Neural network health condition analysis method and system based on pet food intake monitoring

Abstract

The invention provides a neural network health condition analysis method based on monitoring of pet food intake, and the method comprises the steps: obtaining first food intake data in a first preset time period, judging whether the pet food intake in the first preset time period meets a threshold value of the first food intake, and when the pet food intake meets the threshold value of the first food intake, determining that the pet food intake meets the threshold value of the first food intake. On the basis of a second preset time period, the change rate of the food intake amount of the pet is obtained, and when the change rate of the food intake amount of the pet meets a preset threshold value, total information of the food intake amount of the pet in a third preset time period is obtained on the basis of the third preset time period and serves as third food intake data; the first feeding data, the second feeding data and the third feeding data serve as input of the neural network model, and the health state of the pet is obtained. According to the method, the health state of the pet is analyzed through the neural network model, body health changes of the pet are concerned in time, the pet is helped to grow healthily, and high-quality accompanying is provided for the pet.

Description

Technical Field

[0001] The present application relates to the technical field of health monitoring for dogs, cats and similar pets, and specifically to a neural network health status analysis method and system based on monitoring the food intake of pets. Background Art

[0002] Palatability is one of the basic criteria for measuring the success of pet food selection. The special habits of pets will also affect their palatability choices in eating. The palatability evaluation methods generally use the conditioned reflex method, the single bowl method and the double bowl method. In fact, in addition to palatability, the palatability of food to pets is also an essential indicator of the success of pet food. In previous pet research, there are not many studies on palatability. In order to more accurately test the palatability and palatability of pet food, based on the habits and characteristics of pets' irregular eating throughout the day, we can infer the eating and living habits of pets at different times of the day, so as to better understand and care for the pets we raise.

[0003] With the existing technical solutions, it is not easy to monitor and understand the eating habits of pets 24 hours a day, and simply monitoring and analyzing the eating habits of pets 24 hours a day is particularly wasteful of manpower and material resources. At present, companion pets are an important part of people's lives. In-depth understanding of them can help owners pay attention to their pets' food preferences and information on their pets' physical health changes, help their pets grow healthily in a timely manner, and provide them with high-quality companionship. Summary of the invention

[0004] In order to overcome the above problems existing in the prior art, the present application provides a neural network health status analysis method and system based on monitoring the pet's food intake, which adopts the following technical solutions:

[0005] In a first aspect, the present application provides a neural network health status analysis method based on monitoring pet food intake, comprising:

[0006] Step S1, obtaining pet food information, obtaining pet food intake data based on a weighing sensor in a pet feeder, and collecting the pet's intake data and storing it in a database;

[0007] Step S2, the control center reads the first eating data in the database, determines whether the pet's intake in the first preset time period meets the threshold of the first intake, and executes step S3 when the pet's intake meets the threshold of the first intake;

[0008] Step S3, the control center reads the second eating data from the database, obtains the change rate of the pet's food intake based on the second preset time period, and judges the change rate of the pet's food intake. When the change rate of the pet's food intake meets the preset threshold, step S4 is executed;

[0009] Step S4, the control center reads the third eating data in the database, and based on the third preset time period, when the change rate of the amount of food ingested by the pet meets the preset threshold, obtains the total amount of food ingested by the pet in the third preset time period;

[0010] Step S5, using the first eating data, the second eating data and the third eating data as inputs of a neural network model to obtain the health status of the pet;

[0011] Step S6, the control center monitors the first eating data, the second eating data, the third eating data and the health status of the pet in real time, and transmits the monitoring results to the user terminal in real time. When the monitoring result data is abnormal, the control center promptly sends an alarm message to the user terminal to notify the user.

[0012] Furthermore, the first preset time period in step S2 is a time period when the pet eats pet food for the first time.

[0013] Furthermore, the weighing sensor in step S1 is arranged on the magnetic base in the pet feeder, and weighing sensors are arranged on four sides of the magnetic base, and the weighing sensors are half-bridge type weighing sensors.

[0014] Furthermore, the control center in step S2 reads the first eating data in the database to determine whether the pet's intake in the first preset time period meets the threshold of the first intake, which is specifically manifested as follows:

[0015] Assume that the value of the pet cat's food intake over time is x(t), 0≤t≤24h, and the sampling interval is t s = 1s, set the initial weight x(0) = x 0 , set X F =0.5g;

[0016] Select 0≤t≤60s, calculate Δx=x(60s)-x(0), if Δx≤X F , then the output Flg1=1, if Δx≤X is not satisfied F Then the output Flg1=0;

[0017] Where X F It indicates the threshold of the first intake of a pet. When the threshold of the first intake reaches 0.5g or above, Flg1=0. If the threshold of the first intake does not reach 0.5g, Flg1=1.

