Device for monitoring diseases of swinery and computer readable storage medium

Abstract

The invention discloses a device for disease monitoring of swinery and a computer readable storage medium. The apparatus comprises: a processor; the memory is used for storing a program instruction for performing disease monitoring on the swinery, and when the program instruction is executed by the processor, the device realizes the following operations: acquiring basic information of a target swinery and a target image containing the target swinery; inputting the target image into a preset model for attitude detection operation, so as to output the attitude of each pig as an attitude detection result of the target pig herd; based on the posture detection result, determining a first proportion of the pigs whose postures are the target abnormal postures in the target swinery, and based on the first proportion, determining a disease state of the target swinery; and determining a treatment scheme of the target swinery based on the day age, the weight and the illness state. By means of the scheme, the diseases causing the abnormal postures of the swinery can be recognized in time, a reasonable treatment scheme is given, and therefore the health risk of the swinery is reduced.

Description

Technical Field

[0001] The present application generally relates to the field of computer vision technology. More specifically, the present application relates to a device and a computer-readable storage medium for disease monitoring of a pig herd. Background Art

[0002] During the breeding process, changes in the posture of pigs may be early signs of certain diseases. Timely identification of these early signs can help with early diagnosis and treatment, thereby reducing the impact of the disease on the pigs. However, under the traditional breeding model, the same pig problem may lead to different consequences due to the different experience levels of different breeders, and the health of the pigs will also vary significantly. This phenomenon is not conducive to improving production efficiency and expanding production scale.

[0003] Specifically, experienced breeders can keenly detect problems in the early stages of abnormal posture of pigs, and then determine the disease causing the abnormal posture and treat the disease in time. However, inexperienced breeders are very likely to ignore the problem of abnormal posture of pigs, so that they cannot take effective measures to curb the development of the disease in the early stages of the disease, causing the disease to worsen and even eventually lead to the death of the pigs, causing considerable economic losses to the company.

[0004] In view of this, there is an urgent need to provide a solution for disease monitoring of pig herds, so as to timely identify diseases that cause abnormal posture of pig herds and provide reasonable treatment plans, thereby reducing the health risks of pig herds, improving the survival rate of pig herds, and reducing the economic losses of enterprises. Summary of the invention

[0005] In order to at least solve one or more of the technical problems mentioned above, the present application proposes a solution for disease monitoring in a pig herd in multiple aspects.

[0006] In a first aspect, the present application provides a device for disease monitoring of a pig herd, comprising: a processor; a memory, in which program instructions for disease monitoring of a pig herd are stored, and when the program instructions are executed by the processor, the device implements the following operations: obtaining basic information of a target pig herd and a target image containing the pig herd, wherein the basic information includes at least age and weight; inputting the target image into a preset model for posture detection operation to output the posture of each pig as a posture detection result of the target pig herd; determining a first proportion of pigs with a target abnormal posture in the target pig herd based on the posture detection result, and determining the disease state of the target pig herd based on the first proportion; and determining a treatment plan for the target pig herd based on the age, weight and disease state to achieve disease monitoring of the target pig herd.

[0007] In some embodiments, when the program instructions are executed by the processor, the device further performs the following operations to determine the disease status of the target pig group: obtaining the hair condition and spinal condition of the target pig group; and determining the disease status of the target pig group based on the posture detection results, the hair condition and / or the spinal condition.

[0008] In other embodiments, when the program instructions are executed by the processor, the device further performs the following operations to determine the disease state of the target pig group based on the posture detection results, the hair condition and / or the back condition: based on the posture detection results, the hair condition and / or the back condition, determine the second proportion of pigs in the target pig group whose posture is a target abnormal posture, whose hair condition is a target abnormal hair condition and / or whose back condition is an abnormal back condition; and determine the disease state of the target pig group based on the second proportion.

[0009] In some further embodiments, the basic information also includes environmental sampling detection information, and when the program instructions are executed by the processor, the device further performs the following operations to determine the treatment plan for the target pig group: determining the bacterial species type corresponding to the disease state based on the environmental sampling detection information; and determining the treatment plan for the target pig group based on the age, weight, the disease state and the bacterial species type.

[0010] In some further embodiments, the basic information also includes historical medication information, and when the program instructions are executed by the processor, the device further performs the following operations to determine the treatment plan for the target pig group: determine the treatment plan for the target pig group based on the age, weight, the disease state, the bacterial strain type and the historical medication information.

[0011] In some other embodiments, when the program instructions are executed by the processor, the device further performs the following operations to determine the treatment plan for the target pig group: obtain the feeding information of the target pig group and the temperature and humidity information of the pen where the target pig group is located; determine the name and dosage of the medication for the target pig group based on the age, weight, disease status, bacterial strain type and historical medication information; determine the feeding adjustment plan for the target pig group based on the feeding information; and determine the temperature adjustment amount and humidity adjustment amount of the target pig group based on the temperature and humidity information.

[0012] In some other embodiments, when the program instructions are executed by the processor, the device further performs the following operations to achieve disease monitoring of the target pig group: obtaining a new target image containing the target pig group after a preset time interval; inputting the new target image into the preset model for posture detection operation to output the posture of each pig as a new posture detection result of the target pig group; determining the third proportion of pigs with the target abnormal posture in the target pig group based on the new posture detection result; determining whether the third proportion is less than the first proportion; when the third proportion is greater than or equal to the first proportion, adjusting the treatment plan, and continuing to execute the preset time interval to obtain a new target image containing the target pig group.

