Control method and device of pet feeder and pet feeder

Abstract

The present application provides a control method, device, and pet feeder for a pet feeder, relating to the field of intelligent control technology. The method comprises: when it is detected that the distance between the target pet and the feeding tray is within a preset distance range, obtaining multiple pet images captured by a camera device; determining the pet data of the target pet based on the pet images; judging whether the target pet is a pet in a first abnormal state based on the pet data, and configuring a split feeding strategy for the first abnormal state pet, wherein the first abnormal state pet is used to indicate that the fatness or thinness of the target pet is lower than the lower limit of a preset normal range, and the split feeding strategy is used to indicate that a specified first feeding amount is fed in batches within each specified first feeding period; and collaboratively controlling the food dispensing mechanism based on the split feeding strategy and / or feeding monitoring results. The present application improves the rationality and reliability of pet feeding and ensures the good health of different pets.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a control method and device for a pet feeder, and the pet feeder. Background Art

[0002] With the growing popularity of the pet market, some families now keep multiple pets, often sharing a single feeder. For example, cats vary in size, making mixed feeding prone to overeating by overweight cats. This leads to imbalanced food intake, with thinner cats undereating and overeating by overweight cats, potentially leading to health problems. Therefore, controlling pet feeders to prevent undereating and overeating is a pressing issue. Summary of the Invention

[0003] In order to solve the above-mentioned problems in the prior art, the present invention provides a control method and device for a pet feeder and a pet feeder, which can reduce the phenomenon of pets not eating enough or eating too much, improve the rationality of pet feeding, and ensure the good health of different pets.

[0004] In a first aspect, the present application provides a control method for a pet feeder, applicable to a pet feeder equipped with a camera device and a food dispensing mechanism, wherein the food dispensing mechanism includes a feeding tray for loading food; the method comprises:

[0005] When it is detected that the distance between the target pet and the feeding tray is within a preset distance range, a plurality of pet images captured by the camera device are acquired;

[0006] determining pet data of the target pet based on the pet image, the pet data including weight data and target age in months;

[0007] Based on the pet data, determining whether the target pet is a pet in a first abnormal state, and configuring a split feeding strategy for the first abnormal state pet, wherein the first abnormal state pet is used to indicate that the fatness or thinness of the target pet is lower than a lower limit of a preset normal range, and the split feeding strategy is used to instruct to feed a specified first feeding amount in each specified first feeding period in split feeding;

[0008] The food dispensing mechanism is cooperatively controlled based on the divided feeding strategy and / or feeding monitoring results, wherein the feeding monitoring results are used to indicate the detection results of the pet images captured by the camera device during the feeding process of executing the divided feeding strategy.

[0009] In a possible implementation, determining the pet data of the target pet based on the pet image includes:

[0010] Performing identity recognition on the pet image to obtain identity data of the target pet;

[0011] Based on the identity data, matching the corresponding target age in the information database, wherein the information database is configured with a month-age-weight mapping table and an identity mapping table of at least one target pet, the month-age-weight mapping table is used to indicate the correspondence between the age in months and the standard weight data, and the identity mapping table is used to indicate the correspondence between the identity of the target pet and the age in months;

[0012] Extracting the contour data of the target pet based on the pet image, and performing three-dimensional reconstruction on the contour data to obtain a reconstructed image;

[0013] Based on the reconstructed image, the appearance data of the target pet is measured, and the weight data of the target pet is determined according to the appearance data, the identity data and the target age in months.

[0014] In a possible implementation, determining whether the target pet is a pet in a first abnormal state based on the pet data, and configuring a split feeding strategy for the pet in the first abnormal state includes:

[0015] Based on the target age in months, matching corresponding standard weight data in the information database;

[0016] When the weight data of the target pet does not reach the matched standard weight data, it is determined that the fatness or thinness of the target pet is lower than the lower limit of the preset normal range, and the corresponding target pet is marked as a pet in a first abnormal state;

[0017] When the weight data of the target pet exceeds the matched standard weight data, it is determined that the fatness or thinness of the target pet is higher than the upper limit of the preset normal range, and the corresponding target pet is identified as a second abnormal state pet, and an adjusted feeding strategy is configured for the second abnormal state pet, wherein the adjusted feeding strategy is used to indicate a second feeding period and a corresponding second feeding amount, and the total feeding amount in the adjusted feeding strategy is less than the total feeding amount in the divided feeding strategy.

[0018] In a possible implementation, the coordinated control of the feed dispensing mechanism based on the divided feeding strategy and / or the feeding monitoring result includes:

[0019] During any of the first feeding periods, when it is detected that the pet image contains a pet in the first abnormal state, the first feeding amount is fed in divided portions according to the divided feeding strategy. During the current feeding process, when no pet image is detected to contain a pet in the second abnormal state, the next feeding is continued until the total amount of feeding during this first feeding period reaches the first feeding amount.

