Control method and equipment of pet feeder and storage medium
By implementing surplus food and behavioral testing in pet feeders, batch feeding is achieved, which solves the problem that traditional pet feeders cannot flexibly respond to pet food needs, reduces food waste and improves user experience.
Patent Information
- Application Number
- CN202411061294.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-12-17
AI Technical Summary
Traditional pet feeders cannot flexibly respond to pet’s actual eating needs, resulting in food waste and health problems. The feeding method is mechanically scheduled and quantitative, ignoring the eating scenarios of pets.
By realizing surplus food detection and behavioral detection in pet feeders, feeding is carried out in batches according to the received feeding instructions. If the surplus food exceeds the threshold, feeding will be suspended or stopped. If it is less than the threshold, feeding will continue until the specified amount reaches Serving size.
Reduce food waste, improve the user experience of pet feeders, ensure that feeding is more in line with the actual eating needs of pets, and avoid food overflow or accumulation.
Smart Images

Figure CN119148559A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of video detection technology, and in particular to a control method, device and storage medium for a pet feeder. Background Art
[0002] In order to meet the feeding needs and convenience of pet owners, pet feeders have emerged as an innovative device. Pet feeders are designed to provide pet owners with an automatic feeding solution, helping to reduce the burden of daily feeding.
[0003] However, traditional pet feeders usually have some shortcomings. They only mechanically output pet food at a fixed time and fixed quantity. They do not take into account the actual feeding needs of pets, which may cause excessive pet food to accumulate in the feeding tray, and then easily lead to problems such as food spoilage. Not only is there a waste problem, but it is also not good for the health of pets.
[0004] Therefore, there is an urgent need for a more flexible pet feeder control method to improve the user experience. Summary of the invention
[0005] The present application at least provides a control method, device, equipment and computer-readable storage medium for a pet feeder.
[0006] In a first aspect, the present application provides a control method for a pet feeder, comprising: in response to a received pet feeding instruction, performing a remaining food detection on a feeding area of the pet feeder to obtain a current remaining food amount in the feeding area; the pet feeding instruction includes a specified feeding amount; if the current remaining food amount is less than a preset remaining food threshold, performing batch feeding based on the specified feeding amount; in response to detecting that the remaining food amount during the batch feeding process is greater than the remaining food threshold, pausing or stopping the batch feeding process; in response to detecting that the remaining food amount during the batch feeding process is less than or equal to the remaining food threshold, continuing the batch feeding process until the total amount of food fed in the batch feeding process reaches the specified feeding amount.
[0007] In one embodiment, before responding to the received pet feeding instruction, the method further includes: in response to detecting the presence of a target pet in the target area, performing a remaining food detection on the feeding area to obtain an initial remaining food amount; performing a behavior detection process on the target pet to obtain the pet behavior of the target pet; in response to the received pet feeding instruction, performing a remaining food detection on the feeding area of the pet feeder to obtain a current remaining food amount in the feeding area, including: in response to receiving the pet feeding instruction and the pet behavior includes eating behavior, performing a remaining food detection on the feeding area to obtain the current remaining food amount.
[0008] In one embodiment, after the behavior detection processing is performed on the target pet to obtain the pet behavior of the target pet, the method further includes: in response to receiving the pet feeding instruction and the target pet has no eating behavior, determining whether the initial remaining food amount is greater than the remaining food threshold; if the initial remaining food amount is greater than the remaining food threshold, pausing or stopping the remaining food detection and the batch feeding processing.
[0009] In one embodiment, the method further includes: loading a pet detection model and performing pet detection processing on the target area based on the pet detection model; in response to detecting the presence of a target pet in the target area, switching the pet detection model to a remaining food detection model, and performing remaining food detection on the feeding area based on the remaining food detection model to obtain an initial remaining food amount; switching the remaining food detection model to a behavior detection model, and performing behavior detection processing on the target pet based on the behavior detection model to obtain the pet behavior of the target pet.
[0010] In one embodiment, before performing feeding in batches based on the designated feeding portion, the method further includes: performing a food shortage detection on a food storage area of the pet feeder to obtain a food shortage detection result; performing feeding in batches based on the designated feeding portion includes: in response to the food shortage detection result indicating that the pet feeder is not short of food, performing feeding based on the current batch feeding portion.
[0011] In one embodiment, after the feeding process is performed based on the current batch feeding amount, the method further includes: performing pet detection processing on the target area corresponding to the pet feeder; in response to the absence of the target pet in the target area, pausing or stopping the batch feeding process; and / or, performing behavior detection processing on the target pet; in response to the absence of the target pet's eating behavior, pausing or stopping the batch feeding process.
[0012] In one embodiment, the feeding process is performed in batches based on the designated feeding amount, including: performing a food jam detection on each batch of feeding process to obtain a food jam detection result; if the food jam detection result indicates that there is no food jam problem in the pet feeder and no pet food output is detected, food shortage information is generated and the information is reported.
[0013] In one embodiment, after performing food jam detection on each batch of feeding and obtaining a food jam detection result, the method further includes: if the food jam detection result indicates that the pet feeder has a food jam problem, generating food jam information and performing information reporting processing; performing pet detection processing on a target area corresponding to the pet feeder, and / or performing behavior detection processing on a target pet in the target area; in response to the target pet not being present in the target area, and / or the target pet not having eating behavior, stopping the batch feeding process.
[0014] According to a second aspect of the present application, there is provided a control device for a pet feeder, comprising: a remaining food detection module, for performing remaining food detection on a feeding area of the pet feeder in response to a received pet feeding instruction, and obtaining a current remaining food amount in the feeding area; the pet feeding instruction comprises a designated feeding amount; a batch feeding module, for performing batch feeding processing based on the designated feeding amount if the current remaining food amount is less than a preset remaining food threshold; a first feeding control module, for pausing or stopping the batch feeding processing in response to detecting that the remaining food amount during the batch feeding processing is greater than the remaining food threshold; and a second feeding control module, for continuing the batch feeding processing in response to detecting that the remaining food amount during the batch feeding processing is less than or equal to the remaining food threshold, until the total amount of feeding in the batch feeding processing reaches the designated feeding amount.
[0015] A third aspect of the present application provides an electronic device, including a memory and a processor, wherein the processor is used to execute program instructions stored in the memory to implement the control method of the above-mentioned pet feeder.
[0016] A fourth aspect of the present application provides a computer-readable storage medium having program instructions stored thereon, which implement the control method of the above-mentioned pet feeder when the program instructions are executed by a processor.
