Pet feeding control method and system based on posture recognition

Abstract

The invention discloses a pet feeding control method and system based on posture recognition. The method comprises the following steps: acquiring real-time sensing data of a target pet object; determining a real-time behavior type of the target pet object according to the real-time sensing data based on a trained behavior recognition neural network; predicting the next behavior of the target pet object according to the real-time behavior types of the target pet object at the plurality of time points; and when the next behavior comprises a feeding behavior, generating a feeding instruction according to the real-time sensing data, and sending the feeding instruction to feeding equipment for execution. Therefore, more accurate and efficient feeding control can be realized by fully combining sensing data identification of the pet, and the automation degree and the intelligence degree of pet feeding control are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a pet feeding control method and system based on posture recognition. Background Art

[0002] With the improvement of people's living standards and the promotion of pets' status, the pet market has shown higher and higher demand and growth potential, and users are paying more and more attention to how to effectively control pet feeding in pet management. However, in the existing pet feeding solutions, generally only passive feeding is carried out through specific remotely controlled feeding equipment, and the feeding operation is not automatically determined by combining the pet's sensor data recognition. Therefore, the degree of automation and intelligence of feeding control is low, and the feeding effect is poor. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a pet feeding control method and system based on posture recognition, which can fully combine the pet's sensor data recognition to achieve more accurate and efficient feeding control, and improve the degree of automation and intelligence of pet feeding control.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a pet feeding control method based on posture recognition, the method comprising: Acquire real-time sensor data of target pet objects; Based on the trained behavior recognition neural network, determining the real-time behavior type of the target pet object according to the real-time sensing data; Predicting the next behavior of the target pet object according to the real-time behavior type of the target pet object at multiple time points; When the next behavior includes eating behavior, a feeding instruction is generated according to the real-time sensor data and sent to the feeding device for execution.

[0005] As an optional embodiment, in the first aspect of the present invention, the real-time sensing data includes at least one of temperature data, humidity data, radio frequency data, light data, image data, vibration data and sound data.

[0006] As an optional embodiment, in the first aspect of the present invention, the real-time behavior type includes at least one of eating behavior, resting behavior, attacking behavior, mating behavior, slow walking behavior and running behavior.

[0007] As an optional embodiment, in the first aspect of the present invention, the behavior recognition neural network is an RNN neural network, which is trained by a training data set including multiple training sensor data and corresponding pet behavior annotations.

[0008] As an optional embodiment, in the first aspect of the present invention, the method of determining the real-time behavior type of the target pet object based on the trained behavior recognition neural network according to the real-time sensing data includes: For each sensor data in the real-time sensor data, a prediction neural network corresponding to a data type of the sensor data is determined; the data type is temperature data, humidity data, radio frequency data, light data, image data, vibration data or sound data; the prediction neural network is trained by a training data set including a plurality of training sensor data corresponding to the data type and corresponding pet behavior annotations; The sensor data is input into the prediction neural network to obtain the output prediction behavior and the corresponding prediction probability; According to all the predicted behaviors and the predicted probabilities, the real-time behavior type of the target pet object is determined.

[0009] As an optional embodiment, in the first aspect of the present invention, determining the real-time behavior type of the target pet object according to all the predicted behaviors and the predicted probabilities includes: For each behavior type, the weighted sum average of the predicted probabilities of all the predicted behaviors corresponding to the behavior type is calculated to obtain the behavior probability corresponding to the behavior type; the behavior type is eating behavior, resting behavior, attacking behavior, mating behavior, slow walking behavior or running behavior; wherein the weighted calculation weight corresponding to each predicted probability includes a first weight and a second weight; the first weight is proportional to the prediction accuracy of the corresponding prediction neural network in the verification phase; the second weight is proportional to the data volume of the corresponding sensor data; The behavior type with the highest behavior probability is determined as the real-time behavior type of the target pet object.

[0010] As an optional implementation, in the first aspect of the present invention, predicting the next behavior of the target pet object according to the real-time behavior type of the target pet object at multiple time points includes: Arrange the real-time behavior types of the target pet object at multiple time points from early to late according to the corresponding time points to obtain a behavior type sequence corresponding to the target pet object; Based on a preset behavior contradiction rule, the inconsistent real-time behavior types in the behavior type sequence are removed to obtain an optimized type sequence; The optimized type sequence is input into a trained DQN network model to output the next behavior of the target pet object; the DQN network model is trained by a training data set including a plurality of training behavior type sequences and corresponding next behavior annotations.

