CN111109105A - Pet feeding method and device, computer equipment and storage medium - Google Patents
Pet feeding method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111109105A CN111109105A CN201911298604.8A CN201911298604A CN111109105A CN 111109105 A CN111109105 A CN 111109105A CN 201911298604 A CN201911298604 A CN 201911298604A CN 111109105 A CN111109105 A CN 111109105A
- Authority
- CN
- China
- Prior art keywords
- pet
- feeding
- fed
- model
- reference information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; CARE OF BIRDS, FISHES, INSECTS; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K5/00—Feeding devices for stock or game ; Feeding wagons; Feeding stacks
- A01K5/02—Automatic devices
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; CARE OF BIRDS, FISHES, INSECTS; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K15/00—Devices for taming animals, e.g. nose-rings or hobbles; Devices for overturning animals in general; Training or exercising equipment; Covering boxes
- A01K15/02—Training or exercising equipment, e.g. mazes or labyrinths for animals ; Electric shock devices ; Toys specially adapted for animals
- A01K15/027—Exercising equipment, e.g. tread mills, carousels
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; CARE OF BIRDS, FISHES, INSECTS; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K29/00—Other apparatus for animal husbandry
- A01K29/005—Monitoring or measuring activity, e.g. detecting heat or mating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
The invention discloses a pet feeding method, a pet feeding device, computer equipment and a storage medium, wherein the pet feeding method is applied to the computer equipment, and the method comprises the following steps: acquiring feeding reference information of a pet to be fed; predicting the feeding amount of the pet to be fed according to the feeding reference information based on a pet feeding model generated by machine learning model training; generating a feeding instruction according to the predicted feeding amount; sending a feeding instruction to a pet feeder so as to control the pet feeder to put food to the pet to be fed according to the feeding instruction. The pet feeding method, the pet feeding device, the computer equipment and the storage medium solve the problem that feeding of pets in the prior art is not scientific enough.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a pet feeding method, a pet feeding device, computer equipment and a storage medium.
Background
With the improvement of living standard of people, many families can raise pets, most family members are busy in work, the feeding of the pets is difficult to be comprehensively considered, and particularly, the situation of unscientific feeding is common, so that the pets are over obese due to unknown hunger and satiety.
Therefore, the pet feeder is suitable for being taken along, namely, the pet feeder actively puts food to the pet, thereby avoiding manual feeding.
In actual use, when the pet feeder feeds food, the situation of unscientific feeding still exists, and the situation often occurs that the fed food is too much, so that the pet is fat and too much, or the fed food is too little, so that the pet is not full and thin, and further, various diseases such as heart disease, arthritis and the like easily occur to the pet.
Therefore, how to realize the scientific feeding of the pets still needs to be solved urgently.
Disclosure of Invention
The embodiments of the invention provide a pet feeding method, a pet feeding device, a computer device and a storage medium, and solve the problem that pet feeding is not scientific in the related technology.
The technical scheme adopted by the invention is as follows:
according to an embodiment of the invention, a pet feeding method is applied to a computer device, and comprises the following steps: acquiring feeding reference information of a pet to be fed; predicting the feeding amount of the pet to be fed according to the feeding reference information based on a pet feeding model generated by machine learning model training; generating a feeding instruction according to the predicted feeding amount; sending a feeding instruction to a pet feeder so as to control the pet feeder to put food to the pet to be fed according to the feeding instruction.
In one embodiment of the invention, a pet feeding device for use with a computer device, the device comprising: the feeding information acquisition module is used for acquiring feeding reference information of the pet to be fed; the feeding amount prediction module is used for predicting the feeding amount of the pet to be fed according to the feeding reference information based on a pet feeding model generated by machine learning model training; the feeding instruction generating module is used for generating a feeding instruction according to the predicted feeding amount; and the feeding instruction sending module is used for sending a feeding instruction to the pet feeder so as to control the pet feeder to put food to the pet to be fed according to the feeding instruction.
According to another embodiment of the present invention, the feeding information obtaining module includes: the motion data acquisition unit is used for monitoring the motion state of the pet to be fed through the wearable device worn by the pet to be fed to obtain the motion amount of the pet to be fed; the first feeding reference information definition unit is used for taking the motion amount of the pet to be fed as the feeding reference information of the pet to be fed.
According to another embodiment of the present invention, the feeding information obtaining module includes: the variety identification unit is used for identifying the identity of the pet to be fed through the pet feeder to obtain the variety of the pet to be fed; the time acquisition unit is used for acquiring the current feeding time; and the second feeding information definition unit is used for taking the variety of the pet to be fed and the current feeding time as the feeding reference information of the pet to be fed.
According to another embodiment of the invention, the feeding amount prediction module comprises: the characteristic extraction unit is used for inputting the feeding reference information into the pet feeding model to perform initial characteristic extraction; the characteristic connection unit is used for carrying out full connection on the extracted initial characteristics to obtain global characteristics; and the probability calculation unit is used for calculating the probability of the pet to be fed aiming at different feeding amounts according to the global characteristics and predicting the feeding amount of the pet to be fed.
According to another embodiment of the invention, the feeding instruction sending module comprises: the position positioning unit is used for positioning the current position of the pet to be fed through the wearing equipment worn by the pet to be fed; and the instruction sending unit is used for sending the feeding instruction to the pet feeder if the current position of the pet to be fed is within a specific range of the pet feeder.