[0020] In a possible implementation, the collaboratively controlling the feed dispensing mechanism based on the divided feeding strategy and / or the feeding monitoring result further includes:

[0021] If it is detected that the pet image contains the pet in the second abnormal state during any feeding process within the first feeding period, the feeding is stopped until it is detected that the pet image contains only the pet in the first abnormal state.

[0022] In a possible implementation, the collaboratively controlling the feed dispensing mechanism based on the divided feeding strategy and / or the feeding monitoring result further includes:

[0023] Obtaining location data sent by a pet wearable device worn on the pet in the second abnormal state;

[0024] When the pet image detects that the pet in the first abnormal state is being fed and the position difference between the position data and the feeding plate is less than a preset difference threshold, an alarm signal is sent to the pet wearable device worn by the pet in the second abnormal state until the position difference is greater than the difference threshold.

[0025] In a possible implementation, the pet feeder is further configured with an audio device; and the method further includes:

[0026] When it is detected that the total amount of food fed in the first feeding period reaches the first feeding amount, a play signal is sent to the audio device, so that the audio device plays the specified audio in response to the play signal.

[0027] In a second aspect, the present application provides a control device for a pet feeder, which is applicable to a pet feeder equipped with a camera device and a food dispensing mechanism, wherein the food dispensing mechanism includes a feeding tray for loading food; the device includes:

[0028] an image acquisition module, configured to acquire a plurality of pet images captured by the camera device when detecting that the distance between the target pet and the feeding tray is within a preset distance range;

[0029] an image analysis module, configured to determine pet data of the target pet based on the pet image, the pet data including weight data and target age in months;

[0030] a determination module, configured to determine, based on the pet data, whether the target pet is a pet in a first abnormal state, and configure a split feeding strategy for the first abnormal state pet, wherein the first abnormal state pet is used to indicate that the fatness or thinness of the target pet is lower than a lower limit of a preset normal range, and the split feeding strategy is used to instruct to feed a specified first feeding amount in each specified first feeding period in split feeding;

[0031] A control module is used to collaboratively control the food dispensing mechanism based on the divided feeding strategy and / or feeding monitoring results, wherein the feeding monitoring results are used to indicate the detection results of the pet images captured by the camera device during the feeding process of implementing the divided feeding strategy.

[0032] In a third aspect, the present application provides a pet feeder comprising: a camera device, a food dispensing mechanism, and a control unit, wherein the food dispensing mechanism comprises a feeding tray for loading food, the camera device and the food dispensing mechanism are both connected to the control unit, and the control unit executes the steps of the method for controlling the pet feeder according to the first aspect or any possible implementation of the first aspect.

[0033] In one possible implementation, the control unit is communicatively connected to a pet wearable device worn on a target pet.

[0034] The control method, device and pet feeder of the pet feeder provided in the present application collect multiple pet images of the target pet through a camera device, and then determine the weight data and target age of the target pet based on the pet images to judge whether the target pet is a pet in a first abnormal state, and configure a split feeding strategy for the pet in the first abnormal state, so as to collaboratively control the food dispensing mechanism based on the split feeding strategy and / or feeding monitoring results. In this way, by identifying the fat and thin differences of the target pets and configuring corresponding feeding strategies, the feeding amount of the feed can be effectively and accurately controlled. At the same time, by performing split feeding for thin pets and collaboratively controlling the food dispensing mechanism based on the feeding monitoring results, the phenomenon of thin cats not eating enough or fat cats eating too much can be reduced, thereby improving the efficiency and reliability of feeding control, improving the rationality of pet feeding, and ensuring the good health of different pets. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of a method for controlling a pet feeder provided in an embodiment of the present application;

[0036] Figure 2 A schematic structural diagram of a control device for a pet feeder provided in an embodiment of the present application;

[0037] Figure 3A schematic structural diagram of a pet feeder provided in an embodiment of the present application;

[0038] Figure 4 This is a schematic structural diagram of the pet feeder provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0040] See also Figure 1 This is a flow chart of a control method for a pet feeder provided in an embodiment of the present application. The control method is applicable to a pet feeder equipped with a camera and a food dispensing mechanism, wherein the food dispensing mechanism includes a feeding tray for loading food. The method includes steps S101 to S104.

[0041] S101 . When it is detected that the distance between the target pet and the feeding tray is within a preset distance range, a plurality of pet images captured by the camera device are acquired.

[0042] In this application, the pet feeder is equipped with a camera device, which can be a rotatable camera that captures images of the pet (including images of the target pet approaching the feeding tray and images of the pet eating). The camera device can be mounted on the top, side, or above the feeding tray of the pet feeder to cover the area surrounding the feeder.

