Lactagogue massage robot and lactagogue massage system based on convolutional neural network guidance
Through a convolutional neural network-based lactating massage robot, combined with the robotic arm and CNN evaluation module, the problem of difficulty in achieving unified and accurate artificial massage is solved, the maternal patency and lactation volume are improved, and maternal discomfort and medical resource consumption are reduced. Improves breastfeeding efficiency.
Patent Information
- Application Number
- CN202411241350.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-08
AI Technical Summary
The existing clinical lactation massage technology relies on manual operations, making it difficult to achieve unified and precise acupoint massage. The mother is not adaptable to artificial massage and consumes a lot of human resources, which leads to insufficient lactation in the early stages of breastfeeding and difficult to effectively solve the problem of breast pain. solve.
Design a lactating massage robot based on convolutional neural network guidance, combining robotic arms, electric breast pumps, ultrasonic devices and CNN evaluation modules to realize breast abnormality assessment and intelligent massage, and interact with the backend server through processor system and communication system. Provides automated lactating massage and milk storage services.
Automatic lactating massage is realized, which reduces the error of manual operation, improves breast patency and lactation, reduces the discomfort of postpartum masturbation, saves medical resources, and improves the efficiency and adaptability of breastfeeding.
Smart Images

Figure CN118903584A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of intelligent medical technology, and in particular to a lactation-inducing massage robot and a lactation-inducing massage system guided by a convolutional neural network. Background Art
[0002] Breastfeeding refers to the process of feeding a baby directly with the mother's breast milk. It is well known that breastfeeding promotes infant development, improves maternal and child health, and reduces unnecessary economic losses.
[0003] In 2011, the World Health Organization recommended that infants be exclusively breastfed to achieve optimal infant growth. In 2009, WHO and UNICEF launched the Baby-Friendly Hospital Initiative to establish supportive breastfeeding methods. Literature indicates that the first lactation start time for Chinese mothers is about 30 hours, and the average breast milk intake per newborn on the first day of life is 15.1 ml.
[0004] Many studies have shown that insufficient milk production in mothers with babies in the same room is an important factor affecting the low rate of full breastfeeding during hospitalization. In the early stages of breastfeeding, the skin of the mother's nipples is thin, and the newborn's nipples are easily broken and bleeding after sucking, causing breast pain in the mother and reducing her enthusiasm for breastfeeding.
[0005] Some newborns are transferred to the NICU for observation and treatment due to physical reasons. Breast milk has a positive effect on their growth and development and disease prognosis. However, the lactation start time of mothers separated from their babies is delayed, serum prolactin levels decrease, and milk production decreases, which cannot meet the nutritional needs of newborns in the NICU. At the same time, some mothers produce a lot of milk, their breasts are swollen and full, the milk ducts are blocked, and breast nodules form, causing pain.
[0006] Postpartum breast massage is currently implemented in clinical practice. Although postpartum breast massage can effectively shorten the time to start lactation, dredge the mammary ducts, relieve breast pain, and increase milk production; however, most of the breast massages performed in clinical practice are performed by lactation specialists. Artificial lactation cannot achieve homogeneous lactation. Acupoint massage requires lactation specialists to accurately master the distribution of acupoints. However, the current lactation market is mixed, and the qualifications of practitioners vary, making it impossible to implement massage uniformly. In addition, some pregnant women are very reluctant to have "lactation specialists" perform artificial massage to induce lactation on them. They are not very adaptable, and the massage is relatively tiring. Summary of the invention
[0007] In order to solve the above problems, the present application proposes a lactation massage robot and a lactation massage system based on convolutional neural network guidance.