In accordance with another embodiment of the present invention, the pet feeding device further comprises: the model training module is used for generating the pet feeding model through the machine learning model training;
the pet feeding device further comprises: the pet feeding system comprises a weight obtaining module, a feeding module and a feeding module, wherein the weight obtaining module is used for obtaining body information of the pet to be fed, and the body information comprises the weight, the variety, the age and the height of the pet to be fed; the training judgment module is used for judging whether to perform the training of the pet feeding model again according to the body information of the pet to be fed, and if so, taking the feeding reference information and the predicted corresponding feeding amount of the pet to be fed based on the current pet feeding model as first sample data; and the retraining module is used for retraining the pet feeding model according to the first sample data to generate an updated pet feeding model.
According to another embodiment of the present invention, the model training module comprises: the sample data acquisition unit is used for acquiring second sample data, and the second sample data comprises feeding reference information and feeding amount of a plurality of different varieties of pets; the parameter optimization unit is used for constructing the machine learning model and performing iterative optimization on parameters of the machine learning model according to the second sample data; and the model convergence unit is used for converging the machine learning model to obtain the pet feeding model if the specific function corresponding to the machine learning model is converged by the parameters of the iterative optimization.
According to an embodiment of the invention, a computer device comprises a processor and a memory, the memory having stored thereon computer readable instructions which, when executed by the processor, implement a pet feeding method as described above.
According to an embodiment of the invention, a storage medium has stored thereon a computer program which, when executed by a processor, implements a pet feeding method as described above.
In the technical scheme, the computer equipment acquires the feeding reference information of the pet to be fed, the pet feeding model generated based on the machine learning model training is used, the feeding amount of the pet to be fed is predicted according to the feeding reference information, the feeding amount obtained according to prediction is used for generating the feeding instruction, the feeding instruction is transmitted to the pet feeder, and finally the pet feeder is controlled to feed the pet to be fed according to the feeding instruction, so that the phenomenon that the pet feeder puts in food too much or too little can not occur, and the problem that the pet feeding existing in the prior art is not scientific enough is solved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a schematic illustration of an implementation environment in accordance with the present invention.
Fig. 2 is a block diagram illustrating a hardware configuration of a computer device according to an example embodiment.
Fig. 3 is a flow chart illustrating a method of feeding a pet, according to an exemplary embodiment.
FIG. 4 is a flow chart of one embodiment of step 310 in the corresponding embodiment of FIG. 3.
Fig. 5 is a flow chart of step 310 in another embodiment of the corresponding embodiment of fig. 3.
FIG. 6 is a flow chart of one embodiment of step 330 of the corresponding embodiment of FIG. 3.
FIG. 7 is a flow diagram for one embodiment of step 350 of the corresponding embodiment of FIG. 3.
FIG. 8 is a flowchart illustrating a method of generating a pet feeding model by machine learning model training, according to an exemplary embodiment.
FIG. 9 is a flow chart illustrating another method of feeding a pet, according to an exemplary embodiment.
Fig. 10 is a block diagram illustrating a pet feeding device according to an exemplary embodiment.
FIG. 11 is a block diagram illustrating a computer device in accordance with an example embodiment.
While specific embodiments of the invention have been shown by way of example in the drawings and will be described in detail hereinafter, such drawings and description are not intended to limit the scope of the inventive concepts in any way, but rather to explain the inventive concepts to those skilled in the art by reference to the particular embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
FIG. 1 is a schematic illustration of an environment involved in a pet feeding method. The implementation environment includes the pet food dispensing device 110, the server 130, the pet-wearing device 150, and the terminal 170.
The pet feeder 110, which is used for delivering food to a pet, can identify the pet so as to more accurately deliver specific food to a specific pet.
The pet wearing device 150 is worn on a pet body and used for monitoring the motion state, the weight and the like of the pet.
The server 130 is an electronic device that provides background services to the user, for example, background services including pet feeding services and the like.
Of course, according to actual operation needs, a server cluster can be constructed by the plurality of servers 130, so that the pet feeding service is provided by the server cluster to a large number of users for feeding pets.
The terminal 170 may be a desktop computer, a notebook computer, a tablet computer, a smart phone, or other electronic devices with network connection functions, which is not limited herein.
The server 130 establishes a wireless or wired network connection with the pet feeder 110, the pet wearable device 150 and the terminal 170 in advance, so that data transmission between the server 130 and the pet feeder 110, the pet wearable device 150 and the terminal 170 is realized through the network connection. For example, the data transmitted includes: the state of motion of the pet to be fed, feeding instructions, etc.
The server 130 interacts with the pet feeder 110, the pet wearable device 150 and the terminal 170 respectively, the server 130 predicts the feeding amount of the pet to be fed according to the feeding reference information of the pet to be fed based on the pet feeding model, generates a feeding instruction according to the predicted feeding amount and sends the feeding instruction to the pet feeder 110.
After receiving the feeding instruction sent by the server 130, the pet feeder 110 can deliver food to the pet to be fed according to the feeding instruction.
The terminal 170 may prompt the user to view an image of the pet food via an image component configured with the terminal 170 after receiving the feeding instruction sent by the server 130, or when it is determined that the pet food is near the pet food dispensing device 110 based on the position location function provided by the pet wearing device 150.
Fig. 2 is a block diagram illustrating a hardware configuration of a computer device according to an example embodiment. Such a computer device is suitable for use in the server 130 of the implementation environment shown in fig. 1.
It should be noted that this computer device is only one example adapted to the present invention and should not be considered as providing any limitation to the scope of use of the present invention. Nor should such a computer device be interpreted as having a need to rely on or have to have one or more components of the exemplary computer device 200 shown in fig. 2.
The hardware structure of the computer device 200 may be greatly different due to the difference of configuration or performance, as shown in fig. 2, the computer device 200 includes: a power supply 210, an interface 230, at least one memory 250, and at least one Central Processing Unit (CPU) 270.
