Intelligent feeding method

Abstract

The embodiment of the invention provides an intelligent feeding method, and the method comprises the steps: obtaining a current feeding scheme of a target object, carrying out the food putting of the target object based on the current feeding scheme, and obtaining the current feeding information of the target object when the food putting of the target object is carried out based on the current feeding scheme; and determining a target feeding scheme of the target object based on the current feeding information, the historical feeding data and the current feeding scheme, and putting food into the target object based on the target feeding scheme.

Description

Cross-references

[0001] This application claims priority to U.S. Provisional Application No. 63551035, filed on February 7, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This specification relates to the field of pet products, and in particular to an intelligent feeding method. Background Art

[0003] In modern society, pets have become an important part of many families, and a proper diet is crucial to their health. Automatic pet feeding offers convenience. Automatic feeders can provide food and water to pets at regular intervals and in fixed quantities, making it easier for owners to care for their pets. However, different pets have different food preferences and eating habits. Automatic feeders can only mechanically set the feeding amount and time according to a fixed program, making it difficult to meet the specific needs of pets and posing potential health risks.

[0004] Therefore, it is hoped to provide an intelligent feeding method that can more accurately feed pets, meet the dietary needs of different pets in a targeted manner, realize personalized feeding of pets, and ensure the health of pets. Summary of the Invention

[0005] One of the embodiments of the present specification provides an intelligent feeding method, which includes: obtaining a current eating plan of a target object, delivering food to the target object based on the current eating plan, and obtaining current eating information of the target object when delivering food to the target object based on the current eating plan; and determining a target eating plan for the target object based on the current eating information, historical eating data, and the current eating plan, and delivering food to the target object based on the target eating plan.

[0006] In some embodiments, obtaining the current eating plan of the target object includes: determining the current eating plan of the target object through a same type eating model based on the first object information and the initial eating plan of the target object.

[0007] In some embodiments, determining the target eating plan of the target object based on the current eating information, historical eating data, and the current eating plan includes: obtaining the eating goal of the target object; and determining the target eating plan of the target object based on the eating goal, the current eating information, historical eating data, and the current eating plan.

[0008] In some embodiments, determining the target eating plan of the target object based on the eating goal, the current eating information, the historical eating data, and the current eating plan includes: adjusting the current eating plan through a plan adjustment strategy based on the eating goal, the current eating information, and the historical eating data to determine the target eating plan of the target object.

[0009] In some embodiments, determining the target eating plan of the target object based on the eating goal, the current eating information, the historical eating data and the current eating plan includes: obtaining the target eating model of the target object based on the first object information of the target object, the current eating information, the historical eating data and the current eating plan; and determining the target eating plan of the target object through the target eating model based on the second object information of the target object, the current eating plan and the eating goal.

[0010] In some embodiments, the eating goal includes at least one of a target blood glucose stability, a target weight change value, and a target calorie intake of the target subject.

[0011] In some embodiments, the method further includes: determining an eating time period for the target object based on the target eating plan; obtaining a target image of an eating area corresponding to the target object within the eating time period; determining an object to be eaten in the eating area based on the target image; and when the object to be eaten includes the target object, delivering food to the target object based on the target eating plan.

[0012] In some embodiments, the method further includes: when food is delivered to the target object based on the target eating plan, playing a reminder audio corresponding to the target object and / or turning on a reminder light corresponding to the target object.

[0013] In some embodiments, the target eating plan includes multiple stages of sub-eating plans, and delivering food to the target subject based on the target eating plan includes delivering food to the target subject stage by stage based on the multiple stages of sub-eating plans.

[0014] In some embodiments, the delivering food to the target object stage by stage based on the sub-feeding plans of the multiple stages includes: a sub-feeding plan for each stage; delivering food based on the sub-feeding plan of that stage; obtaining an eating image of the eating area; determining the eating objects in the eating area based on the eating image; and when the eating objects include other objects besides the target object, stopping delivering food to the target object based on the sub-feeding plan of the next stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0016] Figure 1 is a schematic diagram of an application scenario of the intelligent feeding device according to some embodiments of this specification;

[0017] Figure 2 is a schematic structural diagram of an intelligent feeding device according to some embodiments of this specification;

[0018] Figure 3 is an exemplary flow chart of an intelligent feeding method according to some embodiments of this specification;

[0019] Figure 4 is an exemplary flow chart of another intelligent feeding method according to some embodiments of this specification;

[0020] Figure 5 is an exemplary flow chart of a multi-stage intelligent feeding method according to some embodiments of this specification;

[0021] Figure 6 This is an exemplary flow chart for determining the food intake of a target object according to some embodiments of this specification. DETAILED DESCRIPTION

[0022] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0023] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0024] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0025] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0026] Figure 1 This is a schematic diagram of an application scenario of the intelligent feeding device according to some embodiments of this specification.

[0027] like Figure 1 As shown, the application scenario 100 of the intelligent feeding device may include a feeding subject 110, a feeder 120, a user terminal 130, a network 140, and a processor 150. In some embodiments, the processor 150 may obtain a current eating plan of the feeding subject 110, control the feeder 120 to deliver food to the feeding subject 110 via the network 140 based on the current eating plan, and obtain initial eating information of the feeding subject 110 when controlling the feeder 120 to deliver food to the feeding subject 110 via the network 140 based on the current eating plan; then, based on the initial eating information, historical eating information, and the current eating plan, determine a target eating plan for the feeding subject 110, and control the feeder 120 to deliver food to the feeding subject 110 via the network 140 based on the target eating plan. For more details about the above embodiments, please refer to the following part of this specification.

[0028] The feeding object 110 is a pet fed by the feeder 120. For example, the feeding object 110 may include but is not limited to various types of cats, dogs, chickens, ducks, and pigs fed by the feeder 120. The feeder 120 can feed one or more feeding objects 110. For each feeding time period corresponding to the feeding object 110, the processor 150 can determine the feeding object 110 as the target object, and determine the feeding object 110 located in the feeding area 170 corresponding to the target object as the object to be fed. The aforementioned object to be fed may or may not include the target object. For example, Figure 1The feeder 120 shown can feed three feeding objects 110. The feeding area corresponding to a certain target object is the feeding area 170. The processor 150 can determine the two feeding objects 110 located in the feeding area 170 as the objects to be fed within the feeding time period corresponding to the target object, and the other feeding object 110 located outside the feeding area 170 is not the object to be fed.

[0029] Feeder 120 is a device for feeding a target pet. It can be used to store and dispense pet food. Feeder 120 can include a controllable feeding volume valve that precisely controls the amount and timing of food released each time based on the target pet's feeding schedule (e.g., current feeding schedule, target feeding schedule, etc.).

[0030] The user terminal 130 refers to one or more terminal devices or software used by the user. The aforementioned user is the user of the feeder 120. The user can query the eating status and eating plan of each feeding object 110 through the user terminal 130. The user can also upload the object information (for example, first object information, second object information, etc.) of each feeding object 110 through the user terminal 130. The user can also upload the eating needs of each feeding object 110 through the user terminal 130. For more information about object information and eating needs, please refer to the relevant description below in this specification. One or more users can use the user terminal 130, which can include users who directly use the service or other related users. The user terminal 130 can be one or any combination of other devices with input and / or output functions, such as a mobile device, a tablet computer, a laptop computer, a desktop computer, etc.