[0008] On the one hand, the present application proposes a lactation massage robot guided by a convolutional neural network, which is constructed based on a massage robot. The massage robot includes a processor system and a mechanical arm. The lactation massage robot includes:
[0009] Communication system, used to provide communication services for control and communication interaction with the host computer;
[0010] Main controller, used to implement logic control;
[0011] An electric breast pump, driven by the mechanical arm, for providing positioning massage and milk pumping services in a preset trajectory;
[0012] Low temperature storage unit for storing milk at low temperature;
[0013] A temperature control module, used to provide a temperature control environment for the low-temperature storage unit;
[0014] A touch screen, used for the user to input various types of control parameters and display corresponding robot service data;
[0015] The electric breast pump is arranged at the end of the mechanical arm of the massage robot and is connected to the low-temperature storage unit through a pipeline;
[0016] The communication system and the main controller are electrically connected to the processor system of the massage robot respectively;
[0017] The electric breast pump, temperature control module and touch screen are electrically connected to the main controller respectively.
[0018] As an optional embodiment of the present application, optionally, the low-temperature storage unit comprises a plurality of milk storage bags;
[0019] The milk storage bag is connected to the electric breast pump through a pipeline, and a solenoid valve is provided on the pipeline, and the solenoid valve is used to open the corresponding pipeline under the control of the main controller to allow milk to flow into the corresponding milk storage bag;
[0020] The solenoid valve is electrically connected to the main controller.
[0021] As an optional embodiment of the present application, optionally, the lactation massage robot further includes:
[0022] A cleaning component, used for providing cleaning services for the milk storage bag and the electric breast pump;
[0023] The cleaning component is electrically connected to the main controller.
[0024] As an optional embodiment of the present application, optionally, the lactation massage robot further includes:
[0025] An ultrasound device, used for performing a breast scan, collecting corresponding breast scan ultrasound data and sending it to the processor system of the massage robot through the main controller, wherein the processor system generates a corresponding breast intra-structure image according to the breast scan ultrasound data and sends it to the CNN evaluation module through the main controller;
[0026] The CNN evaluation module is used to use a preset breast abnormality evaluation model to intelligently identify the breast internal structure image and determine whether there is abnormality in the breast or milk duct:
[0027] If it occurs, a corresponding alarm signal is generated and fed back to the main controller;
[0028] If it does not appear, it is abandoned;
[0029] The ultrasonic device and the CNN evaluation module are electrically connected to the main controller respectively.
[0030] As an optional embodiment of the present application, optionally, the method for generating the breast abnormality assessment model is:
[0031] Collect a number of breast structure images showing abnormalities of breast glands or milk ducts as training data sets;
[0032] Importing the training data set into a preset CNN model, and using a convolutional neural network to learn and train abnormal breast or milk duct image features in the training data set;
[0033] After the training is completed, the breast abnormality assessment model is generated;
[0034] The breast abnormality assessment model is clinically verified and optimized, and put into clinical application after passing the test.
[0035] As an optional implementation scheme of the present application, optionally, the main controller is also used for:
[0036] sending the alarm signal to a processor system of the massage robot;
[0037] The processor system is also configured to:
[0038] In response to the alarm signal, a preset action instruction of the robot arm is generated and sent to the main controller;
[0039] The main controller is also used for:
[0040] The preset action instruction is executed to control the mechanical arm to drive the electric breast pump thereon to move according to the preset trajectory to perform positioning massage and milk pumping services.
[0041] As an optional implementation scheme of the present application, optionally, the processor system is also used for:
[0042] Identifying and marking the breast contour in the breast intrastructural image;
[0043] Comparing the breast contour with a preset contour image, and calculating a similarity value between the breast contour and the preset contour image based on the similarity;
[0044] estimating the amount of milk production of the mammary gland according to the similarity value;
[0045] sending the estimated lactation amount to the touch screen via the main controller;
[0046] The touch screen is also used for:
[0047] The estimated amount of lactation for the mother is displayed.
[0048] On the other hand, the present application provides a lactation massage system, comprising:
[0049] A lactation massage robot guided by convolutional neural network;
[0050] The nurse terminal is used by nurses to log in to the backend server, select and view the corresponding maternal data information;
[0051] A backend server is used to interactively control the nurse terminal and the lactation massage robot, and record the admission information of the parturient through the HIS system;
[0052] The nurse terminal and the lactation massage robot are respectively connected to the backend server for communication.