[0018] Furthermore, the step S3 of obtaining the change rate of the amount of food consumed by the pet based on the second preset time period and judging the change rate of the amount of food consumed by the pet is specifically performed as follows:

[0019] Based on the data within any Δt=60s in the second preset time period, If the preset threshold is met, the output is Flg2 = 1, and the If the preset threshold is not met, the output is Flg2=0;

[0020] in It indicates the rate of change of the amount of food a pet consumes within any 60 seconds, that is, the speed of eating. When Flg2=1, if the change rate of the pet's food intake does not reach , that is, Flg2=0, where dxMax represents the maximum threshold of the pet's eating speed.

[0021] Furthermore, in step S4, the first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period are used as inputs of the neural network model to obtain the health status of the pet, which is specifically manifested as follows:

[0022] Based on the pet's initial food intake x 0 , obtain the total food intake change of the pet within 24 hours, that is, dxend=x(24h)-x(0), and use the total food intake change of the pet within 24 hours as the third food intake data.

[0023] Furthermore, the first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period are used as inputs of the neural network model to obtain the health status of the pet, which is specifically manifested as follows:

[0024] x(t), Flg1, Flg2, dx end =x(24h)-x 0 As X 1 ~X 5 Input into the neural network model, M 1 , N 1 , J 1 As output;

[0025] Expert training of the neural network model, input 100 sets of X 1 ~X 5 Data, give expert judgment for each set of input data; M 1 , N 1, J 1 Divided into four levels, M 1 and N 1 The four levels are excellent, medium, poor, J 1 The four levels are healthy, good, fair, and poor;

[0026] After completing the training of the neural network, the neural network health status analysis algorithm Q = G (x (t)) is obtained; G represents the neural network analysis algorithm, Q represents the output health status, including M 1 , N 1 , J 1 , where M 1 N is the digestion and absorption capacity, 1 For emotional stability, J 1 For physical health status.

[0027] In a second aspect, the present application also provides a neural network health status analysis system based on monitoring the pet's food intake, comprising:

[0028] A first eating data collection module is used to obtain pet food information, obtain pet food eating data based on a weighing sensor in a pet feeder, and collect the eating data of the pet and store it in a database; wherein the eating data includes first eating data, second eating data and third eating data;

[0029] The first intake judgment module is used for the control center to read the first eating data in the database, judge whether the pet's intake in the first preset time period meets the threshold of the first intake, and execute step S3 when the pet's intake meets the threshold of the first intake;

[0030] The food intake change rate judgment module is used for the control center to read the second eating data in the database, obtain the change rate of the pet's food intake based on the second preset time period, and judge the change rate of the pet's food intake. When the change rate of the pet's food intake meets the preset threshold, step S4 is executed;

[0031] A third eating data acquisition module, used to use the first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period as inputs of a neural network model to acquire the health status of the pet;

[0032] The pet health status acquisition module is used to use the first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period as inputs of the neural network model to acquire the health status of the pet.

[0033] The real-time monitoring module is used for the control center to monitor the first eating data, the second eating data, the total amount of food intake of the pet in the third preset time period and the health status of the pet in real time, and transmit the monitoring results to the user terminal in real time. When the monitoring result data is abnormal, the control center promptly sends an alarm message to the user terminal to notify the user.

[0034] In a third aspect, the present application provides an electronic device, including:

[0035] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, cause the device to perform the method as described in the first aspect.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the method described in the first aspect.

[0037] In a fifth aspect, the present application provides a computer program, which, when executed by a computer, is used to execute the method described in the first aspect.

[0038] In one possible design, the program in the fifth aspect may be stored in whole or in part on a storage medium packaged together with the processor, or may be stored in whole or in part on a memory not packaged together with the processor.

[0039] This application has the following beneficial effects:

[0040] 1. This application uses the weighing sensor in the pet feeder to obtain eating information within a first preset time period, and can provide the owner with data on pet diet management and health monitoring, helping the owner to better pay attention to and care for the healthy growth of the pet.

