Pet feeding method and device, electronic equipment and medium

Abstract

The invention relates to the technical field of pet feeding, in particular to a pet feeding method and device, electronic equipment and a medium. According to the pet feeding method, a pre-recorded feature group which is stored in advance of a pre-recorded pet needs to be acquired firstly, and the pre-recorded feature group comprises a pre-recorded pet facial feature Face ID and pre-recorded pet food information; carrying out image acquisition on a target pet and carrying out pet face detection on the acquired image to obtain a target pet face image; calling a pet recognition model to extract the face image of the target pet to obtain face features of the target pet; performing feature similarity comparison on the facial features of the target pet in a pre-recorded pet feature library, determining a matched pre-recorded pet based on Face ID in response to existence of feature similarity information meeting an identity authentication condition, and executing a pet food distribution operation or a pet food exposure operation according to pre-recorded pet food information of the matched pre-recorded pet, and it is ensured that only the authenticated pet can obtain food suitable for himself or herself, and feeding is more accurate.

Description

Technical Field

[0001] The present application relates to the field of pet feeding technology, and in particular to a pet feeding method and device, electronic equipment, and medium. Background Art

[0002] As people's living standards improve, pets are gaining a greater place in the family, and more and more families are keeping pets. However, pet feeding has always been a problem for pet owners. For example, some pets may accidentally eat food that is not suitable for them, leading to indigestion or other health problems. Therefore, to ensure that pets receive the food they need, the idea of ​​using pet facial recognition technology in conjunction with feeding and dispensing operations has emerged. However, pet facial recognition technology is easily affected by factors such as the pet's posture and lighting, resulting in slow recognition and low accuracy. Furthermore, the uncertainty of pets' movements makes it difficult for pet facial recognition to accurately feed active pets in real-world scenarios. Therefore, finding more efficient ways to feed pets remains a pressing issue in the industry. Summary of the Invention

[0003] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a pet feeding method and device, electronic equipment, and medium that can feed pets more accurately.

[0004] The pet feeding method according to the first embodiment of the present application is applied to a pet feeding device, wherein the pet feeding device is provided with a pet identification model, including:

[0005] Obtaining a pre-recorded pet feature library, the pre-recorded pet feature library including a pre-recorded feature group corresponding to a pre-recorded pet, the pre-recorded feature group including pre-recorded pet facial features of the pre-recorded pet, a unique face ID of the pre-recorded pet, and pre-recorded pet food information matching the pre-recorded pet;

[0006] Capturing images of a target pet and performing pet face detection on the captured images to obtain a facial image of the target pet;

[0007] Calling the pet recognition model to perform feature extraction on the target pet facial image to obtain target pet facial features;

[0008] Performing feature similarity comparison on the facial features of the target pet in the pre-recorded pet feature library to determine feature similarity information between the target pet and the pre-recorded pet;

[0009] In response to the presence of the feature similarity information satisfying a preset identity authentication condition, the pre-recorded pet corresponding to the feature similarity information is determined based on the unique Face ID of the pre-recorded pet, and the pet food dispensing operation or the pet food exposure operation is performed according to the pre-recorded pet food information of the matched pre-recorded pet.

[0010] According to some embodiments of the present application, the obtaining of a pre-recorded pet feature library, wherein the pre-recorded pet feature library includes a pre-recorded feature group corresponding to the pre-recorded pet, including:

[0011] Acquire at least two pre-recorded feature groups corresponding to different pre-recorded pets, each of the pre-recorded feature groups comprising pre-recorded pet facial features of the pre-recorded pet, a unique Face ID of the pre-recorded pet, and pre-recorded pet food information matching the pre-recorded pet;

[0012] The comparing the facial features of the target pet with the pre-recorded pet feature library for feature similarity to determine feature similarity information between the target pet and the pre-recorded pet includes:

[0013] The facial features of the target pet are compared with the facial features of the pre-recorded pets in each of the pre-recorded feature groups for feature similarity to determine the feature similarity information between the target pet and each of the pre-recorded pets.

[0014] According to some embodiments of the present application, obtaining at least two pre-recorded feature groups corresponding to different pre-recorded pets includes:

[0015] Obtaining the pre-recorded pet food information of each pre-recorded pet;

[0016] Capturing images of different pre-recorded pets respectively to obtain a pre-recorded pet image corresponding to each pre-recorded pet;

[0017] performing an image quality test on each of the pre-recorded pet images to obtain a quality test result corresponding to the pre-recorded pet image;

[0018] In response to the quality detection result meeting a preset quality qualification condition, calling the pet recognition model to perform feature extraction on the pre-recorded pet image to obtain pre-recorded pet facial features corresponding to the pre-recorded pet;

[0019] The pre-recorded pet facial features of each of the pre-recorded pets and the pre-recorded pet food information of each of the pre-recorded pets are matched and integrated to obtain each of the pre-recorded feature groups.

[0020] According to some embodiments of the present application, the pet recognition model encapsulates an image enhancement algorithm, a pet face capture algorithm, and a pet face recognition sub-model. Calling the pet recognition model to extract features from the pre-recorded pet image to obtain pre-recorded pet facial features corresponding to the pre-recorded pet includes:

[0021] Performing image enhancement processing on each of the pre-recorded pet images using an image enhancement algorithm to obtain a pre-recorded enhanced image;

[0022] Invoking a preset pet face capture algorithm to capture the pet's facial area from the pre-recorded enhanced image;

[0023] The pet facial recognition sub-model is used to perform pet facial recognition on the pet facial area to obtain the pre-recorded pet facial features.

[0024] According to some embodiments of the present application, the step of capturing an image of a target pet and performing pet face detection on the captured image to obtain a facial image of the target pet includes:

[0025] Performing a pet attraction operation; wherein the pet attraction operation is used to attract the target pet to approach the pet feeding device;

[0026] In response to detecting that the target pet enters a preset image acquisition area in the pet feeding device, image acquisition is performed on the image acquisition area to obtain a facial image of the target pet.

[0027] According to some embodiments of the present application, the pre-recorded pet food information includes pet food type sub-information and pet food portion sub-information, and performing a pet food dispensing operation or a pet food exposing operation based on the pre-recorded pet food information of the matched pre-recorded pet includes:

[0028] determining a target feeding plan based on the pet food type sub-information and the pet food portion sub-information;

[0029] The pet food dispensing operation or the pet food exposing operation is performed according to the target feeding plan.

[0030] According to some embodiments of the present application, after performing a pet food dispensing operation or a pet food exposing operation according to the pre-recorded pet food information of the matched pre-recorded pet, the method further includes:

[0031] Monitor the pet eating in the preset image acquisition area to obtain the pet eating picture;

[0032] Identifying the eating action of the target pet according to the pet eating picture to obtain the pet's eating status;

[0033] In response to the pet's eating state not meeting the standard eating state, the pet food dispensing operation or the pet food exposing operation is terminated.

[0034] A pet feeding device according to a second embodiment of the present application includes:

[0035] a feature library acquisition module, configured to acquire a pre-recorded pet feature library, the pre-recorded pet feature library comprising pre-recorded feature groups corresponding to pre-recorded pets, each of the pre-recorded feature groups comprising pre-recorded pet facial features of the pre-recorded pet, a unique Face ID of the pre-recorded pet, and pre-recorded pet food information matching the pre-recorded pet;

[0036] An image acquisition module is used to acquire images of a target pet and perform pet face detection on the acquired images to obtain a facial image of the target pet;

[0037] A feature extraction module is used to call a pet recognition model to extract features from the target pet's facial image to obtain facial features of the target pet;

[0038] A feature comparison module is used to compare the facial features of the target pet with the pre-recorded pet feature library for feature similarity, so as to determine feature similarity information between the target pet and the pre-recorded pet;

[0039] A feeding execution module is used to determine, in response to the presence of the feature similarity information satisfying a preset identity authentication condition, the pre-recorded pet that matches the feature similarity information based on the unique Face ID of the pre-recorded pet, and execute a pet food dispensing operation or a pet food exposing operation according to the pre-recorded pet food information of the matched pre-recorded pet.

[0040] In a third aspect, an embodiment of the present application provides an electronic device comprising: a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the pet feeding method as described in any one of the embodiments of the first aspect of the present application.