[0011] As an optional implementation, in the first aspect of the present invention, generating a feeding instruction according to the real-time sensor data includes: Inputting the real-time sensing data into a trained distance prediction neural network to obtain output distance information between the target pet object and the feeding device; According to the distance information of the target pet object at multiple time points, determining whether the target pet object is in a close state, and obtaining a determination result; When the judgment result is no, calculating a feeding time value proportional to the distance information at the most recent time point; When the judgment result is yes, the distance information of the multiple time points is input into a preset regression fitting model to obtain a predicted next distance of the target pet object, and calculate a feeding time value proportional to the predicted next distance; A feeding instruction is generated for indicating the feeding time value between the feeding time point and the current time point.

[0012] A second aspect of an embodiment of the present invention discloses a pet feeding control system based on posture recognition, the system comprising: An acquisition module, used for acquiring real-time sensor data of a target pet object; A recognition module, for determining the real-time behavior type of the target pet object based on the trained behavior recognition neural network and the real-time sensing data; A prediction module, used to predict the next behavior of the target pet object according to the real-time behavior type of the target pet object at multiple time points; The feeding module is used to generate a feeding instruction according to the real-time sensor data when the next behavior includes eating behavior, and send it to the feeding device for execution.

[0013] As an optional embodiment, in the second aspect of the present invention, the real-time sensing data includes at least one of temperature data, humidity data, radio frequency data, light data, image data, vibration data and sound data.

[0014] As an optional embodiment, in the second aspect of the present invention, the real-time behavior type includes at least one of eating behavior, resting behavior, attacking behavior, mating behavior, slow walking behavior and running behavior.

[0015] As an optional embodiment, in the second aspect of the present invention, the behavior recognition neural network is a RNN neural network, which is trained by a training data set including multiple training sensor data and corresponding pet behavior annotations.

[0016] As an optional embodiment, in the second aspect of the present invention, the recognition module determines the specific manner of the real-time behavior type of the target pet object based on the trained behavior recognition neural network and the real-time sensing data, including: For each sensor data in the real-time sensor data, a prediction neural network corresponding to a data type of the sensor data is determined; the data type is temperature data, humidity data, radio frequency data, light data, image data, vibration data or sound data; the prediction neural network is trained by a training data set including a plurality of training sensor data corresponding to the data type and corresponding pet behavior annotations; The sensor data is input into the prediction neural network to obtain the output prediction behavior and the corresponding prediction probability; According to all the predicted behaviors and the predicted probabilities, the real-time behavior type of the target pet object is determined.

[0017] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the recognition module determines the real-time behavior type of the target pet object according to all the predicted behaviors and the predicted probabilities includes: For each behavior type, the weighted sum average of the predicted probabilities of all the predicted behaviors corresponding to the behavior type is calculated to obtain the behavior probability corresponding to the behavior type; the behavior type is eating behavior, resting behavior, attacking behavior, mating behavior, slow walking behavior or running behavior; wherein the weighted calculation weight corresponding to each predicted probability includes a first weight and a second weight; the first weight is proportional to the prediction accuracy of the corresponding prediction neural network in the verification phase; the second weight is proportional to the data volume of the corresponding sensor data; The behavior type with the highest behavior probability is determined as the real-time behavior type of the target pet object.

[0018] As an optional embodiment, in the second aspect of the present invention, the prediction module predicts the specific manner of the next behavior of the target pet object according to the real-time behavior type of the target pet object at multiple time points, including: Arrange the real-time behavior types of the target pet object at multiple time points from early to late according to the corresponding time points to obtain a behavior type sequence corresponding to the target pet object; Based on a preset behavior contradiction rule, the inconsistent real-time behavior types in the behavior type sequence are removed to obtain an optimized type sequence; The optimized type sequence is input into a trained DQN network model to output the next behavior of the target pet object; the DQN network model is trained by a training data set including a plurality of training behavior type sequences and corresponding next behavior annotations.