[0031] The network 140 can connect the various components of the application scenario 100 of the smart feeding device and / or connect the application scenario 100 of the smart feeding device with external resources. The network 140 enables communication between the various components of the application scenario 100 of the smart feeding device, as well as with other components outside the application scenario 100 of the smart feeding device, facilitating the exchange of data and / or information. The network 140 can be any one or more of a wired network or a wireless network. For example, the network 140 can include a cable network, a fiber optic network, a telecommunications network, the Internet, a local area network, a wide area network, a wireless local area network, a Bluetooth network, near-field communication, an in-device bus, in-device wiring, a cable connection, or any combination thereof. The network connections between the various components can use one of the aforementioned methods or a combination of methods.

[0032] The processor 150 can process data and / or information obtained from other devices or components of the application scenario 100 of the intelligent feeding device. The processor 150 can execute program instructions based on these data, information and / or processing results and control other components of the application scenario 100 of the intelligent feeding device (for example, the feeder 120) to perform one or more functions described in this specification. For example, the processor 150 can obtain the current eating plan of the target object, deliver food to the target object based on the current eating plan, and obtain the initial eating information of the target object when delivering food to the target object based on the current eating plan; and determine the target eating plan of the target object based on the initial eating information, historical eating information and current eating plan, and deliver food to the target object based on the target eating plan. For more explanation of the above examples, please refer to the following part of this specification. In some embodiments, the processor 150 may include one or more sub-processing devices (for example, a single-core processing device or a multi-core multi-core processing device). By way of example only, the processor 150 may include a central processing unit, an application specific integrated circuit, a dedicated instruction processor, a graphics processor, a physical processor, a digital signal processor, a controller, a microcontroller unit, a microprocessor, or the like, or any combination thereof.

[0033] It should be noted that the application scenario 100 of the intelligent feeding device is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those skilled in the art, various modifications or variations can be made based on the description of this specification.

[0034] In some embodiments, the application scenario 100 of the intelligent feeding device may further include an image acquisition device 160, which is used to capture images of the target subject's feeding area (e.g., one or more of a target image, a feeding image, and a food bowl image). For example, the image acquisition device 160 may capture the feeding area 170 during the target subject's corresponding feeding time period to obtain the target image. For another example, the target feeding plan may further include multiple sub-feeding plans, and after the feeder 120 completes feeding based on each sub-feeding plan, the image acquisition device 160 may also capture a feeding image of the feeding area. For another example, after the feeder 120 completes feeding the target subject based on the feeding plan, the image acquisition device 160 may also capture a food bowl image of the food bowl used by the target subject. For more information on the aforementioned target images, feeding images, and food bowl images, please refer to the relevant description below in this specification. The image acquisition device 160 may be implemented using one or more cameras provided on the feeder 120, or may be implemented using one or more home cameras. The image acquired by the image acquisition device 160 may be transmitted to the processor 150 via the network 140 .

[0035] In some embodiments, the application scenario 100 of the smart feeding device may further include an audio player ( Figure 1 (not shown), when food is delivered to the target object based on the target eating plan, the aforementioned audio player can play the reminder audio corresponding to the target object.

[0036] In some embodiments, the application scenario 100 of the smart feeding device may further include a lighting device ( Figure 1 (not shown), when food is delivered to the target object based on the target eating plan, the aforementioned lighting device can turn on the reminder light corresponding to the target object.

[0037] In some embodiments, multiple components of the smart feeding device application scenario 100 can be integrated into a single device. For example, the processor 150 and / or the image acquisition device 160 in the smart feeding device application scenario 100 can be integrated into the feeder 120. For another example, the smart feeding device application scenario 100 can be implemented on other devices to achieve similar or different functions. However, the aforementioned changes and modifications do not depart from the scope of this specification.

[0038] Figure 2 It is a schematic structural diagram of an intelligent feeding device according to some embodiments of this specification.

[0039] The intelligent feeding device 200 can be used to automatically and individually feed the feeding object, thereby reducing manual operation and facilitating daily feeding of pets.

[0040] like Figure 2 As shown, the intelligent feeding device 200 may include a feeder 120 and a processor 150 .

[0041] The feeder 120 can be configured to store and dispense pet food. For more information about the feeder 120, see Figure 1 In some embodiments, the feeder 120 may include one or more feeding ports, each of which may correspond to a food bowl corresponding to a pet, thereby enabling a single feeder 120 to feed multiple pets, reducing costs while also facilitating operations such as changing food and cleaning.

[0042] The processor 150 can be configured to obtain the current eating plan of the target object, deliver food to the target object based on the current eating plan, and obtain the initial eating information of the target object when delivering food to the target object based on the current eating plan; and determine the target eating plan of the target object based on the initial eating information, historical eating information and the current eating plan, and deliver food to the target object based on the target eating plan.

[0043] In some embodiments, the processor 150 is further configured to determine a current eating plan of the target subject based on the first subject information and the initial eating plan of the target subject through a same type eating model.

[0044] In some embodiments, the processor 150 is further configured to obtain the target subject's eating goal; and determine the target eating plan of the target subject based on the eating goal, the initial eating information, the historical eating information, and the current eating plan.

[0045] In some embodiments, the processor 150 is further configured to adjust the current eating plan through a plan adjustment strategy based on the eating goal, the current eating information, and the historical eating data, to determine the target eating plan of the target subject.

[0046] In some embodiments, the processor 150 is further configured to obtain a target eating model of the target object based on the initial eating information, the historical eating information, and the current eating plan; and determine the target eating plan of the target object through the target eating model based on the second object information of the target object, the current eating plan, and the eating goal.

[0047] In some embodiments, the processor 150 is further configured to determine the eating time period of the target object based on the target eating plan; obtain a target image of the eating area corresponding to the target object within the eating time period; determine the object to be eaten in the eating area based on the target image; and when the object to be eaten includes the target object, deliver food to the target object based on the target eating plan.

[0048] In some embodiments, the processor 150 is further configured to play a reminder audio corresponding to the target object and / or turn on a reminder light corresponding to the target object when food is delivered to the target object based on the target eating plan.

[0049] In some embodiments, the target eating plan includes multiple sub-eating plans for different stages, and the processor 150 is further configured to deliver food to the target subject stage by stage based on the sub-eating plans for different stages. In some embodiments, the processor 150 is further configured to control the feeder to deliver food based on the sub-eating plan for each stage; obtain an eating image of the eating area; determine the eating object in the eating area based on the eating image; and, when the eating object includes other objects besides the target subject, stop controlling the feeder to deliver food to the target subject based on the sub-eating plan for the next stage.

[0050] The smart feeding device 200 may also include other components. For example, the smart feeding device 200 may include a memory ( Figure 2 The aforementioned memory can be used for data related to the intelligent feeding device 200 (e.g., initial feeding plan, current feeding plan, target feeding plan, etc.). For another example, the intelligent feeding device 200 can also include an image acquisition device 160. For more information about the image acquisition device 160, please refer to Figure 1 And its related description. In some embodiments, the processor 150 can also obtain at least one of the target image, eating image or food bowl image through a home camera set outside the smart feeding device 200. By obtaining relevant images through one or more home cameras set outside the smart feeding device 200, the user does not need to purchase other additional cameras, which can reduce the user's usage cost and reduce resource waste. In addition, compared with the camera set in the smart feeding device 200, the home camera can have a larger field of view and can obtain relevant images located in different eating areas. For another example, the smart feeding device 200 can also include a lighting device ( Figure 2 (not shown), the aforementioned lighting device can be configured to turn on the reminder light corresponding to the target object when food is delivered to the target object based on the target eating plan. This setting can guide the target object to understand the reminder light when it is eating, achieve targeted feeding, and avoid food snatching behavior. For example, the intelligent feeding device 200 can also include an audio player ( Figure 2 (not shown), the aforementioned audio player can be configured to play the reminder audio corresponding to the target object when food is delivered to the target object based on the target feeding plan. Through this setting, the target object can be guided to understand the reminder audio when eating, achieve targeted feeding, and avoid food snatching behavior.