[0017] In the above scheme, the pet feeder performs a remaining food detection on the feeding area of the pet feeder in response to the received pet feeding instruction to obtain the current remaining food amount in the feeding area; the pet feeding instruction includes a specified feeding amount; if the current remaining food amount is less than a preset remaining food threshold, it indicates that feeding is needed, so the pet feeder performs batch feeding based on the specified feeding amount; during the process of the pet feeder feeding in batches, it is also necessary to perform a remaining food detection; in response to detecting that the remaining food amount during the batch feeding process is greater than the remaining food threshold, the pet feeder performs a batch feeding process based on the specified feeding amount. In response to detecting that the remaining food amount during the batch feeding process is less than or equal to the remaining food threshold, the batch feeding process is continued until the total feeding amount of the batch feeding process reaches the specified feeding amount; thereby preventing the pet feeder from only performing fixed feeding according to the pet feeding instructions while ignoring the fact that the pet usually does not eat at regular times and in regular quantities in actual eating scenarios, thereby reducing the possibility of food waste and improving the user experience of pet owners when using the pet feeder.
[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.
[0020] Figure 1 is a flow chart of an exemplary embodiment of a control method of a pet feeder of the present application;
[0021] Figure 2 is a block diagram of a control device for a pet feeder shown in an exemplary embodiment of the present application;
[0022] Figure 3 It is a structural schematic diagram of an embodiment of the electronic device of the present application;
[0023] Figure 4 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION
[0024] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.
[0025] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.
[0026] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the objects associated before and after are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, can mean including any one or more elements selected from the set consisting of A, B, and C.
[0027] In order to meet the feeding needs and convenience of pet owners for pets, pet feeders have emerged as an innovative device. Pet feeders are designed to provide pet owners with an automatic feeding solution, which helps to reduce the burden of daily feeding. However, traditional pet feeders still have some shortcomings, which not only affect the user experience of pet owners, but may also cause more and more serious problems. It should be noted that in order to accurately control feeding and understand the eating situation of pets, existing pet feeders usually use technologies such as video acquisition and video detection to achieve functions such as pet detection, behavior detection, surplus food detection, food shortage detection, and food jam detection, so that users can better understand the eating situation of pets and the working situation of pet feeders. Therefore, the various algorithm models for pet feeders involved in this application are not specifically limited. The specific algorithm model implementation method in the pet feeder of this application can refer to the prior art, and this application will not be repeated. It should be noted that the pet feeder of this application can be used to feed any pet animal, such as cats, dogs, mice, fish, etc., which is not limited here. The various detection methods mentioned in this application can be algorithms implemented based on visual technology (for example, they can be detection of images collected by a pet feeder). In addition, in some scenarios, some detection methods can be replaced by sensor-based detection methods. These detection methods can be found in the currently commonly used existing technologies and will not be described in detail here.
[0028] See also Figure 1 , Figure 1 1 is a flow chart of an exemplary embodiment of a control method of a pet feeder of the present application. Specifically, the following steps may be included:
[0029] Step S110, in response to the received pet feeding instruction, performing a remaining food detection on the feeding area of the pet feeder to obtain the current remaining food amount in the feeding area; the pet feeding instruction includes a specified feeding amount.
[0030] The pet feeding instruction is an instruction for controlling the pet feeder to output pet food for feeding. It should be noted that the pet feeding instruction received by the pet feeder of the present application can be automatically generated by the pet feeder at a fixed time (for example, periodically generated by setting a timer and other technologies to set a timed feeding task, a timed feeding plan, etc.), or generated by the pet feeder based on certain detected trigger conditions (for example, the pet feeder detects that the target pet is currently eating), or received from an external device that has a communication connection with the pet feeder (for example, the pet owner can send a pet feeding instruction to the pet feeder through a device terminal such as a mobile phone, a personal computer, a smart watch, etc.), which is not limited here.
[0031] It should be noted that the pet feeding instruction should include the corresponding designated feeding amount. The feeding amounts corresponding to different pet feeding instructions may be the same or different, which is not limited here.
[0032] Specifically, in the specific application scenario of the pet feeder of the present application, if a pet feeding instruction is received, the feeding area of the pet feeder is subjected to residual food detection processing. The feeding area refers to an area combined with the pet feeder for holding the pet food output by the pet feeder, such as a common feeding plate, feeding bowl, etc. The pet feeder outputs the pet food to the feeding area, and the pet can eat in the feeding area, which will not be elaborated here. It should be noted that the pet feeder of the present application is not limited to dry food feeding scenarios and / or wet food feeding scenarios. Exemplarily, the residual food detection processing of the feeding area can be performed by collecting an image of the feeding area and detecting the feeding area image based on a preset detection algorithm, or detecting the pet food in the feeding area image. In addition, the field of view of the image captured by the pet feeder may be larger than the feeding area, that is, the pet feeder may capture images based on the target area, and the target area may include the image area. Therefore, after the pet feeder captures the image of the target area, the image area can also be determined from the target area based on a preset image module, or based on a preset detection algorithm. This is not limited here.
[0033] It is understandable that pets usually do not eat all the pet food in the feeding area every time they are fed. Therefore, the pet feeder performs residual food detection processing on the feeding area in order to detect the remaining pet food in the current feeding area (residual food situation) so as to determine the subsequent feeding plan, etc. according to the current residual food situation.
[0034] Step S120: If the current remaining food amount is less than the preset remaining food threshold, batch feeding is performed based on the designated feeding amount.
[0035] In conjunction with the above steps, if the current remaining food amount is less than the preset remaining food threshold, it indicates that feeding is currently required, and the pet feeder outputs pet food to the feeding area based on the pet feeding instruction corresponding to the specified feeding amount, so that the pet can eat. Among them, there can be one or more remaining food thresholds in the present application, which are not limited in the present application. For example, if there are multiple pets in the actual application scenario of the pet feeder, and multiple pets rely on the same pet feeder for feeding, a corresponding remaining food threshold can be set for each pet, and when the pet feeding instruction specifies feeding to a certain target pet, the remaining food threshold corresponding to the target pet can be used for judgment. Or when receiving the pet feeding instruction, the pet feeder detects the pet in the target area, and based on the detected target pet, the remaining food threshold corresponding to the target pet is used for judgment. If multiple pets are detected in the target area at the same time, behavior detection can also be performed on each pet in the target area, and then the pet with eating behavior in the target area is determined as the target pet, and the remaining food threshold corresponding to the target pet is used for judgment. Among them, the target pet refers to the pet that the pet feeder needs to detect or the pet that the pet feeder needs to feed. For example, the pet feeder is set to feed cats only. Then when the pet feeder detects the presence of other animals such as dogs and mice in the target area, these other animals will not be regarded as target pets; further, the detection of target pets can also be limited to the pet attribute information, such as setting a big cat or a small cat as the target pet, setting a white cat or a black cat as the target pet, etc., which will not be elaborated here.