Specifically, the power supply 210 is used to provide operating voltages for various hardware devices on the computer device 200.
The interface 230 includes at least one wired or wireless network interface for interacting with external devices. For example, interaction between the pet food dispensing device 110 and the computer device 130 in the implementation environment shown in fig. 1 is performed.
Of course, in other examples of the present invention, the interface 230 may further include at least one serial-to-parallel conversion interface 233, at least one input/output interface 235, at least one USB interface 237, etc., as shown in fig. 2, which is not limited herein.
The storage 250 is used as a carrier for resource storage, and may be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc., and the resources stored thereon include an operating system 251, an application 253, data 255, etc., and the storage manner may be a transient storage or a permanent storage.
The operating system 251 is used for managing and controlling hardware devices and application programs 253 on the computer device 200, so as to implement operations and processing of the mass data 255 in the memory 250 by the central processing unit 270, which may be windows server, Mac OS XTM, UnixTM, linux, FreeBSDTM, and the like.
The application 253 is a computer program that performs at least one specific task on the operating system 251, and may include at least one module (not shown in fig. 2), each of which may contain a series of computer-readable instructions for the computer device 200. For example, the pet feeding device may be considered an application 253 deployed on the computer device 200.
The data 255 may be photographs, pictures, etc. stored in a disk, or may be pet feeding models, etc. stored in the memory 250.
The central processor 270 may include one or more processors and is configured to communicate with the memory 250 through at least one communication bus to read computer-readable instructions stored in the memory 250, and further implement operations and processing of the mass data 255 in the memory 250. The pet feeding method is accomplished, for example, by the central processor 270 reading a series of computer readable instructions stored in the memory 250.
Furthermore, the present invention can be implemented by hardware circuits or by a combination of hardware circuits and software, and thus, the implementation of the present invention is not limited to any specific hardware circuits, software, or a combination of both.
Referring to fig. 3, in an exemplary embodiment, a pet feeding method is applied to a computer device of the implementation environment shown in fig. 1, the computer device may be a personal computer, a server, or the like, and the hardware structure of the computer device may be as shown in fig. 2.
The pet feeding method can be executed by computer equipment, and can also be understood as being executed by a pet feeding device operated in the computer equipment. In the following method embodiments, for convenience of description, the execution subject of each step is described as a computer device, but the present invention is not limited thereto.
The method of feeding a pet may include the steps of:
in step 310, feeding reference information of the pet to be fed is obtained.
The feeding reference information of the pet to be fed is closely related to the feeding amount of the pet to be fed, and it can also be understood that the feeding amount of the pet to be fed can be predicted by the feeding reference information of the pet to be fed.
The feeding reference information of the pet to be fed includes, but is not limited to: the amount of exercise of the pet to be fed, the feeding time of the pet to be fed, the body information of the pet to be fed, and the like. Further, the physical information of the pet to be fed includes, but is not limited to: the weight, breed, age, height, etc. of the pet to be fed. It is stated that breeds of pets to be fed, e.g. cats and dogs, can be regarded as pets to be fed having different breeds, and that teddy dogs and corgi dogs can also be regarded as pets to be fed having different breeds.
For example, for the same pet to be fed, the amount of exercise is large, and the feeding amount should be large; the amount of exercise is small, and the feeding amount is small; alternatively, the feeding time is noon, it is considered that the feeding amount should be relatively large, and the feeding time is in the evening, the feeding amount should be relatively small.
Alternatively, in the case where the amount of exercise of the pet to be fed is the same, if the breed of the pet to be fed is different, the amount of feed will be different. For example, cats are fed more than dogs for the same amount of exercise.
Therefore, in order to predict the feeding amount of the pet to be fed, the feeding reference information of the pet to be fed needs to be acquired.
Obtaining feeding reference information about a pet to be fed, for example, the amount of motion of the pet to be fed, which can be obtained by monitoring the state of motion of the pet to be fed by a wearable device worn by the pet to be fed; or the variety in the body information of the pet to be fed can be obtained through the identity recognition function provided by the pet feeder; or, the weight, age and height of the pet to be fed can be obtained through user input or machine learning. That is, if the types of the feeding reference information of the pet to be fed are different, the obtaining manner is also different, which is not listed here.
And 330, predicting the feeding amount of the pet to be fed according to the feeding reference information based on the pet feeding model generated by machine learning model training.
The pet feeding model is generated by machine learning model training, and the essence of the pet feeding model is to form a mathematical mapping curve between the feeding reference information of the pet to be fed and the feeding amount of the pet to be fed. That is, the pet feeding model accurately describes the mathematical mapping relationship between the feeding reference information of the pet to be fed and the feeding amount of the pet to be fed through the mathematical mapping curve.
Among these, machine learning models include, but are not limited to: linear models, support vector machines, decision trees, neural networks, etc., which are not limited in this embodiment.
Therefore, after the feeding reference information of the pet to be fed is obtained, the feeding amount of the pet to be fed is predicted by the feeding reference information of the pet to be fed based on the mathematical mapping relation between the feeding reference information of the pet to be fed and the feeding amount of the pet to be fed described by the pet feeding model.
And 350, generating a feeding instruction according to the predicted feeding amount.
It will be appreciated that the pet food dispensing device is responsive to various instructions that satisfy the pet food dispensing device specific data format.
Therefore, in order to inform the pet feeder how to put food to the pet to be fed, the predicted feeding amount needs to be data-packaged so as to be a feeding instruction meeting a specific data format of the pet feeder, and thus, the feeding instruction is conveniently received by a subsequent pet feeder.