[0053] As an optional embodiment of the present application, optionally, the lactation massage robot is also used for:
[0054] Read the basic information of the parturient recorded in the HIS system, and analyze whether there are any preset abnormal conditions in the basic information of the parturient:
[0055] If it occurs, the exception is handed over to the processor system for handling;
[0056] Otherwise give up.
[0057] Technical effects of the present invention:
[0058] Based on the implementation of the present invention, the present invention can use intelligent robots to replace manual labor to implement postpartum supervision and care for parturients, can read the basic information of parturients from the HIS system, and combine with massage robots to complete breast abnormality assessment, lactation massage, milk suction and milk storage operations for parturients, so as to assist parturients in achieving automated lactation and other tasks. Through the lactation massage robot, lactation massage can be implemented in a unified manner to avoid nursing errors caused by uneven qualifications of lactation personnel. At the same time, the professional requirements for lactation can be reduced, and manpower and time can be saved for nurses, parturients, etc., making postpartum care easier. In addition, it can allow some parturients to avoid the symptoms of maladaptation caused by artificial lactation. Robot lactation has a wide market adaptability and high emergency benefits.
[0059] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.
[0061] Figure 1 It is a schematic diagram showing the functional architecture of the lactation massage robot of the present invention;
[0062] Figure 2 The following is a schematic diagram showing the general application system composition of an existing robot;
[0063] Figure 3 The following is a schematic diagram of the functional architecture of an existing robot;
[0064] Figure 4 Schematic diagram of the internal structure of the breast showing abnormalities of the mammary glands or milk ducts;
[0065] Figure 5 Shown is a schematic diagram of the system composition structure of the lactation-promoting massage system of the present invention. DETAILED DESCRIPTION
[0066] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.
[0067] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.
[0068] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.
[0069] Example 1
[0070] This solution is based on a massage robot and an electric breast pump to construct the basic hardware system of a lactation massage robot (referred to as "robot"), and then combined with an intelligent evaluation module and an ultrasound system to allow the lactation massage robot to interact with the background and the nurse side.
[0071] The robot's composition system and its functional architecture are specifically combined with the attached Figure 2 and attached Figure 3 As shown, the basic structure and principle of the robot are not described in detail in this embodiment. For the path calculation, positioning, environmental sensing, infrared face recognition, mobile walking, obstacle avoidance, voice, communication, data processing and interactive control, etc., the existing hardware system of the existing factory robot can continue to be used, and the program is designed and developed by the user.
[0072] The key technology of the present invention mainly lies in the technical architecture of the proposed lactation massage robot. The structure, shape and size, deployment connection, installation, etc. of the corresponding specific lactation massage robot are not taken into consideration. Users can purchase / develop corresponding hardware equipment and software systems according to the principles of the present invention.
[0073] Massage robots, such as moxibustion robots or thermal massage robots, have their own processor systems and can perform some types of data and image processing.
[0074] An electric breast pump can be purchased by yourself, such as a "wearable electric breast pump", and its main control board can be connected to the main controller deployed by the present invention (such as an STM microcontroller or an MCU series chip), or the main controller of the massage robot can be used to achieve joint control.
[0075] The electric breast pump, with its built-in chip, vibration component and air pump, can achieve a series of functions such as massage, lactation, and milk suction. Please understand it in conjunction with the functional service components of the existing "electric breast pump".
[0076] In this embodiment, the specific model of the electric breast pump is not limited.
[0077] like Figure 1As shown, on one hand, the present application proposes a lactation massage robot guided by a convolutional neural network, which is constructed based on a massage robot. The massage robot includes a processor system and a mechanical arm. The lactation massage robot includes:
[0078] Communication system, used to provide communication services for control and communication interaction with the host computer;
[0079] Main controller, used to implement logic control;
[0080] An electric breast pump, driven by the mechanical arm, for providing positioning massage and milk pumping services in a preset trajectory;
[0081] Low temperature storage unit for storing milk at low temperature;
[0082] A temperature control module, used to provide a temperature control environment for the low-temperature storage unit;
[0083] A touch screen, used for the user to input various types of control parameters and display corresponding robot service data;
[0084] The electric breast pump is arranged at the end of the mechanical arm of the massage robot and is connected to the low-temperature storage unit through a pipeline;
[0085] The communication system and the main controller are electrically connected to the processor system of the massage robot respectively;
[0086] The electric breast pump, temperature control module and touch screen are electrically connected to the main controller respectively.
