Database-based intelligent temperature control and proportioning milk brewing method and milk brewing device

Abstract

The invention discloses a milk brewing method and a milk brewing device based on intelligent temperature control and proportioning of a database. The method is applied to a control module of the milk brewing device and comprises the steps that information of a to-be-fed infant is acquired; standard nutrition parameters corresponding to the age parameters are obtained from a pre-constructed database; establishing a dynamic matching model; inputting the physical parameters and the feeding record data into a dynamic matching model, and outputting feeding matching information; the breast milk processing channel and the milk powder processing channel are controlled to work according to the milk feeding proportion information, wherein the breast milk processing channel executes quantitative extraction, temperature adjustment and sterile conveying of refrigerated breast milk, and the milk powder processing channel executes mixing, stirring and sterilization conveying of quantitative milk powder and warm water; generating a safe temperature range according to the age parameter and the physique parameter; the breast milk heating temperature of the breast milk processing channel and the milk powder brewing temperature of the milk powder processing channel are adjusted to be within the safe temperature range according to the water temperature control module, and the operation of feeding the to-be-fed infant is completed.

Description

Technical Field

[0001] The present application relates to the technical field of temperature control, and in particular to a milk making method and a milk making device with intelligent temperature control and proportioning based on a database. Background Art

[0002] In the field of infant feeding, milk makers are widely used in families and medical institutions as a convenient feeding tool. Traditional milk makers mainly mix milk powder with water manually or in a simple automated manner to provide the nutrition required by infants. However, the milk makers in the prior art have some significant shortcomings, which limit their application effect in personalized feeding.

[0003] First, existing milk preparation devices usually lack consideration for individual differences of infants. Infants of different ages and physiques have significantly different nutritional needs. Traditional milk preparation devices often use fixed formulas or simple ratio settings, and cannot dynamically adjust the feeding ratio according to the specific situation of the infant, resulting in unsatisfactory feeding results. This one-size-fits-all feeding method may not meet the personalized nutritional needs of infants and affect their healthy growth.

[0004] Secondly, existing milk preparation devices also have deficiencies in temperature control. Babies are sensitive to the temperature of milk, and overheated or overcooled milk may cause discomfort to their oral and digestive systems. However, traditional milk preparation devices usually use fixed temperature settings and fail to intelligently adjust the temperature of the milk according to the baby's age, physique and other factors, which poses certain feeding risks. In addition, inaccurate temperature control may cause temperature fluctuations in the milk during delivery, further affecting the comfort and safety of feeding.

[0005] In addition, existing milk preparation devices also have limitations in terms of automated processing. Traditional devices usually require manual intervention, such as manually adding milk powder and water, adjusting the temperature, etc. This manual operation not only increases the complexity of feeding, but may also cause hygiene problems and affect the aseptic delivery of milk. At the same time, errors in manual operation may also affect the accuracy and consistency of milk feeding, making it difficult to meet the needs of modern families for intelligent and automated feeding tools.

[0006] Therefore, there is an urgent need for a milk making method and a milk making device to solve at least one of the above technical problems. Summary of the invention

[0007] The present application provides a database-based intelligent temperature control and proportioning milk making method and milk making device, which aims to solve the limitations of existing milk making devices in terms of automated processing. Traditional devices usually require manual intervention, such as manually adding milk powder and water, adjusting the temperature, etc. This manual operation not only increases the complexity of feeding, but may also cause hygiene problems and affect the aseptic delivery of milk. At the same time, errors in manual operation may also affect the accuracy and consistency of milk feeding, making it difficult to meet the needs of modern families for intelligent and automated feeding tools.

[0008] In a first aspect, the present application provides a database-based intelligent temperature control and proportioning method for preparing milk, which is applied to a control module of a milk maker, wherein the milk maker also includes a breast milk processing channel, a milk powder processing channel and a water temperature control module; the method includes:

[0009] Acquiring information about the baby to be fed; the baby information at least includes age parameters, physical parameters and feeding record data;

[0010] Obtaining standard nutritional parameters corresponding to the age parameters from a pre-built database;

[0011] Establish a dynamic proportioning model based on standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters;

[0012] Inputting the physical parameters and feeding record data into the dynamic ratio model, and outputting feeding ratio information; the feeding ratio information includes the number of breastfeeding times, the number of times milk powder is prepared, the single feeding amount and the feeding time interval;

[0013] The breast milk processing channel and the milk powder processing channel are controlled to work according to the feeding ratio information: the breast milk processing channel performs quantitative extraction, temperature adjustment and aseptic transportation of refrigerated breast milk, and the milk powder processing channel performs mixing, stirring and sterilization transportation of quantitative milk powder and warm water;

[0014] Generate a safe temperature range according to the age parameter and the physical parameter;

[0015] According to the water temperature control module, the breast milk heating temperature of the breast milk processing channel and the milk powder brewing temperature of the milk powder processing channel are respectively adjusted within the safe temperature range to complete the feeding operation for the baby to be fed.

[0016] In a second aspect, the present application provides a milk maker, which comprises: a control module, a breast milk processing channel, a milk powder processing channel and a water temperature control module: the control module comprises a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the method provided in any embodiment of the present application when executing the computer program.

[0017] The present application discloses a method and a milk making device for intelligent temperature control and proportioning based on a database. The method comprises: first obtaining basic information of the infant to be fed, including age parameters, physical parameters (such as weight, allergy history, etc.) and feeding record data (such as feeding times, feeding amount and feeding time interval, etc.). Through the pre-built database, the system obtains standard nutritional parameters corresponding to the infant's age parameters to provide basic data support for subsequent proportioning. A dynamic proportioning model is established based on standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters. The infant's physical parameters and feeding record data are input into the model to output personalized feeding proportioning information, including the number of breastfeeding times, the number of milk powder brewing times, the single feeding amount and the feeding time interval. The breast milk processing channel is used to perform quantitative extraction, temperature regulation and aseptic transportation of refrigerated breast milk to ensure the safety and hygiene of breastfeeding. The milk powder processing channel is used to perform mixing, stirring and sterilization transportation of quantitative milk powder and warm water to ensure the accuracy and asepticity of milk powder brewing. A safe temperature range suitable for the infant is generated according to the infant's age parameters and physical parameters. The water temperature control module adjusts the heating temperature of breast milk in the breast milk processing channel and the milk powder brewing temperature in the milk powder processing channel to ensure that the temperature is within a safe range to avoid burns or discomfort caused by hot or cold. Based on the above ratio information and temperature adjustment results, the feeding operation for the baby is completed, realizing full automation from ratio to feeding.

[0018] The provided method has at least the following beneficial effects:

[0019] 1. Improve the accuracy and consistency of feeding. Through the dynamic ratio model and database support, the system can generate accurate feeding ratio information according to the individual needs of the baby, reduce manual operation errors, and ensure the consistency of feeding amount and feeding time.

[0020] 2. Improve the intelligence and automation level of feeding: This method realizes the full automation from infant information acquisition, ratio calculation, temperature adjustment to feeding operation, significantly reduces the need for manual intervention, and meets the needs of modern families for intelligent feeding tools.

[0021] 3. Ensure the safety and hygiene of feeding: Both the breast milk processing channel and the milk powder processing channel adopt aseptic and sterilized conveying technology, which effectively avoids the hygienic problems that may be caused by traditional manual operations and ensures the aseptic delivery of milk. At the same time, through the generation and temperature control of the safe temperature range, it avoids discomfort or harm to the baby caused by too high or too low temperature.

[0022] 4. Personalized nutritional ratio: The system dynamically adjusts the feeding ratio information according to the baby's age, physique and feeding record data to meet the nutritional needs of different babies, especially for babies with special physiques or feeding record requirements, and can provide a more personalized feeding plan.

[0023] 5. Improve feeding efficiency and user experience: Through automated operations, the complexity of the feeding process is significantly reduced, reducing the burden on parents, especially when feeding at night or when frequent feeding is required, and providing more convenient and efficient services.

[0024] In summary, this method solves the limitations of traditional milk preparation devices in automated processing and personalized feeding through intelligent and automated technical means, significantly improves the accuracy, safety and user experience of feeding, and has important application value and market prospects.

[0025] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0027] Figure 1 is a schematic block diagram of the structure of a milk maker provided in one embodiment of the present application;

[0028] Figure 2 It is a schematic flow chart of the steps of a method for preparing milk with intelligent temperature control and proportioning based on a database provided in one embodiment of the present application;

[0029] Figure 3 It is a schematic block diagram of the structure of a control module provided in one embodiment of the present application.

[0030] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0032] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0033] It should be understood that, in order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", etc. are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not necessarily limit the difference.

[0034] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0035] It should also be understood that the term “and / or” used in the specification and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0036] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0037] In the field of infant feeding, milk makers are widely used in families and medical institutions as a convenient feeding tool. Traditional milk makers mainly mix milk powder with water manually or in a simple automated manner to provide the nutrition required by infants. However, the milk makers in the prior art have some significant shortcomings, which limit their application effect in personalized feeding.

[0038] First, existing milk preparation devices usually lack consideration for individual differences of infants. Infants of different ages and physiques have significantly different nutritional needs. Traditional milk preparation devices often use fixed formulas or simple ratio settings, and cannot dynamically adjust the feeding ratio according to the specific situation of the infant, resulting in unsatisfactory feeding results. This one-size-fits-all feeding method may not meet the personalized nutritional needs of infants and affect their healthy growth.

[0039] Secondly, existing milk preparation devices also have deficiencies in temperature control. Babies are sensitive to the temperature of milk, and overheated or overcooled milk may cause discomfort to their oral and digestive systems. However, traditional milk preparation devices usually use fixed temperature settings and fail to intelligently adjust the temperature of the milk according to the baby's age, physique and other factors, which poses certain feeding risks. In addition, inaccurate temperature control may cause temperature fluctuations in the milk during delivery, further affecting the comfort and safety of feeding.

[0040] In addition, existing milk preparation devices also have limitations in terms of automated processing. Traditional devices usually require manual intervention, such as manually adding milk powder and water, adjusting the temperature, etc. This manual operation not only increases the complexity of feeding, but may also cause hygiene problems and affect the aseptic delivery of milk. At the same time, errors in manual operation may also affect the accuracy and consistency of milk feeding, making it difficult to meet the needs of modern families for intelligent and automated feeding tools.