For the pet feeder, after receiving the feeding instruction, the data analysis can be performed on the feeding instruction to obtain the feeding amount of the pet to be fed, and then the food is put into the pet to be fed according to the feeding amount.
Therefore, the food feeding of the pet feeder is carried out according to the feeding amount obtained by prediction strictly, the feeding amount is closely related to the feeding reference information such as the motion amount, feeding time and body information of the pet to be fed, namely, the pet feeder carries out the food feeding according to the actual situation of the pet to be fed, so that the real requirement of the food feeding is well controlled, the phenomenon that the fed food is too much or too little can not occur, and the problem that the pet feeding in the prior art is not scientific enough is solved effectively.
In addition, the phenomenon of serious waste caused by feeding the pet can be effectively avoided by avoiding too much or too little food.
Referring to FIG. 4, in an exemplary embodiment, step 310 may include the steps of:
and 311, monitoring the motion state of the pet to be fed through the wearable device worn by the pet to be fed, so as to obtain the motion amount of the pet to be fed.
The motion state of the pet to be fed is monitored through the wearable device worn by the pet to be fed.
Specifically, the wearing device worn by the pet to be fed may include: temperature sensor, heart rate sensor, respiratory rate sensor, step-counting sensor, etc.
Then, based on the wearable device worn by the pet to be fed, the following are collected: the body temperature, the heart beat frequency, the breathing frequency, the step number and the like of the pet to be fed are monitored, so that the motion state of the pet to be fed is monitored.
For the computer equipment, based on the configured sampling circuit, the body temperature, the heart rate, the breathing rate, the step number and the like of the pet to be fed can be obtained, and the motion amount of the pet to be fed can be further obtained.
For example, the number of steps of the pet to be fed is used as the amount of exercise of the pet to be fed, or the amount of exercise of the pet to be fed is estimated from the body temperature, the heart rate, and the respiratory rate of the pet to be fed.
And 313, taking the exercise amount of the pet to be fed as feeding reference information of the pet to be fed.
Referring to fig. 5, in another exemplary embodiment, step 310 may include the steps of:
and 312, identifying the identity of the pet to be fed through the pet feeder to obtain the variety of the pet to be fed, and acquiring the current feeding time.
First, it should be understood that the pet to be fed is also time-sliced, and for this reason, it is considered that the pet food dispensing device is only required to dispense food to the pet to be fed in a specific time slice, so in this embodiment, the feeding reference information of the pet to be fed includes the current feeding time.
The current feeding time refers to the system time collected by the computer device, so as to determine whether the pet feeder needs to put food to the pet to be fed at the moment, that is, whether the pet to be fed needs to eat at the moment.
For example, assuming that the specific time period for the pet to be fed to eat is 9 o 'clock to 10 o' clock, and the current feeding time is 9 o 'clock to 15 o' clock, the feeding amount predicted by using the specific time period as the feeding reference information is non-zero, that is, the pet feeder is considered to need to feed food to the pet to be fed at this time.
If the current feeding time is 10 o' clock and 15 min, the feeding quantity predicted by taking the current feeding time as the feeding reference information is zero, namely the pet feeder is considered not to need to put food to the pet to be fed at the moment.
Secondly, it is easy to understand that if the amount of motion of the pet to be fed needs to be known before the feeding amount of the pet to be fed is predicted each time, the computer device often needs to consume extra calculation amount, thereby possibly affecting the processing capability and the processing efficiency of the computer device for processing other tasks and being not beneficial to improving the prediction efficiency of the task.
Therefore, in this embodiment, the feeding reference information of the pet to be fed further includes the breed of the pet to be fed. The acquisition of the variety of the pet to be fed is realized through the identification function provided by the pet feeder.
Specifically, the pet feeder shoots the face of the pet based on the configured camera assembly, and carries out image recognition on the shot picture of the face of the pet, so that the variety of the pet to be fed can be recognized.
In this embodiment, the pet feeding model essentially describes the mathematical mapping relationship between different feeding time and feeding amount of different pet species to be fed.
Therefore, as long as the variety of the pet to be fed is identified, the corresponding feeding amount can be obtained through the current feeding time prediction based on the pet feeding model, so that the calculation amount consumed additionally by the computer equipment for acquiring the motion amount of the pet to be fed each time is saved, the prediction efficiency of the feeding amount of the pet to be fed is effectively improved, and the user experience of the pet feeding service is promoted.
And step 314, taking the variety of the pet to be fed and the current feeding time as feeding reference information of the pet to be fed.
Under the effect of the embodiment, the feeding reference information of the pet to be fed is obtained and is used as a data basis for predicting the feeding amount of the pet to be fed, and the prediction of the feeding amount of the pet to be fed based on the pet feeding model is further realized.
Referring to fig. 6, in an exemplary embodiment, step 330 may include the following steps:
In this embodiment, the pet feeding model is generated based on neural network training. The pet feeding model at least comprises: input layer, several hidden layers and output layer.
Specifically, the input layer is responsible for inputting feeding reference information into the pet feeding model; the hidden layer is used for carrying out feature extraction and feature connection on feeding reference information input into the pet feeding model; the output layer is responsible for prediction, namely calculating the probability of different feeding amounts, so that the pet feeding model finally outputs the feeding amount of the pet to be fed.
The initial characteristic is the feeding reference information which roughly describes the pet to be fed in a digital form, so that the full connection of the initial characteristic through the hidden layer is facilitated subsequently.
And 333, fully connecting the extracted initial features to obtain global features.