[0087] The background control software (such as APP or control system) of the lactation massage robot can be deployed on the background server (with HIS system deployed at the same time), and the communication link between it and the background server can be debugged by the administrator. The nurse terminal can be a nursing terminal such as PDA, which can log in to the background to view data and send nursing instructions or control parameters to the lactation massage robot through the background. Specific instructions can be set by the administrator, such as massage parameters, cleaning instructions, etc.
[0088] The low-temperature storage unit can refer to existing low-temperature storage technology, such as an intelligent low-temperature storage box, which can be deployed inside the robot to store milk. A window is provided on the lactation massage robot, allowing the mother to take milk or store milk. During the storage operation, the lactation massage robot can perform facial recognition on the mother through its own camera (the HIS system pre-stores the mother's face), and the system performs facial recognition. If the recognition is successful, the low-temperature storage unit is opened to perform the storage operation. Specifically, it can be understood in combination with existing low-temperature storage equipment (such as the low-temperature storage technology disclosed in patents such as CN109720763A, CN209684561U, and CN220164460U).
[0089] The operating system (intelligent system, the robot's operating system software) on the lactation massage robot in this solution can be selected and installed by the user. The user can select the corresponding system software by himself, and this solution does not limit it.
[0090] The user can interact with the backend server through the operating system of the lactation massage robot, for example, he can read the basic information of the parturient in the HIS system, or send corresponding requests to the backend server, or other control instructions.
[0091] The lactation massage robot is also equipped with a touch screen, which is convenient for nurses or mothers to control or input corresponding instructions or parameters to control the robot's movements.
[0092] The robot has its own mechanical arm, with an electric breast pump installed at the end. Under the control of the system, the mechanical arm of the massage robot can be positioned and moved to the chest of the parturient (the positioning movement trajectory is pre-set to avoid collision and injury), and the system controls the end of the mechanical arm to move along the preset trajectory to simulate the lactation massage action (mainly to achieve back and forth massage operation in space).
[0093] Because the breast pump is in close contact with the patient's breast during use, the breast pump can also simulate the massage and lactation of the mother's breast while simulating the lactation massage movement at the end of the robotic arm, and can also be controlled to perform milk extraction operations.
[0094] If milk storage is required, the mother can issue voice control or corresponding control instructions through the touch screen to open the pipeline of the low-temperature storage unit and store the milk in the breast pump in the low-temperature storage unit.
[0095] These pipeline connections as well as the valves, switches, etc. installed on the pipelines can be set according to needs.
[0096] The temperature control module, under the control of the main controller, can provide a corresponding low-temperature environment for the low-temperature storage unit. The specific low-temperature control parameters can be set in advance, or the nurses, mothers, etc. can input the corresponding low-temperature control parameters to the main controller through the touch screen.
[0097] In addition to the above functions, the present invention also has the following functions.
[0098] As an optional embodiment of the present application, optionally, the low-temperature storage unit comprises a plurality of milk storage bags;
[0099] The milk storage bag is connected to the electric breast pump through a pipeline, and a solenoid valve is provided on the pipeline, and the solenoid valve is used to open the corresponding pipeline under the control of the main controller to allow milk to flow into the corresponding milk storage bag;
[0100] The solenoid valve is electrically connected to the main controller.
[0101] As an optional embodiment of the present application, optionally, the lactation massage robot further includes:
[0102] A cleaning component, used for providing cleaning services for the milk storage bag and the electric breast pump;
[0103] The cleaning component is electrically connected to the main controller.
