 times per minute to 65 times per minute. This adjustment helps to better simulate the baby's sucking rhythm, stimulate the secretion of prolactin, and maintain the continuous flow of milk.

[0046] It should be noted that closed-loop control is the core of the whole process. By continuously monitoring the milk flow rate and adjusting parameters accordingly, the system can adapt to various changes during lactation. For example, at the initial stage of milk extraction, the milk flow rate may be slow, and the system will maintain a low suction intensity and frequency. As the lactation reflex is fully stimulated and the milk flow rate increases, the system will gradually increase the intensity and frequency. After the lactation peak, when the flow rate begins to decline, the system will correspondingly reduce the parameters to ensure a comfortable and efficient process. The advantage of this dynamic adjustment mechanism is that it can be personalized to adapt to the lactation characteristics of each mother. Some mothers may require a higher suction intensity to effectively stimulate milk secretion, while others may respond better to a lower intensity. Through real-time adjustment, the system can find the parameter combination that is most suitable for each user, improving both the milk extraction efficiency and the usage comfort.

[0047] In step S14, compare the real-time fit with a preset fit threshold. If the real-time fit is lower than the fit threshold, start a preset breast shield adjustment mechanism, record and output the real-time pressure.

[0048] Among them, starting the preset breast shield adjustment mechanism, recording and outputting the real-time pressure includes: according to the preset breast shield adjustment mechanism, when the fit decreases, by adjusting the contact surface between the breast shield and the breast, obtain the contact surface pressure, and readjust the fit; record the contact surface pressure and output it to obtain the real-time pressure.

[0049] It should be noted that the preset breast shield adjustment mechanism is triggered by judging whether the fit between the breast shield and the breast has changed based on the pressure sensor data. When the pressure data monitored by the pressure sensor shows abnormal fluctuations or does not conform to the pressure change pattern during normal milk extraction, etc., combined with the fit judgment threshold for analysis, if it is judged that the fit between the breast shield and the breast has decreased (for example, it may be because the mother moves during milk extraction or the breast shield has shifted due to a long wearing time), the preset breast shield adjustment mechanism will be started.

[0050] Specifically, use a pressure sensor to collect the contact surface pressure value of the contact surface between the breast shield and the breast in real time, and transmit the collected value to the data processing module. According to the preset fit judgment threshold, perform a trend analysis on the collected value to obtain the change trend value of the pressure value. If the change trend value is lower than the preset threshold, it is judged that the fit has decreased, and the breast shield position adjustment mechanism is triggered. Through the adjustment mechanism, the position of the breast shield is finely adjusted to make the pressure value of the contact surface reach the preset range value again.

[0051] Exemplarily, one of the core functions of an intelligent electric breast pump is to monitor and optimize the fit between the breast shield and the breast in real time. By collecting the contact surface pressure value in real time through a pressure sensor, the change in the fit can be accurately judged. For example, when a new mother starts using the breast pump, the pressure sensor may detect an initial pressure value of 5 kPa. As the usage time extends, if the pressure value drops to 4 kPa, the system will judge that the fit has decreased. Suppose the threshold is set at 0.5 kPa / min, that is, the pressure value change per minute does not exceed 0.5 kPa. If it is detected that the pressure value drops from 5 kPa to 4.4 kPa within one minute, and the change trend value is 0.6 kPa / min, exceeding the preset threshold, the system will trigger the breast shield position adjustment mechanism. The adjustment mechanism includes fine-tuning the angle of the breast shield or slightly changing its position. For example, the system will guide the user to lift the breast shield slightly upward by 2 - 3 mm, or tilt it slightly towards the center of the breast by 1 - 2 degrees. These minor adjustments can significantly improve the fit and bring the pressure value back to the ideal range, such as around 5 kPa.

[0052] In step S15, a regression analysis operation is performed on the real-time pressure to obtain the pressure-suction relationship. Through the pressure-suction relationship, a suction change curve is obtained, and the breast shield adjustment mechanism is controlled according to the suction change curve, including: when the breast shield adjustment mechanism is started, real-time monitoring is carried out to obtain the real-time pressure and real-time suction; a regression analysis is performed on the real-time pressure to obtain the pressure-suction relationship in which the real-time suction change is affected by the real-time pressure change; according to the pressure-suction relationship, the change in suction after the breast shield adjustment mechanism is started is observed to obtain the suction change curve; wherein, when the suction change curve tends to be stable, it is determined that the breast shield adjustment is completed, and then the breast shield adjustment mechanism is controlled to close.