[0041] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the pet feeding method as described in any one of the embodiments of the first aspect of the present application.

[0042] According to the pet feeding method and device, electronic device, and medium of the embodiment of the present application, at least the following are provided:

[0043] Beneficial effects:

[0044] The pet feeding method of the embodiment of the present application is applied to a pet feeding device, which is provided with a pet recognition model. It is necessary to first obtain a pre-recorded pet feature library, which includes a pre-recorded feature group corresponding to the pre-recorded pet, the pre-recorded feature group including the pre-recorded pet facial features of the pre-recorded pet, the unique Face ID of the pre-recorded pet and the pre-recorded pet food information matching the pre-recorded pet; image capture is performed on the target pet and pet face detection is performed on the captured image to obtain a target pet facial image; the pet recognition model is called to perform feature extraction on the target pet facial image to obtain the target pet facial features; the target pet facial features are compared for feature similarity in the pre-recorded pet feature library to determine feature similarity information between the target pet and the pre-recorded pet; in response to the presence of the feature similarity information meeting a preset identity authentication condition, the pre-recorded pet corresponding to the feature similarity information is determined based on the unique Face ID of the pre-recorded pet, and a pet food dispensing operation or a pet food exposing operation is performed according to the pre-recorded pet food information of the matched pre-recorded pet. In this way, it is ensured that only certified pets can obtain food suitable for them, avoiding the problem of accidental ingestion and allowing pets to be fed more accurately.

[0045] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0047] Figure 1 This is a flow chart of a pet feeding method provided by an embodiment of the present application for different individuals;

[0048] Figure 2 This is another flowchart of the pet feeding method provided by the embodiment of the present application for different individuals;

[0049] Figure 3 This is another flowchart of the pet feeding method provided by the embodiment of the present application for different individuals;

[0050] Figure 4 This is another flowchart of the pet feeding method provided by the embodiment of the present application for different individuals;

[0051] Figure 5 This is another flowchart of the pet feeding method provided by the embodiment of the present application for different individuals;

[0052] Figure 6This is another flowchart of the pet feeding method provided by the embodiment of the present application for different individuals;

[0053] Figure 7 This is another flowchart of the pet feeding method provided by the embodiment of the present application for different individuals;

[0054] Figure 8 This is another flowchart of the pet feeding method provided by the embodiment of the present application for different individuals;

[0055] Figure 9 is a schematic structural diagram of a pet feeding device provided in an embodiment of the present application;

[0056] Figure 10 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application.

[0058] In the description of this application, "several" means one or more, "many" means more than two, "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The terms "first" and "second" are used solely to distinguish technical features and are not to be construed as indicating or implying relative importance, or as implicitly specifying the number or order of the technical features indicated.

[0059] In the description of this application, it should be understood that descriptions involving orientations, such as up, down, left, right, front, and back, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on this application.

[0060] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0061] In the description of this application, it should be noted that, unless otherwise explicitly defined, terms such as "set," "install," and "connect" should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in this application based on the specific content of the technical solution. In addition, the identification of specific steps below does not represent a limitation on the order of steps and execution logic. The execution order and execution logic between each step should be understood and inferred with reference to the content described in the embodiments.

[0062] As people's living standards improve, pets are gaining a greater place in the family, and more and more families are keeping pets. However, pet feeding has always been a problem for pet owners. For example, some pets may accidentally eat food that is not suitable for them, leading to indigestion or other health problems. Therefore, to ensure that pets receive the food they need, the idea of ​​using pet facial recognition technology in conjunction with feeding and dispensing operations has emerged. However, pet facial recognition technology is easily affected by factors such as the pet's posture and lighting, resulting in slow recognition and low accuracy. Furthermore, the uncertainty of pets' movements makes it difficult for pet facial recognition to accurately feed active pets in real-world scenarios. Therefore, finding more efficient ways to feed pets remains a pressing issue in the industry.

[0063] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a pet feeding method and device, electronic equipment, and medium that can feed pets of different individuals.

[0064] The following is a further explanation based on the accompanying drawings.

[0065] Reference Figure 1 According to an embodiment of the present application, the pet feeding method is applied to a pet feeding device, and the pet feeding device is provided with a pet recognition model, which may include:

[0066] Step S101, obtaining a pre-recorded pet feature library, the pre-recorded pet feature library including a pre-recorded feature group corresponding to the pre-recorded pet, the pre-recorded feature group including the pre-recorded pet facial features, the pre-recorded pet's unique Face ID, and pre-recorded pet food information matching the pre-recorded pet;

[0067] Step S102, capturing an image of the target pet and performing pet face detection on the captured image to obtain a facial image of the target pet;

[0068] Step S103, calling a pet recognition model to extract features from the target pet's facial image to obtain facial features of the target pet;

[0069] Step S104, performing feature similarity comparison on the facial features of the target pet in the pre-recorded pet feature library to determine feature similarity information between the target pet and the pre-recorded pet;

[0070] Step S105, in response to the presence of feature similarity information that meets the preset identity authentication conditions, the pre-recorded pet corresponding to the feature similarity information is determined based on the unique Face ID of the pre-recorded pet, and the pet food dispensing operation or the pet food exposure operation is performed according to the pre-recorded pet food information of the matched pre-recorded pet.

[0071] The pet feeding method of the embodiment of the present application is applied to a pet feeding device, which is provided with a pet recognition model. It is necessary to first obtain a pre-recorded pet feature library, which includes a pre-recorded feature group corresponding to the pre-recorded pet, which includes the pre-recorded pet facial features, the pre-recorded pet's unique Face ID and the pre-recorded pet food information matching the pre-recorded pet; image capture is performed on the target pet and pet face detection is performed on the captured image to obtain the target pet facial image; the pet recognition model is called to perform feature extraction on the target pet facial image to obtain the target pet facial features; the target pet facial features are compared for feature similarity in the pre-recorded pet feature library to determine feature similarity information between the target pet and the pre-recorded pet; in response to the presence of feature similarity information that meets a preset identity authentication condition, the feature similarity information is determined to correspond to the matched pre-recorded pet based on the unique Face ID of the pre-recorded pet, and according to the pre-recorded pet food information of the matched pre-recorded pet, a pet food dispensing operation or a pet food exposing operation is performed. In this way, it is ensured that only certified pets can obtain food suitable for them, avoiding the problem of accidental ingestion and allowing pets to be fed more accurately.

[0072] In some embodiments, step S101 is to obtain a pre-recorded pet feature library, the pre-recorded pet feature library including a pre-recorded feature group corresponding to the pre-recorded pet, the pre-recorded feature group including the pre-recorded pet facial features, the pre-recorded pet's unique Face ID, and pre-recorded pet food information matching the pre-recorded pet;

[0073] It should be noted that step S101 involves obtaining a pre-recorded pet feature library, which contains detailed information related to the pre-recorded pets, ensuring the accuracy and efficiency of the subsequent recognition process. This pre-recorded pet feature library not only stores the facial features of the pre-recorded pets, but also includes each pet's unique Face ID and matching pet food information, building a comprehensive and personalized pet information database.

[0074] First, pre-recorded pet facial features are derived through advanced image processing and feature extraction techniques. These features are key data points extracted from pet facial images and accurately describe the unique characteristics of the pet's face. They are crucial for identifying the pet's identity. Even when the pet's face is subject to certain changes or occlusion, the embodiments of the present application can accurately identify the pet based on these features. This facial feature data is stored in the system using a specific data structure for rapid retrieval and comparison.

[0075] It should be noted that the pre-recorded pet facial features are obtained through image acquisition and feature extraction technology. Specifically, a high-definition camera can be used to capture images of each pet from multiple angles to ensure that the key facial features of the pet are captured. Key facial features of a pet may include the shape and position of the pet's facial contours, eyes, nose, ears, and other parts. Using advanced image processing algorithms, the pet feeding device of the present embodiment can extract these features and generate a feature vector, i.e., the pre-recorded pet facial features, for subsequent similarity comparison.

[0076] To build a pre-recorded pet feature library, the present embodiment requires capturing facial images of pets from multiple angles. After pre-processing, such as denoising and enhancement, these images are fed into a pet recognition model for feature extraction. The pet recognition model utilizes a deep learning algorithm to automatically learn and identify key facial features of pets, converting them into storable and comparable feature data. This feature data, along with the pet's Face ID and pre-recorded pet food information, is integrated into the pre-recorded pet feature library.