[0104] Several milk storage bags can be set in the low-temperature storage unit. Each milk storage bag is controlled by a solenoid valve and connected to the electric breast pump through a corresponding pipeline. Specifically, one end of the pipeline is connected to the milk storage bag through a solenoid valve, and the other end is fixed to the end of the robotic arm. When in use, the electric breast pump can be installed at the end of the robotic arm, and the pipeline is connected to the electric breast pump. The solenoid valve is controlled by the main controller. When milk needs to be stored, the main controller controls the solenoid valve to open and store the sucked milk in the corresponding milk storage bag. The milk storage bag is detachably connected, which is convenient for the mother to take it out from the window.
[0105] When storing milk, the milk storage bag can be placed separately in the low-temperature storage unit without connecting it to the pipeline. Whether to use the pipeline for milk extraction can be chosen according to current needs.
[0106] In this document, a cleaning component is provided to clean the milk storage bag or the electric breast pump. The cleaning component generally consists of a water pump, a cleaning nozzle, and a switch, and the water pump is connected to the water channel outside the robot. The cleaning component can be a mechanical component, and the user can manually operate the electric breast pump and the low-temperature storage unit to clean it. It can also be an electric component, such as an electronic water pump, which is controlled by a main controller. The water outlet of the cleaning component is connected to the electric breast pump or the low-temperature storage unit, and the electric breast pump or the low-temperature storage unit can be cleaned under one-button start. As for the specific drainage pipeline and drainage port, the present invention does not limit its setting position on the robot and the drainage pipeline structure.
[0107] like Figure 4 As shown, as an optional embodiment of the present application, optionally, the lactation massage robot further includes:
[0108] An ultrasound device, used for performing a breast scan, collecting corresponding breast scan ultrasound data and sending it to the processor system of the massage robot through the main controller, wherein the processor system generates a corresponding breast intra-structure image according to the breast scan ultrasound data and sends it to the CNN evaluation module through the main controller;
[0109] The CNN evaluation module is used to use a preset breast abnormality evaluation model to intelligently identify the breast internal structure image and determine whether there is abnormality in the breast or milk duct:
[0110] If it occurs, a corresponding alarm signal is generated and fed back to the main controller;
[0111] If it does not appear, it is abandoned;
[0112] The ultrasonic device and the CNN evaluation module are electrically connected to the main controller respectively.
[0113] As an optional embodiment of the present application, optionally, the method for generating the breast abnormality assessment model is:
[0114] Collect a number of breast structure images showing abnormalities of breast glands or milk ducts as training data sets;
[0115] Importing the training data set into a preset CNN model, and using a convolutional neural network to learn and train abnormal breast or milk duct image features in the training data set;
[0116] After the training is completed, the breast abnormality assessment model is generated;
[0117] The breast abnormality assessment model is clinically verified and optimized, and put into clinical application after passing the test.
[0118] Combination Figure 4As shown, parturients are prone to abnormalities in the mammary ducts, which can lead to blockages. When abnormal lactation occurs, the breasts need to be massaged to relieve breast pain and increase milk production. Therefore, in the case of abnormalities in the mammary glands or milk ducts, intelligent image recognition can be used to identify abnormal image features, and the system can determine whether parturients have abnormalities in the mammary glands or milk ducts.
[0119] Therefore, this solution also sets up a CNN evaluation module on the robot, CNN is a convolutional neural network model.
[0120] This solution collects breast ultrasound images (B-ultrasound images) of abnormal breasts or milk duct blockage as training data sets, and extracts breast or milk duct image features from abnormal images through convolutional neural networks, and trains and learns to enable the model to identify abnormal breast image features or abnormal milk duct image features. The training generates a breast abnormality prediction model, and the breast abnormality prediction model is clinically evaluated and optimized, and put into clinical application after passing the test.
[0121] In this solution, the trained model is constructed as a CNN evaluation module. Based on the trained breast abnormality prediction model, the CNN evaluation module can perform feature recognition on the breast ultrasound image of the parturient to determine whether there is an abnormal mammary gland or milk duct abnormality. If so, a corresponding alarm signal is issued. The system immediately reports the alarm signal to the nurse to alert the medical staff.