[0043] The food dispensing mechanism can be located below the food storage barrel within the pet feeder, precisely dispensing food into the feeding tray through mechanical mechanisms (e.g., a rotating dispensing mechanism and plunger control). In this application, the dispensing mechanism is controlled based on the feeding period and feeding amount specified in a feeding strategy (e.g., a split feeding strategy or a regulated feeding strategy). Therefore, this application utilizes a camera to monitor the pet's feeding behavior and controls the dispensing mechanism to ensure the execution of the feeding strategy. Together, these two mechanisms control pet feeding, improving the efficiency and reliability of feeding control.

[0044] S102: Determine pet data of the target pet based on the pet image, where the pet data includes weight data and target age in months.

[0045] In this application, the target pet's age, breed, and other information are stored in advance, along with the age and corresponding standard weight data. Image recognition of the pet's image is then used to identify the target pet and match the corresponding age, breed, and other data. Identity recognition can be achieved through pupils, facial features, palm prints, and other characteristic information, or through information such as a device identifier, RFID tag, or QR code tag on a pet wearable device worn by the target pet, though this application does not limit this. At the same time, image recognition of the pet's image can be used to estimate the pet's weight.

[0046] It should be noted that image recognition refers to the process of using computer technology to understand, analyze and classify information such as targets, scenes, features, etc. in images. It is a practical application of deep learning algorithms. It uses specific algorithms and models to identify the content in images, such as distinguishing people, animals, objects, text, etc. in the image, and determining their category, location, posture and other related information.

[0047] S103. Based on the pet data, determine whether the target pet is a pet in a first abnormal state, and configure a split feeding strategy for the first abnormal state pet, wherein the first abnormal state pet is used to indicate that the fatness or thinness of the target pet is lower than the lower limit of a preset normal range, and the split feeding strategy is used to indicate that a specified first feeding amount is fed in batches within each specified first feeding period.

[0048] S104. Coordinately control the food dispensing mechanism based on the divided feeding strategy and / or feeding monitoring results, wherein the feeding monitoring results are used to indicate detection results of the pet images captured by the camera device during the feeding process of executing the divided feeding strategy.

[0049] In this application, the target pet's weight data and standard weight data are used to determine whether the target pet's fatness or thinness is within a preset normal range, thereby determining whether the target pet is a pet in the first abnormal state. A pet in the first abnormal state is one whose fatness or thinness is below the lower limit of the preset normal range, i.e., a pet in the first abnormal state is a pet that is too thin.

[0050] It should be noted that in the mixed feeding of overweight pets (i.e., pets in the second abnormal state) and thin pets (i.e., pets in the first abnormal state), because overweight pets have greater appetites, size, and strength than thin pets, the overweight pets are prone to competing for food, resulting in an imbalance in food intake between the pets, i.e., thin pets cannot eat their fill or overweight pets eat too much. To address this issue, the present application configures a split-feeding strategy for pets in the first abnormal state (i.e., thin pets). The split-feeding strategy includes a designated first feeding period and a corresponding first feeding amount. The split-feeding strategy instructs that the first feeding amount be fed in batches (i.e., fed in multiple batches) within each first feeding period. The strategy also uses the detection results of pet images captured by the camera device during the feeding process (i.e., whether the pet images only contain pets in the first abnormal state) to collaboratively control the split feeding of the first feeding amount, thereby controlling the food dispensing mechanism. In this way, subsequent feeding is controlled based on the real-time feeding image. The divided feeding strategy can reduce the phenomenon of overweight pets snatching up a large amount of food from thin pets, causing the overweight pets to overeat. At the same time, this application can avoid the situation where the thin pets do not finish eating after a one-time feeding (i.e., the first feeding amount is fed in one go), resulting in the overweight pets eating the remaining food on the feeding tray. This reduces the phenomenon of pets not eating enough or overeating, improves the rationality of pet feeding, can effectively prevent overweight pets from overeating, and ensure the good health of different pets.

[0051] The control method of the pet feeder provided in this embodiment captures multiple pet images of a target pet through a camera device, and then determines the weight data and target age of the target pet based on the pet images to determine whether the target pet is a pet in a first abnormal state, and configures a divided feeding strategy for the pet in the first abnormal state, thereby collaboratively controlling the food dispensing mechanism based on the divided feeding strategy and / or feeding monitoring results. In this way, by identifying the fatness and thinness differences of the target pets and configuring corresponding feeding strategies, the feeding amount of the feed can be effectively and accurately controlled. At the same time, by performing divided feeding for thin pets and collaboratively controlling the food dispensing mechanism based on the feeding monitoring results, the phenomenon of thin cats not eating enough or fat cats eating too much can be reduced, thereby improving the efficiency and reliability of feeding control, improving the rationality of pet feeding, and ensuring the good health of different pets.