[0077] In practical applications, when a target pet needs to be identified, embodiments of the present application can capture a facial image of the target pet and extract facial features from it. These features are then compared with data in a pre-recorded pet feature library to determine the target pet's identity. If a match is successful, embodiments of the present application will perform the corresponding feeding operation based on the pre-recorded pet food information. This process not only improves the accuracy of pet identification, but also enhances the personalized and scientific nature of feeding.

[0078] Secondly, Face ID, as a unique identifier for pre-registered pets, acts like a pet's "ID number" within the system. It not only distinguishes one pet from another but also remains constant throughout the pet's lifecycle, ensuring consistency and traceability of pet information. Face ID is integrated into all pet records and operations, enabling the system to quickly locate and link to other information about a specific pet, such as health records and feeding habits.

[0079] Finally, pre-recorded pet food information is personalized data associated with each pet, recording each pet's dietary preferences, nutritional requirements, and feeding schedule. This information is crucial for personalized feeding, allowing the system to control and distribute pet food based on the pet's specific needs, ensuring the pet receives the appropriate nutrition. Furthermore, pre-recorded pet food information can be combined with the pet's health data to help pet owners monitor their pet's health and adjust feeding strategies in a timely manner.

[0080] It should be noted that pre-recorded pet food information is customized based on the specific needs of each pet. This includes factors such as the pet's breed type, health status, and growth stage. For example, for an adult golden retriever, its feeding information may include high-protein, low-fat dog food to meet its daily needs. For an elderly cat, its feeding information may include easily digestible, vitamin-rich food to support its health. This feeding information is generated and stored in the pet feeding device of the present application through input from the pet owner or veterinarian, combined with the pet's health data and nutritional needs.

[0081] Here are some pet-specific examples of how to create pre-recorded profile groups for different pets:

[0082] Pre-recorded feature set for Golden Retrievers. Pre-recorded pet facial features indicate that Golden Retrievers typically have a rounded facial profile, a broad forehead, and slightly prominent cheekbones. Their eyes are large, round, and typically dark brown, with a gentle expression. Their noses are large, black, and round. Their mouths are long, with thick, naturally drooping lips. Pre-recorded pet food information indicates that Golden Retrievers require a high-protein, low-fat dry food suitable for the daily activities of adult Golden Retrievers. Each meal should be 150 grams, two meals per day, for a total feeding amount of 300 grams. Because Golden Retrievers are susceptible to hip dysplasia, joint health ingredients may be added to their food.

[0083] Pre-recorded feature set for Persian cats. Pre-recorded pet facial features reflect the Persian cat's flat face, high cheekbones, and short, wide nose. Large, round eyes with a variety of colors, often blue, green, or heterochromatic. A short, wide nose matches the coat color. A small, round mouth with thin, naturally shaped lips. Pre-recorded pet food information reflects the Persian cat's need for a high-protein, low-fiber wet food suitable for the digestive needs of adult Persians. Each meal is 70 grams, two meals per day, for a total feeding amount of 140 grams. Because Persian cats are susceptible to urinary tract diseases, urinary tract health ingredients can be added to their food.

[0084] Through these specific examples, it can be seen that each pre-recorded feature set contains facial features and ration information that matches the corresponding pre-recorded pet. The accurate recording and application of this information ensures that each pet receives a diet that meets their health and nutritional needs. This personalized feeding plan not only improves the pet's quality of life but also provides pet owners with a more convenient and reliable pet management method.

[0085] It should be understood that each pre-recorded feature group (including pre-recorded pet facial features and pre-recorded pet food information) is stored in a database so that the pet feeding device of the embodiment of the present application can quickly access it when feeding. This database can be stored locally or in the cloud, depending on the architecture of the pet feeding device of the embodiment of the present application and the needs of the user. Through an effective data management strategy, the pet feeding device of the embodiment of the present application can ensure the security and reliability of the data and prevent data from being lost or tampered with. By acquiring and storing these pre-recorded feature groups, the pet feeding device of the embodiment of the present application can quickly and accurately identify the target pet when feeding and feed it according to its specific feeding information. This not only improves the efficiency of feeding, but also ensures that each pet can obtain a diet suitable for its health status and growth stage. In addition, this method can also dynamically adjust the feeding information according to changes in the health status and growth stage of the pet, further improving the scientificity and effectiveness of feeding.

[0086] Furthermore, the pre-recorded pet feature library is not static. As time passes and a pet grows, its facial features may change. Therefore, embodiments of the present application can regularly update the data in the feature library to ensure recognition accuracy. Embodiments of the present application can also regularly update the pet's facial features by uploading new pet images. Furthermore, pet food information should be adjusted based on the pet's growth stage and health status to meet its ever-changing nutritional needs.

[0087] Reference Figure 2 According to some embodiments of the present application, step S101 obtains a pre-recorded pet feature library. The pre-recorded pet feature library includes a pre-recorded feature group corresponding to the pre-recorded pet, which may include:

[0088] Step S201, obtaining at least two pre-recorded feature groups corresponding to different pre-recorded pets, each pre-recorded feature group including pre-recorded pet facial features of the pre-recorded pet, a Face ID of the pre-recorded pet displacement, and pre-recorded pet food information matching the pre-recorded pet;

[0089] In step S102, the facial features of the target pet are compared with the pre-recorded pet feature library for feature similarity to determine feature similarity information between the target pet and the pre-recorded pet, which may include:

[0090] Step S202 : performing feature similarity comparison between the target pet's facial features and the pre-recorded pet's facial features in each pre-recorded feature group to determine feature similarity information between the target pet and each pre-recorded pet.

[0091] In step S201 of some embodiments, at least two pre-recorded feature groups corresponding to different pre-recorded pets are obtained, each pre-recorded feature group including pre-recorded pet facial features of the pre-recorded pet, a Face ID of the pre-recorded pet displacement, and pre-recorded pet food information matching the pre-recorded pet;

[0092] It should be noted that step S201 further refines this process. The pet feeding device of the present embodiment can obtain at least two pre-recorded feature groups, which means it can identify and manage information for multiple pets. This is very useful in real life, as many families have multiple pets, each of which may have different dietary needs. By establishing a separate pre-recorded feature group for each pet, the feeding device can ensure that each pet receives food that is suitable for it.

[0093] In step S202 of some embodiments, facial features of the target pet are compared with facial features of pre-recorded pets in each pre-recorded feature group for feature similarity to determine feature similarity information between the target pet and each pre-recorded pet.

[0094] It should be noted that the pet feeding device of the embodiment of the present application can compare the characteristics of the target pet with the characteristics of each pre-recorded feature group one by one. This is like using a key to try multiple locks until a matching one is found. In this way, the pet feeding device of the embodiment of the present application can determine which pre-recorded pet has the highest similarity with the target pet, and thus decide whether to feed the pet.

[0095] This multi-feature comparison mechanism not only improves recognition accuracy but also enhances the flexibility of the pet feeding device of the present application. It allows the pet feeding device of the present application to quickly and accurately identify each pet even when handling multiple pets, and feed them according to their individual dietary needs. This design fully considers the complexity of practical application scenarios, providing pet owners with a more convenient and intelligent feeding experience.

[0096] Reference Figure 3 According to some embodiments of the present application, step S201 of obtaining at least two pre-recorded feature groups corresponding to different pre-recorded pets may include:

[0097] Step S301, obtaining pre-recorded pet food information of each pre-recorded pet;

[0098] Step S302, capturing images of different pre-recorded pets to obtain pre-recorded pet images corresponding to each pre-recorded pet;

[0099] Step S303, performing image quality detection on each pre-recorded pet image to obtain a quality detection result corresponding to the pre-recorded pet image;

[0100] Step S304, in response to the quality detection result meeting the preset quality qualification condition, calling the pet recognition model to perform feature extraction on the pre-recorded pet image to obtain pre-recorded pet facial features corresponding to the pre-recorded pet;

[0101] Step S305 , integrating the pre-recorded pet facial features of each pre-recorded pet and the pre-recorded pet food information of each pre-recorded pet to obtain a pre-recorded feature group.