[0122] During model training, normal breast or milk duct images can also be put into the CNN model for retraining, so that the model can recognize the image features of normal breasts and milk ducts. Specific breast ultrasound images are collected by the background, and image preprocessing is provided. The clinical ultrasound images of breasts or milk ducts are divided or the corresponding breast or milk duct ultrasound images are independently constructed. Preprocessing steps can be completed by the background administrator.
[0123] For the clinical verification and optimization of the model, the background can be used to verify and optimize it in the clinic to complete the corresponding model verification, such as using sensitivity value or AUC value, etc. Therefore, in this solution, the robot is equipped with an ultrasound device and a CNN evaluation module, which can cooperate with the main controller and the processor system to complete the abnormal evaluation of breast patency of parturients.
[0124] The training of the convolutional neural network model will not be described in detail in this solution.
[0125] As an optional implementation scheme of the present application, optionally, the main controller is also used for:
[0126] sending the alarm signal to a processor system of the massage robot;
[0127] The processor system is also configured to:
[0128] In response to the alarm signal, a preset action instruction of the robot arm is generated and sent to the main controller;
[0129] The main controller is also used for:
[0130] The preset action instruction is executed to control the mechanical arm to drive the electric breast pump thereon to move according to the preset trajectory to perform positioning massage and milk pumping services.
[0131] If the CNN evaluation module identifies that the parturient has an abnormal condition, the main controller will send the abnormal condition to the processor system, informing the system that the parturient needs to perform a lactation massage. At this time, the processor system responds to the alarm signal and generates a motion command for the robotic arm. The main controller controls the massage robot to move and position (preset height and height) and extend the end of the robotic arm toward the parturient. After the parturient confirms the command through voice or through the touch screen, the main controller controls the robotic arm to move according to the preset trajectory to drive the electric breast pump to position the breasts of the parturient for massage and milk extraction.
[0132] During the specific action process, the mother or nurse can also provide assistance, for example, by issuing corresponding control instructions through voice or touch screen, which will be processed and responded by the massage robot's system. For example, voice interaction can be used to control the massage speed and the start of breastfeeding, etc.
[0133] As an optional implementation scheme of the present application, optionally, the processor system is also used for:
[0134] Identifying and marking the breast contour in the breast intrastructural image;
[0135] Comparing the breast contour with a preset contour image, and calculating a similarity value between the breast contour and the preset contour image based on the similarity;
[0136] estimating the amount of milk production of the mammary gland according to the similarity value;
[0137] sending the estimated lactation amount to the touch screen via the main controller;
[0138] The touch screen is also used for:
[0139] The estimated amount of lactation for the mother is displayed.
[0140] The solution can also be implemented by a processor system to perform breast contour recognition on the ultrasound scanned breast image, and to evaluate the possible milk production of the lactating mother by the size of the breast contour.
[0141] Because the size of different breast contours symbolizes the corresponding amount of milk production, this solution can identify the breast contour and the corresponding milk volume of the mother through the system's recognition and marking of the breast contour.
[0142] The specific contour recognition and marking algorithm (Sobel, Canny) can be selected by the user. In this solution, the amount of milk production corresponding to a breast contour can be pre-set in the system. The similarity principle is subsequently used to evaluate and calculate the amount of milk production of the parturient. After the breast contour of the parturient is identified, the breast contour of the parturient is compared with the preset contour image, and the contour similarity value between the breasts is calculated. The similarity value is multiplied with the preset milk production to estimate the milk production of the parturient (milk production estimate). After the lactation estimate is calculated, it is sent to the touch screen for display.
[0143] Therefore, mothers can estimate the amount of milk that can be secreted by the breasts this time to determine whether to feed with milk powder.
[0144] The system can also write the estimated lactation amount into the HIS system, compare and analyze it with the parameters in the HIS system, and execute the next step of operation.
[0145] The cold or hot compress components can also be replaced at the end of the robotic arm (the components can be replaced by corresponding group settings, for example, the robotic hand at the end of the robotic arm grasps a cold compress component such as a semiconductor refrigeration module or a refrigeration sheet), which can provide hot or cold compress care to the mother. The cold or hot compress components can be implemented by physical cooling or heating, or by using a temperature control component. For example, a low-temperature stored nipple patch, or a nipple patch component controlled by a temperature control module, can be placed and detachably installed at the end of the robotic arm for application care.