[0052] In some embodiments, determining the pet data of the target pet based on the pet image includes:

[0053] Performing identity recognition on the pet image to obtain identity data of the target pet;

[0054] Based on the identity data, matching the corresponding target age in the information database, wherein the information database is configured with a month-age-weight mapping table and an identity mapping table of at least one target pet, the month-age-weight mapping table is used to indicate the correspondence between the age in months and the standard weight data, and the identity mapping table is used to indicate the correspondence between the identity of the target pet and the age in months;

[0055] Extracting the contour data of the target pet based on the pet image, and performing three-dimensional reconstruction on the contour data to obtain a reconstructed image;

[0056] Based on the reconstructed image, the appearance data of the target pet is measured, and the weight data of the target pet is determined according to the appearance data, the identity data and the target age in months.

[0057] In this embodiment, the identity data includes information such as age in months and breed, and the pet's identity data is determined through identity recognition. The identity mapping table contains the correspondence between the target pet's identity and age in months, and the age-in-month weight mapping table is used to indicate the correspondence between age in months and standard weight data. The pet's breed, age in months, and the standard weight data corresponding to the breed and age in months are then determined using the identity mapping table and the age-in-month weight mapping table. It should be noted that by matching the corresponding age in months in the identity mapping table through identity recognition, the target age in months is determined based on the input time of the age in months in the identity mapping table and the current time. This allows for real-time updates of the target age in months, aligning with the changing trend of the pet's weight with age and breed, and improving the accuracy of weight calculations.

[0058] Next, multiple pet images are acquired, which may include various body parts (such as the face, torso, limbs, and buttocks). The pet's outline data is extracted from these acquired pet images. This extracted outline data is then used for 3D reconstruction, mapping the pet's outline into a 3D voxel space. Using the reconstructed images, the pet's appearance data is measured, including key dimensions such as abdominal circumference, chest circumference (at the widest point behind the front legs), back length (from the base of the neck to the base of the tail), and shoulder height (from the highest point of the neck to the ground). The target pet's weight is then determined based on the pet's appearance data, identification data (such as breed), and target age.

[0059] Therefore, this embodiment determines the target age of the target pet through the information database and estimates the pet's appearance data through the pet image, thereby taking into account the appearance estimation, breed and target age, improving the accuracy of pet weight estimation, improving the accuracy of strategy selection, and improving the reliability of feeding control.

[0060] In some embodiments, determining whether the target pet is a pet in a first abnormal state based on the pet data, and configuring a split feeding strategy for the first abnormal state pet, includes:

[0061] Based on the target age in months, matching corresponding standard weight data in the information database;

[0062] When the weight data of the target pet does not reach the matched standard weight data, it is determined that the fatness or thinness of the target pet is lower than the lower limit of the preset normal range, and the corresponding target pet is marked as a pet in a first abnormal state;

[0063] When the weight data of the target pet exceeds the matched standard weight data, it is determined that the fatness or thinness of the target pet is higher than the upper limit of the preset normal range, and the corresponding target pet is identified as a second abnormal state pet, and an adjusted feeding strategy is configured for the second abnormal state pet, wherein the adjusted feeding strategy is used to indicate a second feeding period and a corresponding second feeding amount, and the total feeding amount in the adjusted feeding strategy is less than the total feeding amount in the divided feeding strategy.

[0064] In this embodiment, the target pet's weight data and standard weight data corresponding to its age in months are used to determine the target pet's obesity level, thereby determining whether the target pet is a pet in the first abnormal state or a pet in the second abnormal state. The standard weight data may be a normal weight range related to the pet's age in months and breed. Specifically, if the pet's weight data does not reach the standard weight data, the target pet's obesity level is considered to be below the lower limit of a preset normal range, indicating that the first abnormal state pet is characterized as an underweight pet. If the pet's weight data exceeds the standard weight data, the target pet's obesity level is considered to be above the upper limit of a preset normal range, and the corresponding target pet is identified as a pet in the second abnormal state, indicating that the second abnormal state pet is characterized as an overweight pet.

[0065] Furthermore, the present application determines a corresponding feeding strategy based on the fatness or thinness of the pet. The feeding strategy includes a split feeding strategy and a regulated feeding strategy. The feeding strategy is used to indicate the feeding period and the corresponding feeding amount. Optionally, the split feeding strategy is mainly for thin pets, and the regulated feeding strategy is mainly for fat pets. In this case, the total feeding amount of the split feeding strategy will be greater than the total feeding amount of the regulated feeding strategy, thereby increasing the feeding for thin pets and reducing the feeding for fat pets, ensuring that pets of different body sizes can be fed reasonably, protecting the health of different pets, and improving the accuracy and efficiency of feeding control.

[0066] Specifically, this embodiment configures an adjusted feeding strategy for a pet in a second abnormal state (i.e., a slightly overweight pet). The adjusted feeding strategy includes a specified second feeding period and a corresponding second feeding amount. The adjusted feeding strategy can indicate that the second feeding amount is fed in batches and / or all at once within each second feeding period. This application does not limit this.