[0041] Therefore, there is an urgent need for a milk making method and a milk making device to solve at least one of the above technical problems.

[0042] To solve the above problems, please refer to Figure 1 The application provides a milk maker, which includes: a control module, a breast milk processing channel, a milk powder processing channel and a water temperature control module: the control module includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the method provided in any embodiment of the application when executing the computer program.

[0043] Specifically, the present application provides a database-based intelligent temperature control and proportioning milk maker, the core technical contents of which include the following aspects:

[0044] 1. Control module: The core control module of the milk maker consists of a memory and a processor, which is used to store and execute computer programs. The memory stores pre-built databases, dynamic ratio models, and algorithm programs related to infant feeding. The processor is responsible for calling these programs to obtain infant information, calculate ratios, adjust temperature, and control breast milk processing channels and milk powder processing channels.

[0045] 2. Breast milk processing channel: The breast milk processing channel is mainly used for quantitative extraction, temperature regulation and aseptic transportation of refrigerated breast milk. Specific functions include: Quantitative extraction: Accurately extract the specified amount of breast milk according to the feeding ratio information output by the dynamic ratio model. Temperature regulation: Through the water temperature control module, the breast milk is heated to the safe temperature range of the baby to ensure the appropriate temperature of the breast milk. Aseptic transportation: Aseptic transportation technology is used to avoid contamination of breast milk during transportation and ensure the hygiene of breast milk.

[0046] 3. Milk powder processing channel: The milk powder processing channel is mainly used for mixing and sterilizing the quantitative milk powder and warm water. Specific functions include: quantitative milk powder addition: according to the feeding ratio information, accurately add the specified amount of milk powder. Warm water mixing and stirring: Mix the quantitative milk powder with warm water, and mix them thoroughly through the stirring device to ensure that the milk powder is evenly dissolved. Sterilization and transportation: through the sterilization and transportation technology, ensure that the milk water after the milk powder is brewed is sterile to avoid bacterial contamination.

[0047] 4. Water temperature control module: The water temperature control module is used to adjust the temperature of the breast milk processing channel and the milk powder processing channel. Specific functions include: safe temperature range generation: generate a safe temperature range suitable for the baby according to the age parameters and physical parameters of the baby. Temperature adjustment: adjust the breast milk heating temperature of the breast milk processing channel and the milk powder brewing temperature of the milk powder processing channel respectively to ensure that the temperature is within the safe range to avoid scalding or cold and hot discomfort. The specific implementation of the milk maker includes the following steps: baby information acquisition: the system obtains the basic information of the baby to be fed through input devices (such as touch screens, sensors, etc.), including age parameters, physical parameters (such as weight, allergy history, etc.) and feeding record data (such as feeding times, feeding amounts and feeding time intervals, etc.). Standard nutritional parameter acquisition: the system obtains standard nutritional parameters corresponding to the baby's age parameters from the pre-built database to provide basic data support for subsequent ratio calculations. Dynamic ratio model establishment and application: the system establishes a dynamic ratio model based on standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters. The infant's physical parameters and feeding record data are input into the model, and personalized feeding ratio information is output, including the number of breastfeeding times, the number of times milk powder is prepared, the amount of single feeding, and the feeding interval. Breast milk processing channel control: According to the feeding ratio information, the breast milk processing channel performs the following operations: quantitative extraction of refrigerated breast milk. Adjust the breast milk temperature to a safe temperature range through the water temperature control module. Deliver the breast milk to the feeding device through aseptic delivery technology. Milk powder processing channel control: According to the feeding ratio information, the milk powder processing channel performs the following operations: quantitative addition of milk powder. Mix and stir with warm water to ensure that the milk powder is evenly dissolved. Deliver the milk after milk powder preparation to the feeding device through sterilization delivery technology. Safe temperature range generation and temperature control adjustment: Generate a safe temperature range suitable for the infant based on the infant's age parameters and physical parameters. Adjust the breast milk heating temperature of the breast milk processing channel and the milk powder preparation temperature of the milk powder processing channel through the water temperature control module to ensure that the temperature is within the safe range. The feeding operation is completed: according to the above-mentioned ratio information and temperature adjustment results, the feeding operation of the baby is completed, realizing the full automation from ratio to feeding. Through the dynamic ratio model and database support, the system can generate accurate feeding ratio information according to the individual needs of the baby, reduce manual operation errors, and ensure the consistency of feeding amount and feeding time. The milk maker realizes the full automation from baby information acquisition, ratio calculation, temperature adjustment to feeding operation, significantly reducing the need for manual intervention and meeting the needs of modern families for intelligent feeding tools. Both the breast milk processing channel and the milk powder processing channel adopt aseptic conveying and sterilization conveying technology, which effectively avoids the hygiene problems that may be caused by traditional manual operation and ensures the aseptic delivery of milk. At the same time, through the generation and temperature control of the safe temperature range, the discomfort or harm to the baby caused by too high or too low temperature is avoided.According to the baby's age, physique and feeding record data, the feeding ratio information is dynamically adjusted to meet the nutritional needs of different babies, especially for babies with special physiques or feeding record requirements, a more personalized feeding plan can be provided. Through automated operation, the complexity of the feeding process is significantly reduced, and the burden on parents is reduced, especially in the case of night feeding or frequent feeding, which can provide more convenient and efficient services.

[0048] This milk maker solves the limitations of traditional milk maker devices in automated processing and personalized feeding through intelligent and automated technical means, significantly improving the accuracy, safety and user experience of feeding, and has important application value and market prospects.

[0049] In some embodiments, the milk maker provided by the present application includes: a program part for regulating the machine and retrieving the database for analysis and calculation and issuing instructions to the machine, a breast milk part, a milk powder part and a milk utensil disinfection device respectively arranged at different positions of the machine, a pure water part that provides pure water and high-temperature water vapor for the whole machine, and a data transmission part that connects the machine to a mobile device or a cloud and transmits signals to various parts of the machine. While considering intelligence, safety is taken into account, which greatly facilitates parents to feed their babies. It is characterized in that the program part focuses on a milk-water recommended ratio program tailored for various types of infants of different ages. The program can analyze and calculate the recommended number of breast milk and milk powder feedings per day, time intervals, breast milk amount and milk powder amount according to different stages of infant development, height and weight, etc. using a database. Then the information is transmitted to the mobile terminal APP, the mobile terminal issues an instruction, and after the data transmission part of the machine receives it, the various parts of the machine work. The breast milk part and the milk powder part of the machine are separately arranged, and two sets of independent pipes are used inside the machine. Avoid mixing breast milk and milk powder to damage the intestines and stomach of children. The pure water part will heat the external water source and can be transported to the milk powder part through the internal pipeline for milk making or to the milk utensil sterilizing device to generate water vapor for high-temperature steam sterilization of milk utensil. The data transmission part is installed inside the machine and supports both Wi-Fi and Bluetooth protocols to facilitate users to manage the milk maker on the mobile APP.

[0050] Furthermore, the milk ratio recommendation program tailored for various types of infants of different age groups first obtains the age and physical parameters of the infant, and then obtains the content of various nutritional parameters of milk powder and the nutritional parameter content of breast milk. Then the total nutritional parameters required for infants of similar physical parameters in the age group are searched through the database. The age of the infant is then judged and selected to substitute the data into the data model of the supplementary feeding method or the substitute feeding method for calculation, and the required grams of milk powder and the amount of breast milk are obtained.

[0051] When using it, the user first enters the baby's age, height, weight and other information on the mobile software APP. After the information is transmitted to the cloud, the database is searched and calculated to obtain the recommended total amount of nutritional parameters required for the baby. Then the user selects the milk powder to be put into the milk maker on the APP, and fills in the breast milk test report. If there is no such report, the system will calculate according to the average nutritional parameter content of breast milk. The APP will transmit this data to the cloud, and the cloud will bring the data into the data model of the supplementary teaching method or the substitute teaching method for calculation, and then return the calculation result to the APP, and then issue instructions to the machine through the APP.

[0052] Furthermore, the data model is a data model close to the optimal solution obtained through a large amount of research based on the medical principles of supplementary teaching and substitute teaching. This type of data is processed by different institutions and individuals and may exist in different forms. Therefore, the data model of the supplementary teaching method and substitute teaching method is any processing method that uses the principles of supplementary teaching or substitute teaching to process data.

[0053] Supplementary feeding and substitute feeding are medical terms for infant feeding. Supplementary feeding: infants under six months old should first eat breast milk, and then supplement with formula milk after breast milk is finished. Breast milk and formula milk should be eaten at the same time in one feeding, but the two should not be placed in the same container and mixed. Substitute feeding: infants over six months old are suitable for weaning. At this stage, formula milk can completely replace breast milk. Feeding one meal of breast milk and one meal of formula milk alternately can achieve the effect of weaning step by step.

[0054] Further, the breast milk part includes a storage area, a contact sensing device, a sealing device, a refrigeration device, a disinfection device, a delivery pipeline, a weight detection device, an electromagnetic flow control device, a heating area, and a milk outlet. The storage area is a box structure, and a contact sensing device is equipped below it, which can accommodate two independent milk storage boxes. Two latex connection ports are also provided below the storage area for connecting with the milk storage boxes. The inlet of the delivery pipeline is a latex connection port of the storage area, which is arranged inside the machine to connect to the heating area and the milk outlet. The sealing device is any sealing device on the market, which provides a closed space for the storage area to avoid the invasion of external bacteria. The disinfection device and the refrigeration device are installed inside the storage area. The disinfection device is an ultraviolet irradiation device, and the device works when the sealing environment of the storage area changes. Provide a safe and reliable environment for the storage area. The refrigeration device uses a refrigeration sheet for refrigeration, and can automatically adjust the temperature according to the quality of breast milk. The weight detection device is installed at the contact point with the milk storage box below the storage area, and a varistor or mechanical device is used to measure the milk volume in the milk storage box, and transmit it to the user's mobile device through the data transmission part. The electromagnetic flow control device is installed in the delivery pipeline to block the delivery channel. When it receives the signal from the data transmission part, the flow valve is opened to cancel the blockage. When the signal gives a given amount of breast milk, the flow valve is closed. The heating area is located above the milk outlet. The breast milk can be heated to a temperature suitable for children to eat by a heating device with adjustable temperature. The milk outlet is set outside the machine to deliver the breast milk in the machine to the milk bottle. A sensor is set below it. It can only discharge milk when it senses that the milk bottle is placed in a given position.