[0051] It should be understood that Figure 2 The illustrated intelligent feeding device 200 and its components can be implemented in various ways. It should be noted that the above description of the intelligent feeding device 200 and its components is for illustrative purposes only and does not limit this specification to the illustrated embodiments. It is understood that those skilled in the art, after understanding the principles of the device, may arbitrarily combine the components or construct sub-devices that connect to other components without departing from these principles. Such variations are within the scope of this specification.

[0052] Figure 3 is an exemplary flow chart of the intelligent feeding method according to some embodiments of this specification.

[0053] In some embodiments, process 300 may be performed by a processor of a smart feeding device (e.g., Figure 2The processor 150 of the smart feeding device 200 shown in FIG. Figure 3 As shown, process 300 may include the following steps:

[0054] Step 310: Obtain the current eating plan of the target subject, and deliver food to the target subject based on the current eating plan.

[0055] The current feeding plan may refer to the feeding plan currently being executed by the target subject. A feeding plan refers to a feeding plan for a feeding subject. The intelligent feeding device may store one or more feeding plans, each of which may correspond to a feeding subject. Each feeding subject may correspond to a different feeding plan, and each feeding subject may correspond to multiple feeding plans. For example, a cat may correspond to three feeding plans for different time periods, and the three feeding plans for different time periods may be the same or different.

[0056] For each feeding plan, the feeding object corresponding to the feeding plan is the target object. Later in this manual, the intelligent feeding method will be described based on the target object.

[0057] The feeding plan may at least include the target subject's feeding time period and feeding amount. The feeding amount refers to the weight of pet food delivered by the feeder during the feeding time period. The feeding time period refers to the feeding time period set for the target subject. During the feeding time period, the feeder will deliver pet food of a weight corresponding to the feeding amount to the target subject. For example, the current feeding plan may at least include the target subject's current feeding time period and the current feeding amount required. The feeding plan may also include other relevant parameters, for example, the feeding plan may also include the feeding speed.

[0058] The current eating plan can be obtained in a variety of ways. For example, the current eating plan can be obtained through user input. For another example, the processor can also directly determine the initial eating plan as the current eating plan. For more information about the initial eating plan, please refer to the relevant description below in this specification.

[0059] In some embodiments, the target eating plan of the target object determined when the processor last executed process 300 can be determined as the current eating plan for this execution of process 300, thereby achieving continuous iterative update and adjustment of the eating plan of the target object, so that the eating plan can adapt to the current needs and preferences of the target object, ensuring that the target object can obtain the required nutrients and protect the health of the target object.

[0060] In some embodiments, the processor may further determine a current eating regimen of the target subject based on the first subject information of the target subject.

[0061] The first object information may refer to the object information of the target object before the food is delivered to the target object based on the current eating plan. The object information may refer to information reflecting the physiological condition of the target object. For example, the object information may include but is not limited to one or more of the target object's breed, age, gender, weight, blood sugar level, heart rate, activity level, etc. The aforementioned first object information can be obtained in a variety of ways. For example, the user can obtain the first object information through a user terminal (for example, Figure 1 The user terminal shown in the figure) inputs the first object information, and the processor can obtain the first object information input by the user. For another example, the processor can capture an image with the target object through the image acquisition device 160, and perform image analysis on the aforementioned image to obtain the first object information. In addition, the first object information can also be obtained through an Internet of Things (IoT) device. For example, the target object wears a wearable device, and the aforementioned wearable device can provide data such as the heart rate and activity level of the target object. For another example, the target object can also wear a continuous blood glucose monitoring device, and the aforementioned continuous blood glucose monitoring device can provide blood glucose fluctuations in real time.

[0062] When the processor executes process 300 for the first time, the processor may determine the current eating plan of the target subject based on the first subject information of the target subject.

[0063] In some embodiments, the processor may determine the current feeding plan of the target object based on the first object information of the target object and through a preset feeding rule.

[0064] In some embodiments, the processor may further determine the current eating plan of the target object based on the first object information and the initial eating plan of the target object by using a same type eating model.

[0065] The aforementioned initial dietary regimen may be the dietary regimen of the target subject prior to the iterative update and adjustment of the dietary regimen of the target subject based on process 300. For example, before executing process 300, the processor may determine the current dietary regimen of the target subject based on the first subject information of the target subject and the initial dietary regimen. The processor may optimize the dietary regimen based on the target subject's original dietary regimen, and may try to maintain the continuity of the dietary regimen of the target subject, for example, by maintaining the same food type to minimize the impact of changing the food on the target subject.

[0066] The aforementioned initial eating plan can be obtained through user input. For example, the user can obtain the initial eating plan through a user terminal (e.g., Figure 1 The user terminal shown in the figure) inputs the initial eating plan, and the processor can obtain the initial eating plan input by the user.

[0067] The processor can input the first subject information and the initial eating plan into a similar eating model, and the output of the similar eating model is the current eating plan of the target subject. The aforementioned similar eating model can be a deep learning model or any other machine learning model that can achieve its function.

[0068] The aforementioned same type of eating model can be obtained by training a first training sample with a first label. The first training sample can be the sample first object information and the sample initial eating plan of a similar object corresponding to the target object, and the first label can be the sample current eating plan of the similar object.

[0069] The first object information of the sample is the object information of the similar object before food is delivered to the similar object based on the current eating plan of the sample.

[0070] The similar object may be an object with a similar physiological condition to the target object. The processor may obtain sample first object information of multiple feeding objects, construct a feature vector based on the sample first object information and the first object information, determine sample first object information whose vector distance to the feature vector of the first object information is less than a preset distance threshold, and determine the feeding object corresponding to the determined sample first object information as a similar object to the target object.

[0071] For each similar subject, the processor can obtain sample first subject information and sample second subject information corresponding to the similar subject, determine whether the sample first subject information and sample second subject information corresponding to the similar subject meet the preset feeding conditions, and when the sample first subject information and sample second subject information corresponding to the similar subject meet the preset feeding conditions, obtain the adjusted eating plan of the similar subject as the sample current eating plan, and obtain the eating plan of the similar subject before the adjustment as the sample initial eating plan. The aforementioned sample second subject information can be the object information of the similar subject after the food is fed to the similar subject based on the adjusted eating plan. The preset feeding conditions can be conditions that indicate that the adjusted eating plan of the similar subject is reasonable. For example, the preset feeding conditions can include that the weight of the similar subject in the sample second subject information and the weight change value of the similar subject in the sample first subject information are within a preset weight range (e.g., 0 to +50g). For another example, the preset feeding conditions can also include that the blood sugar stability of the similar subject in the sample second subject information and the blood sugar stability of the similar subject in the sample first subject information are within a preset stability range.

[0072] In some embodiments, the input of the aforementioned same-type eating model also includes the eating goal of the target object. Correspondingly, the aforementioned preset feeding conditions can be determined based on the eating goal of the target object. For example, in the preset feeding conditions, the weight of the similar object in the sample second object information and the weight change value of the similar object in the sample first object information meet the setting of the target weight change value in the eating goal. For another example, the preset feeding conditions may also include the blood glucose value of the similar object in the sample second object information and the blood glucose stability of the similar object in the sample first object information meet the setting of the target blood glucose stability in the eating goal. Correspondingly, when training the same-type eating model, the first label also includes the sample eating goals of similar objects. For more information about eating goals, please refer to the relevant description below in this specification.