[0053] Specifically, the real-time pressure and real-time suction are obtained through a pressure sensor and a suction sensor. By monitoring and analyzing the change in suction affected by the change in the fit, the relationship of mutual influence among suction, pressure, and flow rate is obtained.

[0054] Specifically, a regression analysis is performed on the adjusted pressure value to obtain the corresponding relationship between the suction value and the pressure value. According to the regression analysis result, the change trend value of the suction value is determined, and it is judged whether the suction value is stable. If the suction value is stable, the adjustment mechanism is stopped, and the optimization of the breast shield position is completed.

[0055] It should be noted that the regression model analyzes historical data to establish the relationship between pressure values, flow values, and suction values. For example, by using a multiple linear regression model and training with a large amount of historical data, the model can quickly provide the optimal dynamic adjustment process for different situations. This intelligent breast pumping system can not only improve the breast pumping efficiency but also adapt to the individual differences of different users. Through real-time monitoring and dynamic adjustment, the system can simulate the natural rhythm of infant sucking and promote milk secretion. At the same time, since the parameter adjustment is based on objective data and scientific algorithms, it avoids the subjectivity and uncertainty of human judgment and provides a more scientific and comfortable breastfeeding experience for mothers.

[0056] Exemplarily, during the adjustment process, through regression analysis, a corresponding relationship model between the suction value and the pressure value can be established. Exemplarily, assume that the analysis result shows that when the pressure value is within the range of 4.8 - 5.2 kPa, the suction value remains most stable between 220 - 240 mmHg. This means that the system will strive to maintain the pressure value within this range to ensure the best breast pumping effect. If the suction value is continuously monitored to fluctuate within a reasonable range, and the specific fluctuation situation is adapted to the dynamic adjustment process of the suction (i.e., there is no large-scale suction fluctuation caused by the adjustment of the breast shield), and the duration exceeds 3 minutes, the system will consider that the suction value has stabilized, and at this time, the adjustment mechanism can be stopped.

[0057] In step S16, input the suction flow curve into the suction flow correlation model for data adjustment, dynamically adjust the breast pumping process according to the suction flow correlation model and the breast shield adjustment mechanism, and dynamically update the cumulative flow. When the cumulative flow reaches the preset flow threshold, the breast pumping is completed, including: obtaining suction data and flow data through the analysis of the suction flow curve and inputting them into the pre-established suction flow correlation model; using the gradient descent algorithm to optimize the model parameters of the suction flow correlation model to obtain the updated suction flow correlation model; dynamically updating the suction parameters and dynamically adjusting the suction according to the updated suction flow correlation model and the current flow; dynamically adjusting the position of the breast shield according to the breast shield adjustment mechanism; calculating the cumulative flow at the current moment again. When the cumulative flow is greater than or equal to the preset flow threshold, it is determined that the breast pumping is completed, and the electric breast pump is controlled to stop running.

[0058] The suction flow curve obtained from this breast pumping is the individual data of the user's breast pumping process. Output the suction flow curve into the suction flow correlation model for user data recording to complete the data iteration of the model for the individual.

[0059] Specifically, pressure data and flow rate data are collected in real time by sensors, and the collected data is input into a pre-established suction flow rate correlation model. According to the input suction data and flow rate data, the gradient descent algorithm is used to optimize the model parameters to obtain an updated parameter model. The updated parameter model is applied to the suction adjustment module to generate a new suction adjustment plan. The suction adjustment plan is combined with the updated parameter model, and the updated model is combined with the current flow rate to obtain updated suction parameters, and the iteration loop enters the suction adjustment process such as step S13, so as to generate a dynamic adjustment breast pumping process plan adapted to the individual. By monitoring the suction data and flow rate data in real time, the accuracy and adaptability of the breast pumping process plan are verified to complete the model iteration.

[0060] Specifically, the flow rate value collected in real time by the flow rate sensor is obtained, time series processing is performed on the flow rate value to obtain a real-time value. Cumulative calculation is performed according to the real-time value to obtain the real-time cumulative flow rate. A preset value is extracted from the preset database, and the real-time cumulative flow rate is compared with the preset value to obtain a comparison value. If the comparison value reaches the threshold amount, a trigger value is generated. A control signal is generated according to the trigger value, and the control signal is used to control the shutdown of the electric breast pump.