[0055] Furthermore, the milk powder part includes a storage area, a contact sensing device, a sealing device, a disinfection device, a feeding device, a conveying pipeline, a weight detection device, a water flow control device, a mixing area, a milk outlet, and a sealing device. The storage area has a space for installing a powder storage box, and an interface and a contact sensing device connected to the powder storage box are arranged below, and a feeding mechanism is installed below the interface. The feeding mechanism will block the interface of the storage area in normal state, so that the storage area is isolated from the outside world to avoid the invasion of external bacteria. After receiving the signal from the data transmission part, the device starts to connect the powder storage box with the internal pipeline of the machine, and flows into the weight detection device under the action of gravity or a power-assisting mechanism. The weight detection device uses a varistor or a mechanical device to monitor the weight of the outflowing milk powder in real time, and the feeding system is closed when it reaches the given value received by the data transmission part. The inlet of the conveying pipeline is a latex connection port of the storage area, which is arranged inside the machine to connect to the mixing area and the milk outlet. The water flow control device is installed in the pipeline to act as a partition. Its inlet end is connected to the pure water part, and its outlet end is connected to the mixing area. After receiving the signal from the data transmission part, the flow valve is opened. After the signal-given amount of warm water flows out from the pure water part, the flow valve is closed. The disinfection device and the sealing device are installed inside the storage area. The disinfection device is an ultraviolet irradiation device, and the device works when the sealing environment of the storage area changes. Provide a safe and reliable environment for the storage area. The sealing device is any sealing device on the market, which provides a closed space for the storage area to avoid the invasion of external bacteria. The mixing area is located above the milk outlet, and a stirring device and a control valve are installed inside it. When the milk powder and water enter the mixing area, the stirring device starts to move, and the control valve is opened after the stirring is completed. The milk outlet is set outside the machine to transport the breast milk in the machine to the milk bottle. A sensor is set below it. When it senses that the milk bottle is placed in a given position, milk can be discharged.

[0056] Furthermore, the water supply part includes a water inlet device, a water temperature control module, and a delivery pipeline. The water inlet device can be divided into a water purifier connection device and an external pure water device according to whether it is externally connected to a water purifier. The water purifier connection device is any water pipe connection device on the market, and the external pure water device consists of a water pipe storage area, a water pipe, and a connection device. The water pipe storage area is used to store water pipes, which are connected to the machine delivery pipeline. The connection device is provided with a buckle on the outside and a thread on the inside, which can be connected to an external water bottle or water tank, and the external buckle can be connected to the milk maker. The connection device is equipped with a sealing plug, which can be sealed when the water purifier is directly connected to the machine. The water temperature control module is a heating device with adjustable temperature, which can adjust the water temperature of the water supply part to a given value received by the data transmission part and then be used for brewing milk powder or high-temperature disinfection. The delivery pipeline is connected to other pipes inside the machine, and warm water or high-temperature steam can be delivered to the required part.

[0057] The water supply part is the source of water used by the entire machine. It provides the machine with warm water for making milk, hot water for cleaning the entire machine, and high-temperature steam.

[0058] Furthermore, the milk utensil sterilizing device comprises a milk utensil storage area, a hot air drying device, an ultraviolet disinfection device, a delivery pipeline, and a connecting valve. The milk utensil storage area is a box structure, which can be divided into multiple layers by a detachable partition, and milk utensil is placed layer by layer. A high-temperature steam sterilizing device is arranged below it, and a small hole for steam overflow is opened on the box wall, and a plurality of holes are evenly distributed on the partition for passing steam. The delivery pipeline is used to connect with the delivery pipeline of the water supply part to transfer high-temperature steam for sterilization, and allow the steam to overflow through the small holes inside the milk utensil storage area, and sterilize the milk utensil with high-temperature steam. The hot air drying device is arranged at the bottom of the milk utensil storage area and is composed of a fan and a heating element, which can make the milk utensil after high-temperature steam sterilization quickly dry to avoid bacterial growth. The ultraviolet disinfection device is an ultraviolet irradiation device, which can work through the signal received by the data transmission part to provide a safe and reliable environment for the milk utensil storage area. The connecting valve is a one-way valve installed on the delivery pipeline. When the milk utensil storage area is opened and closed normally, the internal pipeline of the machine will not contact the external environment, so as to avoid the invasion of external bacteria.

[0059] Furthermore, the milk storage box and the powder storage box are a structure in which a cover and a box are combined, the top cover can be directly lifted, a sealing strip is arranged between the cover and the box, and a one-way air inlet hole and an exhaust hole with a cock are arranged on the top cover. A connection port and a contact are arranged at the bottom of the box, the connection port is connected to the connection port in the machine for transmitting the stored material, and the contact is used to detect whether it is installed in place.

[0060] When closing the lid of the milk storage box and the powder storage box, open the cock to facilitate the installation of the top cover on the box. After installation, install the cock into the exhaust hole to complete the seal. When discharging, air is taken in from the one-way air inlet to facilitate discharging.

[0061] In actual use, the invention will automatically match the baby's feeding problem within a period of time after the user fills in the data. The design will calculate the required information and complete the brewing by itself, and the user only needs to receive the milk and feed the baby. It greatly reduces the life pressure of parents, improves the happiness index of the family, and protects the safety of the baby's milk drinking.

[0062] See also Figure 2 , Figure 2 The schematic flow chart of a method for preparing milk with intelligent temperature control and proportioning based on a database provided in one embodiment of the present application is shown in FIG. The execution device of the method is a control module of a milk preparing device provided in any embodiment of the present application.

[0063] like Figure 2As shown, the provided method includes steps S101 to S107. The control module may be a handheld terminal, a notebook computer, a wearable device or a robot, etc., for implementing steps S101 to S107 and their corresponding embodiments.

[0064] Step S101. Obtain information of the baby to be fed; the baby information at least includes age parameters, physical parameters and feeding record data.

[0065] Specifically, it is necessary to first collect basic information about the baby to be breastfed, including but not limited to the baby's age, weight, allergy history, feeding records, etc. These data will serve as the basis for subsequent ratio calculations to ensure the personalization and scientific nature of the feeding plan.

[0066] Parents can manually input basic information such as the baby's age and weight through the user interface of the milk maker (such as a touch screen). The sensor equipped in the milk maker can automatically measure the baby's weight to reduce the error of manual input.

[0067] Parents can import their baby's feeding records from other devices (such as mobile phone applications) into the milk maker to ensure data continuity and integrity.

[0068] By collecting individualized information about infants, the system can develop a feeding plan that meets the infant's needs and improve the accuracy of feeding. Automated data collection reduces manual input errors and ensures data accuracy. The method can adjust the feeding plan based on the infant's allergy history to avoid allergic reactions and improve feeding safety.

[0069] Step S102: Obtain standard nutritional parameters corresponding to age parameters from a pre-constructed database.

[0070] Specifically, standard nutritional parameters corresponding to the infant's age are retrieved from a pre-built database. These parameters generally include recommended intakes of protein, fat, carbohydrates, vitamins and minerals, etc., to ensure that the feeding plan meets the infant's nutritional needs.

[0071] The database stores standard nutritional parameters according to the age of the baby (such as 0-3 months, 4-6 months, etc.) for quick retrieval. The corresponding nutritional parameters are automatically matched according to the baby's age parameters, without the need for manual search. The database is regularly updated to ensure that the nutritional parameters are in line with the latest scientific research and medical advice.

[0072] Standard nutritional parameters provide a scientific basis for feeding plans, ensuring that infants receive balanced nutrition. The automatic matching function improves the efficiency of the system and reduces the complexity of manual operations. The regularly updated database ensures the scientificity and timeliness of nutritional parameters and improves the reliability of feeding plans.

[0073] Step S103: Establish a dynamic proportioning model according to standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters.

[0074] Specifically, the dynamic ratio model combines standard nutritional parameters, the nutritional components of breast milk and the nutritional components of formula to calculate the optimal feeding ratio. The model takes into account the nutritional needs of infants, the nutritional supply of breast milk and formula, and ensures that the feeding plan is scientific and personalized.

[0075] Standard nutritional parameters, breast milk nutritional parameters and formula nutritional parameters are integrated into the model for comprehensive analysis. The model uses mathematical algorithms or machine learning methods to calculate the optimal ratio of breast milk and formula to ensure a balanced supply of nutrition. The model can adjust the feeding ratio in real time according to the baby's physical parameters and feeding record data to adapt to the baby's changing needs.

[0076] The dynamic ratio model can adjust the feeding ratio according to the specific situation of the baby and provide a personalized feeding plan. The model ensures that the baby gets balanced nutrition and promotes healthy growth. Through scientific ratio calculation, it reduces the error of manual intervention and improves the accuracy and consistency of feeding.

[0077] Step S104. Input the physical parameters and feeding record data into the dynamic ratio model, and output the feeding ratio information; the feeding ratio information includes the number of breastfeeding times, the number of times milk powder is prepared, the single feeding amount and the feeding time interval.

[0078] Specifically, the baby's physical parameters (such as weight, allergy history) and feeding record data (such as feeding frequency, amount and time interval) are input into the dynamic ratio model. After processing, the model outputs feeding ratio information, including the number of breastfeeding times, the number of times milk powder is prepared, the single feeding amount and the feeding time interval, etc.

[0079] The baby's physical parameters and feeding record data are input into the system through the user interface or sensors. The dynamic matching model analyzes and calculates the input data to generate personalized feeding matching information. The feeding matching information is displayed on the user interface for parents to view and confirm.

[0080] The feeding ratio information is generated according to the specific situation of the baby to meet the personalized needs of the baby. The feeding ratio information provided by the method provides parents with scientific feeding guidance and reduces the blindness of feeding. Automated processing reduces the decision-making burden of parents and improves the efficiency of feeding.