[0019] As an optional implementation, in the second aspect of the present invention, the specific manner in which the feeding module generates a feeding instruction according to the real-time sensor data includes: Inputting the real-time sensing data into a trained distance prediction neural network to obtain output distance information between the target pet object and the feeding device; According to the distance information of the target pet object at multiple time points, determining whether the target pet object is in a close state, and obtaining a determination result; When the judgment result is no, calculating a feeding time value proportional to the distance information at the most recent time point; When the judgment result is yes, the distance information of the multiple time points is input into a preset regression fitting model to obtain a predicted next distance of the target pet object, and calculate a feeding time value proportional to the predicted next distance; A feeding instruction is generated for indicating the feeding time value between the feeding time point and the current time point.

[0020] The third aspect of the present invention discloses another pet feeding control system based on gesture recognition, the system comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute part or all of the steps in the pet feeding control method based on gesture recognition disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the pet feeding control method based on gesture recognition disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention can determine the real-time behavior type of a pet object according to real-time sensor data based on a trained behavior recognition neural network, so as to predict the next behavior based on the real-time behavior type of the pet object at multiple time points, and generate a feeding instruction when the next behavior includes eating behavior to achieve accurate feeding, thereby being able to fully combine the sensor data recognition of the pet to achieve more accurate and efficient feeding control, and improve the degree of automation and intelligence of pet feeding control. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a pet feeding control method based on posture recognition disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural schematic diagram of a pet feeding control system based on gesture recognition disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural schematic diagram of another pet feeding control system based on gesture recognition disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The present invention discloses a pet feeding control method and system based on posture recognition, which can determine the real-time behavior type of a pet object based on real-time sensor data based on a trained behavior recognition neural network, predict the next behavior based on the real-time behavior type of the pet object at multiple time points, and generate a feeding instruction when the next behavior includes eating behavior to achieve accurate feeding, thereby being able to fully combine the pet's sensor data recognition to achieve more accurate and efficient feeding control, and improve the automation and intelligence of pet feeding control. The following are detailed descriptions.

[0031] Embodiment 1 See also Figure 1 , Figure 1 : is a flow chart of a pet feeding control method based on posture recognition disclosed in an embodiment of the present invention. Figure 1 The pet feeding control method based on gesture recognition described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the pet feeding control method based on gesture recognition may include the following operations: 101. Obtain real-time sensor data of a target pet object.

[0032] 102. Based on the trained behavior recognition neural network, the real-time behavior type of the target pet object is determined according to the real-time sensor data. 103. Predict the next behavior of the target pet object based on the real-time behavior types of the target pet object at multiple time points. 104. When the next behavior includes eating behavior, a feeding instruction is generated according to the real-time sensor data and sent to the feeding device for execution.

[0033] It can be seen that the above-mentioned embodiments of the invention can determine the real-time behavior type of the pet object according to the real-time sensor data based on the trained behavior recognition neural network, so as to predict the next behavior based on the real-time behavior type of the pet object at multiple time points, and generate a feeding instruction when the next behavior includes eating behavior to achieve accurate feeding, thereby being able to fully combine the pet's sensor data recognition to achieve more accurate and efficient feeding control, and improve the degree of automation and intelligence of pet feeding control.

[0034] As an optional embodiment, in the above steps, the real-time sensing data includes at least one of temperature data, humidity data, radio frequency data, light data, image data, vibration data and sound data.

[0035] It can be seen that through the above optional embodiments, the content of real-time sensor data is limited to comprehensively characterize the state characteristics of the pet object, assist in fully combining the pet's sensor data identification to achieve more accurate and efficient feeding control, and improve the degree of automation and intelligence of pet feeding control.

[0036] As an optional embodiment, in the above steps, the real-time behavior type includes at least one of eating behavior, resting behavior, attacking behavior, mating behavior, slow walking behavior and running behavior.

[0037] It can be seen that through the above optional embodiments, the content of the real-time behavior type is limited to effectively characterize the behavioral characteristics of the pet object, assist in fully combining the pet's sensor data recognition to achieve more accurate and efficient feeding control, and improve the degree of automation and intelligence of pet feeding control.