[0036] Among them, the target area needs to be set based on the specific pet feeder. In common application scenarios, since the image acquisition element of the pet feeder is based on the image acquisition of the front of the pet feeder body, the target area can be the front area of the pet feeder. Exemplarily, the image acquisition element of the pet feeder can include but is not limited to a fisheye lens, a wide-angle lens, a zoom lens, etc. And since the feeding area is usually also set in the front area of the pet feeder, the target area may include or exclude the feeding area. It should be noted that there may be different target areas based on different types of pet feeders, which are not limited here.
[0037] It should be noted that the pet feeder of the present application feeds in batches based on the designated feeding portion during the feeding process. Batch feeding refers to dividing the designated feeding portion into multiple equal or unequal partial feeding portions, and feeding (outputting) one of the partial feeding portions in each batch. After the pet feeder has fed the partial feeding portion of the current batch, the partial feeding portion of the next batch can be fed, until the partial feeding portions of all batches in the current feeding process are fed, which is equivalent to the sum of the partial feeding portions of all batches in the current feeding process being equal to the designated feeding portion of the current feeding process. Among them, the pet feeder is usually provided with a grain storage area for storing pet food (such as a grain storage bucket, etc.), and the pet feeder can output the pet food in the grain storage area by rotating a motor to realize the feeding (feeding) function.
[0038] Exemplarily, the designated feeding amount corresponding to the currently received pet feeding instruction is 200g, that is, a total of 200g of pet food should be output in the feeding process based on the pet feeding instruction. Based on the batch feeding processing method of the present application, 200g of pet food can be equally divided into 20 batches of partial feeding amounts, which is equivalent to the pet feeder outputting 10g of pet food in each batch; or the pet food can be unequally divided into 20 batches (for example, 15g for the first batch, 5g for the second batch, ..., which will not be elaborated here). Of course, the division can also be based on other batch quantities, which is not limited by the present application.
[0039] Step S130, in response to detecting that the amount of remaining food during the batch feeding process is greater than the remaining food threshold, pausing or stopping the batch feeding process.
[0040] In conjunction with the above steps, it is also necessary to detect the remaining food in the feeding area during the above batch feeding process. If it is detected that the remaining food amount during the batch feeding process is greater than the remaining food threshold, the current batch feeding process is paused or stopped.
[0041] It should be noted that, on the one hand, combined with the actual eating situation of the pet, it may be that the eating behavior ends after a part of the pet food in the feeding area is eaten. If the traditional pet feeder control method is followed, it is necessary to output all the pet food of the specified feeding amount corresponding to the pet feeding instruction, so it is easy for the pet food to accumulate in the feeding area. The pet feeder of the present application feeds (outputs) pet food in batches and performs residual food detection, which can ensure that after the pet stops eating halfway, if the current residual food portion exceeds the residual food threshold, the output of pet food is suspended in time, and then according to the specific situation, it is selected to suspend the current batch feeding process or stop (end) the current batch feeding process. On the other hand, it is also possible that the pet does not eat during the current batch feeding process, so the output of pet food can be suspended in time when the current residual food portion exceeds the residual food threshold. On the other hand, it is understandable that if a pet eats too fast, it will cause indigestion and other problems. The batch feeding method of the present application can also cultivate the pet's slow eating habits, and can also prevent the problem of pet food overflowing from the feeding area if the traditional method is used to directly feed based on the specified feeding amount.
[0042] Step S140, in response to detecting that the remaining food amount during the batch feeding process is less than or equal to the remaining food threshold, the batch feeding process is continued until the total amount of feeding in the batch feeding process reaches the specified feeding amount.
[0043] Combined with the above steps, in an ideal pet feeding scenario, the pet should be able to finish eating the pet food currently output by the pet feeder as quickly as possible. Therefore, during the batch feeding process, if the pet feeder detects that the remaining food amount during the batch feeding process is less than or equal to the remaining food threshold, it indicates to a certain extent that the pet currently eating still has a need to eat. Therefore, according to the batch feeding plan of the above example, the batch feeding process is continued until the total feeding amount of the current batch feeding process reaches the specified feeding amount, and / or it is detected that the pet currently eating has finished eating. Among them, the total feeding amount of the current batch feeding process refers to the sum of the pet food amounts output in each batch determined based on the currently received pet feeding instructions.
[0044] For example, if the total amount of feeding in the current batch feeding process reaches the specified feeding amount, the feeding task of the pet feeding instruction is completed. If it is detected that the pet currently eating has finished eating, the current batch feeding process can be paused or stopped (ended). Specifically, whether to end the current batch feeding can be determined by setting a waiting time threshold.
[0045] For example, in one possible implementation, when it is detected that the target pet that is currently eating has finished eating or when the target pet is not detected in the target area, the current batch feeding process is suspended, and a waiting timer process is performed to obtain the waiting time. If the target pet and / or other pets still have no eating behavior after the waiting time is greater than the waiting time threshold, the current batch feeding is terminated directly; conversely, if the target pet and / or other pets are detected to have eaten when the waiting time is less than or equal to the waiting time threshold, the batch feeding process for the remaining batches can continue. In another possible implementation, the current batch feeding is terminated directly if it is detected that the target pet has finished eating, or the current batch feeding is terminated directly if it is detected that the target pet has left the target area.
[0046] It can be seen that the pet feeder of the present application performs a remaining food detection on the feeding area of the pet feeder in response to the received pet feeding instruction, and obtains the current remaining food amount in the feeding area; the pet feeding instruction includes a specified feeding amount; if the current remaining food amount is less than a preset remaining food threshold, it indicates that feeding is required, so the pet feeder performs batch feeding based on the specified feeding amount; the remaining food detection is also required during the batch feeding process of the pet feeder; in response to detecting that the remaining food amount during the batch feeding process is greater than the remaining food threshold, the batch feeding process is paused or stopped; in response to detecting that the remaining food amount during the batch feeding process is less than or equal to the remaining food threshold, the batch feeding process is continued until the total amount of feeding in the batch feeding process reaches the specified feeding amount; thereby, it can be avoided that the pet feeder only performs fixed feeding according to the pet feeding instruction, while ignoring that the pet usually does not eat regularly and quantitatively in the actual eating scene, thereby reducing the possibility of food waste and improving the user experience of the pet owner when using the pet feeder.