[0102] In step S301 of some embodiments, pre-recorded pet food information of each pre-recorded pet is obtained;

[0103] It should be noted that, first, the embodiment of the present application needs to obtain the pre-recorded pet food information for each pre-recorded pet. The purpose of this step is to customize a specific diet plan for each pet to meet its specific needs such as breed type, health status, growth stage, etc. The pre-recorded pet food information may include the pet's dietary preferences, nutritional needs, feeding time, feeding amount, etc. This information can be obtained through the pet owner's input or the veterinarian's advice and stored in the embodiment of the present application. By obtaining the pre-recorded pet food information, the embodiment of the present application can provide personalized diet management for each pet.

[0104] In step S302 of some embodiments, image capture is performed for different pre-recorded pets to obtain a pre-recorded pet image corresponding to each pre-recorded pet;

[0105] It should be noted that, next, the embodiment of the present application performs image capture for different pre-recorded pets respectively to obtain pre-recorded pet images corresponding to each pre-recorded pet. The purpose of image capture is to obtain the facial features or facial features of the pet for subsequent pet identification. It should be pointed out that image capture can be completed by a high-definition camera to ensure the clarity and accuracy of the image. When capturing the image, the camera can be facing the pet's face to avoid occlusion and blur. In addition, the environment for image capture should be well-lit and the background should be simple to reduce interference factors.

[0106] In step S303 of some embodiments, image quality detection is performed on each pre-recorded pet image to obtain a quality detection result corresponding to the pre-recorded pet image;

[0107] It should be noted that after image acquisition is completed, embodiments of the present application require that each pre-recorded pet image be subjected to image quality testing to obtain a quality test result corresponding to the pre-recorded pet image. The purpose of image quality testing is to ensure image clarity and accuracy for subsequent feature extraction. Quality testing may include checking the image's resolution, brightness, contrast, noise level, etc. If the image quality does not meet the preset quality qualification criteria, embodiments of the present application may prompt the user to recapture the image to ensure image quality.

[0108] Reference Figure 4 According to some embodiments of the present application, step S303 performs image quality detection on each pre-recorded pet image to obtain a quality detection result corresponding to the pre-recorded pet image, which may include:

[0109] Step S401, performing brightness calculation on the pre-recorded pet image to obtain pre-recorded brightness detection data;

[0110] Step S402, calculating the sharpness of the pre-recorded pet image to obtain pre-recorded sharpness detection data;

[0111] Step S403: When the pre-recorded brightness detection data satisfies a preset brightness detection condition and the pre-recorded sharpness detection data satisfies a preset sharpness detection condition, performing pet face relative angle calculation on the pre-recorded pet image to obtain pet face relative angle data;

[0112] Step S404: In response to the pet's facial relative angle data satisfying a preset facial relative angle detection condition, a quality detection result satisfying a quality qualification condition is obtained.

[0113] In step S401 of some embodiments, brightness calculation is performed on the pre-recorded pet image to obtain pre-recorded brightness detection data;

[0114] It should be noted that, first, a brightness calculation is performed on the pre-recorded pet image to obtain pre-recorded brightness detection data. The purpose of the brightness calculation is to evaluate the overall brightness level of the image to ensure that the image is neither too dark nor too bright. An image that is too dark may cause the pet's facial features to be unclear, while an image that is too bright may produce overexposure, affecting the accuracy of feature extraction. The brightness calculation can be completed by calculating the average brightness value of all pixels in the image. If the brightness value is lower than the preset brightness detection condition, the pet feeding device of the present application can prompt to recapture the image or adjust the brightness.

[0115] In step S402 of some embodiments, sharpness calculation is performed on the pre-recorded pet image to obtain pre-recorded sharpness detection data;

[0116] It should be noted that, next, a sharpness calculation is performed on the pre-recorded pet image to obtain pre-recorded sharpness detection data. The purpose of the sharpness calculation is to assess the image clarity and detail retention, ensuring that the edges and details of the pet's facial features are clearly visible. The sharpness calculation can be completed by calculating the clarity index of the edges and details in the image. If the sharpness value falls below the preset sharpness detection condition, the pet feeding device of the present application can prompt to recapture the image or perform sharpness enhancement processing.

[0117] In step S403 of some embodiments, if the pre-recorded brightness detection data satisfies a preset brightness detection condition and the pre-recorded sharpness detection data satisfies a preset sharpness detection condition, calculating the pet face relative angle on the pre-recorded pet image to obtain pet face relative angle data;

[0118] It should be noted that when both the pre-recorded brightness detection data and the pre-recorded sharpness detection data meet the preset conditions, the pet feeding device of the present application calculates the pet's facial relative angle on the pre-recorded pet image to obtain the pet's facial relative angle data. The purpose of the pet's facial relative angle calculation is to evaluate the angle and position of the pet's face in the image to ensure that the face is facing the camera and the angle is moderate. This step can be accomplished by detecting the positional relationship of facial feature points (such as eyes, nose, mouth, etc.). If the facial angle deviates from the preset facial relative angle detection conditions, the pet feeding device of the present application can prompt to recapture the image or adjust the angle.

[0119] In step S404 of some embodiments, in response to the pet's facial relative angle data satisfying a preset facial relative angle detection condition, a quality detection result that meets a quality qualification condition is obtained.

[0120] It should be noted that, finally, in response to the pet's facial relative angle data satisfying the preset facial relative angle detection conditions, the pet feeding device of the present application generates a quality inspection result that meets the quality qualification conditions. This step ensures that the pre-recorded pet image meets the requirements in terms of brightness, sharpness, and facial angle, thereby providing high-quality image data for subsequent feature extraction and recognition. In this way, the pet feeding device of the present application can ensure the accuracy and reliability of pet recognition, providing a solid foundation for subsequent feeding operations.

[0121] It should be understood that by calculating brightness, sharpness, and the relative angles of the pet's face, the pet feeding device of this application can comprehensively evaluate the quality of pre-recorded pet images. This process not only ensures image clarity and quality but also provides reliable data support for subsequent feature extraction and recognition. In this way, the pet feeding device of this application can better meet the personalized dietary needs of each pet in a multi-pet household, improving the pet's quality of life and the owner's feeding experience.

[0122] In step S304 of some embodiments, in response to the quality detection result satisfying a preset quality qualification condition, calling a pet recognition model to perform feature extraction on the pre-recorded pet image to obtain pre-recorded pet facial features corresponding to the pre-recorded pet;

[0123] It should be noted that when the image quality detection results meet the preset quality qualification conditions, the embodiment of the present application calls the pet recognition model to extract features from the pre-recorded pet image to obtain pre-recorded pet facial features corresponding to the pre-recorded pet. Feature extraction is completed by a deep learning model, which extracts numerical values ​​or vectors that can represent the pet's features from the image. These features can include the shape and position of the pet's facial contour, eyes, nose, mouth, ears and other parts. Through feature extraction, the embodiment of the present application can generate a feature vector for subsequent feature similarity comparison.

[0124] In step S305 of some embodiments, the pre-recorded pet facial features of each pre-recorded pet and the pre-recorded pet food information of each pre-recorded pet are integrated to obtain a pre-recorded feature group.

[0125] It should be noted that, finally, this embodiment of the present application integrates the pre-recorded pet facial features and pre-recorded pet food information for each pre-recorded pet to obtain a pre-recorded feature group. This pre-recorded feature group contains the pet's feature vector and feeding information, providing key data for subsequent pet identification and feeding operations. By integrating this information, this embodiment of the present application can ensure that the target pet is quickly and accurately identified during feeding and fed according to its specific needs. This integration not only improves feeding efficiency, but also ensures that each pet receives a diet appropriate for its health status and growth stage.

[0126] It should be understood that through steps S301 to S305, which involve obtaining pre-recorded pet food information, image capture, image quality detection, feature extraction, and feature group integration, a pre-recorded feature group containing its characteristics and feeding information is established for each pre-recorded pet. This process not only ensures the accuracy of pet identification and feeding precision, but also provides strong support for the personalized dietary needs of each pet in a multi-pet household. In this way, the embodiments of the present application can significantly improve the quality of life of pets and the feeding experience of their owners.