The overall characteristics accurately describe the feeding reference information of the pet to be fed in a digital form, and then the feeding quantity prediction is conveniently carried out through an output layer.
And step 335, calculating the probability of the pet to be fed for different feeding amounts according to the global features, and predicting the feeding amount of the pet to be fed.
Wherein the prediction is realized by a softmax activation function.
For example, assuming that there are m1 and m2 for different feeding amounts, the probability of the different feeding amounts is calculated as P1 and P2 by the softmax activation function, respectively.
If P1> P2, the predicted feeding volume for the pet to be fed is m 1.
On the contrary, if P1< P2, the feeding amount of the pet to be fed is predicted to be m 2.
Through the process, the feed amount prediction of the pet to be fed based on the pet feeding model is realized, so that the pet feeder can realize the feed putting according to the actual situation of the pet to be fed, the real demand of the feed putting is well controlled, the phenomenon of excessive or insufficient food putting is avoided, and the problem that the pet feeding in the prior art is not scientific is effectively solved.
Referring to FIG. 7, in an exemplary embodiment, step 350 may include the steps of:
Wherein, treat that wearing equipment that feeding pet wore includes at least: the GPS positioning component is used for realizing the position positioning of the pet to be fed.
And 353, if the current position of the pet to be fed is within a specific range of the pet feeder, sending the feeding instruction to the pet feeder.
The specific range of the pet feeder can be flexibly set according to the actual needs of the application scene, for example, the specific range of the pet feeder is set to be a circle with the pet feeder as the center of a circle and 1 meter as the radius.
Then, if the pet to be fed is not within the specified range of the pet food dispensing device, the pet to be fed is deemed not to be in the vicinity of the pet food dispensing device, and the computer device will not send feeding instructions to the pet food dispensing device.
For the pet feeder, as the feeding instruction is not received, the food is not put into the pet to be fed, so that the phenomenon that the put food is eaten by other pets due to the fact that the food is put by mistake is avoided, or the put food is not eaten nearby because the pet to be fed is not put into the pet feeder, the placing time is too long, and the phenomenon that the pet is fed is seriously wasted.
In an exemplary embodiment, before step 330, the method as described above may further include the steps of:
training by the machine learning model to generate the pet feeding model.
Specifically, as shown in fig. 8, in an implementation of an embodiment, the model training process may include the following steps:
Wherein the second sample data comprises feeding reference information and feeding amount of a plurality of different varieties of pets.
And 430, constructing the machine learning model, and performing iterative optimization on parameters of the machine learning model according to the second sample data.
And step 450, if the specific function corresponding to the machine learning model is converged by the parameters of the iterative optimization, converging the machine learning model to obtain the pet feeding model.
It can be understood that modeling, i.e. constructing a machine learning model, only preliminarily forms a mathematical mapping curve, and model training optimizes the mathematical mapping curve, i.e. optimizes the mathematical mapping relationship described by the data mapping curve.
And model training, which is essentially a process of performing iterative optimization on parameters of the machine learning model to make a specific function corresponding to the machine learning model converge gradually. Wherein the specific function includes but is not limited to: a desired function, a loss function, etc.
The process of model training is illustrated below with a particular function as the loss function.
Specifically, parameters of the machine learning model are initialized randomly, and a loss function corresponding to the machine learning model is constructed according to the current second sample data and the initialized parameters.
If the loss value of the loss function reaches a minimum, the loss function converges, i.e., the machine learning model converges to the pet feeding model.
Otherwise, if the loss value of the loss function does not reach the minimum, the loss function is not converged, at this time, the parameters of the machine learning model are updated, the loss function corresponding to the machine learning model is reconstructed according to the latter second sample data and the updated parameters, and whether the loss value of the loss function reaches the minimum is judged.
Therefore, based on a large amount of second sample data, the machine learning model can gradually converge along with reconstruction of the loss function and updating of parameters of the machine learning model, and the pet feeding model is obtained.
Of course, in other embodiments, the number of iterations may be set in consideration of the efficiency of model training, and then, when the loss value of the loss function fails to reach the minimum value, but the number of iterations reaches the maximum value, the updating of the parameters of the machine learning model is stopped, which is considered that the machine learning model has converged, and this embodiment is not specifically limited to this.
The iteration times can be flexibly set according to the actual needs of the application scenarios, for example, if the application scenarios with high prediction accuracy requirements are met, a larger iteration time is set.
Through the process, model training of the machine learning model is achieved, the pet feeding model is obtained through convergence, and the feeding quantity of the pet to be fed is predicted according to the prediction capability of the pet feeding model.
Referring to fig. 9, in an exemplary embodiment, before step 330, the method as described above may further include the following steps:
and step 510, acquiring the body information of the pet to be fed.
Wherein the body information comprises the weight, variety, age and height of the pet to be fed. The body information can be acquired through user input, machine learning, monitoring, identity recognition and the like.
For example, the weight acquisition of the pet to be fed can be monitored by the wearable device, and can also be predicted by machine learning.
For example, a wearable device worn by a pet to be fed includes at least: and the weighing-pressure sensor is used for realizing the weight monitoring of the pet to be fed.
Or, when the user registers, the weight of the pet to be fed is input through an application program or other tools, so that the initial weight of the pet to be fed can be obtained.
Or, the current weight of the pet to be fed is predicted according to the motion amount, feeding amount and the like of the pet to be fed through machine learning based on the initial weight of the pet to be fed input by the user. .
And step 530, judging whether to perform the training of the pet feeding model again according to the body information of the pet to be fed.
The following describes the judgment process of the retraining of the pet feeding model by taking the weight in the body information as an example.