[0041] 2. The present application can help the owner to timely understand the palatability of the pet to the pet food by evaluating the palatability of the pet when the pet first contacts the pet food and judging whether the pet's intake within the first preset time period meets the threshold of the first intake. When the selected pet food has poor palatability, the owner can replace the pet food for the pet in time.

[0042] 3. This application determines the rate of change of the pet's food intake when the pet's intake meets the threshold of the initial intake, which can help the owner evaluate the palatability of the pet's food. If the pet has a poor palatability for the current food, the owner can consider changing the pet's food.

[0043] 4. Based on the pet's food having good palatability and tolerance, this application analyzes the pet's health through a neural network model, which can provide an in-depth understanding of the pet's health, help the owner pay attention to changes in the pet's physical health, help the pet grow healthily in a timely manner, and provide the pet with high-quality companionship.

[0044] 5. In this application, when the monitoring result data is abnormal, the control center promptly sends an alarm message to the user terminal to notify the user, so that the pet owner can pay attention to the pet's physical health changes when the pet is not with the pet, discover the pet's abnormal condition in time, and take timely measures for the pet's abnormal condition to ensure the health and safety of the pet. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0046] Figure 2 A flow chart of a method according to an embodiment of the present application;

[0047] Figure 3 A schematic diagram of a neural network model according to an embodiment of the present application;

[0048] Figure 4 This is a system flow chart of an embodiment of the present application;

[0049] Figure 5 It is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0051] 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 application. The appearance of the phrase in various locations 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.

[0052] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0053] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0054] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0055] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers and desktop computers, etc.

[0056] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0057] It should be noted that the neural network health status analysis method based on monitoring the pet's food intake provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the neural network health status analysis system based on monitoring the pet's food intake is generally set in the server / terminal device.

[0058] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0059] Continue to refer Figure 2 , the figure shows a flow chart of a neural network health status analysis method based on monitoring pet food intake in the present application, the method comprising the following steps:

[0060] Step S1, obtaining pet food information, obtaining pet food eating data based on a weighing sensor in a pet feeder, collecting the eating data of the pet and storing it in a database; wherein the eating data includes first eating data, second eating data and third eating data;

[0061] Obtaining pet food information includes obtaining the name information of the pet food. When the database records the pet food for the first time, a unique identifier is generated for the pet food. This application ensures that the recorded pet food has not changed by collecting the name information of the pet food. When the pet food changes, the name information of the pet food needs to be updated, and a unique identifier is generated for the new pet food to distinguish it from other recorded information of pet food and avoid inaccurate collected data.

[0062] The present application obtains pet food information, obtains photo information of the pet food based on a camera provided in a pet feeder, and obtains name information of the pet food by performing feature extraction on the photo information of the pet food.

[0063] The photo information of the pet food is the photo information of the outer packaging of the pet food or the photo information marked on the box containing the pet food. Some pet owners are accustomed to storing the pet food in the packaging bag after purchasing the pet food; while some owners will repack the pet food into the box for storage after purchasing the pet food; if the camera cannot obtain the valid information of the pet food, the control center sends a prompt message to the owner's user terminal to confirm the pet food information, and the pet owner confirms the pet food information. After the control center receives the pet information confirmation message from the pet owner, if the pet food has not changed, the pet eating information is recorded in the pet food information.

[0064] In a possible implementation, the first preset time period in step S2 is a time period when the pet eats pet food for the first time.

[0065] In a possible implementation, the weighing sensor in step S1 is disposed on a magnetic base in the pet feeder, and weighing sensors are disposed on four sides of the magnetic base, and the weighing sensors are half-bridge weighing sensors.

[0066] Step S2, the control center reads the first eating data in the database, determines whether the pet's intake in the first preset time period meets the threshold of the first intake, and executes step S3 when the pet's intake meets the threshold of the first intake;

[0067] The first eating data includes the weight information of the pet food collected regularly based on a preset time interval. The collecting unit collects the time point of the recording moment and the weight information of the pet food in the weighing sensor, and transmits it to the database for recording.

[0068] In a possible implementation, the control center in step S2 reads the first eating data in the database to determine whether the pet's intake in the first preset time period meets the threshold of the first intake, which is specifically performed as follows:

[0069] Assume that the value of the pet cat's food intake over time is x(t), 0≤t≤24h, and the sampling interval is t s = 1s, set the initial weight x(0) = x 0 , set X F =0.5g;

[0070] Select 0≤t≤60s, calculate Δx=x(60s)-x(0), if Δx≤X F , then the output Flg1=1, if Δx≤X is not satisfied F Then the output Flg1=0;

[0071] Where X F It indicates the threshold of the first intake of a pet. When the threshold of the first intake reaches 0.5g or above, Flg1=0. If the threshold of the first intake does not reach 0.5g, Flg1=1.