[0038] As an optional embodiment, in the above steps, the behavior recognition neural network is a RNN neural network, which is trained by a training data set including a plurality of training sensor data and corresponding pet behavior annotations.

[0039] It can be seen that through the above optional embodiments, the network details and training details of the behavior recognition neural network are limited for accurate pet behavior prediction, which assists in fully combining the pet's sensor data recognition to achieve more accurate and efficient feeding control, and improves the degree of automation and intelligence of pet feeding control.

[0040] As an optional embodiment, in the above steps, based on the trained behavior recognition neural network and according to the real-time sensor data, determining the real-time behavior type of the target pet object includes: For each sensor data in the real-time sensor data, determine a prediction neural network corresponding to the data type of the sensor data; optionally, the data type is temperature data, humidity data, radio frequency data, light data, image data, vibration data or sound data; the prediction neural network is trained by a training data set including a plurality of training sensor data corresponding to the data type and corresponding pet behavior annotations; The sensor data is input into a prediction neural network to obtain output prediction behavior and corresponding prediction probability; Based on all predicted behaviors and predicted probabilities, the real-time behavior type of the target pet object is determined.

[0041] It can be seen that through the above-mentioned optional embodiments, it is possible to perform predictive analysis of sensor data based on neural networks corresponding to different data types to accurately determine the behavior type of the pet, so as to facilitate subsequent feeding control, and assist in fully combining the pet's sensor data identification to achieve more accurate and efficient feeding control, thereby improving the degree of automation and intelligence of pet feeding control.

[0042] As an optional embodiment, in the above step, determining the real-time behavior type of the target pet object according to all predicted behaviors and predicted probabilities includes: For each behavior type, calculate the weighted sum average of the predicted probabilities of all predicted behaviors corresponding to the behavior type to obtain the behavior probability corresponding to the behavior type; optionally, the behavior type is eating behavior, resting behavior, attacking behavior, mating behavior, slow walking behavior or running behavior; wherein the weighted calculation weight corresponding to each predicted probability includes a first weight and a second weight; the first weight is proportional to the prediction accuracy of the corresponding prediction neural network in the verification phase; the second weight is proportional to the data volume of the corresponding sensor data; The behavior type with the highest behavior probability is determined as the real-time behavior type of the target pet object.

[0043] It can be seen that through the above-mentioned optional embodiments, the predicted probabilities of all outputs can be weightedly calculated based on the weight rules related to the predictive neural network and sensor data, so as to accurately determine the behavior type of the pet, so as to facilitate the subsequent feeding control, and assist in fully combining the pet's sensor data identification to achieve more accurate and efficient feeding control, thereby improving the degree of automation and intelligence of pet feeding control.

[0044] As an optional embodiment, in the above step, predicting the next behavior of the target pet object according to the real-time behavior type of the target pet object at multiple time points includes: Arrange the real-time behavior types of the target pet object at multiple time points from early to late according to the corresponding time points to obtain a behavior type sequence corresponding to the target pet object; Based on the preset behavior contradiction rules, the inconsistent real-time behavior types in the behavior type sequence are removed to obtain the optimized type sequence; The optimized type sequence is input into the trained DQN network model to output the next behavior of the target pet object; the DQN network model is trained by a training data set including multiple training behavior type sequences and corresponding next behavior annotations.

[0045] It can be seen that through the above optional embodiments, after optimizing the behavior sequence of pets arranged from morning to night according to the behavior contradiction rule, the next behavior of the pet can be predicted based on the trained DQN network to facilitate subsequent feeding control, assist in fully combining the pet's sensor data recognition to achieve more accurate and efficient feeding control, and improve the degree of automation and intelligence of pet feeding control.

[0046] As an optional embodiment, in the above steps, generating a feeding instruction according to real-time sensor data includes: Input the real-time sensor data into the trained distance prediction neural network to obtain the output distance information between the target pet object and the feeding device; According to the distance information of the target pet object at multiple time points, determine whether the target pet object is in a close state, and obtain a determination result; When the judgment result is no, a feeding time value proportional to the distance information of the most recent time point is calculated; When the judgment result is yes, the distance information of multiple time points is input into a preset regression fitting model to obtain the predicted next distance of the target pet object, and calculate the feeding time value proportional to the predicted next distance; A feeding instruction is generated for indicating a feeding time value between a feeding time point and a current time point.