[0081] Step S105. Control the operation of the breast milk processing channel and the milk powder processing channel according to the feeding ratio information: the breast milk processing channel performs quantitative extraction, temperature adjustment and aseptic transportation of refrigerated breast milk, and the milk powder processing channel performs mixing, stirring and sterilization transportation of quantitative milk powder and warm water.

[0082] Specifically, according to the feeding ratio information, the breast milk processing channel and the milk powder processing channel are controlled to ensure that the processing of breast milk and milk powder meets the ratio requirements. The breast milk processing channel is responsible for quantitative extraction of breast milk, temperature adjustment and aseptic delivery, while the milk powder processing channel is responsible for quantitative addition of milk powder, mixing and stirring, and sterilization and delivery.

[0083] According to the feeding ratio information, the method controls the breast milk processing channel to accurately extract the specified amount of breast milk. The water temperature control module heats the breast milk to a suitable temperature to ensure that the temperature is appropriate. The aseptic delivery technology is used to ensure that the breast milk is not contaminated during the delivery process.

[0084] The method controls the milk powder processing channel to accurately add a specified amount of milk powder. Mix the quantitative milk powder with warm water and stir it thoroughly through a stirring device to ensure that the milk powder is evenly dissolved. Through the sterilization conveying technology, the milk water after the milk powder is brewed is ensured to be sterile and avoid bacterial contamination.

[0085] Quantitative extraction and addition ensure the accurate ratio of breast milk and milk powder, and improve the accuracy of feeding. Aseptic and sterilized delivery technology ensures the hygiene of milk and reduces the risk of bacterial contamination. The method automatically controls the processing of breast milk and milk powder, reduces manual intervention, and improves the efficiency and safety of feeding.

[0086] Step S106: Generate a safe temperature range according to age parameters and physical parameters.

[0087] Specifically, an appropriate milk temperature range is generated based on the baby's age and physical parameters. This temperature range takes into account the baby's digestive system development stage and temperature sensitivity, ensuring that the milk temperature is appropriate and avoiding discomfort to the baby caused by overheating or overcooling.

[0088] Methods Obtain the baby's age and physical parameters, such as weight, allergy history, etc. Generate a safe temperature range suitable for the baby through algorithm analysis to ensure that the milk temperature is appropriate. Methods Monitor the milk temperature in real time to ensure that it is within the safe range.

[0089] The generated safe temperature range ensures that the milk temperature is appropriate and improves the comfort of feeding. It prevents overheated or overcooled milk from harming the baby's oral cavity and digestive system, and improves the safety of feeding. The temperature range is generated according to the specific situation of the baby to meet personalized needs.

[0090] Step S107. According to the water temperature control module, the breast milk heating temperature of the breast milk processing channel and the milk powder brewing temperature of the milk powder processing channel are respectively adjusted within a safe temperature range to complete the feeding operation for the baby to be fed.

[0091] Specifically, the water temperature control module adjusts the breast milk heating temperature in the breast milk processing channel and the milk powder brewing temperature in the milk powder processing channel according to the safe temperature range to ensure that the milk temperature is within the appropriate range. The system monitors the temperature in real time through the temperature sensor and adjusts it as needed to complete the feeding operation.

[0092] The water temperature control module adjusts the temperature of breast milk and milk powder according to the safe temperature range to ensure that it is within the appropriate range. The temperature sensor monitors the temperature of the milk in real time to ensure that the temperature is stable within the safe range. After the processing of breast milk and milk powder is completed, the milk is transported to the feeding device to complete the feeding operation.

[0093] Precise temperature regulation and real-time monitoring ensure the stability of milk temperature and avoid the impact of temperature fluctuations on babies. Appropriate milk temperature improves feeding comfort and reduces the crying of babies due to temperature discomfort. The method automatically completes temperature regulation and feeding operations, reducing the burden on parents and improving feeding efficiency.

[0094] In some embodiments, the dynamic proportioning model includes a gradient boosting decision tree model and a convolutional neural network model; the feeding record data includes multiple historical feeding data; the physical parameters and feeding record data are input into the dynamic proportioning model, and the feeding proportioning information is output, including: parsing the physical parameters to obtain the baby's body temperature, heart rate and digestion cycle data; constructing a dynamic mapping relationship between the physical parameters and each historical feeding data; inputting the dynamic mapping relationship into the gradient boosting decision tree model, and the gradient boosting decision tree model outputs the personalized feeding coefficient of the baby to be fed; inputting the personalized feeding coefficient and the standard nutritional parameters into the convolutional neural network model, and outputting the feeding proportioning information.

[0095] The baby's physiological indicators such as body temperature, heart rate and digestion cycle are obtained through sensors or user input. These data reflect the baby's health status and feeding needs. The baby's historical feeding data is extracted from the feeding record, including information such as feeding time, amount, duration, and baby response. These data provide the basis for the model to learn.

[0096] Clean and standardize the collected physical parameters and historical feeding data to ensure data quality. Extract key features from physical parameters, such as temperature fluctuation range, heart rate change trend, and digestion cycle length. Extract features from historical feeding data, such as feeding interval, single feeding amount, and infant crying frequency. Use statistical methods or machine learning algorithms to analyze the association between physical parameters and historical feeding data and build a dynamic mapping relationship. For example, it is found that the feeding amount requirement increases when the body temperature rises, or the feeding interval decreases when the heart rate increases. Use historical feeding data and physical parameters to train a gradient boosting decision tree model. The model improves the accuracy and robustness of predictions by combining multiple decision trees. Input the constructed dynamic mapping relationship into the model, which analyzes the infant's physiological state and feeding history and outputs personalized feeding coefficients. These coefficients may include the ratio of breast milk to formula, feeding amount, and time interval. Combine the personalized feeding coefficients with standard nutritional parameters as input to the convolutional neural network model. Standard nutritional parameters include recommended intakes of protein, fat, carbohydrates, etc. Use historical feeding data and standard nutritional parameters to train the convolutional neural network model. The model captures complex data patterns through multi-layer neural networks and generates detailed feeding ratio information. After model processing, it outputs specific feeding ratio information, such as the number of breastfeeding times, the number of times milk powder is prepared, the amount of single feeding, and the feeding interval. According to the output feeding ratio information, the breast milk processing channel and the milk powder processing channel are controlled to perform quantitative extraction, temperature adjustment, mixing and stirring operations. Sensors are used to monitor the temperature, flow rate and baby's response of milk in real time, and the feeding plan is dynamically adjusted according to feedback information to ensure the comfort and safety of feeding. After feeding is completed, the data of this feeding is recorded, the baby's feeding record is updated, and new data samples are provided for subsequent model training.

[0097] Through the combination of the gradient boosting decision tree model and the convolutional neural network model, personalized feeding ratio information can be generated according to the baby's physical parameters and feeding history to meet the individual needs of the baby. According to the baby's digestive cycle and feeding history, the feeding interval is reasonably arranged to avoid overfeeding or hunger and promote the healthy growth of the baby. Through the scientific ratio of breast milk and milk powder, ensure that the baby gets balanced nutrition, promote digestion and absorption, and reduce feeding-related problems such as flatulence or diarrhea. Monitor the milk temperature in real time to ensure that it is within the safe range to avoid discomfort or harm to the baby caused by overheating or overcooling. Use aseptic and sterilized delivery technology to reduce the risk of bacterial contamination and ensure the safety of infant feeding.

[0098] The method automatically completes the processing, temperature adjustment and feeding of breast milk and formula, reducing the burden on parents and improving the efficiency of feeding. Through intelligent algorithms and automated equipment, it reduces the errors caused by human operation and ensures the accuracy and consistency of feeding.

[0099] By recording the data of each feeding, the dynamic ratio model is continuously optimized to improve the accuracy and effectiveness of the feeding plan. As the baby grows and his physique changes, the feeding plan can be dynamically adjusted to adapt to the baby's changing needs and provide long-term feeding support.

[0100] By combining the gradient boosting decision tree model and the convolutional neural network model, the physical parameters and historical feeding data of the infant are used to construct a dynamic mapping relationship and generate personalized feeding ratio information. This method not only improves the accuracy and safety of feeding, but also significantly improves the feeding efficiency and the health of the infant through automated operation and data-driven optimization. The innovation of the embodiment is to apply the machine learning algorithm to the calculation of the feeding ratio, which provides a scientific basis and technical support for the intelligent temperature control and ratio milk making method.

[0101] In some embodiments, before the physical parameters and feeding record data are input into the dynamic proportioning model, it also includes: detecting the breast milk nutritional parameters corresponding to the breast milk in the breast milk processing channel in real time according to a preset spectral analysis module, the breast milk nutritional parameters at least including fat content and protein concentration; obtaining the milk powder nutritional parameters and milk powder identification information corresponding to the milk powder processing channel; building a milk powder nutritional parameter traceability network, and using blockchain technology to verify the authenticity of the milk powder nutritional parameters according to the milk powder identification information; if the deviation between the breast milk nutritional parameters and the milk powder nutritional parameters and the standard value of the database exceeds the preset deviation, the dynamic proportioning model is self-corrected.

[0102] In the breast milk processing channel, the nutritional parameters of breast milk are detected in real time through the preset spectral analysis module. Spectral analysis technology can quickly and non-destructively measure key indicators such as fat content and protein concentration in breast milk. The detected breast milk nutritional parameters are recorded and stored in real time as the basic data for subsequent feeding ratio calculations.

[0103] The nutritional parameters of milk powder are obtained from the milk powder processing channel, including protein concentration, fat content, carbohydrate content, etc. These parameters are usually provided by milk powder manufacturers or measured by testing equipment.

[0104] The system reads the identification information on the milk powder packaging, such as production batch, product number, production date, etc. This information is used for subsequent traceability verification. Blockchain technology is used to build a traceability network for milk powder nutritional parameters. Through the decentralized and tamper-proof characteristics of blockchain, the system can verify the authenticity of milk powder identification information and ensure the credibility of milk powder nutritional parameters.