[0067] Therefore, this embodiment uses the target pet's weight data and standard weight data to identify whether the pet is in the first abnormal state or the second abnormal state, and then configures a corresponding feeding strategy based on the pet's body size difference. Subsequently, a split feeding strategy is configured for the first abnormal state pet, and an adjusted feeding strategy is configured for the second abnormal state pet. This ensures that the feeding amount for thin pets is increased while the feeding amount for overweight pets is reduced, reducing the occurrence of undereating or overeating in pets, improving the rationality of pet feeding, effectively preventing overeating in overweight pets, and ensuring the good health of different pets.

[0068] In some embodiments, the coordinated control of the feed dispensing mechanism based on the divided feeding strategy and / or feeding monitoring results includes:

[0069] During any of the first feeding periods, when it is detected that the pet image contains a pet in the first abnormal state, the first feeding amount is fed in divided portions according to the divided feeding strategy. During the current feeding process, when no pet image is detected to contain a pet in the second abnormal state, the next feeding is continued until the total amount of feeding during this first feeding period reaches the first feeding amount.

[0070] In this embodiment, real-time feeding monitoring is achieved by capturing pet images captured by a camera device in real time and detecting pet images within a first feeding period. Specifically, a split-feeding strategy is used to instruct the pet to feed a first feeding amount in split portions within the first feeding period. For example, the first feeding amount is divided into multiple feeding portions, and then food of the feeding portions is fed in multiple sub-periods within the first feeding period until the total amount fed in the first feeding period reaches the first feeding amount. Subsequently, if the feeding monitoring result indicates that a pet in a first abnormal state (i.e., a thin pet) is detected in the pet image for the first time within the first feeding period, the pet in the first abnormal state is deemed to be near the feeding tray. In this case, the pet is fed the first feeding amount according to the split-feeding strategy, i.e., the first feeding of the aforementioned feeding portion is performed. Furthermore, when the pet image identifies that the pet in the first abnormal state is eating (i.e., this feeding process), the pet image detects that only the pet in the first abnormal state (i.e., the thin pet) appears, and the pet in the second abnormal state (i.e., the fat pet) does not appear, then it is considered that the fat pet does not show any food-grabbing behavior, and the thin pet can eat continuously, then the next feeding is triggered, that is, the second feeding of the above-mentioned feeding amount of food, until the total amount of feeding in the first feeding period reaches the first feeding amount.

[0071] Therefore, this embodiment combines the feeding monitoring results and the divided feeding strategy. When the feeding monitoring results detect that the pet is only eating in the first abnormal state, the next feeding is triggered, thereby ensuring the food intake of thin pets, improving the rationality of pet feeding, and ensuring the reliability and efficiency of feeding control.

[0072] In some embodiments, the collaborative control of the feed dispensing mechanism based on the divided feeding strategy and / or feeding monitoring results further includes:

[0073] If it is detected that the pet image contains the pet in the second abnormal state during any feeding process within the first feeding period, the feeding is stopped until it is detected that the pet image contains only the pet in the first abnormal state.

[0074] In this embodiment, when a pet in a first abnormal state is identified by the pet image and a pet in a second abnormal state (i.e., a fat pet) appears during the eating process (i.e., the current feeding process), it is considered that the fat pet is snatching food, so the next feeding is stopped to avoid the second abnormal state pet snatching food and causing overeating, until it is detected that the pet image only contains the pet in the first abnormal state (the thin pet) and does not contain the pet in the second abnormal state (the fat pet). At this time, the fat pet leaves the feeding plate and the thin pet approaches the feeding plate, which triggers the continuation of the next feeding, and so on, until the first feeding amount is completed.

[0075] It should be noted that if it is detected that the pet image does not contain the first abnormal state pet and the second abnormal state pet after any feeding in the first feeding period, it is considered that the thin pet does not continue to eat, and the next feeding is stopped.

[0076] Therefore, this embodiment combines the feeding monitoring results and the divided feeding strategy. When the feeding monitoring results detect that the pet is in the second abnormal state, the next feeding is stopped until it is detected that only the pet is in the first abnormal state. The next feeding is resumed, thereby avoiding the situation where obese pets grab food and eat too much, improving the rationality of pet feeding, and ensuring the reliability and efficiency of feeding control.

[0077] In some embodiments, the collaborative control of the feed dispensing mechanism based on the divided feeding strategy and / or feeding monitoring results further includes:

[0078] Obtaining location data sent by a pet wearable device worn on the pet in the second abnormal state;

[0079] When the pet image detects that the pet in the first abnormal state is being fed and the position difference between the position data and the feeding plate is less than a preset difference threshold, an alarm signal is sent to the pet wearable device worn by the pet in the second abnormal state until the position difference is greater than the difference threshold.