[0047] It can be seen that through the above-mentioned optional embodiments, distance prediction can be performed according to real-time sensor data and more accurate feeding instructions can be generated based on distance changes, thereby fully combining the pet's sensor data recognition to achieve more precise and efficient feeding control, thereby improving the degree of automation and intelligence of pet feeding control.

[0048] Embodiment 2 See also Figure 2 , Figure 2 : is a structural diagram of a pet feeding control system based on posture recognition disclosed in an embodiment of the present invention. Figure 2 The pet feeding control system based on gesture recognition described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the pet feeding control system based on gesture recognition may include: The acquisition module 201 is used to acquire real-time sensor data of the target pet object.

[0049] The recognition module 202 is used to determine the real-time behavior type of the target pet object based on the trained behavior recognition neural network and the real-time sensor data. The prediction module 203 is used to predict the next behavior of the target pet object according to the real-time behavior types of the target pet object at multiple time points. The feeding module 204 is used to generate a feeding instruction according to the real-time sensor data when the next behavior includes eating behavior, and send it to the feeding device for execution.

[0050] It can be seen that the above-mentioned embodiments of the invention can determine the real-time behavior type of the pet object according to the real-time sensor data based on the trained behavior recognition neural network, so as to predict the next behavior based on the real-time behavior type of the pet object at multiple time points, and generate a feeding instruction when the next behavior includes eating behavior to achieve accurate feeding, thereby being able to fully combine the pet's sensor data recognition to achieve more accurate and efficient feeding control, and improve the degree of automation and intelligence of pet feeding control.

[0051] As an optional embodiment, the real-time sensing data includes at least one of temperature data, humidity data, radio frequency data, light data, image data, vibration data and sound data.

[0052] It can be seen that through the above optional embodiments, the content of real-time sensor data is limited to comprehensively characterize the state characteristics of the pet object, assist in fully combining the pet's sensor data identification to achieve more accurate and efficient feeding control, and improve the degree of automation and intelligence of pet feeding control.

[0053] As an optional embodiment, the real-time behavior type includes at least one of eating behavior, resting behavior, attacking behavior, mating behavior, slow walking behavior and running behavior.

[0054] It can be seen that through the above optional embodiments, the content of the real-time behavior type is limited to effectively characterize the behavioral characteristics of the pet object, assist in fully combining the pet's sensor data recognition to achieve more accurate and efficient feeding control, and improve the degree of automation and intelligence of pet feeding control.

[0055] As an optional embodiment, the behavior recognition neural network is a RNN neural network, which is trained by a training data set including a plurality of training sensor data and corresponding pet behavior annotations.

[0056] It can be seen that through the above optional embodiments, the network details and training details of the behavior recognition neural network are limited for accurate pet behavior prediction, which assists in fully combining the pet's sensor data recognition to achieve more accurate and efficient feeding control, and improves the degree of automation and intelligence of pet feeding control.

[0057] As an optional embodiment, the recognition module determines the specific manner of the real-time behavior type of the target pet object based on the trained behavior recognition neural network and the real-time sensing data, including: For each sensor data in the real-time sensor data, determine a prediction neural network corresponding to the data type of the sensor data; optionally, the data type is temperature data, humidity data, radio frequency data, light data, image data, vibration data or sound data; the prediction neural network is trained by a training data set including a plurality of training sensor data corresponding to the data type and corresponding pet behavior annotations; The sensor data is input into a prediction neural network to obtain output prediction behavior and corresponding prediction probability; Based on all predicted behaviors and predicted probabilities, the real-time behavior type of the target pet object is determined.

[0058] It can be seen that through the above-mentioned optional embodiments, it is possible to perform predictive analysis of sensor data based on neural networks corresponding to different data types to accurately determine the behavior type of the pet, so as to facilitate subsequent feeding control, and assist in fully combining the pet's sensor data identification to achieve more accurate and efficient feeding control, thereby improving the degree of automation and intelligence of pet feeding control.