[0127] Reference Figure 5 According to some embodiments of the present application, the pet recognition model encapsulates an image enhancement algorithm, a pet face capture algorithm, and a pet face recognition sub-model. In step S304, the pet recognition model is called to extract features from the pre-recorded pet image to obtain pre-recorded pet facial features corresponding to the pre-recorded pet, which may include:

[0128] Step S501, performing image enhancement processing on each pre-recorded pet image using an image enhancement algorithm to obtain a pre-recorded enhanced image;

[0129] Step S502, calling a preset pet face capture algorithm to capture the pet's face area from the pre-recorded enhanced image;

[0130] Step S503: performing pet facial recognition on the pet facial area using the pet facial recognition sub-model to obtain pre-recorded pet facial features.

[0131] In some embodiments, the pet recognition model encapsulates an image enhancement algorithm, a pet face capture algorithm, and a pet face recognition sub-model. These components work together to ensure accurate pet feature extraction from pre-recorded pet images. The image enhancement algorithm improves image quality, the pet face capture algorithm locates the pet's face, and the pet face recognition sub-model extracts features from the facial region.

[0132] In step S501 of some embodiments, image enhancement processing is performed on each pre-recorded pet image using an image enhancement algorithm to obtain a pre-recorded enhanced image;

[0133] It should be noted that, first, each pre-recorded pet image is enhanced using an image enhancement algorithm to produce a pre-recorded enhanced image. The purpose of image enhancement is to improve image clarity and quality, enabling more accurate facial capture and feature extraction. Image enhancement algorithms can include operations such as denoising, contrast enhancement, and brightness and sharpness adjustments. These operations can reduce random noise in the image, making the pet's facial features more distinct, thereby improving recognition accuracy.

[0134] In step S502 of some embodiments, a preset pet face capture algorithm is called to capture the pet face region from the pre-recorded enhanced image;

[0135] It should be noted that next, a preset pet face capture algorithm is called to capture the pet's facial area from the pre-recorded enhanced image. The pet face capture algorithm can be based on a deep learning model, capable of automatically detecting the pet's face in the image and separating it from the background. This step ensures that subsequent feature extraction focuses only on the pet's face, rather than the entire image, thereby improving the accuracy and efficiency of feature extraction. The face capture algorithm may be implemented using a convolutional neural network (CNN) or other advanced image processing techniques.

[0136] In step S503 of some embodiments, pet facial recognition is performed on the pet facial region using a pet facial recognition sub-model to obtain pre-recorded pet facial features.

[0137] It should be noted that, finally, the pet facial recognition sub-model performs pet facial recognition on the pet's facial area to obtain pre-recorded pet facial features. The pet facial recognition sub-model is a trained deep learning model that can extract representative feature vectors from pet facial images. These feature vectors contain key information about the pet's face, such as facial contours, the shape and position of the eyes, nose, mouth, and other parts. Through feature extraction, the pet feeding device of this application can generate a unique feature vector for subsequent feature similarity comparison and pet identification.

[0138] It should be understood that the accuracy and efficiency of the entire feature extraction process depends on the coordinated work of three steps: image enhancement, facial capture, and feature extraction. Image enhancement ensures image clarity, facial capture ensures accurate feature extraction, and feature extraction generates feature vectors for identification. Through these steps, the pet feeding device of the present application can generate a precise feature vector for each pre-recorded pet. These feature vectors are integrated with the pre-recorded pet food information to form a pre-recorded feature set, providing basic data for subsequent pet identification and feeding operations.

[0139] In some embodiments, when a pet recognition model is used to extract features from pre-recorded pet images to obtain pre-recorded pet facial features corresponding to the pre-recorded pet, the AI ​​ISP algorithm can be used to enhance the algorithm collected from the camera, and YOLOv11 can be used to capture pet facial images and extract pet facial features using the Facenet model. It should be understood that the pet recognition model of this application is not limited to the above examples.

[0140] In step S102 of some embodiments, an image of a target pet is captured and pet face detection is performed on the captured image to obtain a facial image of the target pet;

[0141] It should be noted that step S102 involves capturing an image of the target pet. This step is a key component of the entire pet feeding method, as it provides basic data for subsequent pet identification and feeding operations. The quality of image capture directly impacts the accuracy of pet identification and feeding.

[0142] It should be noted that the primary purpose of image acquisition is to obtain facial images of the target pet so that the pet recognition model can subsequently extract features and compare them with pre-recorded feature sets. These images must clearly display the pet's facial features, including key areas such as the eyes, nose, mouth, and ears. High-quality image acquisition ensures that the pet recognition model can accurately extract the target pet's features, thereby improving recognition accuracy. Image acquisition can be performed in a variety of ways. One common method is to use a high-definition camera to photograph the target pet. These cameras can be fixed to the pet feeding device or used as mobile devices held by the pet owner (such as smartphones or tablets). To ensure image quality, the camera needs to have good resolution and low-light imaging capabilities. In addition, during image acquisition, it is necessary to ensure that the pet's face is facing the camera to avoid obstructions and blur.

[0143] In practical applications, image acquisition can face some challenges. For example, a pet may move or turn during the acquisition process, resulting in a blurry or incomplete image. To address these issues, embodiments of the present application may employ the following methods: capturing images of the pet from multiple angles (e.g., front, side, top, etc.) to ensure high-quality facial images; using a rapid continuous shooting mode to capture images of the pet at different moments to increase the chance of obtaining a clear image; and stitching multiple images into a complete image to compensate for the shortcomings of a single image.

[0144] It should be understood that capturing images of a target pet provides critical data for subsequent pet identification and feeding operations. Through high-quality image capture, the pet feeding device of the present application can more accurately identify the target pet and feed it according to its specific needs, thereby meeting the personalized dietary needs of each pet in a multi-pet household.

[0145] Reference Figure 6 According to some embodiments of the present application, step S102 of capturing an image of a target pet and performing pet face detection on the captured image to obtain a facial image of the target pet may include:

[0146] Step S601, performing a pet attracting operation; wherein the pet attracting operation is used to attract a target pet to approach the pet feeding device;

[0147] Step S602 : In response to detecting that the target pet enters a preset image acquisition area in the pet feeding device, image acquisition is performed in the image acquisition area to obtain a facial image of the target pet.

[0148] In some embodiments, step S601 is to perform a pet attraction operation, wherein the pet attraction operation is used to attract a target pet to approach the pet feeding device;

[0149] It should be noted that the pet attraction operation is intended to attract the target pet to the pet feeding device. This step is crucial to ensuring the pet is in the appropriate position during image capture. The pet attraction operation can be implemented in a variety of ways, such as using the pet's favorite sounds, lights, or toys to attract its attention. For example, the feeding device could be equipped with a small toy that can be activated in a pet-entertaining mode to attract the pet's attention and draw it closer to the feeding device. Furthermore, the feeding device could emit familiar sounds or display a light pattern that the pet enjoys to further attract the pet.

[0150] In step S602 of some embodiments, in response to detecting that the target pet enters a preset image acquisition area in the pet feeding device, image acquisition is performed on the image acquisition area to obtain a facial image of the target pet.

[0151] It should be noted that after performing the pet attraction operation, the pet feeding device of this application detects whether the target pet has entered a preset image capture area. The image capture area is a specific area in front of the device, which can be defined and monitored using infrared sensors, cameras, or other detection technologies. When a pet enters this area, the pet feeding device of this application automatically detects its presence and prepares for image capture. This step ensures accurate and timely image capture and avoids image quality issues caused by improper pet positioning.

[0152] In some embodiments, if a target pet is detected to have entered an image acquisition area, an image acquisition process may be immediately initiated to acquire an image of the target pet. Image acquisition may be performed by a high-definition camera to ensure image clarity and accuracy.

[0153] In step S103 of some embodiments, a pet recognition model is called to extract features from the target pet's facial image to obtain facial features of the target pet;

[0154] It should be noted that step S103 is to call the pet recognition model to extract features from the target pet's facial image to obtain the features of the target pet. The pet recognition model is a trained deep learning model that can recognize and extract key features of a pet's face. The preset process of this pet recognition model can use a large amount of pet image data to train it to ensure that it can accurately identify pets of different breeds, ages and health conditions. The facial features of the target pet are the key basis for identity authentication and feeding operations in subsequent steps. By comparing the facial features of the target pet with the pre-recorded pet facial features in the pre-recorded feature group, the pet feeding device of the embodiment of the present application can determine the identity of the target pet and perform feeding operations according to its corresponding pre-recorded pet food information. This ensures that each pet can obtain food that suits its needs and avoids competition and accidental eating among pets.