It will be appreciated that if the weight of the pet to be fed changes, the feeding amount of the pet to be fed may also change, for example, the feeding amount increases, and at this time, the feeding amount prediction based on the current pet feeding model may have an error.
Therefore, in this embodiment, whether to re-train the pet feeding model depends on whether the weight of the pet to be fed is greatly changed, that is, whether the weight of the pet to be fed is changed beyond a specific weight range.
If the weight of the pet to be fed changes beyond a specific weight range, that is, the weight of the pet to be fed changes greatly, it is considered that there may be a large error in the predicted feeding amount of the current pet feeding model, and steps 550 to 570 should be performed, that is, retraining to generate an updated pet feeding model.
On the contrary, if the weight of the pet to be fed does not change beyond the specific weight range, that is, the weight of the pet to be fed does not change greatly, the error of the predicted feeding amount of the current pet feeding model is considered to be small and still sufficient to ensure the accuracy of the prediction, the step 550 should not be executed, and the step 510 is returned to, and the weight of the pet to be fed is continuously monitored.
By analogy, no matter the weight, variety, age or height of the body information is changed, the pet feeding model is retrained, namely, the steps 550 to 570 are executed.
And step 550, taking the feeding reference information and the predicted corresponding feeding amount of the pet to be fed based on the current pet feeding model as first sample data.
After it is determined that retraining is required, acquisition of the first sample data is performed. At this time, unlike the source of the second sample data, the first sample data is derived from the feeding reference information and the predicted corresponding feeding amount of the pet to be fed based on the current pet feeding model.
And 570, re-training the pet feeding model according to the first sample data to generate an updated pet feeding model.
In the process, the pet feeding model is updated in time according to actual conditions such as the weight of the pet to be fed, so that the prediction capability of the pet feeding model is continuously enhanced along with the increase of sample data from different pet feeders, the prediction accuracy is fully guaranteed, and the phenomenon of serious waste in pet feeding is further avoided.
The following are examples of devices of the present invention that may be used to perform the pet feeding methods of the present invention. For details not disclosed in the embodiments of the device of the present invention, reference is made to the embodiments of the method of feeding pets according to the present invention.
Referring to fig. 10, in an exemplary embodiment, a pet feeding device 900 for use with a computer device, the pet feeding device 900 includes, but is not limited to: a feeding information obtaining module 910, a feeding amount predicting module 930, a feeding instruction generating module 950 and a feeding instruction transmitting module 970.
The feeding information obtaining module 910 is configured to obtain feeding reference information of a pet to be fed.
A feeding amount prediction module 930, configured to predict a feeding amount of the pet to be fed according to the feeding reference information based on a pet feeding model generated by machine learning model training.
A feeding instruction generating module 950, configured to generate a feeding instruction according to the predicted feeding amount.
The feeding instruction sending module 970 is configured to send a feeding instruction to the pet feeder to control the pet feeder to put food to the pet to be fed according to the feeding instruction.
It should be noted that, when the pet feeding device provided in the above embodiment feeds a pet, only the division of the above functional modules is taken as an example, in practical applications, the above functions may be distributed by different functional modules according to needs, that is, the internal structure of the pet feeding device is divided into different functional modules to complete all or part of the above described functions.
In addition, the pet feeding device provided by the above embodiment and the embodiment of the pet feeding method belong to the same concept, wherein the specific manner of executing operations by each module has been described in detail in the method embodiment, and is not described again here.
Referring to fig. 11, in an exemplary embodiment, a computer device 1000 includes at least one processor 1001, at least one memory 1002, and at least one communication bus 1003.
Wherein the memory 1002 has computer readable instructions stored thereon, the processor 1001 reads the computer readable instructions stored in the memory 1002 through the communication bus 1003.
The computer readable instructions, when executed by the processor 1001, implement the pet feeding methods of the various embodiments described above.
In an exemplary embodiment, a storage medium has a computer program stored thereon, which when executed by a processor implements the pet feeding method in the above embodiments.
The above-mentioned embodiments are merely preferred examples of the present invention, and are not intended to limit the embodiments of the present invention, and those skilled in the art can easily make various changes and modifications according to the main concept and spirit of the present invention, so that the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A pet feeding method, applied to a computer device, comprising:
acquiring feeding reference information of a pet to be fed;
predicting the feeding amount of the pet to be fed according to the feeding reference information based on a pet feeding model generated by machine learning model training;
generating a feeding instruction according to the predicted feeding amount;
sending a feeding instruction to a pet feeder so as to control the pet feeder to put food to the pet to be fed according to the feeding instruction.
2. The method of claim 1, wherein the obtaining feeding reference information of the pet to be fed comprises:
monitoring the motion state of the pet to be fed through the wearable equipment worn by the pet to be fed to obtain the motion amount of the pet to be fed;
and taking the motion amount of the pet to be fed as feeding reference information of the pet to be fed.
3. The method of claim 1, wherein the obtaining feeding reference information of the pet to be fed comprises:
identifying the identity of the pet to be fed through the pet feeder to obtain the variety of the pet to be fed, and acquiring the current feeding time;
and taking the variety of the pet to be fed and the current feeding time as feeding reference information of the pet to be fed.
4. The method of claim 1, wherein the predicting the feeding amount of the pet to be fed according to the feeding reference information based on the pet feeding model trained by the machine learning model comprises:
inputting the feeding reference information into the pet feeding model for initial feature extraction;
fully connecting the extracted initial features to obtain global features;
and calculating the probability of the pet to be fed aiming at different feeding amounts according to the global features, and predicting the feeding amount of the pet to be fed.