[0061] Exemplarily, the intelligent control system of the electric breast pump optimizes the breast pumping process by monitoring and analyzing the milk flow rate in real time to ensure safe and efficient breast pumping. The flow rate sensor continuously collects milk flow rate data, and the system performs time series processing on these raw data to obtain a real-time value reflecting the current flow rate state. This processing method can effectively eliminate the influence of instantaneous fluctuations and provide more stable and reliable flow rate information. The real-time flow rate value is subjected to cumulative calculation to obtain the real-time cumulative flow rate, which represents the total amount of milk that has been pumped out. The system compares the cumulative amount with a pre-set target value to judge the progress of breast pumping. For example, if the preset target is 150 ml, when the cumulative amount reaches 135 ml, the system may generate a trigger value to indicate that breast pumping is about to be completed. This trigger value is converted into a signal value to control the operating state of the electric breast pump, such as reducing the suction force or preparing to stop. Machine learning algorithms play an important role in flow rate anomaly detection. By analyzing historical data, the algorithm can establish a model of the normal flow rate pattern. In actual use, if it is detected that the flow rate suddenly increases or decreases to an abnormal range, the system will immediately stop the cumulative amount calculation and generate an abnormal signal to trigger the safety shutdown mechanism of the electric breast pump.

[0062] The working process of the present invention is described below by taking a relatively common scenario as an example. Please also refer to Figure 2 , which is Figure 1 a schematic diagram of the working scenario of the method.

[0063] Step 1: Start the electric breast pump to prepare for breast milk pumping. The flow rate and pressure sensors are activated, and the initial flow rate, initial suction force, real-time fit, and cumulative flow rate are obtained.

[0064] Step 2: The obtained data is transmitted into a preset suction force - flow rate correlation model to obtain the suction force parameter matching the current flow rate, and the suction force parameter is transmitted to the suction force intensity control module.

[0065] Step 3: Compare the suction force parameter with the current suction force, adjust the suction force of the electric breast pump in the direction of the suction force parameter trend, and the flow rate and pressure sensors monitor. If the flow rate increases, the suction force intensity is increased; if the flow rate decreases, the suction force intensity is decreased.

[0066] Step 4: Monitor through the flow rate and pressure sensors. If the flow rate is stable and the cumulative flow rate increases, the current suction force parameter is maintained; if the flow rate is unstable or the flow rate does not increase, feedback adjustment is performed.

[0067] Step 5: Obtain the fit data through the pressure sensor, and judge the fit data with a preset fit range. If the fit data is within the fit range, it is maintained; otherwise, a preset breast shield adjustment mechanism is activated to adjust the fit to ensure that breast milk pumping is not affected.

[0068] Step 6: Judge according to the real - time cumulative flow rate obtained by the flow rate and pressure sensors. When the real - time cumulative flow rate reaches the preset flow rate threshold, breast milk pumping is completed, a stop signal is sent and transmitted to the control system to stop the electric breast pump.

[0069] In summary, the present invention has the following beneficial effects: The present invention discloses a control method, system, and storage medium for an electric breast pump, including obtaining an initial flow rate, real - time fit, and cumulative flow rate; inputting the initial flow rate into a preset suction force - flow rate correlation model to obtain a suction force parameter; adjusting the suction force of the breast pump according to the suction force parameter, monitoring the flow rate to obtain the real - time flow rate, and judging according to the real - time flow rate. If the flow rate increases, the suction force intensity is increased; if the flow rate decreases, the suction force intensity is decreased, recording the changes in suction force and flow rate and outputting to obtain a suction force - flow rate curve; comparing the real - time fit with a preset fit threshold. If the real - time fit is lower than the fit threshold, a preset breast shield adjustment mechanism is activated, recording and outputting the real - time pressure; performing a regression analysis operation on the real - time pressure to obtain a pressure - suction force relationship, obtaining a suction force change curve through the pressure - suction force relationship, and controlling the breast shield adjustment mechanism according to the suction force change curve; inputting the suction force - flow rate curve into the suction force - flow rate correlation model for data adjustment, and dynamically adjusting the breast milk pumping process according to the suction force - flow rate correlation model and the breast shield adjustment mechanism. When the cumulative flow rate reaches the preset flow rate threshold, breast milk pumping is completed.

[0070] The present invention monitors the fit between the breast shield and the breast in real time through a pressure sensor, combines with a flow sensor to collect milk flow rate and cumulative flow data, and forms a set of key parameters during the milk pumping process. A correlation model of pressure, flow rate and suction force is established using machine learning algorithms, and the suction force intensity and frequency are dynamically adjusted according to real-time data. The position of the breast shield is adjusted by triggering a fit judgment threshold. At the same time, it is judged that the milk pumping is completed by comparing the cumulative flow with a preset threshold to avoid over-milking. This method realizes the intelligent control of the electric breast pump, can adaptively adjust the suction parameters according to the breast milk secretion state, and improves the milk pumping efficiency and comfort level.