[0072] In a possible implementation, the palatability of the pet is determined by determining whether the pet's intake within the first preset time period meets a threshold for the first intake. If the threshold for the first intake is met, it indicates that the pet has good palatability for the current food. If the threshold for the first intake is not met, it indicates that the pet has poor palatability for the current food. If the pet has poor palatability, then changing the food for the pet may be considered.

[0073] Step S3, the control center reads the second eating data from the database, obtains the change rate of the pet's food intake based on the second preset time period, and judges the change rate of the pet's food intake. When the change rate of the pet's food intake meets the preset threshold, step S4 is executed;

[0074] In a possible implementation manner, the step S3 of obtaining the change rate of the amount of food ingested by the pet based on the second preset time period and judging the change rate of the amount of food ingested by the pet is specifically performed as follows:

[0075] Based on the data within any Δt=60s in the second preset time period, If the preset threshold is met, the output is Flg2 = 1, and the If the preset threshold is not met, the output is Flg2=0;

[0076] in It indicates the rate of change of the amount of food a pet consumes within any 60 seconds, that is, the speed of eating. When Flg2=1, if the change rate of the pet's food intake does not reach , that is, Flg2=0, where dxMax represents the maximum threshold of the pet's eating speed.

[0077] In one possible implementation, when the pet has good palatability for the current food, the pet's tolerance to the current food can be obtained by judging the rate of change of the pet's food intake. When the rate of change of the pet's food intake is greater than or equal to a preset threshold, it indicates that the pet has good tolerance for the current food. When the rate of change of the pet's food intake is less than the preset threshold, it indicates that the pet has poor tolerance for the current food. If the pet has poor tolerance to the current food, it may be considered to change the pet's food.

[0078] Step S4, using the first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period as inputs of a neural network model to obtain the health status of the pet;

[0079] In a possible implementation, the step S4 uses the first eating data, the second eating data, and the total amount of food intake of the pet in the third preset time period as inputs to the neural network model to obtain the health status of the pet, which is specifically manifested as follows:

[0080] Based on the pet's initial food intake x 0 , obtain the total food intake change of the pet within 24 hours, that is, dxend=x(24h)-x(0), and use the total food intake change of the pet within 24 hours as the third food intake data.

[0081] Step S5, using the first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period as input to a neural network model to obtain the health status of the pet.

[0082] In a possible implementation, the first eating data, the second eating data, and the total amount of food intake of the pet in the third preset time period are used as inputs of a neural network model to obtain the health status of the pet, which is specifically manifested as follows:

[0083] x(t), Flg1, Flg2, dx end =x(24h)-x 0 As X 1 ~X 5 Input into the neural network model, M 1 , N 1 , J 1 As output;

[0084] Expert training of the neural network model, input 100 sets of X 1 ~X 5 Data, give expert judgment for each set of input data; M 1 , N 1 , J 1 Divided into four levels, M 1 and N 1 The four levels are excellent, medium, poor, J 1 The four levels are healthy, good, fair, and poor;

[0085] After completing the training of the neural network, the neural network health status analysis algorithm Q = G (x (t)) is obtained; G represents the neural network analysis algorithm, Q represents the output health status, including M 1 , N 1 , J 1 , where M 1 N is the digestion and absorption capacity, 1 For emotional stability, J 1 For physical health status.

[0086] Step S6, the control center monitors the first eating data, the second eating data, the total amount of food intake of the pet in the third preset time period and the health status of the pet in real time, and transmits the monitoring results to the user terminal in real time. When the monitoring result data is abnormal, the control center promptly sends an alarm message to the user terminal to notify the user.

[0087] In a possible implementation manner, the user terminal includes a mobile phone, a PC, a PAD, etc.