[0155] It's important to note that feature extraction is one of the model's core functions. It extracts numerical values ​​or vectors representing the pet's characteristics from the target pet's facial image. These features can include the pet's facial contour, the shape and position of its eyes, nose, mouth, ears, and other parts; they can also include facial features such as the pet's fur, body shape, and posture. Through a series of complex mathematical operations and algorithms, the model converts the pixel values ​​in the image into semantically meaningful feature vectors.

[0156] It's important to note that pet recognition models can employ a convolutional neural network (CNN) architecture, a deep learning model specifically designed for processing image data. CNNs extract image features layer by layer through multiple convolutional, pooling, and fully connected layers. Convolutional layers capture local features in an image, such as edges and textures; pooling layers reduce the dimensionality of features while retaining important information; and fully connected layers integrate these features to form a complete feature vector.

[0157] In some embodiments, the AI ​​ISP algorithm can also be used to enhance the algorithm collected from the camera, and YOLOv11 can be used to capture pet facial images and the Facenet model can be used to extract pet facial features. It should be understood that the pet recognition model of this application is not limited to the above examples.

[0158] It should be understood that step S103 extracts features from the target pet's facial image by invoking the pet recognition model to obtain the target pet's facial features, providing key data support for subsequent identity authentication and feeding operations. This process not only improves the efficiency of the pet feeding device of the present application embodiment, but also ensures accurate and personalized pet feeding.

[0159] In step S104 of some embodiments, facial features of the target pet are compared with pre-recorded pet feature libraries for feature similarity to determine feature similarity information between the target pet and the pre-recorded pets;

[0160] It should be noted that step S104 involves comparing the target pet's facial features against a pre-recorded pet feature library to determine the similarity between the target pet and the pre-recorded pets. This step is a core component of the entire pet feeding method, as it directly determines the accuracy of pet identification and the precision of subsequent feeding operations. Through feature similarity comparison, the pet feeding device of the present embodiment can determine the identity of the target pet and provide appropriate feeding information.

[0161] It's important to note that the feature similarity comparison process involves comparing the target pet's feature vector with each pre-recorded pet facial feature vector in the pre-recorded pet facial feature set. This can be accomplished by calculating the distance or similarity metric between the two feature vectors. Possible similarity metrics include Euclidean distance and cosine similarity. Euclidean distance measures the linear distance between two vectors in multidimensional space, while cosine similarity measures the cosine of the angle between two vectors, reflecting their directional similarity.

[0162] In some specific embodiments, in practical applications, feature similarity comparison can be achieved through the following steps:

[0163] Extract feature vectors from the target pet face image, which can be done by the pet recognition model.

[0164] Load pre-recorded pet facial feature groups from the database. Each feature group contains a pre-recorded pet's feature vector and corresponding feeding information.

[0165] The similarity between the feature vector of the target pet and the feature vector of each pre-recorded pet is calculated to obtain a similarity value, that is, feature similarity information.

[0166] It should be understood that the advantages of feature similarity comparison lie in its efficiency and accuracy. By calculating the similarity between the target pet's facial features and pre-recorded pet facial features, the pet feeding device of the present embodiment can quickly determine the target pet's identity. This method not only processes large amounts of feature data but also maintains high recognition accuracy in complex environments. Furthermore, feature similarity comparison can control the strictness of recognition by adjusting the similarity threshold, thereby adapting to different application scenarios.

[0167] In step S105 of some embodiments, in response to the presence of feature similarity information that meets a preset identity authentication condition, the pre-recorded pet corresponding to the feature similarity information is determined based on the unique Face ID of the pre-recorded pet, and the pet food dispensing operation or the pet food exposure operation is performed according to the pre-recorded pet food information of the matched pre-recorded pet.

[0168] It should be noted that step S105 is in response to the presence of feature similarity information that meets the preset identity authentication conditions, and determines the pre-recorded pet that matches the feature similarity information based on the unique Face ID of the pre-recorded pet, and performs the pet food dispensing operation or the pet food exposure operation according to the pre-recorded pet food information of the matched pre-recorded pet. The setting of the identity authentication conditions is the key to ensuring the accuracy of pet identification. This condition is a similarity threshold. Only when the similarity between the facial features of the target pet and the facial features of the pre-recorded pet exceeds this threshold, can it be considered that the target pet and the pre-recorded pet are successfully matched. The setting of this threshold needs to comprehensively consider the diversity of pet features and the accuracy of recognition to ensure that only truly matched pets can pass the identity authentication.

[0169] It should be noted that when the target pet's feature similarity information meets the identity authentication criteria, the pet feeding device of the present embodiment will identify the pre-recorded pet corresponding to the similarity information. This step is performed by comparing the target pet's feature vector with the facial feature vectors of each pre-recorded pet in the pre-recorded feature group to find the pre-recorded pet with the highest similarity. This process not only ensures the accuracy of the pet's identity but also provides a basis for subsequent feeding operations. In this way, the pet feeding device of the present embodiment can effectively prevent competition and accidental ingestion among pets, ensuring that each pet receives food that suits its needs.

[0170] It should be noted that, based on the determined pre-recorded pet food information of the pre-recorded pet, the pet feeding device of the embodiment of the present application will perform the corresponding pet food dispensing operation or pet food exposing operation.

[0171] In an embodiment of the present application, when it is detected that the feature similarity information meets the preset identity authentication conditions, the pre-recorded pet that matches the feature similarity information will be determined based on the unique Face ID of the pre-recorded pet. This process ensures that only pets that have been authenticated can trigger subsequent pet food distribution or exposure operations. Face ID is the unique identifier of each pet and runs through the entire identification and feeding process. When the embodiment of the present application compares the facial features of the target pet with the data in the pre-recorded pet facial feature library and finds that there is similarity information that meets the conditions, the identity of the target pet can be determined, and the corresponding pre-recorded pet information can be quickly located based on its Face ID.

[0172] After determining the matched pre-recorded pet, the embodiment of the present application will perform the corresponding pet food dispensing operation or pet food exposure operation according to the pre-recorded pet food information of the pet. The pre-recorded pet food information is customized according to the specific needs of each pet, including factors such as the pet's breed type, health status, growth stage, etc. For example, for an adult golden retriever, its feeding information may include high-protein, low-fat dog food to meet its daily activities. For an elderly cat, its feeding information may include easily digestible, vitamin-rich food to support its health. In this way, the pet feeding device of the embodiment of the present application can ensure that each pet can obtain a diet suitable for its health status and growth stage, thereby improving the scientificity and effectiveness of feeding.

[0173] In practical applications, the authentication conditions can be dynamically adjusted as needed. For example, when there are a large number of pets or the similarity of pet characteristics is high, the similarity threshold can be appropriately increased to ensure recognition accuracy. Conversely, when there are a small number of pets or the pet characteristics vary greatly, the similarity threshold can be appropriately lowered to improve recognition efficiency. This dynamic adjustment mechanism enables the pet feeding device of the present embodiment to adapt to different application scenarios and needs, further enhancing the personalized and intelligent level of pet feeding. The setting and adjustment of the authentication conditions need to be tailored to the specific pet feeding device and application scenario. For example, in a home environment, where there are fewer pets and their characteristics vary greatly, a lower similarity threshold can be used to improve recognition efficiency. In contrast, in places such as pet foster centers or pet hospitals, where there are a large number of pets and the similarity of their characteristics is high, a higher similarity threshold can be used to ensure recognition accuracy. In this way, the pet feeding device of the present embodiment can better meet the pet feeding needs of different scenarios, improving the pet's quality of life and the owner's satisfaction.

[0174] It should be understood that by setting and adjusting the identity authentication conditions, the accuracy of pet identification and feeding operations is ensured. By identifying a matching pre-recorded pet and executing the feeding operation based on its pre-recorded pet food information, the pet feeding device of the present embodiment can effectively meet the personalized dietary needs of each pet in a multi-pet household. This identity authentication-based feeding method not only improves the scientific nature and effectiveness of feeding, but also provides strong support for pet health management, significantly enhancing the pet's quality of life and the owner's feeding experience.