[0105] Compare the detected nutritional parameters of breast milk and milk powder with the standard values ​​in the database. The standard value can be an industry recommended value or a reference value for infant nutritional needs. If the deviation of the nutritional parameters of breast milk or milk powder from the standard value exceeds the preset threshold (such as the deviation of fat content exceeds 5%, and the deviation of protein concentration exceeds 10%), the system will trigger the parameter self-correction mechanism of the dynamic matching model. According to the detected deviation, adjust the parameters of the dynamic matching model to ensure the accuracy and reliability of the feeding matching information. For example, if the fat content of breast milk is low, the model will automatically increase the proportion of fat added to the milk powder.

[0106] The tested and verified nutritional parameters of breast milk and formula, together with the baby's physical parameters and feeding record data, serve as the input of the dynamic matching model. Based on the integrated data, the dynamic matching model outputs personalized feeding matching information, such as the ratio of breast milk to formula, feeding amount and feeding time interval.

[0107] Through the spectral analysis module and blockchain technology, the nutritional parameters of breast milk and milk powder can be detected in real time and their authenticity can be verified. This ensures that the data input into the dynamic proportioning model is accurate and reliable.

[0108] Traditional feeding ratio calculations may rely on manual data entry, which is prone to errors. The embodiment significantly reduces human errors through automated detection and verification. Through blockchain technology, the system can verify the authenticity of milk powder identification information and prevent the use of counterfeit and inferior milk powder. This provides a guarantee for infant feeding safety. The transparency and immutability of blockchain technology enhance users' trust in the system's feeding plan, especially in terms of the source and quality of milk powder.

[0109] If the nutritional parameters of breast milk or formula deviate greatly from the standard values, the dynamic ratio model can automatically adjust the parameters and output feeding ratio information that better meets the needs of the baby. This improves the adaptability and robustness of the model. Through real-time detection and self-correction, the feeding plan can be dynamically adjusted according to the actual nutritional parameters of breast milk and formula to better meet the nutritional needs of the baby. With accurate nutritional parameters of breast milk and formula, the system can generate more accurate feeding ratio information to avoid health problems caused by insufficient or excessive nutrition. The self-correction mechanism of the dynamic ratio model can promptly detect and correct deviations in the feeding plan, reducing feeding problems caused by nutritional imbalance, such as flatulence, diarrhea or malnutrition.

[0110] Through real-time detection and verification, the parameters of the dynamic ratio model are continuously optimized to improve the scientificity and effectiveness of the feeding plan. As the baby grows and the nutritional needs change, the feeding plan can be dynamically adjusted through real-time detection and self-correction to provide long-term personalized feeding support.

[0111] Through real-time detection of breast milk nutritional parameters, blockchain traceability verification of milk powder nutritional parameters, and the self-correction mechanism of the dynamic ratio model, the accuracy of feeding data and the adaptability of the model are significantly improved. This method not only ensures the authenticity and reliability of breast milk and milk powder nutritional parameters, but also optimizes the accuracy and safety of the feeding plan by dynamically adjusting the feeding ratio information. The innovation of the embodiment is to combine spectral analysis technology and blockchain technology to build a data-driven, highly reliable intelligent feeding system, which provides scientific protection for the healthy growth of infants.

[0112] In some embodiments, the dynamic rationing model is established according to the standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters, including: updating the standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters respectively based on machine learning, retaining the key nutritional components in the standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters; generating standard feature information, breast milk feature information and milk powder feature information respectively according to the updated standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters; obtaining complementary information corresponding to the breast milk feature information and the milk powder feature information; and constructing the dynamic rationing model according to the standard feature information, breast milk feature information, milk powder feature information and complementary information.

[0113] According to the baby's age, weight and health status, the recommended standard nutritional parameters are obtained from the nutritional database, including the required amount of key nutrients such as protein, fat, carbohydrates, calcium, iron, etc. The spectral analysis module is used to detect the nutritional components in breast milk in real time to obtain data such as fat content, protein concentration, lactose content, etc. The nutritional parameters of milk powder, such as protein concentration, fat content, carbohydrate ratio, etc., are obtained from the data provided by the milk powder manufacturer or the testing equipment.

[0114] Use machine learning algorithms (such as cluster analysis or principal component analysis) to identify the core nutrients that are most critical to infant growth and development. For example, protein, fat, calcium, and iron may be identified as key components. Based on historical feeding data and infant growth records, standard nutritional parameters, breast milk nutritional parameters, and formula nutritional parameters are updated using regression algorithms or neural network models. This step aims to dynamically adjust parameter values ​​based on the actual needs and nutritional absorption of the infant.

[0115] Extract features from updated standard nutritional parameters, such as daily recommended protein intake, fat intake ratio, etc. Extract features from breast milk nutritional parameters, such as fat content, protein concentration, lactose content, etc. Extract features from milk powder nutritional parameters, such as protein concentration, fat content, carbohydrate ratio, etc.

[0116] Analyze the nutritional complementarity between breast milk and formula. For example, breast milk may be rich in certain nutrients, while formula is rich in other nutrients. The combination of the two can better meet the comprehensive nutritional needs of infants.

[0117] Through statistical analysis or machine learning methods, extract the complementary information between breast milk and formula, such as the synergistic effect of protein and fat, and the mutual promotion of calcium and iron absorption. Use machine learning algorithms (such as support vector machines, random forests, or deep learning models) to build a dynamic matching model. Model inputs include standard feature information, breast milk feature information, formula feature information, and complementary information. Use historical feeding data and infant growth data to train the model, optimize model parameters, and improve the accuracy and reliability of predictions. Verify the performance of the model through cross-validation and actual feeding data testing. Based on the verification results, further optimize the model structure and parameters to improve the model's prediction ability.

[0118] Based on the output of the dynamic ratio model, personalized feeding ratio information is generated, such as the ratio of breast milk to formula, the amount of single feeding, and the feeding interval. Based on the feeding ratio information, the breast milk processing channel and the formula processing channel are controlled to perform quantitative extraction, temperature adjustment, mixing and stirring operations to ensure the accurate implementation of the feeding plan. Sensors are used to monitor the temperature, flow rate, and baby's response of milk in real time, and the feeding plan is dynamically adjusted based on feedback information to ensure the comfort and safety of feeding.

[0119] By updating nutrition parameters through machine learning and building a dynamic ratio model, the system can generate personalized feeding ratio information according to the individual needs of infants to ensure that infants receive comprehensive and balanced nutrition. Analyze the nutritional complementarity of breast milk and formula, optimize the feeding ratio, promote the absorption and utilization of nutrients by infants, and reduce the problem of insufficient or excessive nutrition. Through scientific feeding ratios, ensure that infants receive adequate nutritional support and promote their healthy physical and intellectual development. Monitor the feeding process in real time, dynamically adjust the feeding plan according to the baby's response and nutrient absorption, and avoid health problems caused by improper feeding. Automatically complete the processing, temperature adjustment and feeding operations of breast milk and formula, reduce the burden on parents and improve the efficiency of feeding. Through intelligent algorithms and automated equipment, the errors of human operation are reduced to ensure the accuracy and consistency of feeding.

[0120] By recording the data of each feeding, the dynamic ratio model is continuously optimized to improve the accuracy and effectiveness of the feeding plan. As the baby grows and his physical condition changes, the system can dynamically adjust the feeding plan to adapt to the baby's changing needs and provide long-term feeding support.

[0121] Through the feeding ratio information generated by machine learning, the system can provide a transparent feeding plan and enhance the user's trust in the system's feeding plan. Strict data security measures are adopted to ensure that the baby's health data is not leaked or tampered with, and to protect user privacy.

[0122] The embodiment uses machine learning technology to update and feature extract standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters, and analyzes the nutritional complementarity of breast milk and milk powder to build a dynamic feeding ratio model. This model can adjust the feeding plan in real time according to the specific needs of the baby, provide personalized nutritional support, thereby improving the feeding effect and the health level of the baby. The innovation of the embodiment is to combine machine learning and nutrition knowledge to build an intelligent and personalized feeding system, which provides scientific protection for the healthy growth of babies.

[0123] In some embodiments, before controlling the operation of the breast milk processing channel and the milk powder processing channel according to the feeding ratio information, it includes: constructing a preset long short-term memory network, the long short-term gene network is used to calculate the risk of breast milk deterioration according to the breast milk storage time corresponding to the breast milk processing channel and the preset component change rate; the refrigeration temperature of the milk powder processing channel according to the breast milk deterioration risk; establishing a three-dimensional motion trajectory model according to the structural information corresponding to the milk powder processing channel, so as to optimize the stirring parameters corresponding to the milk powder processing channel through fluid mechanics simulation; the stirring parameters at least include the stirring angular velocity.

[0124] First, the storage time data of breast milk in the breast milk processing channel and the change rate data of breast milk components are collected. This data can be collected in real time by sensors or extracted from historical records. Key features such as storage time, changes in fat content, changes in protein concentration, etc. are extracted from the collected data. These features will be used as inputs to the LSTM network. The LSTM network is trained using machine learning methods so that it can predict the risk of breast milk deterioration based on the input storage time and composition change rate. During the training process, the system will use historical data for verification to ensure the accuracy of the model. The trained LSTM model is deployed to the system to monitor the storage status of breast milk in real time and predict the risk of deterioration. The LSTM model evaluates the risk of breast milk deterioration in real time. If the risk of deterioration exceeds the preset threshold, the system will trigger the adjustment mechanism. The system adjusts the refrigeration temperature of the milk powder processing channel based on the evaluation results. For example, if the risk of breast milk deterioration is high, the system may lower the temperature of the milk powder processing channel to slow down the deterioration of the milk powder. Through a precise temperature control system, the temperature of the milk powder processing channel is ensured to be maintained within the optimal range to maintain the quality and safety of the milk powder. Obtain the structural information of the milk powder processing channel, including the shape, size, material, etc. of the channel. Based on the obtained structural information, construct a three-dimensional motion trajectory model of the milk powder processing channel. This model can simulate the flow and stirring process of milk powder in the processing channel. Define stirring parameters in the model, such as stirring angular velocity, shape and angle of stirring blades, etc.

[0125] In the 3D motion trajectory model, set the fluid mechanics simulation parameters, such as fluid viscosity, density, stirring speed, etc. Run the fluid mechanics simulation to simulate the flow and mixing process of milk powder under different stirring parameters. Through the simulation results, analyze the impact of different stirring parameters on the mixing uniformity of milk powder. Optimize parameters such as stirring angular velocity to improve the efficiency and uniformity of milk powder processing. Verify the effect of the optimized stirring parameters in actual applications to ensure that the simulation results are consistent with the actual operation.