[0073] Some embodiments of this specification are based on the first object information and initial eating plan of the target object. Through the same type of eating model, the current eating plan suitable for the target object can be quickly and accurately determined to ensure the reasonable eating of the target object and lay a good foundation for the iteration of the eating plan of the target object.

[0074] The processor can control the feeder (e.g., Figure 2 The feeder 120 shown in the figure delivers pet food of a weight corresponding to the feeding amount in the current feeding plan to the target object.

[0075] Step 320 : obtaining the current eating information of the target object when food is delivered to the target object based on the current eating plan.

[0076] Current eating information is the feedback information provided by the target subject after the target subject is fed food based on the current eating plan. For example, the current eating information may include the target subject's food intake, fastest eating speed, average eating speed, total eating time, single continuous eating time, whether the target subject is a picky eater, etc. For another example, the current eating information may also include the target subject's degree of fullness after eating, the target subject's preference for the corresponding pet food, and whether the target subject burps, vomits, or experiences indigestion after eating. For another example, the current eating information may also include the target subject's blood sugar stability after eating, weight change value, and the target subject's actual calorie intake value.

[0077] The current eating information can be obtained in a variety of ways. For example, the current eating information can be obtained through user input. For another example, after feeding the target subject based on the current eating plan, the processor can continuously obtain multiple images containing the target subject through an image acquisition device, and perform image analysis on the aforementioned multiple images to determine the current eating information. For another example, after feeding the target subject based on the eating plan, an image of the food bowl used by the target subject is obtained. The processor can continuously obtain multiple images containing the target subject through an image acquisition device, and perform image analysis on the aforementioned food bowl images to determine the amount of food consumed in the current eating information.

[0078] Step 330 : Determine a target eating plan for the target subject based on the current eating information, historical eating data, and the current eating plan, and deliver food to the target subject based on the target eating plan.

[0079] The historical eating data may be data related to the target subject's previous eating. The historical eating data may include historical eating plans and historical eating information, wherein the historical eating plans may be eating plans previously executed by the target subject, and the historical eating information may be feedback information from the target subject after food is delivered to the target subject based on each historical eating plan. Each time the processor executes process 300, the acquired data (e.g., current eating information) or the determined data (e.g., target eating plan) may be stored in the memory. When necessary, the processor may obtain the data stored in the memory, for example, the processor may obtain the historical eating data of the target subject in the memory.

[0080] The target feeding plan may refer to the next feeding plan to be executed by the target subject. The target feeding plan may at least include the feeding time period for the target subject's next feeding and the next amount of food to be fed. The target feeding plan may also include other relevant parameters, for example, the target feeding plan may also include the feeding speed of the intelligent feeding device for the next feeding.

[0081] In some embodiments, the processor can perform modeling or use various data analysis algorithms, such as regression analysis, discriminant analysis, etc., to analyze and process current eating information, historical eating data, and current eating plan to determine the target eating plan for the target object.

[0082] The processor can analyze and process the historical eating data to build a eating database for the target object. The aforementioned eating database may include but is not limited to the target object's preference for various pet foods, the corresponding relationship between the digestion time of different food ingredients and the pet's satiety, the glycemic index, the target object's metabolic rate, the food ingredients that may cause the target object's blood sugar to rise, allergies, vomiting or diarrhea, the target object's eating time preference (for example, a specific eating time period), food texture preference (for example, dry food or wet food), etc., and dynamically update the aforementioned eating database through the current eating information and the current eating plan, and then optimize the current eating plan based on the aforementioned updated eating database to obtain a target eating plan. For example, the processor can determine the digestion time after the target object's current meal based on the updated eating database, thereby determining the eating time period for the next meal in the target eating plan. For another example, the processor can determine that the target object's eating speed is too fast based on the updated eating database, thereby determining the feeding speed of the intelligent feeding device for the next feeding in the target eating plan.

[0083] In some embodiments, the processor may obtain a target subject's eating goal and determine a target eating plan for the target subject based on the eating goal, current eating information, historical eating data, and current eating plan.

[0084] The eating goal may be a goal for the target subject's next meal. In some embodiments, the eating goal may include at least one of a target blood sugar stability, a target weight change value, and a target calorie intake of the target subject.

[0085] The target blood glucose stability is the stability of the target subject's blood glucose after the next meal compared to the current blood glucose level. The target blood glucose stability can be represented by a score (e.g., 1 to 10 points), with a larger score indicating more stable blood glucose in the target subject. The target blood glucose stability can be related to the blood glucose level and / or the blood glucose variation value. The processor can determine the target subject's blood glucose level after the next meal based on the current blood glucose level, using the target blood glucose stability, based on a preset blood glucose correspondence.

[0086] The target weight change value is the change in the target subject's weight after the next meal compared to the current weight. The target weight change value can be represented by a specific weight value. It is understandable that the aforementioned target weight change value can be a positive value (for example, +10g) or a negative value (for example, -10g). When the target weight change value is positive, it indicates that the target subject needs to gain weight; when the target weight change value is negative, it indicates that the target subject needs to lose weight.

[0087] The target calorie intake is the target calorie intake for the next meal. The target calorie intake change can be expressed as a specific calorie value. For example, the target calorie intake can be 60kcal.

[0088] In some embodiments, the eating goal may also include other data for the target subject's next meal. For example, the eating goal may also include the target subject's total food intake for the next meal. For another example, the eating goal may also include the target subject's next meal without vomiting, burping, or indigestion.

[0089] Eating goals can be obtained in a variety of ways. For example, eating goals can be obtained through user input. For another example, the processor can analyze and process the current eating information and historical eating information of the target object to determine the eating goal. For example, after analyzing and processing the current eating information and historical eating information of the target object, the processor determines that the target object's current blood sugar is too high and needs to be controlled, thereby further determining the target blood sugar stability in the eating goal. For another example, the processor can determine the eating goal based on the integration of other data sources. For example, the processor can analyze the activity level and exercise level of the target object through an image acquisition device, and determine the target calorie intake of the target object based on the aforementioned activity level and exercise level.

[0090] In some embodiments of this specification, by setting a dietary goal for a target subject, a target dietary plan that better matches the target subject's health condition can be obtained, thereby achieving personalized feeding for the target subject. For example, if the target subject has diabetes, a target dietary plan can help maintain the target subject's blood sugar level.

[0091] In some embodiments, the processor can adjust the current eating plan based on the eating goal, current eating information, and historical eating data through a plan adjustment strategy to obtain a target eating plan. The aforementioned plan adjustment strategy is a strategy for adjusting the current eating plan. The aforementioned plan adjustment strategy can be obtained through presets.

[0092] In some embodiments, the aforementioned scheme adjustment strategy can also be obtained through optimization iteration. During the optimization iteration process, the scheme adjustment strategy may include a scheme adjustment strategy to be analyzed and / or a target scheme adjustment strategy. Specifically, the processor may determine a plurality of similar objects of the target object, and the eating goals of the aforementioned plurality of similar objects are the same or similar to the target object (for example, the eating goals are all related to weight loss). For more information about similar objects, please refer to the relevant description above in this specification. The processor may determine the target object and similar objects of the target object as objects to be analyzed, and then group the aforementioned plurality of objects to be analyzed. For each group, the processor may adjust the current eating scheme corresponding to the object to be analyzed corresponding to the group based on the eating goals, current eating information, and historical eating data corresponding to each object to be analyzed, and obtain the eating scheme corresponding to the object to be analyzed corresponding to the group (for example, the target eating scheme corresponding to the target object). Wherein, the scheme adjustment strategy to be analyzed corresponding to each group of objects to be analyzed is different. After feeding each object to be analyzed based on the eating plan, the processor can obtain the object information of each group of objects to be analyzed, and analyze and process the object information of each group of objects to be analyzed to determine the group among multiple groups of objects to be analyzed whose results after eating are most consistent with the eating target. For example, the processor can determine the group among multiple groups of objects to be analyzed whose weight change value is closest to the weight change value in the eating target. The processor can determine the adjustment strategy of the plan to be analyzed as the target plan adjustment strategy, and process the aforementioned multiple objects to be analyzed based on the target plan adjustment strategy.