[0175] Reference Figure 7 According to some embodiments of the present application, the pre-recorded pet food information includes pet food type sub-information and pet food portion sub-information. In step S105, performing a pet food dispensing operation or a pet food exposing operation based on the pre-recorded pet food information may include:

[0176] Step S701, determining a target feeding plan based on pet food type sub-information and pet food portion sub-information;

[0177] Step S702: performing pet food dispensing or pet food exposing operations according to the target feeding plan.

[0178] In some embodiments, pre-recorded pet food information is key data in pet feeding methods, providing a personalized feeding plan for each pre-recorded pet. Pre-recorded pet food information includes pet food type sub-information and pet food serving size information, which together determine the content and quantity of the pet's diet. The pet food type sub-information specifies the type of pet food suitable for a specific pet, such as dry food, wet food, or prescription food, while the pet food serving size information specifies the amount to be fed per meal or per day. Accurately recording and applying this information ensures that each pet receives a diet that meets their health and nutritional needs.

[0179] In some embodiments, step S701 , a target feeding plan is determined based on the pet food type sub-information and the pet food portion sub-information;

[0180] It should be noted that before performing the pet food dispensing operation or the pet food exposing operation, the pet feeding device of the present application needs to determine the target feeding plan based on the pre-recorded pet food information of the pet. This step is completed by analyzing the pet food type sub-information and pet food portion sub-information in the pre-recorded pet food information. The pet feeding device of the present application will select the appropriate type of pet food based on factors such as the pet's breed, age, weight, and health status, and determine the feeding amount for each meal or day. For example, for an adult golden retriever, the pet feeding device of the present application can select high-protein, low-fat dry food and determine the feeding amount for each meal based on its weight and activity level. In this way, the pet feeding device of the present application can develop a personalized feeding plan for each pet to ensure that it obtains adequate nutrition.

[0181] In step S702 of some embodiments, a pet food dispensing operation or a pet food exposing operation is performed according to a target feeding plan.

[0182] It should be noted that after determining the target feeding plan, the pet feeding device of the present application will perform the pet food dispensing operation or the pet food exposing operation according to the plan. This step can be completed automatically by the pet feeding device to ensure the accuracy and timeliness of feeding. The pet feeding device will take out the corresponding type and quantity of pet food from the pet food storage area according to the feeding type and feeding amount in the target feeding plan, and feed it to the pet through the feeder. For example, if the target feeding plan stipulates a specific dry food and the feeding amount per meal, the feeding device will automatically take out the corresponding amount of dry food from the storage area and feed it to the pet at the appropriate time. In this way, the pet feeding device of the present application not only improves the efficiency of feeding, but also ensures that each pet can obtain food that suits its needs.

[0183] It should be understood that by executing pet food dispensing or pet food exposure operations based on pre-recorded pet food information, the pet feeding device of the present application can achieve personalized feeding for each pet in a multi-pet household. This not only meets the dietary needs of different pets, but also avoids competition and accidental ingestion among pets. In addition, the pet feeding device of the present application can dynamically adjust feeding information based on the pet's health status and growth stage, further improving the scientific nature and effectiveness of feeding. This automated feeding method not only improves feeding efficiency, but also provides strong support for pet health management, significantly enhancing the pet's quality of life and the owner's feeding experience.

[0184] Reference Figure 8 According to some embodiments of the present application, after performing the pet food dispensing operation or the pet food exposing operation according to the target feeding plan in step S702, the following steps may also be included:

[0185] Step S801, monitoring the pet eating in a preset image acquisition area to obtain a pet eating picture;

[0186] Step S802, identifying the target pet's eating action based on the pet eating picture to obtain the pet's eating status;

[0187] Step S803 , in response to the pet's eating state not meeting the standard eating state, the pet food dispensing operation or the pet food exposing operation is terminated.

[0188] In step S801 of some embodiments, pet eating is monitored in a preset image acquisition area to obtain a pet eating picture;

[0189] It should be noted that after performing the pet food dispensing operation or the pet food exposure operation according to the target feeding plan, the pet feeding device of the present application can further monitor the pet's eating. The purpose of this step is to ensure that the pet can eat correctly, avoid food waste and pet health problems. By monitoring the pet's eating process, the pet feeding device of the present application can understand the pet's eating status in real time and take measures when necessary to ensure the pet's diet is healthy. It should be pointed out that pet eating monitoring is performed on the preset image acquisition area to obtain the pet eating picture. In this way, the pet feeding device of the present application uses a camera to monitor the pet eating area in real time and capture the picture of the pet eating. These pictures can be used to analyze the pet's eating behavior and status.

[0190] It should be understood that the advantage of pet feeding monitoring is that it can provide real-time insights into a pet's eating habits, allowing for the timely identification and resolution of feeding issues. By monitoring a pet's eating behavior, the pet feeding device of this application can ensure that the pet receives adequate nutrition and avoid health issues caused by improper feeding. Furthermore, pet feeding monitoring can improve the convenience and satisfaction of pet owners with their pet's diet management, enhancing interaction and trust between pets and owners.

[0191] In step S802 of some embodiments, the eating action of the target pet is recognized based on the pet eating picture to obtain the pet's eating status;

[0192] It should be noted that the target pet's eating actions are identified based on the pet eating image to determine the pet's eating status. The pet feeding device of the present application uses image processing and behavior recognition technology to analyze the pet's eating actions and determine whether the pet is eating normally. For example, the pet feeding device of the present application can identify the pet's head movements, chewing movements, etc. to determine whether the pet is actively eating.

[0193] In step S803 of some embodiments, in response to the pet's eating state not meeting the standard eating state, the pet food dispensing operation or the pet food exposing operation is terminated.

[0194] It should be noted that in response to the pet's eating state not meeting the standard eating state, the pet food dispensing operation or the pet food exposure operation is terminated: If the pet feeding device of the present application determines that the pet's eating state does not meet the preset standard eating state, for example, the pet does not start eating within the specified time or exhibits abnormal behavior during eating, the pet feeding device of the present application will terminate the pet food dispensing operation or the pet food exposure operation. This can avoid food waste and ensure the pet's diet is healthy.

[0195] It's important to note that pet food intake monitoring has significant application value in a variety of scenarios. For example, in multi-pet households, monitoring pets' food intake can ensure that each pet receives adequate food, preventing competition and accidental ingestion. In places like pet care centers and veterinary hospitals, pet food intake monitoring can help staff better manage pets' diets and ensure their health and safety. Furthermore, pet food intake monitoring can be used for pet behavior research, providing a scientific basis for pet diet management and health care.

[0196] It should be understood that by monitoring pets' eating after dispensing or exposing pet food, the pet feeding device of the present application can ensure that pets are eating healthy and properly. This not only improves the pet's quality of life but also provides pet owners with a more convenient and reliable pet diet management solution. In this way, the pet feeding device of the present application can better meet the needs of multi-pet households and pet-related facilities, enhancing the pet's eating experience and health management results.

[0197] Reference Figure 9 The pet feeding device according to the embodiment of the present application may include:

[0198] A feature library acquisition module 901 is used to acquire a pre-recorded pet feature library, the pre-recorded pet feature library including a pre-recorded feature group corresponding to the pre-recorded pet, the pre-recorded feature group including the pre-recorded pet facial features, the pre-recorded pet's unique Face ID, and pre-recorded pet food information matching the pre-recorded pet;

[0199] An image acquisition module 902 is configured to acquire an image of a target pet and perform pet face detection on the acquired image to obtain a facial image of the target pet;

[0200] The feature extraction module 903 is used to call the pet recognition model to extract features from the target pet's facial image to obtain the target pet's facial features;

[0201] A feature comparison module 904 is used to compare the facial features of the target pet with the pre-recorded pet feature library to determine feature similarity information between the target pet and the pre-recorded pets;

[0202] The feeding execution module 905 is used to respond to the presence of feature similarity information that meets the preset identity authentication conditions, determine the pre-recorded pet that matches the feature similarity information based on the unique Face ID of the pre-recorded pet, and execute the pet food dispensing operation or the pet food exposure operation according to the pre-recorded pet food information of the matched pre-recorded pet.