[0080] In this embodiment, the pet wearable device can be a collar, which can be a vibrating collar, and each target pet wears the pet wearable device. If a pet in a first abnormal state is detected eating and a pet in a second abnormal state is relatively close to the feeding tray, the pet in the second abnormal state is considered to be engaging in food snatching behavior. A corresponding alarm signal is generated and sent to the pet wearable device. Upon receiving the alarm signal, the pet wearable device generates an alarm, such as a vibration, to alert the pet in the second abnormal state to the behavior and drive the pet away from the feeding tray, thereby reducing disturbances to the first abnormal state pet while eating and increasing the first abnormal state pet's food intake.

[0081] In addition, by configuring pet wearable devices to alert pets in the second abnormal state, behavioral training of pets in the second abnormal state can be achieved, so that pets in the second abnormal state can develop habits and improve the efficiency and reliability of feeding control.

[0082] Therefore, this embodiment configures the pet wearable device to alert the pet in the second abnormal state, so as not to disturb the eating of the pet in the first abnormal state, improves the efficiency and reliability of feeding control, reduces the phenomenon of thin cats not eating enough or fat cats eating too much, and ensures the good health of different pets.

[0083] In this application, even if the pet wearable device fails to prevent the pet from snatching food in the second abnormal state, it can effectively avoid the situation where the pet in the second abnormal state overeats due to snatching food by implementing a divided feeding strategy.

[0084] In some embodiments, the pet feeder is further configured with an audio device; and the method further comprises:

[0085] When it is detected that the total amount of food fed in the first feeding period reaches the first feeding amount, a play signal is sent to the audio device, so that the audio device plays the specified audio in response to the play signal.

[0086] In this embodiment, the audio device can be configured on the pet feeder. After the first feeding amount is fed in each first feeding period, the audio device is triggered to play a specified audio, thereby implementing feeding training for the pet in the first abnormal state, thereby improving feeding efficiency and reliability.

[0087] See also Figure 2 This is a schematic diagram of a control device for a pet feeder according to an embodiment of the present application. The control device 200 is suitable for a pet feeder equipped with a camera and a food dispensing mechanism, wherein the food dispensing mechanism includes a feeding tray for loading food. The control device 200 includes:

[0088] The image acquisition module 201 is configured to acquire a plurality of pet images captured by the camera device when it is detected that the distance between the target pet and the feeding tray is within a preset distance range;

[0089] An image analysis module 202 is configured to determine pet data of the target pet based on the pet image, the pet data including weight data and target age in months;

[0090] a determination module 203 for determining, based on the pet data, whether the target pet is a pet in a first abnormal state, and configuring a split feeding strategy for the first abnormal state pet, wherein the first abnormal state pet indicates that the target pet's fatness or thinness is below a lower limit of a preset normal range, and the split feeding strategy indicates that a specified first feeding amount is fed in split portions within each specified first feeding period;

[0091] The control module 204 is used to collaboratively control the food dispensing mechanism based on the divided feeding strategy and / or feeding monitoring results, wherein the feeding monitoring results are used to indicate the detection results of the pet images captured by the camera device during the feeding process of implementing the divided feeding strategy.

[0092] In some embodiments, the image analysis module 202 includes:

[0093] an identification unit, configured to perform identification on the pet image to obtain the identity data of the target pet;

[0094] A data matching unit is configured to match the corresponding target age in a database based on the identity data, wherein the database is configured with a monthly age-weight mapping table and an identity mapping table of at least one target pet, the monthly age-weight mapping table is used to indicate the correspondence between the monthly age and the standard weight data, and the identity mapping table is used to indicate the correspondence between the identity of the target pet and the monthly age;

[0095] a reconstruction unit, configured to extract contour data of the target pet based on the pet image, and perform three-dimensional reconstruction on the contour data to obtain a reconstructed image;

[0096] A weight measurement unit is used to measure the appearance data of the target pet based on the reconstructed image, and determine the weight data of the target pet according to the appearance data, the identity data and the target age in months.

[0097] In some embodiments, the determination module 203 includes:

[0098] a standard weight matching unit, configured to match corresponding standard weight data in the information database based on the target age;

[0099] a first abnormal state pet identification unit, configured to determine that the fatness or thinness of the target pet is lower than a lower limit of a preset normal range when the weight data of the target pet does not reach the matched standard weight data, and identify the corresponding target pet as a first abnormal state pet;

[0100] The second abnormal state pet identification unit is used to determine that the fatness of the target pet is higher than the upper limit of the preset normal range when the weight data of the target pet exceeds the matched standard weight data, identify the corresponding target pet as a second abnormal state pet, and configure an adjusted feeding strategy for the second abnormal state pet, wherein the adjusted feeding strategy is used to indicate a second feeding period and a corresponding second feeding amount, and the total feeding amount in the adjusted feeding strategy is less than the total feeding amount in the divided feeding strategy.