[0126] The risk of breast milk spoilage is monitored in real time through the LSTM network, and the refrigeration temperature of the milk powder processing channel is adjusted according to the risk to ensure the quality and safety of breast milk and milk powder. By establishing a three-dimensional motion trajectory model and fluid mechanics simulation, the stirring parameters of the milk powder processing channel are optimized, the efficiency and uniformity of milk powder processing are improved, and the nutrients in the milk powder are ensured to be fully released and mixed. Through automated monitoring and adjustment, the embodiment reduces the need for manual intervention and improves the automation level and operating efficiency of the entire system. By precisely controlling the processing of breast milk and milk powder, it ensures that infants receive high-quality nutrition and promotes their healthy growth.

[0127] Dynamically adjust the refrigeration temperature and stirring parameters of the milk powder processing channel, so that the method can adapt to different storage conditions and milk powder types, enhancing the adaptability and flexibility of the system. Through real-time data collection and the application of machine learning models, the processing of breast milk and milk powder can be continuously optimized to provide more accurate and reliable feeding solutions.

[0128] By building a long-term and short-term memory network, adjusting the refrigeration temperature of the milk powder processing channel, establishing a three-dimensional motion trajectory model, and optimizing the stirring parameters, the quality and efficiency of breast milk and milk powder processing have been comprehensively improved. These measures not only ensure that babies receive safe and nutritionally balanced feeding, but also improve the automation level and adaptability of the entire system, laying a solid foundation for the further development of the intelligent feeding system.

[0129] In some embodiments, after the breast milk heating temperature of the breast milk processing channel and the milk powder brewing temperature of the milk powder processing channel are respectively adjusted within a preset safety temperature range according to the water temperature control module, it also includes: acquiring an infant feeding image acquired by a preset image acquisition module; parsing the infant feeding image to acquire the infant swallowing frequency and the milk drop speed corresponding to the milk maker; calculating the swallowing comfort according to the infant swallowing frequency and the milk drop speed; and optimizing the dynamic proportioning model according to the swallowing comfort.

[0130] An image acquisition module, such as a camera, is integrated into the feeding device to capture images of the baby in real time during the feeding process. During the feeding process, the image acquisition module captures the baby's face and the flow of milk from the feeding device in real time.

[0131] Using advanced computer vision technology, we analyze baby feeding images, identify and track the baby's swallowing movements. By analyzing the baby's facial expressions and movements, we calculate the baby's swallowing frequency, that is, the number of times the baby swallows per unit time. Through image analysis, we monitor the flow of milk in the feeding device and calculate the milk drop speed, that is, the amount of milk reduced per unit time.

[0132] According to the baby's swallowing frequency and milk drop speed, the preset comfort calculation model is used to evaluate the baby's comfort during feeding. Comfort indicators may include the suitability of swallowing frequency, the matching of milk flow rate, etc., to comprehensively evaluate the baby's feeding comfort. The calculated swallowing comfort is fed back to the dynamic ratio model as an important basis for optimizing the model. According to the comfort evaluation results, the ratio of breast milk and milk powder, as well as the brewing temperature, are dynamically adjusted to improve the baby's feeding comfort. The baby's swallowing situation and milk flow rate are monitored in real time, and the feeding parameters are continuously optimized to ensure that the baby always remains comfortable during the feeding process.

[0133] By monitoring the baby's swallowing frequency and the speed at which the milk drops in real time, the system can accurately adjust the ratio of breast milk and formula, as well as the brewing temperature, to ensure that the flow rate of the milk matches the baby's swallowing frequency, reducing the risk of choking or discomfort.

[0134] Monitor the baby's feeding process in real time, promptly detect and adjust any parameters that may cause discomfort to the baby, and improve the safety of feeding. Through the baby's swallowing comfort feedback, the dynamic ratio model can be continuously optimized to provide a more personalized and accurate feeding plan to ensure that the baby gets the best nutrition and feeding experience. Through automated monitoring and adjustment, the need for parental intervention during the feeding process is reduced, the burden on parents is reduced, and the feeding process is made easier and more efficient. By optimizing feeding parameters, ensure that the baby gets balanced nutrition and promotes its healthy physical and intellectual development. The embodiment significantly improves the intelligence level of feeding equipment by introducing image acquisition and analysis technology, combined with the optimization of the dynamic ratio model, and provides important technical support for future intelligent feeding systems.

[0135] The embodiment introduces an image acquisition module and computer vision technology to monitor the baby's swallowing frequency and milk drop speed in real time, evaluate the baby's feeding comfort, and optimize the dynamic ratio model based on comfort feedback. This innovative method not only significantly improves the comfort and safety of infant feeding, but also optimizes the nutritional ratio during feeding to ensure that the baby has the best feeding experience. The introduction of the embodiment provides a more comprehensive and accurate solution for the intelligent feeding system, and promotes the further development of infant feeding technology.

[0136] Among them, to determine the weight of each factor. According to actual research, this application found that temperature has the greatest impact on comfort, followed by flow rate, and finally texture and age. Therefore, the following weights are used: temperature: weight 0.4 flow rate: weight 0.3 texture: weight 0.2 baby's age: weight 0.1.

[0137] Therefore, swallowing comfort is 0.4T+0.3F+0.2×Q+0.1A. T is the temperature of the liquid in the feeding container. F is the flow rate of the liquid in the feeding container. Q is the texture of the liquid in the feeding container (such as viscosity), which will also affect the swallowing experience of the baby. A is the age of the baby. T, F, Q and A can be standardized first.

[0138] In some embodiments, before controlling the operation of the breast milk processing channel and the milk powder processing channel according to the feeding ratio information, it also includes: parsing the feeding record data to obtain feeding operation habit information; the feeding operation habit information at least includes feeding angle, feeding flow rate, shaking force and feeding duration; obtaining the environmental humidity information corresponding to the milk maker; updating the feeding ratio information according to the feeding operation information and the environmental humidity information.

[0139] Feeding record data usually comes from sensors built into the feeding device, such as accelerometers, flow sensors, etc., or is manually input by the user. These sensors can monitor key parameters such as the baby's feeding angle, feeding flow rate, shaking intensity, and feeding duration during feeding in real time.

[0140] In order to extract information about feeding habits from raw data, the system needs to use specific algorithms or machine learning models. For example, the feeding angle and shaking force can be determined by analyzing the data from the accelerometer, and the feeding flow rate and duration can be measured through the data from the flow sensor.

[0141] The analyzed feeding operation habit information needs to be stored in the system database for subsequent analysis and updating of feeding ratio information. This data can be stored in chronological order to facilitate subsequent trend analysis and pattern recognition.

[0142] A humidity sensor is integrated into the milk maker to monitor the humidity of the surrounding environment in real time. The humidity sensor can be a resistive, capacitive or other type of sensor. The appropriate sensor type and accuracy can be selected according to specific needs.

[0143] The humidity sensor collects environmental humidity data periodically or in real time and transmits it to the central processing unit of the system. The frequency of collection can be adjusted according to actual needs, such as once per minute or once per second.

[0144] The collected environmental humidity data is associated with the feeding operation habit information so that the influence of environmental factors can be comprehensively considered when updating the feeding ratio information.

[0145] Integrate feeding operation habit information (such as feeding angle, feeding flow rate, shaking force and feeding duration) with environmental humidity information into a unified data model. This can be achieved through database management or data fusion technology.

[0146] Based on the integrated data, the system uses a preset algorithm or machine learning model to dynamically adjust the ratio of breast milk and formula, as well as other parameters that may affect the feeding effect. For example, if the ambient humidity is high, the concentration of the formula may need to be adjusted to ensure the solubility and nutritional balance of the formula.

[0147] The updated feeding ratio information is fed back to the breast milk processing channel and the milk powder processing channel to guide their specific work. This may include adjusting the heating temperature of breast milk, the brewing temperature of milk powder, and the mixing parameters of milk powder.

[0148] By analyzing the feeding record data, the system can identify the user's feeding habits and provide a personalized feeding ratio. This not only improves the baby's comfort, but also enhances the effect of feeding, making it easier for the baby to accept and digest.

[0149] Ambient humidity is an important factor affecting the quality of milk powder preparation. By real-time monitoring of ambient humidity and incorporating it into the adjustment factor of the feeding ratio, the system can optimize the concentration of milk powder preparation according to actual environmental conditions to ensure the solubility and nutritional balance of milk powder.

[0150] Dynamically adjust the feeding ratio to make the amount of each feeding more accurate and reduce the waste caused by improper ratio. This not only saves resources, but also reduces the economic burden on parents. According to information such as feeding angle and feeding flow rate, the system can optimize the feeding process and reduce the risk of infant choking. This not only improves the safety of feeding, but also enhances the confidence of parents in feeding. By continuously parsing feeding record data and environmental humidity information, the system can continuously optimize the feeding ratio and provide a more accurate and intelligent feeding solution. This not only improves the efficiency of feeding, but also provides valuable data support for the future development of feeding technology. The embodiment significantly improves the intelligence level of the feeding system by introducing feeding operation habit information and environmental humidity information. The system can autonomously adjust the feeding ratio according to real-time data and user habits, reducing the need for manual intervention and making the feeding process more automated and intelligent.

[0151] By analyzing feeding record data and environmental humidity information, the feeding ratio is dynamically adjusted to provide a more personalized and safe feeding experience for babies. This innovative method not only optimizes the nutritional ratio during feeding, but also significantly improves the intelligence level of the feeding system, laying a solid foundation for the development of intelligent feeding technology. The embodiment provides a more comprehensive and accurate solution for infant feeding, promoting the further development of infant feeding technology.

[0152] In some embodiments, generating a safe temperature range based on the age parameters and physical parameters includes: obtaining sensitivity information of the physical parameters and temperature; obtaining digestion capacity information of the age parameters and temperature; obtaining first state information of breast milk and temperature and obtaining second state information of milk powder and temperature; the first state information and the second state information are respectively used to feedback the physical states of breast milk and milk powder at different temperatures; based on a preset autoregressive learning algorithm, generating the safe temperature range according to the sensitivity information, digestion capacity information, the first state information and the second state information.