[0047] Based on the above embodiments, the present embodiment of the application describes the steps before responding to the received pet feeding instruction and the steps of detecting the remaining food in the feeding area of the pet feeder in response to the received pet feeding instruction to obtain the current remaining food amount in the feeding area. Specifically, the method of this embodiment includes the following steps:
[0048] In response to detecting the presence of a target pet in a target area, a food remaining detection is performed on the feeding area to obtain an initial food remaining amount; a behavior detection process is performed on the target pet to obtain the pet behavior of the target pet; in response to receiving a pet feeding instruction and the pet behavior includes eating behavior, a food remaining detection is performed on the feeding area to obtain a current food remaining amount.
[0049] In conjunction with the above-mentioned embodiment, before responding to the received pet feeding instruction, the method of the present application may further include: the pet feeder performs pet detection on the target area, and in response to detecting the presence of the target pet in the target area, performs a remaining food detection on the feeding area to obtain an initial remaining food amount. Performs behavior detection processing on the target pet to obtain the pet behavior of the target pet. If the received pet feeding instruction and the pet behavior of the target pet include eating behavior, performs a remaining food detection on the feeding area again to obtain the current remaining food amount.
[0050] It should be noted that when the pet feeding instruction is not received (for example, before the pet feeding instruction is received, or after the feeding task corresponding to the pet feeding instruction is completed), the pet feeder can perform pet detection on the target area to determine whether there is a pet that may have a need to eat. Therefore, the remaining food is detected in the feeding area to obtain the initial remaining food portion. If the target pet is detected to have eating behavior, the initial remaining food portion will definitely continue to decrease. Therefore, when the pet feeding instruction is received and the target pet has eating behavior, it is necessary to perform remaining food detection on the feeding area to obtain the current remaining food portion. It can be understood that under normal circumstances, if the target pet has eating behavior, the initial remaining food portion is different from the current remaining food portion; if the target pet does not have eating behavior, the initial remaining food portion is the same as the current remaining food portion. That is, there can also be an implementable method including: the pet feeder performs pet detection on the target area, and in response to detecting the presence of the target pet in the target area, performs remaining food detection on the feeding area to obtain the initial remaining food portion. In response to receiving a pet feeding instruction and the pet behavior not including eating behavior, the initial remaining food amount is used as the current remaining food amount without performing remaining food detection again.
[0051] Based on the above embodiments, the present embodiment of the application describes the steps after the behavior detection process is performed on the target pet to obtain the pet behavior of the target pet. Specifically, the method of this embodiment includes the following steps:
[0052] In response to receiving a pet feeding instruction and the target pet has no eating behavior, it is determined whether the initial remaining food amount is greater than the remaining food threshold; if the initial remaining food amount is greater than the remaining food threshold, the remaining food detection and batch feeding processing are suspended or stopped.
[0053] In conjunction with the above-mentioned embodiment, if a pet feeding instruction is received and the pet behavior is determined not to include eating behavior when the pet in the target area is detected before the instruction is received, it indicates that the initial remaining food amount is equal to the current remaining food amount. Therefore, it is only necessary to determine whether the initial remaining food amount is greater than the remaining food threshold to determine whether feeding is required based on the currently received pet feeding instruction.
[0054] Exemplarily, the process of determining whether the initial remaining food amount is greater than the remaining food threshold may be performed when the initial remaining food amount is obtained, or when the pet feeding instruction is received, which is not limited here. When the pet feeder receives the pet feeding instruction, if in the pet detection process before receiving the pet feeding instruction, it is detected that the pet behavior of the target pet does not include eating behavior, and it is determined that the initial remaining food amount is greater than the remaining food threshold, it means that there is a lot of pet food remaining in the current feeding area, so even if the pet feeding instruction is received, there is no need to perform remaining food detection and batch feeding processing as in step S110 and step S120. On the contrary, if it is determined that the initial remaining food amount is less than or equal to the remaining food threshold, it means that there is less pet food remaining in the current feeding area, so after receiving the pet feeding instruction, you can refer to step S120 to perform batch feeding processing.
[0055] Based on the above embodiment, the present embodiment of the application describes the steps before responding to the received pet feeding instruction. Specifically, the method of this embodiment includes the following steps:
[0056] A pet detection model is loaded and pet detection processing is performed on the target area based on the pet detection model; in response to detecting the presence of a target pet in the target area, the pet detection model is switched to a remaining food detection model, and a remaining food detection is performed on the feeding area based on the remaining food detection model to obtain an initial remaining food amount; the remaining food detection model is switched to a behavior detection model, and behavior detection processing is performed on the target pet based on the behavior detection model to obtain the pet behavior of the target pet.
[0057] In combination with the above-mentioned embodiments, this embodiment provides a specific implementation method before responding to a received pet feeding instruction. The pet feeder of the present application can use a pet detection model to perform pet detection processing on the target area when no pet feeding instruction is received. If the target pet is detected in the target area, the remaining food detection model is used to perform remaining food detection on the feeding area to obtain the initial remaining food amount. In addition, the behavior detection model can also be used to perform behavior detection processing on the target pet to obtain the pet behavior of the target pet.
[0058] It should be noted that the method of the present application may include pet detection and pet behavior detection. Pet detection mainly detects pet attribute information, such as pet name (pet identification), pet category, etc., which can be used to determine whether the target pet exists in the target area. Especially in multi-pet scenarios, different pets correspond to different pet attribute information (pet attribute characteristics). Through pet detection, the pet feeder of the present application can provide different feeding plans (specify feeding portions) for different pets detected and record corresponding eating information, eating habits, etc. for different pets, thereby improving the versatility of the pet feeder. Pet behavior detection mainly detects pet behavior information, such as eating behavior, approach behavior, leaving behavior and other behaviors, which will not be elaborated here.
[0059] It should also be noted that the pet detection algorithm model needs to be used in the process of pet detection, the surplus detection algorithm model needs to be used in the process of surplus detection, and the behavior detection algorithm model needs to be used in the process of behavior detection. The pet detection algorithm model is a category model, the surplus detection algorithm model is a classification model, and the behavior detection algorithm model is a behavior model. Therefore, in the process of implementing the specific method of the above embodiment, it is not possible to detect all aspects by sharing a model, but it is necessary to load each model. However, for small devices such as pet feeders, their low device specifications (such as small running memory) will lead to weak computing power. Therefore, in this application, the operation process of the pet feeder can be optimized by loading the algorithm model one by one to reduce its operating load. By detecting the pet activity and the working condition of the feeder, the corresponding video detection algorithm scheduling is performed, which can not only achieve effective monitoring of pet feeding and the working condition of the feeder, but also reduce the memory space required when the algorithm model is loaded, thereby saving costs.