[0059] As an optional embodiment, the specific manner in which the recognition module determines the real-time behavior type of the target pet object based on all predicted behaviors and predicted probabilities includes: For each behavior type, calculate the weighted sum average of the predicted probabilities of all predicted behaviors corresponding to the behavior type to obtain the behavior probability corresponding to the behavior type; optionally, the behavior type is eating behavior, resting behavior, attacking behavior, mating behavior, slow walking behavior or running behavior; wherein the weighted calculation weight corresponding to each predicted probability includes a first weight and a second weight; the first weight is proportional to the prediction accuracy of the corresponding prediction neural network in the verification phase; the second weight is proportional to the data volume of the corresponding sensor data; The behavior type with the highest behavior probability is determined as the real-time behavior type of the target pet object.

[0060] It can be seen that through the above-mentioned optional embodiments, the predicted probabilities of all outputs can be weightedly calculated based on the weight rules related to the predictive neural network and sensor data, so as to accurately determine the behavior type of the pet, so as to facilitate the subsequent feeding control, and assist in fully combining the pet's sensor data identification to achieve more accurate and efficient feeding control, thereby improving the degree of automation and intelligence of pet feeding control.

[0061] As an optional embodiment, the prediction module predicts the specific manner of the next behavior of the target pet object according to the real-time behavior type of the target pet object at multiple time points, including: Arrange the real-time behavior types of the target pet object at multiple time points from early to late according to the corresponding time points to obtain a behavior type sequence corresponding to the target pet object; Based on the preset behavior contradiction rules, the inconsistent real-time behavior types in the behavior type sequence are removed to obtain the optimized type sequence; The optimized type sequence is input into the trained DQN network model to output the next behavior of the target pet object; the DQN network model is trained by a training data set including multiple training behavior type sequences and corresponding next behavior annotations.

[0062] It can be seen that through the above optional embodiments, after optimizing the behavior sequence of pets arranged from morning to night according to the behavior contradiction rule, the next behavior of the pet can be predicted based on the trained DQN network to facilitate subsequent feeding control, assist in fully combining the pet's sensor data recognition to achieve more accurate and efficient feeding control, and improve the degree of automation and intelligence of pet feeding control.

[0063] As an optional embodiment, the specific manner in which the feeding module generates a feeding instruction according to the real-time sensor data includes: Input the real-time sensor data into the trained distance prediction neural network to obtain the output distance information between the target pet object and the feeding device; According to the distance information of the target pet object at multiple time points, determine whether the target pet object is in a close state, and obtain a determination result; When the judgment result is no, a feeding time value proportional to the distance information of the most recent time point is calculated; When the judgment result is yes, the distance information of multiple time points is input into a preset regression fitting model to obtain the predicted next distance of the target pet object, and calculate the feeding time value proportional to the predicted next distance; A feeding instruction is generated for indicating a feeding time value between a feeding time point and a current time point.

[0064] It can be seen that through the above-mentioned optional embodiments, distance prediction can be performed according to real-time sensor data and more accurate feeding instructions can be generated based on distance changes, thereby fully combining the pet's sensor data recognition to achieve more precise and efficient feeding control, thereby improving the degree of automation and intelligence of pet feeding control.

[0065] Embodiment 3 See also Figure 3 , Figure 3 This is another pet feeding control system based on gesture recognition disclosed in an embodiment of the present invention. Figure 3The described pet feeding control system based on gesture recognition is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the pet feeding control system based on gesture recognition may include: A memory 301 storing executable program codes; a processor 302 coupled to the memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the pet feeding control method based on gesture recognition described in the first embodiment.

[0066] Embodiment 4 An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the pet feeding control method based on gesture recognition described in the first embodiment.

[0067] Embodiment 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the pet feeding control method based on gesture recognition described in the first embodiment.

[0068] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0070] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0071] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0072] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0075] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0076] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0077] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0078] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0079] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0080] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0081] Finally, it should be noted that the pet feeding control method and system based on posture recognition disclosed in the embodiment of the present invention discloses only the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A pet feeding control method based on posture recognition, characterized in that: The method comprises: Acquire real-time sensor data of target pet objects; Based on the trained behavior recognition neural network, determining the real-time behavior type of the target pet object according to the real-time sensing data; Predicting the next behavior of the target pet object according to the real-time behavior type of the target pet object at multiple time points; When the next behavior includes eating behavior, a feeding instruction is generated according to the real-time sensor data and sent to the feeding device for execution.