5. The method of claim 1, wherein sending feeding instructions to the pet food dispensing device comprises:
positioning the current position of the pet to be fed through the wearing equipment worn by the pet to be fed;
sending the feeding instruction to the pet feeder if the current position of the pet to be fed is within a specific range of the pet feeder.
6. The method of any of claims 1 to 5, further comprising:
training the machine learning model to generate the pet feeding model;
the method further comprises the following steps:
acquiring body information of the pet to be fed, wherein the body information comprises the weight, variety, age and height of the pet to be fed;
judging whether to carry out the training of the pet feeding model again according to the body information of the pet to be fed;
if so, taking the feeding reference information and the predicted corresponding feeding amount of the pet to be fed based on the current pet feeding model as first sample data;
and re-training the pet feeding model according to the first sample data to generate an updated pet feeding model.
7. The method of claim 6, wherein said training by said machine learning model to generate said pet feeding model comprises:
acquiring second sample data, wherein the second sample data comprises feeding reference information and feeding amount of a plurality of different varieties of pets;
constructing the machine learning model, and performing iterative optimization on parameters of the machine learning model according to the second sample data;
and if the parameters of the iterative optimization enable the specific function corresponding to the machine learning model to be converged, converging the machine learning model to obtain the pet feeding model.
8. A pet feeding device for use with a computer device, the device comprising:
the feeding information acquisition module is used for acquiring feeding reference information of the pet to be fed;
the feeding amount prediction module is used for predicting the feeding amount of the pet to be fed according to the feeding reference information based on a pet feeding model generated by machine learning model training;
the feeding instruction generating module is used for generating a feeding instruction according to the predicted feeding amount;
and the feeding instruction sending module is used for sending a feeding instruction to the pet feeder so as to control the pet feeder to put food to the pet to be fed according to the feeding instruction.
9. A computer device, comprising:
a processor; and
a memory having stored thereon computer readable instructions which, when executed by the processor, implement a pet feeding method as claimed in any one of claims 1 to 7.
10. A storage medium having stored thereon a computer program for implementing a method of feeding a pet according to any one of claims 1 to 7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911298604.8A CN111109105A (en) | 2019-12-17 | 2019-12-17 | Pet feeding method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911298604.8A CN111109105A (en) | 2019-12-17 | 2019-12-17 | Pet feeding method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111109105A true CN111109105A (en) | 2020-05-08 |
Family
ID=70498127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911298604.8A Pending CN111109105A (en) | 2019-12-17 | 2019-12-17 | Pet feeding method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111109105A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111869579A (en) * | 2020-07-30 | 2020-11-03 | 北京小米移动软件有限公司 | Control method, device and equipment for feeding pet and storage medium |
| CN112493203A (en) * | 2020-11-26 | 2021-03-16 | 小佩网络科技（上海）有限公司 | Pet food intake determining method and device, electronic equipment and storage medium |
| CN112868559A (en) * | 2021-01-27 | 2021-06-01 | 珠海格力电器股份有限公司 | Feeding method, device, equipment and storage medium |
| CN113207722A (en) * | 2021-03-30 | 2021-08-06 | 广州朗国电子科技有限公司 | Artificial intelligence agricultural and animal husbandry automatic feeding method, equipment and medium |
| CN114097645A (en) * | 2020-08-26 | 2022-03-01 | 中移动信息技术有限公司 | Training method, device, equipment and storage medium of pet health model |
| CN114303973A (en) * | 2021-12-28 | 2022-04-12 | 新瑞鹏宠物医疗集团有限公司 | Feeding method, feeding device, storage medium and electronic equipment |
| CN114467782A (en) * | 2022-01-07 | 2022-05-13 | 珠海一微半导体股份有限公司 | Intelligent feeding method for pet robot, chip and robot |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101023442A (en) * | 2004-07-29 | 2007-08-22 | Can科技公司 | System and method for optimizing animal production based on environmental nutrient inputs |
| US20160007565A1 (en) * | 2013-03-01 | 2016-01-14 | Cleverpet Llc | Animal interaction device, system, and method |
| CN105961213A (en) * | 2016-05-05 | 2016-09-28 | 江西智能无限物联科技有限公司 | Intelligent pet feeder and intelligent feeding system |
| CN106156463A (en) * | 2015-04-03 | 2016-11-23 | 宠邦智能科技（上海）有限公司 | There is the pet health living management system and method for self-learning capability |
| CN106472332A (en) * | 2016-10-10 | 2017-03-08 | 重庆科技学院 | Pet feeding method and system based on dynamic intelligent algorithm |
| CN106538404A (en) * | 2016-11-03 | 2017-03-29 | 北京探感科技股份有限公司 | The method and system of accurate feeding |
| CN107318680A (en) * | 2017-08-02 | 2017-11-07 | 深圳市广和通无线股份有限公司 | Pet feeding control method and device |
| CN107372158A (en) * | 2017-07-13 | 2017-11-24 | 深圳市沃特沃德股份有限公司 | Feeding pet method and system |
| CN109392752A (en) * | 2018-11-28 | 2019-03-01 | 嘉兴学院 | Pet interactive device, system and interactive approach |
| CN110363247A (en) * | 2019-07-19 | 2019-10-22 | 太原理工大学 | A kind of live pig diet exception intelligent monitoring method and system |