[0203] It can be seen that the contents of the above-mentioned pet feeding method embodiment are all applicable to the embodiment of the present pet feeding device. The functions specifically implemented by the present pet feeding device embodiment are the same as those of the above-mentioned pet feeding method embodiment, and the beneficial effects achieved are also the same as those achieved by the above-mentioned pet feeding method embodiment.

[0204] Reference Figure 10 , Figure 10 The hardware structure of an electronic device according to another embodiment is shown. The electronic device may include:

[0205] The processor 1001 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0206] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program codes are stored in the memory 1002 and are called by the processor 1001 to execute the pet feeding method of the embodiments of this application.

[0207] Input / output interface 1003, used to implement information input and output;

[0208] Communication interface 1004, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0209] Bus 1005 , which transmits information between various components of the device (e.g., processor 1001 , memory 1002 , input / output interface 1003 , and communication interface 1004 );

[0210] The processor 1001 , the memory 1002 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via the bus 905 .

[0211] The embodiment of the present application further provides a computer program product, which includes a computer program. A processor of a computer device reads and executes the computer program, so that the computer device executes the above-mentioned pet feeding method.

[0212] The terms "first," "second," "third," "fourth," and the like (if any) in the specification of the present disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present disclosure described herein, for example, can be implemented in orders other than those illustrated or described herein. In addition, the terms "comprises" and "comprising," and any variations thereof, are intended to cover non-exclusive inclusions, e.g., a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or apparatus.

[0213] It should be understood that in the present disclosure, "at least one (item)" refers to one or more, and "plurality" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0214] It should be understood that in the description of the embodiments of the present application, multiple (or multiple items) means more than two, greater than, less than, exceed, etc. are understood to exclude the number itself, and above, below, within, etc. are understood to include the number itself.

[0215] In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0216] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0217] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0218] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the various embodiments of the present disclosure. The aforementioned storage medium may include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media that can store program codes.

[0219] It should also be understood that the various implementation methods provided in the embodiments of the present application can be combined arbitrarily to achieve different technical effects.

[0220] The above is a specific description of the implementation methods of the present disclosure, but the present disclosure is not limited to the above implementation methods. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present disclosure. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present disclosure.

Claims

1. A pet feeding method, characterized in that: Applicable to a pet feeding device, the pet feeding device is provided with a pet identification model, including: Obtaining a pre-recorded pet feature library, the pre-recorded pet feature library including a pre-recorded feature group corresponding to a pre-recorded pet, the pre-recorded feature group including pre-recorded pet facial features of the pre-recorded pet, a unique FaceID of the pre-recorded pet, and pre-recorded pet food information matching the pre-recorded pet; Capturing images of a target pet and performing pet face detection on the captured images to obtain a facial image of the target pet; Calling the pet recognition model to perform feature extraction on the target pet facial image to obtain target pet facial features; Performing feature similarity comparison on the facial features of the target pet in the pre-recorded pet feature library to determine feature similarity information between the target pet and the pre-recorded pet; In response to the presence of the feature similarity information satisfying a preset identity authentication condition, the pre-recorded pet corresponding to the feature similarity information is determined based on the unique Face ID of the pre-recorded pet, and the pet food dispensing operation or the pet food exposure operation is performed according to the pre-recorded pet food information of the matched pre-recorded pet.

2. The method according to claim 1, characterized in that The obtaining of a pre-recorded pet feature library, wherein the pre-recorded pet feature library includes a pre-recorded feature group corresponding to the pre-recorded pet, including: Acquire at least two pre-recorded feature groups corresponding to different pre-recorded pets, each of the pre-recorded feature groups comprising pre-recorded pet facial features of the pre-recorded pet, a unique Face ID of the pre-recorded pet, and pre-recorded pet food information matching the pre-recorded pet; The comparing the facial features of the target pet with the pre-recorded pet feature library for feature similarity to determine feature similarity information between the target pet and the pre-recorded pet includes: The facial features of the target pet are compared with the facial features of the pre-recorded pets in each of the pre-recorded feature groups for feature similarity to determine the feature similarity information between the target pet and each of the pre-recorded pets.

3. The method according to claim 2, characterized in that The obtaining of at least two pre-recorded feature groups corresponding to different pre-recorded pets includes: Obtaining the pre-recorded pet food information of each pre-recorded pet; Capturing images of different pre-recorded pets respectively to obtain a pre-recorded pet image corresponding to each pre-recorded pet; performing an image quality test on each of the pre-recorded pet images to obtain a quality test result corresponding to the pre-recorded pet image; In response to the quality detection result meeting a preset quality qualification condition, calling the pet recognition model to perform feature extraction on the pre-recorded pet image to obtain pre-recorded pet facial features corresponding to the pre-recorded pet; The pre-recorded pet facial features of each of the pre-recorded pets and the pre-recorded pet food information of each of the pre-recorded pets are matched and integrated to obtain each of the pre-recorded feature groups.

4. The method according to claim 3, characterized in that The pet recognition model encapsulates an image enhancement algorithm, a pet face capture algorithm, and a pet face recognition sub-model. The pet recognition model is called to extract features from the pre-recorded pet image to obtain pre-recorded pet facial features corresponding to the pre-recorded pet, including: Performing image enhancement processing on each of the pre-recorded pet images using an image enhancement algorithm to obtain a pre-recorded enhanced image; Invoking a preset pet face capture algorithm to capture the pet's facial area from the pre-recorded enhanced image; The pet facial recognition sub-model is used to perform pet facial recognition on the pet facial area to obtain the pre-recorded pet facial features.

5. The method according to claim 1, wherein The step of collecting images of a target pet and performing pet face detection on the collected images to obtain a facial image of the target pet includes: Performing a pet attraction operation; wherein the pet attraction operation is used to attract the target pet to approach the pet feeding device; In response to detecting that the target pet enters a preset image acquisition area in the pet feeding device, image acquisition is performed on the image acquisition area to obtain a facial image of the target pet.

6. The method according to claim 1, characterized in that The pre-recorded pet food information includes pet food type sub-information and pet food portion sub-information. The performing of the pet food dispensing operation or the pet food exposing operation according to the pre-recorded pet food information of the matched pre-recorded pet includes: determining a target feeding plan based on the pet food type sub-information and the pet food portion sub-information; The pet food dispensing operation or the pet food exposing operation is performed according to the target feeding plan.

7. The method according to claim 1, characterized in that After performing a pet food dispensing operation or a pet food exposing operation according to the pre-recorded pet food information of the matched pre-recorded pet, the method further includes: Monitor the pet eating in the preset image acquisition area to obtain the pet eating picture; Identifying the eating action of the target pet according to the pet eating picture to obtain the pet's eating status; In response to the pet's eating state not meeting the standard eating state, the pet food dispensing operation or the pet food exposing operation is terminated.

8. A pet feeding device, characterized in that: include: a feature library acquisition module, configured to acquire a pre-recorded pet feature library, the pre-recorded pet feature library comprising pre-recorded feature groups corresponding to pre-recorded pets, each of the pre-recorded feature groups comprising pre-recorded pet facial features of the pre-recorded pet, a unique Face ID of the pre-recorded pet, and pre-recorded pet food information matching the pre-recorded pet; An image acquisition module is used to acquire images of a target pet and perform pet face detection on the acquired images to obtain a facial image of the target pet; A feature extraction module is used to call a pet recognition model to extract features from the target pet's facial image to obtain facial features of the target pet; A feature comparison module is used to compare the facial features of the target pet with the pre-recorded pet feature library for feature similarity, so as to determine feature similarity information between the target pet and the pre-recorded pet; A feeding execution module is used to determine, in response to the presence of the feature similarity information satisfying a preset identity authentication condition, the pre-recorded pet that matches the feature similarity information based on the unique Face ID of the pre-recorded pet, and execute a pet food dispensing operation or a pet food exposing operation according to the pre-recorded pet food information of the matched pre-recorded pet.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the pet feeding method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The storage medium stores a program, and the program is executed by a processor to implement the pet feeding method according to any one of claims 1 to 7.

Images