[0153] The baby's physical parameters, such as weight, height, allergy history, etc., are collected through the baby's health records, information provided by parents, or smart devices. At the same time, the baby's sensitivity to temperature is collected, such as the baby's comfort response at different temperatures.

[0154] According to the age of the baby, refer to medical research and feeding guidelines to obtain data on the baby's digestive ability at different age groups, such as the digestion and absorption efficiency of food at different temperatures.

[0155] Collect data on the physical state of breast milk at different temperatures, such as fluidity in liquid and warm states, stability of nutrients, etc. Collect data on the physical state of milk powder at different temperatures, such as solubility, fluidity, dissolution of nutrients, etc.

[0156] Clean the collected data, remove outliers and noise data, and ensure the accuracy and reliability of the data. Extract key features from the raw data, such as temperature sensitivity, digestibility index, physical state parameters of breast milk and formula, etc. Based on the preset autoregressive learning algorithm (such as ARIMA, LSTM, etc.), build a model that can comprehensively analyze physical parameters, age parameters, temperature sensitivity, digestibility, and physical state of breast milk and formula.

[0157] The model is trained using historical data to ensure that it can accurately predict the safe temperature range for babies under different conditions. In actual applications, the model receives new data input in real time, dynamically adjusts and generates a safe temperature range suitable for the baby's current state.

[0158] The model calculates and generates a scientific safe temperature range based on the input physical parameters, age parameters, temperature sensitivity, digestion ability, and physical state information of breast milk and formula. The generated safe temperature range is applied to the feeding equipment to automatically adjust the heating temperature of breast milk and formula to ensure that the baby gets the best temperature experience during feeding.

[0159] By comprehensively analyzing the baby's physique, age, temperature sensitivity and digestive ability, an accurate safe temperature range is generated to reduce the baby's discomfort or health problems caused by temperature discomfort. It ensures that the baby obtains the appropriate temperature during feeding, improves the comfort of feeding, and reduces crying and discomfort.

[0160] According to the physical state of breast milk and formula at different temperatures, the feeding temperature is optimized to ensure the full dissolution and absorption of nutrients and improve the efficiency of infant nutrition intake. Through the autoregressive learning algorithm, the feeding device can dynamically adjust the feeding temperature according to the real-time status and environmental data of the infant, improving the intelligence and automation level of the device. Based on scientific data analysis and intelligent algorithms, personalized feeding temperature recommendations are provided to help infants obtain the best nutrition and feeding experience and promote their healthy physical and intellectual development.

[0161] Automatic adjustment of feeding temperature reduces the trouble of parents having to manually adjust the temperature during feeding, and reduces the difficulty and time cost of feeding. By continuously collecting and analyzing feeding data, the calculation model of feeding temperature can be continuously optimized, providing more accurate and personalized feeding plans to ensure that babies get the best feeding experience.

[0162] By comprehensively analyzing the baby's physique, age, temperature sensitivity, digestive ability, and the physical state of breast milk and formula, and using an autoregressive learning algorithm, a scientific and safe temperature range is generated to ensure that the baby gets the best temperature experience during feeding. This innovative method not only improves the safety and comfort of infant feeding, but also optimizes the nutrient absorption efficiency during feeding, providing strong support for the healthy growth of infants. It provides a more comprehensive and accurate solution for the intelligent feeding system and promotes the further development of infant feeding technology.

[0163] In some embodiments, after respectively adjusting the breast milk heating temperature of the breast milk processing channel and the milk powder brewing temperature of the milk powder processing channel within a preset safety temperature range according to the water temperature control module, it also includes: after each feeding operation is completed, the milk utensils of the milk maker are sterilized at high temperature according to a preset steam sterilization program; the steam sterilization program includes conveying high-temperature steam to the milk utensil storage area through an independent sterilization pipeline, and cooperating with an ultraviolet disinfection device to implement a composite disinfection.

[0164] After each feeding operation, the system automatically detects that the feeding utensils have been used and immediately starts the steam sterilization process. This automated design reduces the number of user operation steps and improves the convenience of use. Users can also choose to manually start the sterilization process when needed, providing greater flexibility and control.

[0165] The internal design of the milk maker is equipped with an independent sterilization pipeline, which is specially used to deliver high-temperature steam to ensure that the steam is directly delivered to the milk storage area to avoid steam leakage or heat loss. This design improves the utilization rate of steam and ensures the sterilization effect.

[0166] The milk maker has a built-in high-temperature steam generator that can quickly generate high-temperature steam. The steam temperature is usually controlled above 90°C to ensure the sterilization effect. High-temperature steam can effectively kill microorganisms such as bacteria and viruses, especially for microorganisms that are resistant to high temperatures. Through the intelligent control module, the time and flow of steam delivery are adjusted to ensure that the steam concentration and temperature in the milk storage area achieve the best disinfection effect. The intelligent control module can automatically adjust the steam delivery parameters according to the number of milk utensils and the size of the storage area to ensure the comprehensiveness and effectiveness of disinfection.

[0167] The milking utensils storage area is equipped with an ultraviolet disinfection device, which can sterilize the surface of milking utensils with ultraviolet light while performing steam sterilization. Ultraviolet light can destroy the DNA structure of microorganisms, further enhancing the sterilization effect, especially for microorganisms that are difficult to completely kill with steam.

[0168] The 260-280nm ultraviolet band is used, which has the strongest bactericidal effect on bacteria, viruses and other microorganisms. This wavelength selection ensures the effectiveness and safety of ultraviolet disinfection. According to the number of milking utensils and the size of the storage area, the ultraviolet irradiation time is intelligently adjusted to ensure the comprehensiveness and effectiveness of disinfection. The intelligent control module can dynamically adjust the ultraviolet irradiation time according to the actual situation to avoid over-irradiation or under-irradiation.

[0169] High-temperature steam can effectively kill microorganisms such as bacteria and viruses, especially for microorganisms that are resistant to high temperatures. The sterilization effect of high-temperature steam is to destroy the cell structure of microorganisms through high temperature, making them inactive. Ultraviolet rays can destroy the DNA structure of microorganisms, further enhancing the sterilization effect, especially for microorganisms that are difficult to completely kill with steam. The sterilization effect of ultraviolet rays is to destroy the genetic material of microorganisms, making them unable to reproduce. High-temperature steam and ultraviolet rays work together to form a double sterilization guarantee, ensuring that the milk utensils in the milk utensils storage area meet high standards of hygiene requirements. This composite disinfection method not only improves the sterilization effect, but also reduces the sterilization blind spots that may exist due to a single disinfection method.

[0170] The synergistic effect of high-temperature steam and ultraviolet rays can effectively kill bacteria, viruses and other microorganisms, ensuring the hygiene and safety of milk utensils. The dual sterilization mechanism significantly improves the sterilization effect and reduces the sterilization blind spots that may exist due to a single sterilization method. The sterilization program is automatically triggered after each feeding operation is completed, without manual intervention, which improves the convenience and efficiency of use. The automated design reduces the user's operating burden and improves the user experience. High-temperature steam is delivered through an independent sterilization pipeline to reduce the heat loss of steam and improve energy utilization efficiency. The intelligent control module can dynamically adjust the steam delivery time and flow rate according to actual conditions to avoid energy waste. The ultraviolet disinfection device has low energy consumption, which further reduces the overall energy consumption. This design is not only environmentally friendly, but also saves users' usage costs.

[0171] High-temperature steam and ultraviolet disinfection are gentle and will not cause chemical corrosion or physical damage to the milking utensils, thus extending the service life of the milking utensils. This design reduces the frequency of milking utensils replacement and reduces the financial burden on users.

[0172] Through efficient disinfection measures, the hygiene and safety of feeding utensils are ensured, and the user's trust and satisfaction with the product are improved. Users can use double-sterilized feeding utensils with confidence, reducing health concerns caused by contamination of feeding utensils. The disinfection method provided meets national health standards, ensuring the safety of feeding utensils, especially for babies. High-standard disinfection measures provide a safer feeding environment for babies.

[0173] By thoroughly disinfecting milk utensils, the risk of cross infection caused by milk utensils contamination can be effectively reduced, thus ensuring the health of babies. The dual sterilization mechanism significantly reduces the possibility of milk utensils carrying pathogens and reduces the risk of infants getting sick. The milk maker has a built-in intelligent control module that can automatically adjust the steam delivery time and ultraviolet irradiation time to ensure the disinfection effect while improving the level of intelligence in use. Intelligent design enhances the product's sense of technology and user experience. Integrating high-temperature steam disinfection and ultraviolet disinfection into one system achieves multi-functional integration and saves space and resources. The integrated design reduces the space occupied by the equipment and improves the product's aesthetics and practicality.

[0174] The independent disinfection pipeline and ultraviolet disinfection device design facilitates daily cleaning and maintenance, ensuring the long-term stable operation of the disinfection system. Users can easily clean and maintain it, extending the service life of the equipment.

[0175] Through the synergistic effect of high-temperature steam and ultraviolet rays, efficient, safe and intelligent disinfection of milk utensils is achieved, which not only improves the hygiene and safety of milk utensils, but also enhances the user experience and trust. This innovative method not only reduces the health risks caused by milk utensil contamination, but also improves the convenience and efficiency of use through automation and intelligent design. It provides more comprehensive and reliable hygiene protection for smart milk makers, promotes the technological development of infant feeding equipment, and has important practical application value.

[0176] The embodiment of the present application also provides a milk-making device with intelligent temperature control and proportioning based on a database. The milk-making device with intelligent temperature control and proportioning based on a database is used to execute the steps of the milk-making method with intelligent temperature control and proportioning based on a database shown in the above embodiments. The milk-making device with intelligent temperature control and proportioning based on a database can be a single server or a server cluster, or the milk-making device with intelligent temperature control and proportioning based on a database can be a terminal, which can be a handheld terminal, a laptop computer, a wearable device or a robot, etc.