[0060] Exemplarily, when a pet eats, it needs to move to the front of the pet feeder before eating. Therefore, when the pet feeder does not receive the pet feeding instruction, it loads the pet detection model in the memory and performs pet detection processing on the target area based on the pet detection model (for example, after the pet feeder is powered on, it starts to load the pet detection model in the memory for pet detection). When the target pet is detected in the target area, the target pet information can be reported, and then the pet feeder switches the pet detection model running in the memory to the remaining food detection model for remaining food detection to obtain the initial remaining food portion. After that, the remaining food detection model in the memory can be switched back to the pet detection model to continue pet detection. If it is detected that the distance between the target pet and the pet feeder is less than a preset distance threshold (for example, through infrared detection, radar detection or based on visual detection, the pixel ratio occupied by the target pet in the collected image is greater than a preset ratio threshold), or when the head of the target pet is detected close to the feeding area, it means that the target pet is about to eat. At this time, the algorithm model running in the memory is switched again, that is, the pet detection model is switched to the behavior detection algorithm model, and continuous detection is performed. When the pet's eating behavior is detected, the eating information can be generated and reported to the client (such as a mobile client APP, etc.). If the eating behavior of the target pet is detected to be finished, the pet detection model is switched back again.
[0061] It should be further explained that in order to maximize the versatility of the pet feeder, it can be set to run only one algorithm model in the memory of the pet feeder at a time, and then the corresponding algorithm model scheduling can be performed in the memory of the pet feeder based on the detection results of different algorithm models. In addition, it is also possible to load and run two algorithm models, three algorithm models or more in the memory of the pet feeder at the same time. It can be set specifically according to the actual memory situation of the pet feeder. For pet feeders with sufficient memory, all algorithm models can also be run for detection at the same time.
[0062] For example, the memory load required for each algorithm model to run can be preset, and then the actual load of the pet feeder during operation can be combined to select whether to load the algorithm models one by one or load multiple algorithm models in parallel. Alternatively, the actual load of the pet feeder during operation can be compared with a preset load threshold to select whether to load the algorithm models one by one or load multiple algorithm models in parallel, which will not be elaborated here.
[0063] Based on the above embodiment, the embodiment of the present application describes the steps before batch feeding based on the specified feeding portion and the steps of batch feeding based on the specified feeding portion. Specifically, the method of this embodiment includes the following steps:
[0064] A food shortage detection is performed on a food storage area of the pet feeder to obtain a food shortage detection result; in response to the food shortage detection result indicating that the pet feeder is not short of food, feeding is performed based on the current batch feeding amount.
[0065] As explained in conjunction with the foregoing embodiments, during the batch feeding process of the method of the present application, it is also necessary to perform a food shortage detection on the food storage area of the pet feeder. The food shortage detection is to determine whether there is a shortage of pet food in the food storage area, thereby avoiding the problem of a shortage of pet food and inability to deliver food when feeding is required. If the food shortage detection result indicates that the pet feeder is not short of food, the feeding process can be performed based on the current batch feeding amount according to the normal feeding process of the foregoing embodiments. If the food shortage detection result indicates that the pet feeder is short of food, it is necessary to generate and report food shortage information, and suspend or stop the feeding process of the current batch.
[0066] Exemplarily, the food shortage detection method may include but is not limited to detection by a detection sensor set in the food storage area. For example, an infrared sensor may be set in the food storage area, and when it is detected that the height of the pet food in the food storage area is lower than a preset height threshold, it is determined that there is a shortage of food. Alternatively, a gravity sensor may be set in the food storage area, and when it is detected that the gravity of the pet food in the food storage area is lower than a preset gravity threshold, it is determined that there is a shortage of food. In addition, it is also possible to determine whether there is a shortage of food by detecting whether the food outlet of the pet feeder outputs pet food.
[0067] Based on the above embodiment, the present embodiment of the application describes the steps after the feeding process is performed based on the current batch feeding portion. Specifically, the method of this embodiment includes the following steps:
[0068] Perform pet detection processing on the target area corresponding to the pet feeder; in response to the absence of the target pet in the target area, suspend or stop the batch feeding processing; and / or, perform behavior detection processing on the target pet; in response to the absence of eating behavior of the target pet, suspend or stop the batch feeding processing.
[0069] In combination with the above-mentioned embodiments, after each batch of feeding is performed, the pet feeder can also perform pet detection processing on the target area and / or behavior detection processing on the target pet in the target area to determine whether the target pet has a need for food, and then decide whether to continue feeding subsequent batches.
[0070] In response to the absence of the target pet in the target area, the batch feeding process is suspended or stopped; and / or in response to the absence of the target pet eating behavior, the batch feeding process is suspended or stopped.
[0071] Based on the above embodiment, the present embodiment of the application describes the steps of batch feeding based on the specified feeding amount. Specifically, the method of this embodiment includes the following steps:
[0072] A food jam detection is performed on each batch of feeding to obtain a food jam detection result; if the food jam detection result indicates that there is no food jam problem in the pet feeder and no pet food output is detected, food shortage information is generated and the information is reported.
[0073] In combination with the above-mentioned embodiments, in the batch feeding process of the present application, a food jam detection can be performed for each batch of feeding, or a food jam detection can be performed once every two batches of feeding, or a food jam detection can be performed once every multiple batches of feeding, which is not limited here. The food jam detection is to detect whether the pet feeder cannot successfully output the pet food normally due to a food jam problem when outputting the pet food, thereby causing feeding failure.
[0074] It should be noted that the food jam detection is mainly to determine whether the pet feeder can normally output the pet food in the food storage area. If the food release motor of the pet feeder fails, or the food delivery channel of the pet feeder is blocked, food jam will occur. Specifically, during the feeding process, the food release motor of the pet feeder starts to rotate to realize the output of pet food from the food storage area to the feeding area. If there is no food jam after the food release motor rotates, and pet food is detected to be output from the food outlet, it can be indicated that the pet feeder is not short of food at this time. On the contrary, if there is no food jam after the food release motor rotates, and no pet food is detected to be output from the food outlet, it indicates that the pet feeder is short of food at this time, so food shortage information is generated and the information is reported for processing.