[0093] It is worth noting that in order to avoid reducing the impact of interfering variables and ensure the comparability of adjustment strategies for different analysis plans, the environment of each group of subjects to be analyzed (such as temperature, humidity, feeding time) should be as similar as possible, the type of food in the eating plan should be as similar as possible, and the monitoring frequency of subject information (such as the fixed number of blood glucose tests per day) should be as similar as possible.

[0094] In some embodiments, the processor may further adjust the target solution adjustment strategy (e.g., adjusting the method for determining the feeding frequency, food composition, time arrangement, etc. in the target solution adjustment strategy), obtain multiple new solution adjustment strategies to be analyzed, and re-analyze and process the multiple objects to be analyzed based on the aforementioned multiple solution adjustment strategies to be analyzed, and continuously determine new target solution adjustment strategies in a loop. When the processor first executes the aforementioned solution adjustment strategy loop iteration scheme, the solution adjustment strategy to be analyzed may be determined by a preset method.

[0095] Some embodiments of this specification use the aforementioned method to iterate the optimization of the plan adjustment strategy corresponding to the target object, implement a data-driven optimization cycle, find the plan adjustment strategy that is currently most suitable for the target object, and continuously optimize the target eating plan corresponding to the target object.

[0096] In some embodiments, the processor can determine an updated eating database for the target object based on current eating information, historical eating data, and the current eating plan, and optimize the current eating plan according to the eating goal based on the updated eating database to obtain a target eating plan.

[0097] In some embodiments, the processor can obtain a target eating model of the target object based on the first object information, current eating information, historical eating data and current eating plan of the target object; and determine the target eating plan of the target object through the target eating model based on the second object information, current eating plan and eating goal of the target object.

[0098] The second object information may refer to the object information of the target object after the food is delivered to the target object based on the current eating plan. The specific content and acquisition method of the second object information can refer to the first object information.

[0099] The target eating model is a machine learning model that matches the target subject's current eating habits. The target eating model can be a deep learning model or any other machine learning model that can achieve its functionality. The target eating model's inputs can include information about the second subject, the current eating plan, and the eating goal, and its output can include the target eating plan.

[0100] The target eating model can be obtained by training a second training sample with a second label.

[0101] In some embodiments, the processor can use the target object's object information at each stage (for example, the object information of the current stage, i.e., the first object information), the eating results of the next stage corresponding to the stage, and the eating plan of the stage as the second training sample, and the eating plan of the next stage corresponding to the stage as the second label, and the target eating model can be directly trained based on the second training sample with the second label. Among them, the processor can obtain the historical object information of the target object, and determine the object information of the target object at each stage based on the historical object information and the first object information. The aforementioned historical object information can be the object information of the target object before and after each eating, and the historical object information can be obtained from the memory. The eating plan of the aforementioned target object at each stage can be determined based on the current eating plan and historical eating plan of the target object. The eating results of the aforementioned target object at each stage can be determined based on the current eating information and historical eating information of the target object. For example, when the current eating information includes the target subject's blood sugar stability, weight change value, and actual calorie intake value after eating, the processor can directly determine the target subject's eating results at each stage based on the target subject's current eating information and historical eating information. For another example, when the current eating information does not include the target subject's blood sugar stability, weight change value, and actual calorie intake value after eating, the processor can analyze the target subject's current eating information and historical eating information to determine the target subject's blood sugar stability, weight change value, and calorie intake after this meal.

[0102] In some embodiments, the processor can also iteratively update the target eating model so that the target eating model is more consistent with the current eating situation of the target object, enhance the robustness and generalization ability of the target eating model, and reduce the amount of computation required for direct training to obtain the target eating model, thereby reducing computing resource consumption.

[0103] Specifically, the processor can obtain the initial eating model of the target object, and the aforementioned initial eating model is a machine learning model that conforms to the eating conditions of the target object last time. The processor can determine the target eating model obtained last time as the initial eating model for this time. Specifically, when the processor iteratively updates the target eating model for the first time, the same type of eating model can be determined as the initial eating model. The processor can use the first object information and the current eating information as the second training sample, use the current eating plan as the second label, and continue to iteratively update the initial eating model based on the second training sample with the second label to obtain the target eating model.

[0104] After determining the target eating plan, the processor can control the intelligent feeding device to deliver food to the target object based on the target eating plan.

[0105] In some embodiments of the present specification, through the aforementioned process 300, a target subject can be more accurately fed intelligently, specifically meeting the dietary and health needs of the target subject, achieving personalized feeding for the target subject, and protecting the health of the target subject. For example, the processor can achieve this by adjusting the eating speed and frequency in the target eating plan, so that the target subject can eat small meals frequently to ensure the target blood sugar stability of the target subject. The processor can continuously execute process 300 to obtain the target eating plan that best meets the dietary and health needs of the target subject.

[0106] In some embodiments, the processor may determine a health management plan for the target subject based on the target subject's target dietary plan. The health management plan may be a plan related to the target subject's health. For example, the health management plan may include, but is not limited to, the target subject's amount of exercise, amount of water consumed, timing of water consumption, insulin dosage, medication feeding schedule, nutrient intake ratio, etc.

[0107] The processor can determine the health management plan of the target object based on the target eating plan of the target object through the preset health management rules. For example, the health management rules may include feeding the target object with medicine 2 hours after a meal. The processor can determine the medicine feeding time in the health management plan of the target object based on the eating time period in the target eating plan of the target object through the aforementioned preset health management rules. The health management rules can also be related to other devices. For example, related to the water dispenser corresponding to the target object. For example, the health management rules can also include that the target object cannot drink water within 30 minutes after a meal to prevent vomiting. Correspondingly, the processor can also control the water dispenser corresponding to the target object not to discharge water within 30 minutes after the target object has eaten. Furthermore, the processor can also send the aforementioned health management plan to the user terminal (for example, Figure 1 The user terminal 130 shown in the figure) allows the user to perform health management on the target object.

[0108] Some embodiments of this specification may determine a health management plan for a target object based on the target eating plan of the target object, and assist the user in performing personalized health management for the target object.

[0109] It is understandable that a user may feed multiple pets. If the smart feeding device directly delivers the corresponding amount of pet food within the feeding time period based on the target feeding plan, multiple pets may compete for food, resulting in the target pet being unable to eat according to the target feeding plan, which may affect the target pet's health. The following part of this manual explains how to prevent food competition between multiple pets.

[0110] In some embodiments, the processor may be based on Figure 4The process 400 shown is to deliver food to the target object, thereby avoiding food snatching behavior among multiple pets.

[0111] Figure 4 is an exemplary flow chart of the intelligent feeding method according to some embodiments of the present specification. In some embodiments, process 400 can be performed by a processor of the intelligent feeding device (e.g., Figure 2 The processor 150 of the smart feeding device 200 shown in FIG. Figure 4 As shown, process 400 may include the following steps:

[0112] In step 410 , the processor determines a meal time period for the target subject based on the target meal plan of the target subject.

[0113] In step 420 , the processor obtains a target image of the eating area corresponding to the target object during the eating time period.

[0114] The eating area corresponding to the target object refers to the area where the target object eats during the eating time period. The eating area of each target object can be the same or different.