[0071] Referring to Figure 2 , the second embodiment of the present invention provides a control system for an electric breast pump, including: a data acquisition module for acquiring the initial flow rate, real-time fit and cumulative flow rate; a suction force calculation module for inputting the initial flow rate into a preset suction force-flow rate correlation model to obtain suction force parameters; a flow rate adjustment module for adjusting the suction force of the breast pump according to the suction force parameters, monitoring the flow rate to obtain the real-time flow rate, and judging according to the real-time flow rate that if the flow rate increases, the suction force intensity is increased, if the flow rate decreases, the suction force intensity is decreased, recording the changes in suction force and flow rate and outputting to obtain a suction force-flow rate curve; a fit adjustment module for comparing the real-time fit with a preset fit threshold, if the real-time fit is lower than the fit threshold, starting a preset breast shield adjustment mechanism, recording and outputting the real-time pressure; a pressure analysis module for performing a regression analysis operation on the real-time pressure to obtain a pressure-suction force relationship, obtaining a suction force change curve through the pressure-suction force relationship, and controlling the breast shield adjustment mechanism according to the suction force change curve; a data feedback module for inputting the suction force-flow rate curve into the suction force-flow rate correlation model for data adjustment, dynamically adjusting the milk pumping process according to the suction force-flow rate correlation model and the breast shield adjustment mechanism, and dynamically updating the cumulative flow rate. When the cumulative flow rate reaches a preset flow rate threshold, the milk pumping is completed.

[0072] It should be noted that the control system for an electric breast pump provided in the embodiment of the present invention is used to execute all the process steps of the control method for an electric breast pump in the above embodiment. Their working principles and beneficial effects correspond one by one, so they will not be elaborated here.

[0073] The embodiment of the present invention also provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a control program for an electric breast pump. When the processor executes the computer program, the steps in the above embodiments of the control method for an electric breast pump are implemented, such as Figure 1The step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above device embodiments, such as the data acquisition module.

[0074] Exemplarily, the computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the electronic device.

[0075] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device. It may include more or fewer components than the above, or combine certain components, or different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0076] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device and connects various parts of the entire electronic device through various interfaces and lines.

[0077] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory and invoking the data stored in the memory, the processor realizes various functions of the electronic device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0078] Among them, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-described various method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0079] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0080] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. In particular, for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A control method for an electric breast pump, characterized in that: include: Get initial traffic, real-time fit and cumulative traffic; Inputting the initial flow into a preset suction flow correlation model to obtain a suction parameter; The suction of the breast pump is adjusted according to the suction parameters, and the flow rate is monitored to obtain the real-time flow rate. According to the real-time flow rate, if the flow rate increases, the suction strength is increased, and if the flow rate decreases, the suction strength is reduced. The changes in suction and flow are recorded and output to obtain a suction flow curve; comparing the real-time fit with a preset fit threshold, and if the real-time fit is lower than the fit threshold, activating a preset breast shield adjustment mechanism, and recording and outputting the real-time pressure; Performing a regression analysis operation on the real-time pressure to obtain a pressure-suction relationship, obtaining a suction change curve through the pressure-suction relationship, and controlling the breast shield adjustment mechanism according to the suction change curve; Inputting the suction flow curve into the suction flow correlation model for data adjustment, dynamically adjusting the breast pumping process according to the suction flow correlation model and the breast shield adjustment mechanism, and dynamically updating the accumulated flow, and completing the breast pumping when the accumulated flow reaches a preset flow threshold; The training process of the suction flow correlation model includes: Obtain flow samples obtained under different suction forces, and obtain a flow range according to the flow samples; the flow samples include historical suction parameters and historical flow data; Combined with machine learning algorithms, different suction forces are matched with corresponding flow ranges to obtain a basic matching model. The flow samples are divided into a training set, a validation set and a test set to train the basic matching model to obtain trained model parameters. When the trained model parameters pass the model verification, a suction flow correlation model is obtained.

2. The control method of the electric breast pump according to claim 1, characterized in that: Get initial traffic, real-time fit and cumulative traffic, including: The initial flow rate is obtained through the flow rate sensor, and the accumulated flow rate at the current moment is calculated; The pressure value of the contact surface between the breast shield and the breast is obtained through a pressure sensor; The real-time fit degree corresponding to the contact surface pressure value is obtained through a preset pressure fit degree curve.