[0075] Based on the above embodiment, the embodiment of the present application describes the steps after performing grain jam detection on each batch of feeding and obtaining the grain jam detection result. Specifically, the method of this embodiment includes the following steps:
[0076] If the food jam detection result indicates that there is a food jam problem in the pet feeder, food jam information is generated and the information is reported; pet detection is performed on the target area corresponding to the pet feeder, and / or behavior detection is performed on the target pet in the target area; in response to the absence of the target pet in the target area and / or the absence of eating behavior by the target pet, batch feeding is stopped.
[0077] In conjunction with the above-mentioned embodiment, if the food jam detection result indicates that there is a food jam problem in the pet feeder, it indicates that the pet feeder is temporarily unable to output pet food normally, so in the actual eating situation of the pet, the pet may give up eating because the pet feeder does not output pet food. Therefore, in the method of the present application, if there is a food jam problem in the pet feeder, a pet detection process is performed on the target area, and / or a behavior detection process is performed on the target pet. If there is no target pet in the target area, and / or the target pet does not have eating behavior, it can be indicated that the target pet has stopped eating, so the pet feeder can also stop feeding in batches.
[0078] On the basis of the above embodiment, in order to save the hardware cost of the pet feeder and ensure the operating capacity of the pet feeder, the embodiment of the present application exemplifies the algorithm model scheduling process of each execution step in the above embodiment. It should be noted that in this embodiment, the pet feeder mainly loads each algorithm model into the memory one by one and runs it separately. In actual use scenarios, more algorithm models can be loaded and run at the same time according to the hardware specifications and operating load of the pet feeder, which will not be described in detail here.
[0079] Exemplarily, after the pet feeder is powered on, the pet detection algorithm model can be loaded into the memory to run and start pet detection. The pet feeder of the present application can be provided with a fisheye lens to obtain a larger field of view. Since the pet needs to move to the front of the pet feeder when eating, and then eat. Therefore, the pet feeder first loads the pet detection algorithm model to start pet detection. When the target pet is detected in the target area, the detected target pet information can be reported, and the pet detection algorithm model running in the memory can be switched to the remaining food detection algorithm model for remaining food detection. After obtaining the remaining food detection result (for example, the initial remaining food portion), the remaining food detection algorithm model running in the memory can be switched back to the pet detection algorithm model for pet detection. The pet feeder can continue to perform pet detection based on the pet detection algorithm model until the target pet is detected to be close to the feeding area of the pet feeder, and then the pet detection algorithm model running in the memory can be switched to the behavior detection model (more specifically, the eating behavior detection model) to perform eating detection on the target pet. When the pet eating behavior is detected, the eating information is generated and reported. If it is detected that the pet has finished eating, the algorithm model running in the memory can be switched back to the pet detection model to perform the regular pet detection process as described in the previous example.
[0080] It should be noted that, under normal circumstances, if the initial remaining food amount is greater than the remaining food threshold, food will not be output when the pet feeding instruction is received. However, if the pet has eating behavior after the initial remaining food amount is detected, the current remaining food amount may be less than the remaining food threshold, so food output is required. Exemplarily, when the pet is eating, if a pet feeding instruction is received (for example, a pre-set pet feeding plan is triggered), the remaining food detection will be performed again to determine whether to feed and release food. Among them, since pets usually do not leave when eating, the pet detection model running in the memory can be switched to the remaining food detection model for remaining food detection to obtain the current remaining food amount, and determine whether it is necessary to output pet food according to the pet feeding instruction based on the comparison result between the current remaining amount and the remaining food threshold. After completing this remaining food detection, the remaining food detection model running in the memory can be immediately switched back to the pet behavior detection model.
[0081] If the target pet is not detected in the target area or the detected target pet does not have any eating behavior before receiving the pet feeding instruction, that is, only the pet detection model can be running in the memory. After receiving the pet feeding instruction, the pet detection model can be switched to the remaining food detection model. After the remaining food detection is completed, if the remaining food reaches the remaining food threshold, no food will be released, and it will be switched back to the pet detection model. If the remaining food does not reach the remaining food threshold, prepare to release the food, and switch to the food shortage detection model before each batch of food release begins. If the food shortage detection model detects that there is no food shortage problem, it will switch to the pet detection model. After the current food release action is completed, if the target pet is still not detected in the target area or the target pet is not detected to have eating behavior, the subsequent batches of food release will be paused or stopped. If the target pet is detected in the target area or the target pet is detected to have eating behavior, the food can continue to be released. Before the next batch of food is discharged, switch to the food shortage detection model in the same way. Thereby, only one algorithm model is running in the memory of the pet feeder. If a target pet is detected in the target area based on the pet detection model (for example, when the target pet is close to the feeding bowl), then referring to the above embodiment, the behavior detection model can be switched to in the same way.
[0082] Furthermore, in the feeding process of the pet feeder of the present application, the feeding amount specified by the pet feeding instruction is divided into multiple feeding amounts and the food is released in sequence to achieve the effect of releasing food in batches. Therefore, when the grain release motor starts to rotate during each batch of feeding, the pet behavior detection model running in the memory can be switched to the food shortage detection model for operation. If there is no food jam problem after the grain release motor rotates, and it is detected that there is food output at the grain outlet, it indicates that the pet feeder is not short of food at this time, and then the food shortage detection model is switched to the behavior detection model, and at this time, the pet food fed in this batch will continue to be output until the pet food of this batch is finished. Then the next batch of pet food is output, and similarly, referring to the above method, the eating behavior detection is switched to the food shortage detection, and if there is no food shortage, it is switched to the eating behavior detection again, until the feeding amount specified by the current pet feeding instruction is output, the algorithm model is no longer switched, and the eating behavior detection model is maintained. After waiting for the target pet's eating behavior to end, choose whether to switch to other algorithm models.
[0083] It should be noted that if it is detected that the pet feeder is out of food, that is, the pet feeder cannot output pet food, the pet may leave immediately and end the eating behavior in the food shortage scenario. Therefore, when it is detected that the pet feeder is out of food, the behavior detection model is switched to the pet detection model. If it is detected that the target pet does not have the eating behavior, the behavior detection model is switched to the pet detection model for conventional pet detection. Exemplarily, if it is detected that the target pet does not have the eating behavior, the eating end information can also be generated and reported.