[0101] In some embodiments, the control module 204 includes:

[0102] The first strategy execution unit is configured to trigger, when detecting that the pet image contains the pet in the first abnormal state within any of the first feeding time periods, the divided feeding of the first feeding amount according to the divided feeding strategy; and when no pet image contains the pet in the second abnormal state during the current feeding process, continuing the next feeding until the total amount of feeding within the first feeding time period reaches the first feeding amount.

[0103] In some embodiments, the control module 204 further includes:

[0104] The second strategy execution unit is configured to stop feeding in batches when it is detected that the pet image contains the pet in the second abnormal state during any feeding process within the first feeding period, until it is detected that the pet image only contains the pet in the first abnormal state.

[0105] In a possible implementation, the control module 204 further includes:

[0106] a position data acquiring unit, configured to acquire position data sent by a pet wearable device worn on the pet in the second abnormal state;

[0107] An alarm unit is configured to send an alarm signal to a pet wearable device worn by the pet in the second abnormal state when it is detected from the pet image that the pet in the first abnormal state is being fed and the position difference between the position data and the feeding plate is less than a preset difference threshold, until the position difference is greater than the difference threshold.

[0108] In one possible implementation, the pet feeder is further configured with an audio device; the apparatus 200 further includes:

[0109] The audio control unit is configured to send a play signal to the audio device when detecting that the total amount of food fed during the first feeding period reaches the first feeding amount, so that the audio device plays the specified audio in response to the play signal.

[0110] The device of the embodiment of the present application can execute the method provided by the embodiment of the present application, and its implementation principle is similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, and will not be repeated here.

[0111] See also Figure 3 This is a structural schematic diagram of a pet feeder provided in an embodiment of the present application. The present application provides a pet feeder 300, including: a camera device 301, a food dispensing mechanism 302 and a control unit 303. The food dispensing mechanism 302 includes a feeding tray for loading food. The camera device 301 and the food dispensing mechanism 302 are both connected to the control unit 303, and the control unit 303 executes the steps of the above-mentioned pet feeder control method.

[0112] In a possible implementation, the control unit 303 is in communication with a pet wearable device 400 worn on a target pet.

[0113] In the description of the embodiments of the present invention, the terms "first," "second," "third," and "fourth" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly specifying the number of the technical features indicated. Therefore, a feature specified as "first," "second," "third," or "fourth" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0114] In the description of the embodiments of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "installed," "connected," "connected," and "assembled" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to direct connections, indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention in specific circumstances.

[0115] In the description of the embodiments of the present invention, specific features, structures, materials or characteristics may be combined in an appropriate manner in any one or more embodiments or examples.

[0116] In describing the embodiments of the present invention, it should be understood that "-" and "~" represent a range between two values, and the range includes the endpoints. For example, "AB" represents a range greater than or equal to A and less than or equal to B. "A~B" represents a range greater than or equal to A and less than or equal to B.

[0117] In describing the embodiments of the present invention, the term "and / or" is used herein to describe a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the character " / " is generally used herein to indicate that the associated objects are in an "or" relationship.

[0118] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for controlling a pet feeder, characterized in that: A pet feeder is suitable for being equipped with a camera device and a food dispensing mechanism, wherein the food dispensing mechanism includes a feeding tray for loading food; the method comprises: When it is detected that the distance between the target pet and the feeding tray is within a preset distance range, a plurality of pet images captured by the camera device are acquired; determining pet data of the target pet based on the pet image, the pet data including weight data and target age in months; Based on the pet data, determining whether the target pet is a pet in a first abnormal state, and configuring a split feeding strategy for the first abnormal state pet, wherein the first abnormal state pet is used to indicate that the fatness or thinness of the target pet is lower than a lower limit of a preset normal range, and the split feeding strategy is used to instruct to feed a specified first feeding amount in each specified first feeding period in split feeding; The food dispensing mechanism is cooperatively controlled based on the split feeding strategy and / or feeding monitoring results, wherein the feeding monitoring results are used to indicate the detection results of the pet images captured by the camera device during the feeding process of executing the split feeding strategy, including: in any first feeding period, when it is detected that the pet image contains a pet in the first abnormal state, the first feeding amount is triggered to be split according to the split feeding strategy, and when the pet image does not contain a pet in the second abnormal state during the current feeding process, the next feeding is continued until the total feeding amount in the first feeding period reaches the first feeding amount, and an adjusted feeding strategy is configured for the pet in the second abnormal state, the second abnormal state pet is used to indicate that the fatness or thinness degree is higher than the upper limit of the preset normal range, the adjusted feeding strategy is used to indicate a second feeding period and a corresponding second feeding amount, and the total feeding amount in the adjusted feeding strategy is less than the total feeding amount in the split feeding strategy.