[0088] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0089] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0090] Continue to refer Figure 4 The neural network health status analysis system based on monitoring pet food intake described in this embodiment includes:

[0091] The first eating data collection module 401 is used to obtain pet food information, obtain pet food eating data based on the weighing sensor in the pet feeder, and collect the eating data of the pet and store it in the database; wherein the eating data includes first eating data, second eating data and third eating data;

[0092] The first intake determination module 402 is used for the control center to read the first eating data in the database, determine whether the pet's intake in the first preset time period meets the threshold of the first intake, and execute step S3 when the pet's intake meets the threshold of the first intake;

[0093] The food intake change rate judgment module 403 is used for the control center to read the second eating data in the database, obtain the change rate of the pet's food intake based on the second preset time period, and judge the change rate of the pet's food intake. When the change rate of the pet's food intake meets the preset threshold, step S4 is executed;

[0094] A third eating data acquisition module 404 is used to use the first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period as inputs of a neural network model to acquire the health status of the pet;

[0095] The pet health status acquisition module 405 is used to use the first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period as inputs of the neural network model to acquire the health status of the pet.

[0096] The real-time monitoring module 406 is used for the control center to monitor the first eating data, the second eating data, the total amount of food intake of the pet in the third preset time period and the health status of the pet in real time, and transmit the monitoring results to the user terminal in real time. When the monitoring result data is abnormal, the control center promptly sends an alarm message to the user terminal to notify the user.

[0097] To solve the above technical problems, the present application also provides a computer device. Figure 5 , Figure 5 This is a basic structural block diagram of the computer device in this embodiment.

[0098] The computer device 5 includes a memory 5a, a processor 5b, and a network interface 5c that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 5 with components 5a-5c, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0099] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0100] The memory 5a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 5a can be an internal storage unit of the computer device 5, such as a hard disk or memory of the computer device 5. In other embodiments, the memory 5a can also be an external storage device of the computer device 5, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 5. Of course, the memory 5a can also include both the internal storage unit of the computer device 5 and its external storage device. In this embodiment, the memory 5a is generally used to store the operating system and various application software installed on the computer device 5, such as the program code of the neural network health status analysis method based on monitoring the food intake of pets. In addition, the memory 5a can also be used to temporarily store various types of data that have been output or are to be output.

[0101] The processor 5b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 5b is generally used to control the overall operation of the computer device 5. In this embodiment, the processor 5b is used to run the program code stored in the memory 5a or process data, such as running the program code of the neural network health status analysis method based on monitoring the food intake of the pet.

[0102] The network interface 5c may include a wireless network interface or a wired network interface. The network interface 5c is generally used to establish a communication connection between the computer device 5 and other electronic devices.

[0103] The present application also provides another embodiment, namely, providing a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a program of a neural network health status analysis method based on monitoring a pet's food intake, and the neural network health status analysis based on monitoring a pet's food intake can be executed by at least one processor, so that the at least one processor executes the steps of the neural network health status analysis method based on monitoring a pet's food intake as described above.

[0104] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0105] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A neural network health status analysis method based on monitoring pet food intake, characterized in that: include: Step S1, obtaining pet food information, obtaining pet food eating data based on a weighing sensor in a pet feeder, collecting the eating data of the pet and storing it in a database; wherein the eating data includes first eating data, second eating data and third eating data; Step S2, the control center reads the first eating data in the database, determines whether the pet's intake in the first preset time period meets the threshold of the first intake, and executes step S3 when the pet's intake meets the threshold of the first intake; Step S3, the control center reads the second eating data from the database, obtains the change rate of the pet's food intake based on the second preset time period, and judges the change rate of the pet's food intake. When the change rate of the pet's food intake meets the preset threshold, step S4 is executed; Step S4, the control center reads the third eating data in the database, and based on the third preset time period, when the change rate of the amount of food ingested by the pet meets the preset threshold, obtains the total amount of food ingested by the pet in the third preset time period; Step S5, using the first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period as inputs of a neural network model to obtain the health status of the pet; Step S6, the control center monitors the first eating data, the second eating data, the total amount of food intake of the pet in the third preset time period and the health status of the pet in real time, and transmits the monitoring results to the user terminal in real time. When the monitoring result data is abnormal, the control center promptly sends an alarm message to the user terminal to notify the user.

2. The neural network health status analysis method based on monitoring pet food intake according to claim 1, characterized in that: The weighing sensor in step S1 is arranged on the magnetic base in the pet feeder, and weighing sensors are arranged on four sides of the magnetic base, and the weighing sensors are half-bridge type weighing sensors.

3. The neural network health status analysis method based on monitoring pet food intake according to claim 1, characterized in that: The first preset time period in step S2 is the time period when the pet eats pet food for the first time.