[0115] The eating area corresponding to the target object can be determined in a variety of ways. For example, the user can use a user terminal (e.g., Figure 1 The user terminal 130 (shown) obtains a regional image of the area where the feeder is located and marks the target subject's feeding area in the regional image. For another example, the processor can assign a feeder delivery port to the target subject and obtain a regional image of the area where the feeder is located. Based on the regional image and the delivery port corresponding to the target subject, the processor determines the area within a preset range of the delivery port as the target subject's feeding area.

[0116] The target image refers to an image of the eating area corresponding to the target object during the eating time period. The target image is obtained before the food is delivered. Figure 1 The image acquisition device 160 shown in the figure can capture images of the eating area corresponding to the target object during the eating time period to obtain a target image, and the processor can obtain the aforementioned target image from the image acquisition device.

[0117] In step 430 , the processor determines the object to be eaten in the eating area based on the target image.

[0118] The object to be fed is the feeding object located in the feeding area corresponding to the target object during the feeding time period. The object to be fed may include or exclude the target object.

[0119] The target image may include one or more objects to be eaten, or may not include any objects to be eaten. When the target image does not include any objects to be eaten, the processor may continue to acquire target images until the acquired target image includes any objects to be eaten.

[0120] In some embodiments, the processor may perform modeling or employ various data analysis algorithms, such as regression analysis, discriminant analysis, etc., to analyze and process the target image and determine the object to be eaten within the eating area.

[0121] In some embodiments, the processor may perform image recognition on the target image through a variety of methods to determine feature information of the object to be eaten.

[0122] Feature information is information that can reflect the individual differences of the subject being fed. In some embodiments, the feature information may include one or more of the subject's breed, body shape, and texture characteristics. The aforementioned breed characteristics characterize the subject's breed. For example, if the target subject is a Siamese cat, the breed characteristics may include facial coloration. For another example, if the target subject is a hairless cat, the breed characteristics may include fur-free skin. Body shape characteristics characterize the subject's size. Body shape characteristics may represent at least one of the subject's height, length, and width. Texture characteristics characterize the subject's pattern. In some embodiments, the feature information may also include additional features of the subject being fed. These additional features are additional features added to the subject being fed. For example, additional features may include the color or pattern of a scarf or foreign object worn by the subject. It is worth noting that when there are multiple subjects with similar breed, body shape, and texture characteristics, the user can add different additional features to similar subjects to facilitate identification by the processor. For example, if a user's home has two black cats of similar size, the user can give them different colored scarves. The processor can then determine the additional feature of the two black cats, namely the color of the scarves, to distinguish them. Some embodiments of this specification improve the accuracy of processor recognition by adding additional features to similar feeding objects, ensuring the smooth implementation of intelligent feeding methods.

[0123] For example, the processor may analyze and process the target image through an image recognition algorithm to determine feature information of the object to be eaten.

[0124] In some embodiments, the processor may also perform image recognition on the target image through a feature extraction model to determine the feature information of the object to be eaten. The feature extraction model may be one or a combination of a convolutional neural network, a deep learning model, or any other machine learning model that can achieve its function. The input of the feature extraction model is the target image, and the output is the feature information of each object to be eaten. The feature extraction model can be obtained by training multiple groups of third training samples with third labels. The third training sample may include a sample image of the sample object, and the third label may be the feature information of the sample object. The third training sample can be obtained by photographing the sample object, and the third label can be obtained by manually annotating the sample image.

[0125] In some embodiments, the processor can determine the objects to be fed within the feeding area based on the feature information. The processor can obtain the feature information of each feeding object. For example, a user can upload images of each feeding object through a user terminal, and the processor can perform image recognition on the aforementioned images using a feature extraction model to determine the feature information of each feeding object. The processor can compare the feature information of each feeding object with the feature information of the objects to be fed using various methods (e.g., vector distance or machine learning models) to determine the objects to be fed.

[0126] For example, the processor may determine that the target image includes feature information of two objects to be fed, and generate two third feature vectors based on the feature information of each of the two objects to be fed, and generate multiple fourth feature vectors based on the feature information of each feeding object. For each third feature vector, the processor may determine the vector distance between the third feature vector and the multiple fourth feature vectors, and then determine the feeding object corresponding to the fourth feature vector with the smallest vector distance to the third feature vector as the feeding object to be fed.

[0127] Step 440: When the object to be fed includes a target object, the processor delivers food to the target object based on the target feeding plan.

[0128] In some embodiments, after determining that the object to be fed includes the target object, the processor may determine the amount of food to be fed to the target object in the feeding time period based on the target feeding plan, and control the feeder to feed the pet food of the corresponding weight.

[0129] In some embodiments, after determining that the object to be fed includes the target object, the processor may further determine whether there are other objects other than the target object. When the object to be fed includes and only includes the target object, the processor determines the amount of food to be fed to the target object in the feeding time period based on the feeding plan, and controls the feeder to deliver pet food of the corresponding weight.

[0130] When the object to be eaten does not include the target object, the processor may continue to acquire the target image until the target object is identified.

[0131] Some embodiments of this specification can automatically deliver food to the target object by identifying the target object during the feeding time period, making it easier for users to feed their pets and improving the user experience.

[0132] In some embodiments, a reminder light and / or a reminder audio may be set to avoid food grabbing among multiple pets.

[0133] In some embodiments, when food is delivered to a target subject based on a target eating plan, and the subject to be fed includes the target subject, the processor may control the audio player to play a reminder audio corresponding to the target subject. The reminder audio is an audio that reminds the target subject to eat. The reminder audio corresponding to the target subject may be preset, for example, a user may set different reminder audios for different target subjects at different eating time periods through the user terminal.

[0134] In some embodiments, when food is delivered to the target object based on the target feeding plan, and the object to be fed includes the target object, the processor may further control the lighting device to turn on the reminder light corresponding to the target object. The reminder light is a light that reminds the target object to eat. The reminder light corresponding to the target object can be determined by preset, for example, the user sets reminder lights of different colors for different target objects in different feeding time periods through the user terminal. In addition, when the lighting in the feeding area is insufficient (for example, at night or on a cloudy day), the processor may further control the lighting device to illuminate the feeding area so that the image acquisition device can obtain a target image with more feature information, thereby improving the processor's recognition accuracy of the feeding object in the feeding area.

[0135] Some embodiments of this specification can specifically remind target objects to eat at different feeding time periods by setting different corresponding reminder lights and / or reminder audios for different feeding objects, cultivate the pet's eating habits at the corresponding time, and thus avoid food snatching behavior among multiple pets.

[0136] In some embodiments, when the target object is not included in the object to be eaten within the eating time period corresponding to the target eating plan, the processor may also control the audio player to play the reminder audio corresponding to the target object and / or control the lighting device to turn on the reminder light corresponding to the target object to remind the target object to eat. After the reminder audio and / or reminder light are played, the processor may obtain the target image to determine whether the target object is in the eating area. In response to the target object not being in the eating area, the processor may again control the audio player to play the reminder audio corresponding to the target object and / or control the lighting device to turn on the reminder light corresponding to the target object, and obtain the target image for judgment until the target object is detected to be in the eating area, or the number of times the reminder audio is played exceeds a preset reminder number threshold (for example, 3 times). When the number of times the reminder audio is played exceeds a preset reminder number threshold, the processor may delay the eating time period corresponding to the eating plan of the target object, wherein the delay time can be determined by preset. For example, the delay time is 1 hour. In some embodiments, for each eating plan of a target subject, when the number of times the eating time period in the eating plan is delayed exceeds a preset delay threshold, the processor can determine the target subject's actual eating time period in the eating plan from the historical eating data, and adjust the eating time period in the target eating plan based on the aforementioned actual eating time period. For example, when the historical eating data of a target subject indicates that the eating time period has been delayed more than a preset delay threshold of 5 times, the processor can determine the target subject's actual eating time period for the first five times from the historical eating data, and perform modeling or various data analysis algorithms, such as regression analysis and discriminant analysis, on the first five actual eating time periods to determine the eating time period in the target eating plan.