[0084] In addition, a short feeding time is required for each batch of feeding (for example, it takes 3 seconds to output a batch of pet food). Therefore, when the food starts to be discharged, it will switch to the food shortage detection model. If there is a problem of food jamming, it will switch to the behavior detection model immediately. If there is no problem of food jamming, the food shortage detection still does not detect the food after the food release action of the batch feeding process is completed, then the food shortage information is generated and reported at this time, and then the behavior detection model is switched. In addition, it should be noted that in the batch feeding process of the present application, the user may pre-set batch parameters to specify how many batches the specified feeding amount is divided into and / or how many portions are output per batch. For example, multiple batches, such as 20 portions, can be pre-set in the batch parameters. If 20 portions of food are released continuously, it is easy for the food to overflow the feeding bowl. Therefore, the batch threshold can also be preset in the batch parameters. For example, if 10 portions of food are discharged and the batch threshold is reached, the food is suspended at this time, and the remaining 10 portions are output after the pet eats and consumes, until all portions of food in this plan are released. Alternatively, the pet feeder can learn and record the eating habits of the target pet within a preset period of time based on a preset algorithm model, and then obtain the corresponding food intake of the target pet during each eating behavior, thereby determining how to divide the specified feeding amount into batches and / or the number of portions per batch, as well as the batch threshold in the batch feeding process. For example, if the specified feeding amount is 200g, the eating habits of the target pet are learned and recorded within a preset period of time to determine that the average food intake of the target pet each time is 100g (it can also be the mode of food intake, the median of food intake, etc.), then the pet feeder can suspend the feeding of subsequent batches after outputting 100g, and if it is detected that the target pet continues to maintain the eating behavior, it will output the subsequent amount to be fed in batches.
[0085] During the continuous batch feeding process after the feeding plan starts, the eating detection model and the food shortage detection model switch between each other. At this time, only one algorithm model can be running in the memory. When the continuous feeding reaches the remaining food threshold, the feeding can be paused or stopped, and the remaining food detection model can be switched first. If the remaining food threshold is not reached, it means that the pet is eating continuously. At this time, a 5-second switching time can be preset between the remaining food detection model and the behavior detection model. At this time, only one algorithm model is loaded into the memory for running. When the remaining food detection model detects that there is less remaining food, it will continue to feed the subsequent batches of pet food of this feeding plan in batches, and when each portion of food starts to be released, it can switch to the food shortage detection model for operation, and when it is detected that there is no shortage of food, it will switch back to the behavior detection model for eating behavior detection. At the beginning of each subsequent portion of food, it can switch to the food shortage detection model for food shortage detection until all the food in this batch is output, and then switch back to the eating detection model.
[0086] If the behavior detection model detects that the target pet is no longer eating, the feeding end information is reported. Even if the current feeding plan corresponding to the pet feeding instruction has not ended, the subsequent food release process can be directly stopped and ended. If it is detected that the target pet has left the target area, the remaining food detection model can be switched to first, and the remaining food amount can be reported, and then the pet detection model can be switched to. At this time, only the pet detection model can be kept running until the pet detection model detects that there is a target pet in the target area, and then the method of the above embodiment is continued to be repeated.
[0087] In summary, when the pet feeder of the present application can perform various detection services, it only needs to load one of the algorithm models into the memory. While saving hardware costs, it can also realize pet eating detection and feeder delivery detection, which not only achieves a good feeding effect, but also improves the user experience, so that users do not need to set up the pet feeding plan of the pet feeder too cumbersomely.
[0088] It should be further explained that the execution subject of the control method of the pet feeder may be a control device of the pet feeder, for example, the control method of the pet feeder may be executed by a terminal device or a server or other processing device, wherein the terminal device may be a user equipment (UE), a computer, a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the control method of the pet feeder may be implemented by a processor calling computer-readable instructions stored in a memory.
[0089] Figure 2 FIG. 1 is a block diagram of a control device for a pet feeder shown in an exemplary embodiment of the present application. Figure 2 As shown, the exemplary pet feeder control device 200 includes: a remaining food detection module 210, a batch feeding module 220, a first feeding control module 230 and a second feeding control module 240. Specifically:
[0090] The remaining food detection module 210 is used to perform remaining food detection on the feeding area of the pet feeder in response to the received pet feeding instruction to obtain the current remaining food amount in the feeding area; the pet feeding instruction includes a specified feeding amount.
[0091] The batch feeding module 220 is used to perform batch feeding based on a specified feeding amount if the current remaining food amount is less than a preset remaining food threshold.
[0092] The first feeding control module 230 is configured to suspend or stop the batch feeding process in response to detecting that the amount of remaining food during the batch feeding process is greater than a remaining food threshold.
[0093] The second feeding control module 240 is used to continue the batch feeding process in response to detecting that the remaining food amount during the batch feeding process is less than or equal to the remaining food threshold, until the total feeding amount of the batch feeding process reaches the specified feeding amount.
[0094] In the control device of the exemplary pet feeder, in response to the received pet feeding instruction, the feeding area of the pet feeder is detected for remaining food, and the current remaining food amount in the feeding area is obtained; the pet feeding instruction includes a specified feeding amount; if the current remaining food amount is less than a preset remaining food threshold, it indicates that feeding is needed, so the pet feeder performs batch feeding based on the specified feeding amount; the remaining food detection is also required during the batch feeding process of the pet feeder; in response to detecting that the remaining food amount during the batch feeding process is greater than the remaining food threshold, the batch feeding process is paused or stopped; in response to detecting that the remaining food amount during the batch feeding process is less than or equal to the remaining food threshold, the batch feeding process is continued until the total amount of feeding in the batch feeding process reaches the specified feeding amount; thereby, it is possible to avoid the pet feeder only performing fixed feeding according to the pet feeding instruction, while ignoring the fact that the pet usually does not eat regularly and quantitatively in the actual eating scene, thereby reducing the possibility of food waste and improving the user experience of the pet owner when using the pet feeder.
[0095] It should be noted that the device provided in the above embodiment and the method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, and will not be repeated here. In practical applications, the device provided in the above embodiment can distribute the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.
[0096] The functions of each module can be found in the control method embodiment of the pet feeder, which will not be described in detail here.
[0097] See also Figure 3 , Figure 31 is a schematic diagram of the structure of an embodiment of an electronic device of the present application. The electronic device 100 includes a memory 101 and a processor 102, and the processor 102 is used to execute program instructions stored in the memory 101 to implement the steps in any of the above-mentioned pet feeder control method embodiments. In a specific implementation scenario, the electronic device 100 may include but is not limited to: a microcomputer, a server, and in addition, the electronic device 100 may also include a mobile device such as a laptop computer and a tablet computer, which is not limited here.
[0098] Specifically, the processor 102 is used to control itself and the memory 101 to implement the steps in any of the above-mentioned pet feeder control method embodiments. The processor 102 can also be called a CPU (Central Processing Unit). The processor 102 may be an integrated circuit chip with signal processing capabilities. The processor 102 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 102 can be implemented by an integrated circuit chip.