[0146] The specific application method of the present invention is as follows:
[0147] 1. The lactation massage robot is equipped with an intelligent system, which obtains maternal age, gravidity and parity, delivery time, pregnancy disease status, newborn weight, Apgar score, urination and defecation, and breastfeeding status from the His system.
[0148] 2. The nurse selects the pregnant woman and clicks the "Breast Assessment" button on the smart system. The robot then goes to the pregnant woman's bed to carry out the assessment.
[0149] 3. The robot can interact with the mother. After scanning the mother's breasts, it generates image data and combines it with His data to analyze whether the mother's milk production meets the newborn's feeding needs, helping the mother complete breast massage.
[0150] 4. If the mother has breast pain and fever, accompanied by breast lumps, the robot can apply ice to the breasts to help clear the milk ducts, empty the breasts, relieve pain and fever, and eliminate breast lumps caused by milk accumulation.
[0151] 5. If the mother's milk production is insufficient, the robot will apply hot compresses to the breasts and massage acupoints to promote breast milk secretion and increase milk production.
[0152] 8. The robot’s milk storage area is a refrigerated area with a self-cleaning function.
[0153] 9. The robot has self-cleaning function and can adjust the temperature, cold compress, hot compress and normal temperature.
[0154] 10. The robot estimates the amount of milk produced by the mother on the day by scanning and massaging, combined with various image data. The robot obtains the newborn's weight, number of urination and defecation, jaundice value, and blood sugar value on the day through the HIS system, analyzes whether the mother's milk production on the day meets the newborn's breastfeeding needs, and guides the nurse whether additional formula milk is needed for the newborn.
[0155] Please implement it in combination with the present invention.
[0156] Obviously, those skilled in the art should understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.
[0157] Example 2
[0158] like Figure 5 As shown, based on the implementation principle of Example 1, the present application, on the other hand, proposes a lactation massage system, comprising:
[0159] A lactation massage robot guided by convolutional neural network;
[0160] The nurse terminal is used by nurses to log in to the backend server, select and view the corresponding maternal data information;
[0161] A backend server is used to interactively control the nurse terminal and the lactation massage robot, and record the admission information of the parturient through the HIS system;
[0162] The nurse terminal and the lactation massage robot are respectively connected to the backend server for communication.
[0163] As an optional embodiment of the present application, optionally, the lactation massage robot is also used for:
[0164] Read the basic information of the parturient recorded in the HIS system, and analyze whether there are any preset abnormal conditions in the basic information of the parturient:
[0165] If it occurs, the exception is handed over to the processor system for handling;
[0166] Otherwise give up.
[0167] Please refer to the description of Example 1 for a detailed understanding of the system interaction, which will not be repeated in this example.
[0168] The modules or steps of the present invention described above can be implemented by a general-purpose computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by a program code executable by a computing system, so that they can be stored in a storage system and executed by the computing system, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
[0169] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.
Claims
1. A lactation massage robot guided by a convolutional neural network, constructed based on a massage robot, the massage robot comprises a processor system and a mechanical arm, characterized in that: The lactation massage robot comprises: Communication system, used to provide communication services for control and communication interaction with the host computer; Main controller, used to implement logic control; An electric breast pump, driven by the mechanical arm, for providing positioning massage and milk pumping services in a preset trajectory; Low temperature storage unit for storing milk at low temperature; A temperature control module, used to provide a temperature control environment for the low-temperature storage unit; A touch screen, used for the user to input various types of control parameters and display corresponding robot service data; The electric breast pump is arranged at the end of the mechanical arm of the massage robot and is connected to the low-temperature storage unit through a pipeline; The communication system and the main controller are electrically connected to the processor system of the massage robot respectively; The electric breast pump, temperature control module and touch screen are electrically connected to the main controller respectively.