| CN110495399A (en) * | 2019-08-16 | 2019-11-26 | 斯威方德(深圳)智能科技有限公司 | Method, apparatus, computer equipment and the storage medium of automatic feeding |
| CN110547210A (en) * | 2019-09-04 | 2019-12-10 | 北京海益同展信息科技有限公司 | feed supply method and system, computer system, and storage medium |
-
2019
- 2019-12-17 CN CN201911298604.8A patent/CN111109105A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101023442A (en) * | 2004-07-29 | 2007-08-22 | Can科技公司 | System and method for optimizing animal production based on environmental nutrient inputs |
| US20160007565A1 (en) * | 2013-03-01 | 2016-01-14 | Cleverpet Llc | Animal interaction device, system, and method |
| CN106156463A (en) * | 2015-04-03 | 2016-11-23 | 宠邦智能科技（上海）有限公司 | There is the pet health living management system and method for self-learning capability |
| CN105961213A (en) * | 2016-05-05 | 2016-09-28 | 江西智能无限物联科技有限公司 | Intelligent pet feeder and intelligent feeding system |
| CN106472332A (en) * | 2016-10-10 | 2017-03-08 | 重庆科技学院 | Pet feeding method and system based on dynamic intelligent algorithm |
| CN106538404A (en) * | 2016-11-03 | 2017-03-29 | 北京探感科技股份有限公司 | The method and system of accurate feeding |
| CN107372158A (en) * | 2017-07-13 | 2017-11-24 | 深圳市沃特沃德股份有限公司 | Feeding pet method and system |
| CN107318680A (en) * | 2017-08-02 | 2017-11-07 | 深圳市广和通无线股份有限公司 | Pet feeding control method and device |
| CN109392752A (en) * | 2018-11-28 | 2019-03-01 | 嘉兴学院 | Pet interactive device, system and interactive approach |
| CN110363247A (en) * | 2019-07-19 | 2019-10-22 | 太原理工大学 | A kind of live pig diet exception intelligent monitoring method and system |
| CN110495399A (en) * | 2019-08-16 | 2019-11-26 | 斯威方德(深圳)智能科技有限公司 | Method, apparatus, computer equipment and the storage medium of automatic feeding |
| CN110547210A (en) * | 2019-09-04 | 2019-12-10 | 北京海益同展信息科技有限公司 | feed supply method and system, computer system, and storage medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111869579A (en) * | 2020-07-30 | 2020-11-03 | 北京小米移动软件有限公司 | Control method, device and equipment for feeding pet and storage medium |
| CN114097645A (en) * | 2020-08-26 | 2022-03-01 | 中移动信息技术有限公司 | Training method, device, equipment and storage medium of pet health model |
| CN112493203A (en) * | 2020-11-26 | 2021-03-16 | 小佩网络科技（上海）有限公司 | Pet food intake determining method and device, electronic equipment and storage medium |
| CN112868559A (en) * | 2021-01-27 | 2021-06-01 | 珠海格力电器股份有限公司 | Feeding method, device, equipment and storage medium |
| CN113207722A (en) * | 2021-03-30 | 2021-08-06 | 广州朗国电子科技有限公司 | Artificial intelligence agricultural and animal husbandry automatic feeding method, equipment and medium |
| CN114303973A (en) * | 2021-12-28 | 2022-04-12 | 新瑞鹏宠物医疗集团有限公司 | Feeding method, feeding device, storage medium and electronic equipment |
| CN114467782A (en) * | 2022-01-07 | 2022-05-13 | 珠海一微半导体股份有限公司 | Intelligent feeding method for pet robot, chip and robot |
| CN114467782B (en) * | 2022-01-07 | 2023-10-24 | 珠海一微半导体股份有限公司 | Intelligent feeding method of pet robot, chip and robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111109105A (en) | Pet feeding method and device, computer equipment and storage medium | |
| CN111527478B (en) | System and method for detecting abnormal user experience and performance in cooperation with cloud equipment | |
| US20210342745A1 (en) | Artificial intelligence model and data collection/development platform | |
| WO2017215668A1 (en) | Posture estimation method and apparatus, and computer system | |
| US10824669B2 (en) | Sticker recommendation method and apparatus, server cluster, and storage medium | |
| US10360482B1 (en) | Crowd-sourced artificial intelligence image processing services | |
| CN107632697B (en) | Processing method, device, storage medium and the electronic equipment of application program | |
| CN110544109A (en) | user portrait generation method and device, computer equipment and storage medium | |
| WO2020151175A1 (en) | Method and device for text generation, computer device, and storage medium | |
| CN113080094B (en) | Pet companion method, pet companion device and computer equipment | |
| US20230368028A1 (en) | Automated machine learning pre-trained model selector | |
| CN113887447A (en) | Training method of object classification model, object classification prediction method and device | |
| CN109558889A (en) | Live pig Analysis of Human Comfort method and device | |
| CN110809043A (en) | Data processing method, device, equipment and storage medium based on Internet of things | |
| CN112529027A (en) | Data processing method, client, device and computer readable storage medium | |
| WO2023142349A1 (en) | Behavior sequence generation method and apparatus, storage medium and electronic device | |
| CN115345305A (en) | Inference system, method, device and related equipment | |
| US10853704B2 (en) | Model-based image labeling and/or segmentation | |
| CN113935251A (en) | User behavior prediction model generation method and device and user behavior prediction method and device | |
| CN113850390A (en) | Method, device, equipment and medium for sharing data in federal learning system | |
| CN107609645B (en) | Method and apparatus for training convolutional neural network | |
| CN109670579A (en) | Model generating method and device | |
| CN113676603B (en) | Call control method, device, equipment and storage medium | |
| TWI832679B (en) | Computer system and computer-implemented method for knowledge-preserving neural network pruning, and non-transitory computer-readable storage medium thereof | |
| US11599793B2 (en) | Data integration demand management using artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |
|
| RJ01 | Rejection of invention patent application after publication |