[0099] In this exemplary electronic device, in response to a received pet feeding instruction, a remaining food detection is performed on a feeding area of the pet feeder to obtain a current remaining food amount in the feeding area; the pet feeding instruction includes a specified feeding amount; if the current remaining food amount is less than a preset remaining food threshold, it indicates that feeding is required, so the pet feeder performs batch feeding based on the specified feeding amount; remaining food detection is also required during the batch feeding process of the pet feeder; in response to detecting that the remaining food amount during the batch feeding process is greater than the remaining food threshold, the batch feeding process is paused or stopped; in response to detecting that the remaining food amount during the batch feeding process is less than or equal to the remaining food threshold, the batch feeding process is continued until the total amount of feeding in the batch feeding process reaches the specified feeding amount; thereby, it is possible to avoid the pet feeder only performing fixed feeding according to the pet feeding instruction, while ignoring the fact that pets usually do not eat at regular times and in fixed quantities in actual eating scenarios, thereby reducing the possibility of food waste and improving the user experience of pet owners when using the pet feeder.
[0100] See also Figure 4 , Figure 4The computer-readable storage medium 110 stores program instructions 111 that can be executed by a processor, and the program instructions 111 are used to implement the steps in any of the above-mentioned pet feeder control method embodiments.
[0101] In this exemplary storage medium, the pet feeder of the present application executes a remaining food detection on the feeding area of the pet feeder in response to a received pet feeding instruction by running the program instructions in the storage medium, and obtains the current remaining food amount in the feeding area; the pet feeding instruction includes a specified feeding amount; if the current remaining food amount is less than a preset remaining food threshold, it indicates that feeding is needed, so the pet feeder performs batch feeding based on the specified feeding amount; during the process of batch feeding by the pet feeder, remaining food detection is also required; in response to detecting the batch feeding process In response to detecting that the remaining food amount during the batch feeding process is less than or equal to the remaining food threshold, the batch feeding process is continued until the total feeding amount of the batch feeding process reaches the specified feeding amount; thereby preventing the pet feeder from only performing fixed feeding according to the pet feeding instructions, while ignoring the fact that the pet usually does not eat at regular times and in regular quantities in actual eating scenarios, thereby reducing the possibility of food waste and improving the user experience of pet owners when using the pet feeder.
[0102] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.
[0103] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.
[0104] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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 through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.
[0105] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. 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 application is essentially 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, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.
Claims
1. A method for controlling a pet feeder, characterized in that: The method is applied to a pet feeder, and the method comprises: In response to the received pet feeding instruction, a remaining food detection is performed on the feeding area of the pet feeder to obtain the current remaining food amount in the feeding area; the pet feeding instruction includes a specified feeding amount; If the current remaining food amount is less than the preset remaining food threshold, feeding is performed in batches based on the specified feeding amount; In response to detecting that the amount of remaining food during the batch feeding process is greater than the remaining food threshold, pausing or stopping the batch feeding process; In response to detecting that the remaining food amount during the batch feeding process is less than or equal to the remaining food threshold, the batch feeding process is continued until the total feeding amount of the batch feeding process reaches the specified feeding amount.
2. The method according to claim 1, characterized in that Prior to responding to the received pet feeding instruction, the method further includes: In response to detecting the presence of a target pet in the target area, performing a remaining food detection on the feeding area to obtain an initial remaining food amount; Performing behavior detection processing on the target pet to obtain the pet behavior of the target pet; In response to the received pet feeding instruction, performing a remaining food detection on the feeding area of the pet feeder to obtain the current remaining food amount in the feeding area includes: In response to receiving the pet feeding instruction and the pet behavior including eating behavior, a remaining food detection is performed on the feeding area to obtain the current remaining food amount.
3. The method according to claim 2, characterized in that After performing behavior detection processing on the target pet to obtain the pet behavior of the target pet, the method further includes: In response to receiving the pet feeding instruction and the target pet not having any eating behavior, determining whether the initial remaining food amount is greater than the remaining food threshold; If the initial remaining grain amount is greater than the remaining grain threshold, the remaining grain detection and the batch feeding process are suspended or stopped.
4. The method according to claim 2, characterized in that: The method further comprises: Loading a pet detection model and performing pet detection processing on a target area based on the pet detection model; In response to detecting the presence of a target pet in the target area, switching the pet detection model to a remaining food detection model, and performing remaining food detection on the feeding area based on the remaining food detection model to obtain an initial remaining food amount; The remaining food detection model is switched to a behavior detection model, and behavior detection processing is performed on the target pet based on the behavior detection model to obtain the pet behavior of the target pet.
5. The method according to claim 1, characterized in that Before performing the batch feeding process based on the specified feeding portion, the method further includes: Performing food shortage detection on the food storage area of the pet feeder to obtain a food shortage detection result; The batch feeding process based on the specified feeding amount includes: In response to the food shortage detection result indicating that the pet feeder is not short of food, feeding processing is performed based on the current batch feeding amount.
6. The method according to claim 5, characterized in that After the feeding process is performed based on the current batch feeding portion, the method further includes: Performing pet detection processing on a target area corresponding to the pet feeder; In response to the absence of the target pet in the target area, pausing or stopping the batch feeding process; and / or, performing behavior detection processing on the target pet; In response to the target pet not having any eating behavior, the batch feeding process is paused or stopped.
7. The method according to claim 1, characterized in that The batch feeding process based on the specified feeding amount includes: Conduct grain-stuck detection on each batch of feeding treatment and obtain the grain-stuck detection result; If the food jam detection result indicates that there is no food jam problem in the pet feeder and no pet food output is detected, food shortage information is generated and the information is reported for processing.
8. The method according to claim 7, characterized in that After performing grain-stuck detection on each batch of feeding and obtaining the grain-stuck detection result, the method further includes: If the food jam detection result indicates that the pet feeder has a food jam problem, food jam information is generated and reported; Performing pet detection processing on a target area corresponding to the pet feeder, and / or performing behavior detection processing on a target pet in the target area; In response to the target pet not being present in the target area and / or the target pet not having any eating behavior, the batch feeding process is stopped.
9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the processor is used to execute program instructions stored in the memory to implement the method according to any one of claims 1 to 8.
10. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.
Citation Information
Cited By
Pet feeding method and system based on camera
CN120814491A
Pet feeder control method and system, terminal equipment and storage medium
CN121336725A
Livestock feeder control system based on internet of things
CN122672362A