2. The pet feeding control method based on gesture recognition according to claim 1, characterized in that: The real-time sensing data includes at least one of temperature data, humidity data, radio frequency data, light data, image data, vibration data and sound data.

3. The pet feeding control method based on gesture recognition according to claim 1, characterized in that: The real-time behavior type includes at least one of eating behavior, resting behavior, attacking behavior, mating behavior, slow walking behavior and running behavior.

4. The pet feeding control method based on gesture recognition according to claim 1, characterized in that: The behavior recognition neural network is a RNN neural network, which is trained by a training data set including a plurality of training sensor data and corresponding pet behavior annotations.

5. The pet feeding control method based on gesture recognition according to claim 1, characterized in that: The method of determining the real-time behavior type of the target pet object based on the trained behavior recognition neural network and the real-time sensing data includes: For each sensor data in the real-time sensor data, a prediction neural network corresponding to a data type of the sensor data is determined; the data type is temperature data, humidity data, radio frequency data, light data, image data, vibration data or sound data; the prediction neural network is trained by a training data set including a plurality of training sensor data corresponding to the data type and corresponding pet behavior annotations; The sensor data is input into the prediction neural network to obtain the output prediction behavior and the corresponding prediction probability; According to all the predicted behaviors and the predicted probabilities, the real-time behavior type of the target pet object is determined.

6. The pet feeding control method based on gesture recognition according to claim 5, characterized in that: Determining the real-time behavior type of the target pet object according to all the predicted behaviors and the predicted probabilities includes: For each behavior type, the weighted sum average of the predicted probabilities of all the predicted behaviors corresponding to the behavior type is calculated to obtain the behavior probability corresponding to the behavior type; the behavior type is eating behavior, resting behavior, attacking behavior, mating behavior, slow walking behavior or running behavior; wherein the weighted calculation weight corresponding to each predicted probability includes a first weight and a second weight; the first weight is proportional to the prediction accuracy of the corresponding prediction neural network in the verification phase; the second weight is proportional to the data volume of the corresponding sensor data; The behavior type with the highest behavior probability is determined as the real-time behavior type of the target pet object.

7. The pet feeding control method based on gesture recognition according to claim 1, characterized in that: The predicting the next behavior of the target pet object according to the real-time behavior type of the target pet object at multiple time points includes: Arrange the real-time behavior types of the target pet object at multiple time points from early to late according to the corresponding time points to obtain a behavior type sequence corresponding to the target pet object; Based on a preset behavior contradiction rule, the inconsistent real-time behavior types in the behavior type sequence are removed to obtain an optimized type sequence; The optimized type sequence is input into a trained DQN network model to output the next behavior of the target pet object; the DQN network model is trained by a training data set including a plurality of training behavior type sequences and corresponding next behavior annotations.

8. The pet feeding control method based on gesture recognition according to claim 1, characterized in that: The step of generating a feeding instruction according to the real-time sensor data comprises: Inputting the real-time sensing data into a trained distance prediction neural network to obtain output distance information between the target pet object and the feeding device; According to the distance information of the target pet object at multiple time points, determining whether the target pet object is in a close state, and obtaining a determination result; When the judgment result is no, calculating a feeding time value proportional to the distance information at the most recent time point; When the judgment result is yes, the distance information of the multiple time points is input into a preset regression fitting model to obtain a predicted next distance of the target pet object, and calculate a feeding time value proportional to the predicted next distance; A feeding instruction is generated for indicating the feeding time value between the feeding time point and the current time point.

9. A pet feeding control system based on gesture recognition, characterized in that: The system comprises: An acquisition module, used for acquiring real-time sensor data of a target pet object; A recognition module, for determining the real-time behavior type of the target pet object based on the trained behavior recognition neural network and the real-time sensing data; A prediction module, used to predict the next behavior of the target pet object according to the real-time behavior type of the target pet object at multiple time points; The feeding module is used to generate a feeding instruction according to the real-time sensor data when the next behavior includes eating behavior, and send it to the feeding device for execution.

10. A pet feeding control system based on gesture recognition, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the pet feeding control method based on gesture recognition as described in any one of claims 1-8.

Images