3. The control method of the electric breast pump according to claim 1, characterized in that: The suction of the breast pump is adjusted according to the suction parameters, and the flow rate is monitored to obtain the real-time flow rate. According to the real-time flow rate, if the flow rate increases, the suction strength is increased, and if the flow rate decreases, the suction strength is reduced. The changes in suction and flow are recorded and output to obtain a suction flow curve, including: Calculate the force difference between the collected real-time suction force and the suction force parameter; Divide the force difference into steps to obtain the adjustment step length; Adjust the suction power of the breast pump according to the adjustment step length; During the suction adjustment process, the milk flow is monitored in real time to obtain the real-time flow rate; The strength is judged and adjusted based on the real-time flow rate. If the flow rate increases, the suction strength is increased. If the flow rate decreases, the suction strength is reduced. The flow rate and strength are recorded to obtain a suction flow curve.

4. The control method of the electric breast pump according to claim 1, characterized in that: Activate preset breastshield adjustment mechanisms, record and output real-time pressure, including: According to the preset breast shield adjustment mechanism, when the fit is reduced, the fit is readjusted by adjusting the fit surface between the breast shield and the breast to obtain the fit surface pressure; The lamination surface pressure is recorded and outputted to obtain real-time pressure.

5. The control method of the electric breast pump according to claim 1, characterized in that: Performing a regression analysis operation on the real-time pressure to obtain a pressure-suction relationship, obtaining a suction change curve through the pressure-suction relationship, and controlling the breast shield adjustment mechanism according to the suction change curve, including: When the breast shield adjustment mechanism is activated, real-time monitoring is performed to obtain real-time pressure and real-time suction; Performing regression analysis on the real-time pressure to obtain a pressure-suction relationship in which the real-time pressure change affects the real-time suction change; According to the pressure-suction relationship, the change of suction when the breast shield adjustment mechanism is activated is observed to obtain a suction change curve; When the suction force variation curve tends to be stable, it is determined that the adjustment of the breast shield is completed, and the breast shield adjustment mechanism is controlled to be closed.

6. The control method of the electric breast pump according to claim 1, characterized in that: Inputting the suction flow curve into the suction flow correlation model for data adjustment, dynamically adjusting the breast pumping process according to the suction flow correlation model and the breast shield adjustment mechanism, and dynamically updating the accumulated flow, and completing breast pumping when the accumulated flow reaches a preset flow threshold, including: Obtaining suction data and flow data through the suction flow curve analysis, and inputting them into a pre-established suction flow correlation model; The model parameters of the suction-flow correlation model are optimized by using the gradient descent algorithm to obtain an updated suction-flow correlation model. According to the updated suction-flow correlation model and the current flow, the suction parameters are dynamically updated and the suction is dynamically adjusted; Dynamic adjustment of the bra position according to the bra adjustment mechanism; The accumulated flow rate at the current moment is calculated again. When the accumulated flow rate is greater than or equal to the preset flow rate threshold, it is determined that the milk pumping is completed, and the electric breast pump is controlled to stop running.

7. A control system for an electric breast pump, characterized in that: A control method for implementing the electric breast pump according to any one of claims 1 to 6, comprising: Data acquisition module, used to obtain initial flow, real-time fit and cumulative flow; A suction calculation module, used for inputting the initial flow into a preset suction flow correlation model to obtain suction parameters; A flow rate adjustment module, for adjusting the suction of the breast pump according to the suction parameters, and monitoring the flow rate to obtain a real-time flow rate, judging according to the real-time flow rate, if the flow rate increases, the suction strength is increased, if the flow rate decreases, the suction strength is reduced, and the changes in suction and flow are recorded and output to obtain a suction flow curve; A fit adjustment module, used for comparing the real-time fit with a preset fit threshold, and if the real-time fit is lower than the fit threshold, activating a preset breast shield adjustment mechanism, and recording and outputting the real-time pressure; A pressure analysis module, used for performing a regression analysis operation on the real-time pressure to obtain a pressure-suction relationship, obtaining a suction change curve through the pressure-suction relationship, and controlling the breast shield adjustment mechanism according to the suction change curve; The data feedback module is used to input the suction flow curve into the suction flow correlation model for data adjustment, dynamically adjust the breast pumping process according to the suction flow correlation model and the breast shield adjustment mechanism, and dynamically update the cumulative flow. When the cumulative flow reaches a preset flow threshold, breast pumping is completed.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the control method of the electric breast pump according to any one of claims 1 to 6.

Images