2. The lactation-promoting massage robot based on convolutional neural network guidance according to claim 1 is characterized in that: The low-temperature storage unit comprises a plurality of milk storage bags; The milk storage bag is connected to the electric breast pump through a pipeline, and a solenoid valve is provided on the pipeline, and the solenoid valve is used to open the corresponding pipeline under the control of the main controller to allow milk to flow into the corresponding milk storage bag; The solenoid valve is electrically connected to the main controller.
3. The lactation-promoting massage robot based on convolutional neural network guidance according to claim 1, characterized in that: The lactation massage robot also includes: A cleaning component, used for providing cleaning services for the milk storage bag and the electric breast pump; The cleaning component is electrically connected to the main controller.
4. The lactation-promoting massage robot based on convolutional neural network guidance according to claim 1, characterized in that: The lactation massage robot also includes: An ultrasound device, used for performing a breast scan, collecting corresponding breast scan ultrasound data and sending it to the processor system of the massage robot through the main controller, wherein the processor system generates a corresponding breast intra-structure image according to the breast scan ultrasound data and sends it to the CNN evaluation module through the main controller; The CNN evaluation module is used to use a preset breast abnormality evaluation model to intelligently identify the breast internal structure image and determine whether there is abnormality in the breast or milk duct: If it occurs, a corresponding alarm signal is generated and fed back to the main controller; If it does not appear, it is abandoned; The ultrasonic device and the CNN evaluation module are electrically connected to the main controller respectively.
5. The lactation-promoting massage robot based on convolutional neural network guidance according to claim 4 is characterized in that: The generation method of the breast abnormality assessment model: Collect a number of breast structure images showing abnormalities of breast glands or milk ducts as training data sets; Importing the training data set into a preset CNN model, and using a convolutional neural network to learn and train abnormal breast or milk duct image features in the training data set; After the training is completed, the breast abnormality assessment model is generated; The breast abnormality assessment model is clinically verified and optimized, and put into clinical application after passing the test.
6. The lactation-promoting massage robot based on convolutional neural network guidance according to claim 4 is characterized in that: The main controller is also used for: sending the alarm signal to a processor system of the massage robot; The processor system is also configured to: In response to the alarm signal, a preset action instruction of the robot arm is generated and sent to the main controller; The main controller is also used for: The preset action instruction is executed to control the mechanical arm to drive the electric breast pump thereon to move according to the preset trajectory to perform positioning massage and milk pumping services.
7. The lactation-promoting massage robot based on convolutional neural network guidance according to claim 4 is characterized in that: The processor system is also configured to: Identifying and marking the breast contour in the breast intrastructural image; Comparing the breast contour with a preset contour image, and calculating a similarity value between the breast contour and the preset contour image based on the similarity; estimating the amount of milk production of the mammary gland according to the similarity value; sending the estimated lactation amount to the touch screen via the main controller; The touch screen is also used for: The estimated amount of lactation for the mother is displayed.
8. Lactation massage system, characterized in that: include: The lactation massage robot based on convolutional neural network guidance according to any one of claims 1 to 7; The nurse terminal is used by nurses to log in to the backend server, select and view the corresponding maternal data information; A backend server is used to interactively control the nurse terminal and the lactation massage robot, and record the admission information of the parturient through the HIS system; The nurse terminal and the lactation massage robot are respectively connected to the backend server for communication.
9. The lactation-promoting massage system according to claim 8, characterized in that: The lactation massage robot is also used for: Read the basic information of the parturient recorded in the HIS system, and analyze whether there are any preset abnormal conditions in the basic information of the parturient: If it occurs, the exception is handed over to the processor system for handling; Otherwise give up.
Citation Information
Patent Citations
Computer breast scanning automatic machine positioning system
CN107981888A
Multifunctional detection and massage nursing system and nursing method for breasts
CN114098819A
Breast milk storage and heating and feeding bottle cleaning and disinfecting integrated system
CN115644705A
Breast massage device, control method, breast pump and storage medium
CN117731948A
Milk storage ice bag
CN214609212U