4. The neural network health status analysis method based on monitoring pet food intake according to claim 1, characterized in that: The control center in step S2 reads the first eating data in the database to determine whether the pet's intake in the first preset time period meets the threshold of the first intake, which is specifically manifested as follows: Assume that the value of the pet cat's food intake over time is x(t), 0≤t≤24h, and the sampling interval is t s = 1s, set the initial weight x(0) = x0, set X F =0.5g; Select 0≤t≤60s, calculate Δx=x(60s)-x(0), if Δx≤X F , then the output Flg1=1, if Δx≤X is not satisfied F Then the output Flg1=0; Where X F It indicates the threshold of the first intake of a pet. When the threshold of the first intake reaches 0.5g or above, Flg1=0. If the threshold of the first intake does not reach 0.5g, Flg1=1.

5. The neural network health status analysis method based on monitoring pet food intake according to claim 4 is characterized in that: The control center in step S3 reads the second eating data in the database, obtains the change rate of the pet's food intake based on the second preset time period, and judges the change rate of the pet's food intake, which is specifically manifested as: Based on the data within any Δt=60s in the second preset time period, If the preset threshold is met, the output is Flg2 = 1, and the If the preset threshold is not met, the output is Flg2=0; in It indicates the rate of change of the amount of food a pet consumes within any 60 seconds, that is, the speed of eating. When Flg2=1, if the change rate of the pet's food intake does not reach , that is, Flg2=0, where dxMax represents the maximum threshold of the pet's eating speed.

6. The neural network health status analysis method based on monitoring pet food intake according to claim 5, characterized in that: The control center in step S4 reads the third eating data in the database, and based on the third preset time period, when the change rate of the amount of food ingested by the pet meets the preset threshold, obtains the total amount of food ingested by the pet in the third preset time period, which is specifically manifested as: Based on the initial food intake x0 of the pet, the total food intake change of the pet within 24 hours is obtained, that is, dxend=x(24h)-x(0), and the total food intake change of the pet within 24 hours is used as the third food intake data.

7. The neural network health status analysis method based on monitoring pet food intake according to claim 6, characterized in that: The first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period are used as inputs of the neural network model to obtain the health status of the pet, which is specifically manifested as follows: x(t), Flg1, Flg2, dx end =x(24h)-x0 are respectively input into the neural network model as X1~X5, and M1, N1, J1 are output; The neural network model is trained by experts, 100 groups of X1-X5 data are input, and expert judgment is given for each group of input data; after the neural network training is completed, a neural network health status analysis algorithm Q=G(x(t)) is obtained; G represents the neural network analysis algorithm, and Q represents the output health status, including M1, N1, and J1, where M1 represents digestion and absorption capacity, N1 represents emotional stability, and J1 represents physical health status.

8. A neural network health status analysis system based on monitoring pet food intake, used to implement the neural network health status analysis method based on monitoring pet food intake of claims 1-7, characterized in that: include: A first eating data collection module is used to obtain pet food information, obtain pet food eating data based on a weighing sensor in a pet feeder, and collect the eating data of the pet and store it in a database; wherein the eating data includes first eating data, second eating data and third eating data; The first intake judgment module is used for the control center to read the first eating data in the database, judge whether the pet's intake in the first preset time period meets the threshold of the first intake, and execute step S3 when the pet's intake meets the threshold of the first intake; The food intake change rate judgment module is used for the control center to read the second eating data in the database, obtain the change rate of the pet's food intake based on the second preset time period, and judge the change rate of the pet's food intake. When the change rate of the pet's food intake meets the preset threshold, step S4 is executed; A third eating data acquisition module, used to use the first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period as inputs of a neural network model to acquire the health status of the pet; A pet health status acquisition module, used to use the first eating data, the second eating data and the total amount of food intake of the pet in the third preset time period as inputs of a neural network model to acquire the health status of the pet; The real-time monitoring module is used for the control center to monitor the first eating data, the second eating data, the total amount of food intake of the pet in the third preset time period and the health status of the pet in real time, and transmit the monitoring results to the user terminal in real time. When the monitoring result data is abnormal, the control center promptly sends an alarm message to the user terminal to notify the user.

9. An electronic device, characterized in that: include: one or more processors; Memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, enable the device to perform the steps of the neural network health status analysis method based on monitoring the pet's food intake as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the steps of the neural network health status analysis method based on monitoring the food intake of a pet as described in any one of claims 1 to 7.

Images