[0137] In some embodiments, other methods can be used to prevent food snatching between multiple pets. For example, the feeding time periods of multiple feeding subjects can be staggered to avoid direct competition caused by overlapping feeding periods. For another example, when the feeding time periods of multiple feeding subjects overlap, the processor can control the intelligent feeding device to adjust the feeding speed to accommodate feeding subjects with different appetites and eating speeds, ensuring that they can complete their meals within a similar timeframe. When a slower feeding subject has not yet finished feeding, the processor can delay the release of pet food to a faster feeding subject, preventing the faster feeding subject from moving to the feeding area of another feeding subject and competing for food. For another example, multiple feeding subjects can be assigned separate feeding areas. For another example, a water sprayer can be installed on the intelligent feeding device to force any pets competing for food to leave if food snatching occurs. For another example, a blocking device can be installed on the intelligent feeding device to ensure that only the target subject can eat in the feeding area, thereby preventing food snatching.

[0138] The intelligent feeding device can avoid food competition among multiple pets through one or more of the aforementioned embodiments, and avoid interference from other pets when the target object is eating based on the target eating plan, resulting in interruption of the target object's eating and affecting the health management of the target object. At the same time, it can also avoid health problems caused by other feeding objects eating outside of their corresponding eating plans.

[0139] When feeding a pet, eating too quickly can cause vomiting, indigestion, and other problems, impacting the pet's health. Existing solutions for slow feeding pets include specially designed slow feeding bowls and feeding devices with switches or turntables. These bowls often have uneven interior surfaces or built-in obstructions, slowing down the pet's feeding speed. The special design of slow feeding bowls makes them difficult to clean and prone to harboring dirt, compromising hygiene and causing discomfort for pets. Feeding devices with switches or turntables are complex and can also pinch the pet during opening and closing.

[0140] The following instructions will explain how to set it up to prevent your pet from eating too quickly.

[0141] In some embodiments, the processor can prevent the pet from eating too quickly by controlling the feeding speed during the feeding regimen.

[0142] In some embodiments, during the process of delivering food to the target object, the processor can also obtain the weight of the pet food in the food bowl. When the weight of the pet food in the food bowl is less than a preset weight threshold (for example, 5g), the food delivery is continued to avoid excessive accumulation of pet food in the food bowl, thereby controlling the amount of food the pet eats each time to prevent the pet from eating too fast.

[0143] In some embodiments, the feeding plan may also include sub-feeding plans for multiple stages. For example, the target feeding plan and / or the current feeding plan may include sub-feeding plans for multiple stages. The sub-feeding plan for each stage may include a sub-feeding time period and a sub-feeding amount. For the sub-feeding plan for each stage, the sub-feeding time period may be the eating time of the target object at that stage, and the sub-feeding amount may be the weight of the pet food given to the target object at that stage. For example, a certain feeding plan includes three-stage sub-feeding plans, wherein the sub-feeding plan for the first stage includes a sub-feeding time period: 08:00-08:10 and a sub-feeding amount of 5g, and the sub-feeding plan for the second stage includes a sub-feeding time period: 08:10-08:20 and a sub-feeding amount of 5g, and 08:20-08:30 and a sub-feeding amount of 5g.

[0144] The processor can obtain the sub-eating plans for multiple stages in a variety of ways. For example, the processor can segment the target eating plan according to a preset segmentation rule to obtain the sub-eating plans for multiple stages corresponding to the target eating plan. For another example, the processor can analyze and process the target subject's current eating information to determine a segmentation method for the target eating plan, and then segment the target eating plan based on the segmentation method to obtain the sub-eating plans for multiple stages corresponding to the target eating plan. For another example, the output of the target eating model is a target eating plan that includes the sub-eating plans for multiple stages.

[0145] In some embodiments, the processor can control the intelligent feeding device to deliver food to the target subject in stages based on the multiple sub-feeding plans. For each sub-feeding plan, the processor can control the feeder to deliver pet food of a weight corresponding to the sub-feeding amount during the sub-feeding time period of the sub-feeding plan until all sub-feeding plans for each stage are completed. This configuration can control the pet's eating speed, avoiding health issues caused by overeating, facilitating cleaning, and eliminating the need for additional equipment, thereby reducing pet feeding costs.

[0146] In some embodiments, for each stage of the sub-eating plan, after the processor delivers food to the target object based on the sub-eating plan, it can also determine whether there is a food snatching phenomenon and further determine whether to continue to deliver food to the next stage. For more information about the above embodiments, please refer to Figure 5 and its related descriptions.

[0147] Figure 5 is an exemplary flow chart of a multi-stage intelligent feeding method according to some embodiments of the present specification. In some embodiments, process 500 can be performed by a processor of an intelligent feeding device (e.g., Figure 2 The processor 150 of the smart feeding device 200 shown in FIG. Figure 5 As shown, for each stage of the feeding plan, the processor may execute process 500 to determine whether to continue with the next stage of food delivery. Process 500 may include the following steps:

[0148] In step 510 , the processor delivers food based on the sub-eating plan of the current phase.

[0149] The processor may control the feeder to deliver pet food of corresponding weight in a corresponding time period based on the sub-feeding time period and the sub-feeding amount in the sub-feeding plan of the stage.

[0150] In step 520 , the processor obtains an eating image of the eating area.

[0151] A feeding image refers to an image of the feeding area corresponding to the target pet after the pet food is delivered according to the sub-feeding plan for that phase. Similar to the target image, after the processor controls the feeder to deliver food according to the sub-feeding plan for that phase, the image capture device can capture an image of the feeding area corresponding to the target pet to obtain the feeding image. The processor can obtain the aforementioned feeding image from the image capture device.

[0152] In step 530 , the processor determines the eating object in the eating area based on the eating image.

[0153] The feeding object refers to the feeding object in the target object's feeding area after the pet food is released based on the sub-feeding plan of this stage. The aforementioned feeding object can be eating, or the aforementioned feeding object can also not be eating, but just in the target object's feeding area.

[0154] The processor can perform image recognition on the eating image to determine the eating object in the eating area. For example, the processor can process the eating image using a feature extraction model to determine the feature information of the eating object; and determine the eating object based on the feature information of the eating object. For more information about feature extraction models and feature information, please refer to Figure 4 and its related descriptions.

[0155] Step 540: When the feeding objects include other objects besides the target object, the processor stops delivering food to the target object based on the sub-feeding plan of the next stage.

[0156] It is worth noting that the eating time periods in the eating plans of multiple target objects may overlap, but the eating areas of multiple target objects at the same time point do not overlap, so as to ensure the normal operation of the intelligent feeding method shown in the embodiment of this specification.

[0157] When the eating objects do not include other objects besides the target object, the processor may continue to control the feeder to deliver food to the target object based on the sub-feeding plan of the next stage; when the eating objects include other objects besides the target object, the processor may stop controlling the feeder to deliver food to the target object based on the sub-feeding plan of the next stage.

[0158] When the eating objects include other objects besides the target object, the processor can also continue to obtain the eating objects in the eating area. When the processor identifies that the eating objects in the eating area include and only include the target object, it can continue to control the feeder to deliver food to the target object based on the next stage of the sub-feeding plan.