[0177] The database-based intelligent temperature control and proportioning milk making device includes:

[0178] An information acquisition unit, used to acquire information about the baby to be fed; the baby information at least includes age parameters, physical parameters and feeding record data;

[0179] A parameter acquisition unit, used for acquiring standard nutritional parameters corresponding to the age parameters from a pre-built database;

[0180] A model building unit, used to build a dynamic ratio model according to standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters;

[0181] A parameter input unit, used to input the physical parameters and feeding record data into the dynamic ratio model, and output feeding ratio information; the feeding ratio information includes the number of breastfeeding times, the number of milk powder brewing times, the single feeding amount and the feeding time interval;

[0182] A working control unit, used for controlling the operation of the breast milk processing channel and the milk powder processing channel according to the feeding ratio information: the breast milk processing channel performs quantitative extraction, temperature regulation and aseptic transportation of refrigerated breast milk, and the milk powder processing channel performs mixing, stirring and sterilization transportation of quantitative milk powder and warm water;

[0183] A range generating unit, used for generating a safe temperature range according to the age parameter and the physical parameter;

[0184] The temperature regulating unit is used to adjust the breast milk heating temperature of the breast milk processing channel and the milk powder brewing temperature of the milk powder processing channel to the safe temperature range according to the water temperature control module, so as to complete the feeding operation for the baby to be fed.

[0185] It should be noted that, technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the above-described database-based intelligent temperature control and proportioning milk making device and the specific working process of each unit can refer to the corresponding process in the database-based intelligent temperature control and proportioning milk making method embodiments described in the above-mentioned embodiments, and will not be repeated here.

[0186] The above-mentioned embodiment corresponding to the database-based intelligent temperature control and proportioning milk preparation method can be implemented in the form of a computer program, and the computer program can be run on the above-mentioned device.

[0187] See also Figure 3 , Figure 3 : is a schematic block diagram of the structure of a control module provided in an embodiment of the present application. The control module includes a processor, a memory and a network interface connected via a device bus, wherein the memory may include a storage medium and an internal memory.

[0188] The storage medium can store an operating device and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any embodiment corresponding to the database-based intelligent temperature control and proportioning milk making method.

[0189] The processor is used to provide computing and control capabilities and support the operation of the entire control module.

[0190] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any embodiment corresponding to the database-based intelligent temperature control and proportioning milk making method.

[0191] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the terminal to which the scheme of the present application is applied. The specific control module may include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0192] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0193] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0194] Acquiring information about the baby to be fed; the baby information at least includes age parameters, physical parameters and feeding record data;

[0195] Obtaining standard nutritional parameters corresponding to the age parameters from a pre-built database;

[0196] Establish a dynamic proportioning model based on standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters;

[0197] Inputting the physical parameters and feeding record data into the dynamic ratio model, and outputting feeding ratio information; the feeding ratio information includes the number of breastfeeding times, the number of times milk powder is prepared, the single feeding amount and the feeding time interval;

[0198] The breast milk processing channel and the milk powder processing channel are controlled to work according to the feeding ratio information: the breast milk processing channel performs quantitative extraction, temperature adjustment and aseptic transportation of refrigerated breast milk, and the milk powder processing channel performs mixing, stirring and sterilization transportation of quantitative milk powder and warm water;

[0199] Generate a safe temperature range according to the age parameter and the physical parameter;

[0200] According to the water temperature control module, the breast milk heating temperature of the breast milk processing channel and the milk powder brewing temperature of the milk powder processing channel are respectively adjusted within the safe temperature range to complete the feeding operation for the baby to be fed.

[0201] It should be noted that technicians in the relevant field can clearly understand that for the convenience and brevity of description, the specific working process of the processor described above can refer to the corresponding process in the method embodiments described in the above embodiments, and will not be repeated here.

[0202] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement the steps of the database-based intelligent temperature control and proportioning milk making method provided in the above embodiments of the present application.

[0203] The computer-readable storage medium may be an internal storage unit of the control module described in the above embodiment, such as a hard disk or memory of the control module. The computer-readable storage medium may also be an external storage device of the control module, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the control module.

[0204] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for preparing milk with intelligent temperature control and proportioning based on a database, characterized in that: A control module applied to a milk maker, wherein the milk maker further comprises a breast milk processing channel, a milk powder processing channel and a water temperature control module; and the method comprises: Acquiring information about the baby to be fed; the baby information at least includes age parameters, physical parameters and feeding record data; Obtaining standard nutritional parameters corresponding to the age parameters from a pre-built database; Establish a dynamic proportioning model based on standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters; Inputting the physical parameters and feeding record data into the dynamic ratio model, and outputting feeding ratio information; the feeding ratio information includes the number of breastfeeding times, the number of times milk powder is prepared, the single feeding amount and the feeding time interval; The breast milk processing channel and the milk powder processing channel are controlled to work according to the feeding ratio information: the breast milk processing channel performs quantitative extraction, temperature adjustment and aseptic transportation of refrigerated breast milk, and the milk powder processing channel performs mixing, stirring and sterilization transportation of quantitative milk powder and warm water; Generate a safe temperature range according to the age parameter and the physical parameter; According to the water temperature control module, the breast milk heating temperature of the breast milk processing channel and the milk powder brewing temperature of the milk powder processing channel are respectively adjusted within the safe temperature range to complete the feeding operation for the baby to be fed.

2. The method according to claim 1, characterized in that The dynamic ratio model includes a gradient boosting decision tree model and a convolutional neural network model; the feeding record data includes multiple historical feeding data; the physical parameters and feeding record data are input into the dynamic ratio model, and the feeding ratio information is output, including: Analyze the physical parameters to obtain the baby's body temperature, heart rate and digestion cycle data; Constructing a dynamic mapping relationship between the physical parameters and each historical feeding data; Inputting the dynamic mapping relationship into the gradient boosting decision tree model, and the gradient boosting decision tree model outputs the personalized feeding coefficient of the infant to be fed; The personalized feeding coefficient and the standard nutritional parameters are input into the convolutional neural network model, and the feeding ratio information is output.

3. The method according to claim 1, characterized in that Before inputting the physical parameters and feeding record data into the dynamic matching model, the method further includes: Detecting in real time the breast milk nutritional parameters corresponding to the breast milk in the breast milk processing channel according to the preset spectral analysis module, where the breast milk nutritional parameters at least include fat content and protein concentration; Obtain the milk powder nutritional parameters and milk powder identification information corresponding to the milk powder processing channel; Constructing a milk powder nutritional parameter traceability network, and using blockchain technology to verify the authenticity of the milk powder nutritional parameters according to the milk powder identification information; If the deviation between the standard value of the database and any one of the breast milk nutritional parameter and the milk powder nutritional parameter exceeds a preset deviation, the dynamic proportioning model is subjected to parameter self-correction.

4. The method according to claim 1, characterized in that The dynamic proportioning model is established according to the standard nutritional parameters, the nutritional parameters of breast milk and the nutritional parameters of milk powder, including: Based on machine learning, the standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters are updated respectively, and key nutritional components in the standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters are retained; Generate standard characteristic information, breast milk characteristic information and milk powder characteristic information respectively according to the updated standard nutritional parameters, breast milk nutritional parameters and milk powder nutritional parameters; Obtaining complementary information corresponding to breast milk characteristic information and milk powder characteristic information; The dynamic proportioning model is constructed according to the standard characteristic information, breast milk characteristic information, milk powder characteristic information and complementary information.

5. The method according to claim 1, characterized in that: Before controlling the operation of the breast milk processing channel and the milk powder processing channel according to the feeding ratio information, the method includes: Constructing a preset long short-term memory network, wherein the long short-term gene network is used to calculate the risk of breast milk deterioration according to the breast milk storage time corresponding to the breast milk processing channel and the preset component change rate; Refrigeration temperature of the milk powder processing channel according to the risk of breast milk spoilage; A three-dimensional motion trajectory model is established according to the structural information corresponding to the milk powder processing channel, so as to optimize the stirring parameters corresponding to the milk powder processing channel through fluid mechanics simulation; the stirring parameters at least include the stirring angular velocity.

6. The method according to claim 1, characterized in that After the breast milk heating temperature of the breast milk processing channel and the milk powder brewing temperature of the milk powder processing channel are respectively adjusted within a preset safe temperature range according to the water temperature control module, the method further includes: Acquire a baby feeding image acquired by a preset image acquisition module; Analyze the baby feeding image to obtain the baby swallowing frequency and the milk drop speed corresponding to the milk maker; Calculating swallowing comfort according to the baby's swallowing frequency and the milk drop speed; The dynamic ratio model is optimized according to the swallowing comfort.

7. The method according to claim 1, characterized in that Before controlling the operation of the breast milk processing channel and the milk powder processing channel according to the feeding ratio information, the method further includes: Parsing the feeding record data to obtain feeding operation habit information; the feeding operation habit information at least includes feeding angle, feeding flow rate, shaking strength and feeding duration; Obtaining environmental humidity information corresponding to the milk maker; The feeding ratio information is updated according to the feeding operation information and the environmental humidity information.

8. The method according to claim 1, characterized in that: Generating a safe temperature range according to the age parameter and the physical parameter includes: Obtaining sensitivity information of the physical parameters and temperature; Obtaining digestibility information of the age parameter and temperature; Acquire first state information of breast milk and temperature and acquire second state information of milk powder and temperature; the first state information and the second state information are used to feedback the physical states of breast milk and milk powder at different temperatures respectively; Based on a preset autoregressive learning algorithm, the safe temperature range is generated according to the sensitivity information, the digestibility information, the first state information and the second state information.

9. The method according to claim 1, characterized in that: After the breast milk heating temperature of the breast milk processing channel and the milk powder brewing temperature of the milk powder processing channel are respectively adjusted within a preset safe temperature range according to the water temperature control module, the method further includes: After each feeding operation is completed, the milk utensils of the milk maker are sterilized at high temperature according to a preset steam sterilization program; The steam sterilization procedure includes delivering high-temperature steam to the milk utensil storage area through an independent sterilization pipeline, and implementing composite sterilization in conjunction with an ultraviolet sterilization device.

10. A milk maker, characterized in that The milk maker includes: a control module, a breast milk processing channel, a milk powder processing channel and a water temperature control module: The control module comprises a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the method according to any one of claims 1 to 9 when executing the computer program.

Images