2. The pet feeder control method according to claim 1, characterized in that: The determining of the pet data of the target pet based on the pet image includes: Performing identity recognition on the pet image to obtain identity data of the target pet; Based on the identity data, matching the corresponding target age in the information database, wherein the information database is configured with a month-age-weight mapping table and an identity mapping table of at least one target pet, the month-age-weight mapping table is used to indicate the correspondence between the age in months and the standard weight data, and the identity mapping table is used to indicate the correspondence between the identity of the target pet and the age in months; Extracting the contour data of the target pet based on the pet image, and performing three-dimensional reconstruction on the contour data to obtain a reconstructed image; Based on the reconstructed image, the appearance data of the target pet is measured, and the weight data of the target pet is determined according to the appearance data, the identity data and the target age in months.

3. The pet feeder control method according to claim 2, characterized in that: The determining, based on the pet data, whether the target pet is a pet in a first abnormal state, and configuring a divided feeding strategy for the pet in the first abnormal state includes: Based on the target age in months, matching corresponding standard weight data in the information database; When the weight data of the target pet does not reach the matched standard weight data, it is determined that the fatness or thinness of the target pet is lower than the lower limit of the preset normal range, and the corresponding target pet is marked as a pet in a first abnormal state; When the weight data of the target pet exceeds the matched standard weight data, it is determined that the fatness or thinness of the target pet is higher than the upper limit of the preset normal range, and the corresponding target pet is identified as a pet in the second abnormal state.

4. The pet feeder control method according to claim 3, characterized in that: The coordinated control of the feed dispensing mechanism according to the divided feeding strategy and / or the feeding monitoring result further includes: If it is detected that the pet image contains the pet in the second abnormal state during any feeding process within the first feeding period, the feeding is stopped until it is detected that the pet image contains only the pet in the first abnormal state.

5. The pet feeder control method according to claim 4, characterized in that: The coordinated control of the feed dispensing mechanism according to the divided feeding strategy and / or the feeding monitoring result further includes: Obtaining location data sent by a pet wearable device worn on the pet in the second abnormal state; When the pet image detects that the pet in the first abnormal state is being fed and the position difference between the position data and the feeding plate is less than a preset difference threshold, an alarm signal is sent to the pet wearable device worn by the pet in the second abnormal state until the position difference is greater than the difference threshold.

6. The pet feeder control method according to claim 5, characterized in that: The pet feeder is further configured with an audio device; the method further comprises: When it is detected that the total amount of food fed in the first feeding period reaches the first feeding amount, a play signal is sent to the audio device, so that the audio device plays the specified audio in response to the play signal.

7. A control device for a pet feeder, characterized in that: A pet feeder is suitable for being equipped with a camera device and a food dispensing mechanism, wherein the food dispensing mechanism includes a feeding tray for loading food; the device includes: an image acquisition module, configured to acquire a plurality of pet images captured by the camera device when detecting that the distance between the target pet and the feeding tray is within a preset distance range; an image analysis module, configured to determine pet data of the target pet based on the pet image, the pet data including weight data and target age in months; a determination module, configured to determine, based on the pet data, whether the target pet is a pet in a first abnormal state, and configure a split feeding strategy for the first abnormal state pet, wherein the first abnormal state pet is used to indicate that the fatness or thinness of the target pet is lower than a lower limit of a preset normal range, and the split feeding strategy is used to instruct to feed a specified first feeding amount in each specified first feeding period in split feeding; The control module is configured to collaboratively control the food dispensing mechanism based on the split feeding strategy and / or feeding monitoring results, wherein the feeding monitoring results are used to indicate detection results of pet images captured by the camera device during the feeding process of executing the split feeding strategy, including: when, in any of the first feeding time periods, it is detected that the pet image contains a pet in the first abnormal state, triggering split feeding of the first feeding amount according to the split feeding strategy; and when no pet in the second abnormal state is detected in the pet image during the current feeding process, continuing the next feeding until the total feeding amount in the first feeding time period reaches the first feeding amount, configuring an adjusted feeding strategy for the pet in the second abnormal state, the second abnormal state pet being used to indicate that the fatness or thinness degree is higher than the upper limit of the preset normal range, the adjusted feeding strategy being used to indicate a second feeding time period and a corresponding second feeding amount, and the total feeding amount in the adjusted feeding strategy being less than the total feeding amount in the split feeding strategy.

8. A pet feeder, characterized in that: include: A camera device, a food discharging mechanism and a control unit, wherein the food discharging mechanism includes a feeding tray for loading food, the camera device and the food discharging mechanism are both connected to the control unit, and the control unit executes the steps of the control method of the pet feeder according to any one of claims 1 to 6.

9. The pet feeder according to claim 8, characterized in that: The control unit is communicatively connected to a pet wearable device worn on a target pet.

Images