[0159] In some embodiments, when the processor recognizes that the target object is not included in the eating area, it can also play a reminder audio and / or a reminder light to attract the target object back to the eating area. For more information about the reminder audio, please refer to the relevant description above in this specification.

[0160] Some embodiments of this specification can effectively prevent other objects other than the target object from snatching food by identifying the eating object in the eating area to determine whether to continue to release food, accurately control the food intake of each object, avoid the occurrence of obesity problems, and ensure the health of pets.

[0161] Figure 6 is an exemplary flow chart for determining the amount of food consumed by a target subject according to some embodiments of this specification. In some embodiments, process 600 may be performed by a processor of a smart feeding device (e.g., Figure 2 The processor 150 of the intelligent feeding device 200 is executed as shown. Figure 6 As shown, process 600 may include the following steps:

[0162] In step 610 , after the processor has finished feeding the target object based on the feeding plan, it obtains an image of the food bowl used by the target object.

[0163] The food bowl image refers to an image of the food bowl used by the target subject after the target subject has been fed according to a feeding plan (e.g., the current feeding plan, the target feeding plan, etc.). Similar to the target image, after the processor controls the feeder to feed the target subject according to the feeding plan (e.g., after the feeding time period in the feeding plan has ended), the image acquisition device can capture an image of the food bowl used by the target subject within the feeding area corresponding to the target subject to obtain a food bowl image. The processor can obtain the aforementioned food bowl image from the image acquisition device.

[0164] In step 620 , the processor determines the remaining weight of the food remaining in the food bowl based on the food bowl image.

[0165] In some embodiments, the processor may analyze and process the food bowl image through various methods (eg, modeling or various data analysis algorithms) to determine the remaining weight of the remaining food in the food bowl.

[0166] Exemplarily, the processor may input the food bowl image into a weight analysis model, and the output of the weight analysis model is the remaining weight of the food remaining in the food bowl. The weight analysis model may be one or more of a convolutional neural network model, a deep learning model, or any other machine learning model that can achieve its function. The weight analysis model may be obtained by training multiple sets of fourth training samples with fourth labels, wherein the fourth training samples may include sample food bowl images, and the fourth labels may include the remaining weight of the food remaining in the food bowl in the sample food bowl images. The fourth training samples may be obtained by photographing, and the fourth labels may be obtained by measuring the remaining weight of the food remaining in the food bowl in the sample food bowl images. In some embodiments, the input of the weight analysis model may also include other information. For example, the input of the weight analysis model may also include at least one of the types and brands of pet food, etc., and at least one of the types and brands of pet food may be obtained through user input. Correspondingly, when training the weight analysis model, the fourth training samples may also include at least one of the types and brands of sample pet food. By inputting at least one of the type and brand of pet food into the gravimetric analysis model, the accuracy of the output results of the gravimetric analysis model can be guaranteed, and errors caused by differences in different types and brands of pet food (for example, different water content) can be avoided.

[0167] In step 630 , the processor determines the food intake of the target subject based on the food intake plan and the remaining weight.

[0168] The processor can determine the amount of food to be fed in the feeding plan based on the feeding plan, and calculate the difference between the amount of food to be fed and the remaining weight of the remaining food. The difference is the amount of food consumed by the target object based on the feeding plan.

[0169] In some embodiments of this specification, by monitoring the remaining weight of the remaining food in the food bowl, the amount of food consumed by the target object at each meal can be understood, which helps the user to understand the feeding situation of the feeding object and the growth information of the feeding object.

[0170] It should be noted that the above descriptions of the various processes are for illustration and purpose only and do not limit the scope of application of this specification. Those skilled in the art may make various modifications and alterations to the various processes under the guidance of this specification. However, such modifications and alterations are still within the scope of this specification.

[0171] Some embodiments of the present specification also provide an intelligent feeding system, which includes: at least one storage device including a set of instructions; at least one processor communicating with the at least one storage device, wherein when the set of instructions is executed, the at least one processor is configured to cause the system to perform operations, including: obtaining a current eating plan of a target object, delivering food to the target object based on the current eating plan, and obtaining current eating information of the target object when delivering food to the target object based on the current eating plan; and determining a target eating plan for the target object based on the current eating information, historical eating data, and the current eating plan, and delivering food to the target object based on the target eating plan.

[0172] Some embodiments of the present specification also provide a computer non-transitory readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the non-transitory readable storage medium, it runs an intelligent feeding method, including: obtaining a current eating plan of a target object, delivering food to the target object based on the current eating plan, and obtaining current eating information of the target object when delivering food to the target object based on the current eating plan; and determining a target eating plan for the target object based on the current eating information, historical eating data, and the current eating plan, and delivering food to the target object based on the target eating plan.

[0173] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0174] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0175] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0176] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0177] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values are as accurate as possible within the feasible range.

[0178] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0179] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. An intelligent feeding method, comprising: Acquiring a current eating plan of a target subject, delivering food to the target subject based on the current eating plan, and acquiring current eating information of the target subject when delivering food to the target subject based on the current eating plan; as well as Based on the current eating information, historical eating data and the current eating plan, a target eating plan for the target subject is determined, and food is delivered to the target subject based on the target eating plan.

2. The method according to claim 1, wherein obtaining the current eating plan of the target subject comprises: Based on the first subject information and the initial eating plan of the target subject, a current eating plan of the target subject is determined through a same type eating model.

3. The method of claim 1 , wherein determining the target eating plan of the target subject based on the current eating information, historical eating data, and the current eating plan comprises: obtaining the target object's eating goal; as well as A target eating plan for the target subject is determined based on the eating goal, the current eating information, historical eating data, and the current eating plan.

4. The method of claim 3, wherein determining the target eating plan of the target subject based on the eating goal, the current eating information, the historical eating data, and the current eating plan comprises: Based on the eating goal, the current eating information and the historical eating data, the current eating plan is adjusted through a plan adjustment strategy to determine the target eating plan of the target subject.

5. The method of claim 3, wherein determining the target eating plan of the target subject based on the eating goal, the current eating information, the historical eating data, and the current eating plan comprises: obtaining a target eating model of the target subject based on the first subject information of the target subject, the current eating information, the historical eating data, and the current eating plan; as well as Based on the second object information of the target object, the current eating plan and the eating goal, a target eating plan of the target object is determined through the target eating model. 6 . The method of claim 3 , wherein the eating goal comprises at least one of a target blood sugar stability, a target weight change, and a target calorie intake of the target subject.

7. The method of claim 1 , further comprising: Determining a meal time period for the target subject based on the target meal plan; Acquiring a target image of the eating area corresponding to the target object during the eating time period; Determining an object to be eaten in the eating area based on the target image; as well as When the object to be fed includes the target object, food is delivered to the target object based on the target feeding plan.

8. The method of claim 1 , further comprising: When food is delivered to the target object based on the target eating plan, a reminder audio corresponding to the target object is played and / or a reminder light corresponding to the target object is turned on.

9. The method according to any one of claims 1 to 8, wherein the target eating plan comprises a plurality of sub-eating plans in stages. The delivering food to the target subject based on the target eating plan includes: Based on the sub-eating plans of the multiple stages, food is delivered to the target subject stage by stage.

10. The method of claim 9, wherein the step of delivering food to the target subject stage by stage based on the multiple-stage sub-eating plans comprises: Sub-feeding plans for each phase; Food delivery is based on the sub-feeding plan for that phase; Acquiring a feeding image of the feeding area; determining an eating object in the eating area based on the eating image; as well as When the feeding objects include other objects other than the target object, the feeding of food to the target object based on the sub-feeding plan of the next stage is stopped.

Images