[0013] In some other embodiments, when the program instructions are executed by the processor, the device further performs the following operations to achieve disease monitoring of the target pig group: when the third proportion is less than the first proportion, the treatment plan is kept unchanged, and the new target image containing the target pig group is acquired after continuing to execute the preset interval time.

[0014] In a second aspect, the present application provides a computer-readable storage medium having stored thereon computer-readable instructions for disease monitoring of a pig herd; when the computer-readable instructions are executed by one or more processors, the operations performed by the apparatus as described in one or more embodiments of the first aspect above are implemented.

[0015] Through the scheme for disease monitoring of pig herds as provided above, the embodiment of the present application no longer relies on the experience of the breeder when monitoring the pig herd for diseases, but detects and analyzes the posture of the target pig herd by using a preset model, so that the proportion of pigs with abnormal posture in the target pig herd can be determined, and the disease state of the target pig herd can be determined based on the proportion. Furthermore, the treatment plan for the target pig herd can be determined in combination with the age and weight of the target pig herd. Based on this, the disease that causes abnormal posture of the pig herd can be identified as early as possible, and a reasonable treatment plan can be given, which can not only reduce the health risk of the pig herd, improve the survival rate of the pig herd, and reduce the economic losses of the enterprise, but also help to improve production efficiency and expand the scale of production. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easy to understand. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0017] Figure 1is an exemplary structural block diagram showing an apparatus for disease monitoring of a pig herd according to an embodiment of the present application;

[0018] Figure 2 is an exemplary schematic diagram showing an abnormal posture of a pig according to an embodiment of the present application;

[0019] Figure 3 is an exemplary flowchart showing operations performed by a device for disease monitoring of a pig herd according to an embodiment of the present application;

[0020] Figure 4 It is an exemplary structural block diagram showing a device for disease monitoring of a pig herd according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0022] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present application indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0023] It should be understood that when the terms "first", "second", "third" and "fourth" are used in the claims, the specification and the drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0024] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this application specification and claims, unless the context clearly indicates otherwise, the singular forms of "a", "an" and "the" are intended to include plural forms. It should also be further understood that the term "and / or" used in this application specification and claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0025] As used in this specification and claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0026] Figure 1 1 is an exemplary structural block diagram showing an apparatus 100 for disease monitoring of a pig herd according to an embodiment of the present application. Figure 1 As shown in , the device 100 may include a processor 101 and a memory 102. The processor 101 may include, for example, a general-purpose processor ("CPU") or a dedicated graphics processor ("GPU"), and the memory 102 stores program instructions that can be executed on the processor. In some embodiments, the memory 102 may include, but is not limited to, a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), and an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory).

[0027] Furthermore, the memory 102 may store program instructions for disease monitoring of a pig herd. When the program instructions are executed by the processor, the device 100 performs the following operations: obtaining basic information of a target pig herd and a target image containing the target pig herd, wherein the basic information includes at least age and weight; inputting the target image into a preset model for posture detection operation to output the posture of each pig as the posture detection result of the target pig herd; determining the proportion of pigs with abnormal postures in the target pig herd based on the posture detection result (for distinction, it may be referred to as the first proportion), and determining the disease state of the target pig herd based on the first proportion; and determining the treatment plan of the target pig herd based on age, weight and disease state, thereby realizing disease monitoring of the target pig herd. In one embodiment, the disease state may include at least the name and severity of the disease, and the treatment plan may include at least the name and dosage of the medication.

[0028] In the scheme of the present application, the target pig group can be a pig group consisting of all pigs in any pen of a pig breeding site. Thus, the target image containing the target pig group can be obtained by any one of the image acquisition devices such as mobile phone cameras, cameras and monitors. In actual operation, two schemes of manual acquisition and automatic acquisition can be adopted. In the case of manual acquisition, the photographer can use the image acquisition device to shoot the target image containing the target pig group at a predetermined shooting height and shooting angle. In the case of automatic acquisition, the shooting time can be set in advance so that the image acquisition device shoots the target image containing the target pig group at a predetermined shooting height and shooting angle when the shooting time is reached.

[0029] It is understandable that those skilled in the art can select specific values ​​of shooting height and shooting angle according to actual needs, which can usually satisfy that the collected target image includes all pigs in the target pig herd, and the pigs have clear appearance, obvious posture characteristics, and no serious stacking between pigs.

[0030] It can also be understood that the quality of the target image is directly related to the accuracy of the posture detection result. In order to improve the accuracy of the posture detection result, reduce the amount of computing resources used, and improve the utilization rate of computing resources, in practical applications, before inputting the target image into the preset model for posture detection operation, the target image can be first cleaned to filter out the target image that is of unqualified quality and not suitable for input into the preset model for the next posture detection operation.

[0031] Based on this, the target image can be input into the multi-classification model to perform a multi-classification operation to obtain at least one type label of the target image. Thereafter, whether the target image is of qualified quality can be determined based on the at least one type label. For target images of qualified quality, they can be input into the preset model to perform a posture detection operation to obtain a posture detection result. For target images of unqualified quality, they can be eliminated.

[0032] The above-mentioned multi-classification model can be a model built using any of a variety of open source projects such as ResNet and VGG. The type label can identify the interference conditions of the target image, which may include but is not limited to water mist, blur, abnormal lighting and tilt. It is understandable that those skilled in the art can select type labels according to actual needs, and this disclosure does not make specific limitations on this. In one embodiment, when the number of type labels of the target image is 0, it can be determined that the target image quality is qualified.

[0033] In the scheme of the present application, in addition to the above-mentioned age and weight, the basic information of the target pig herd may also include pen information, breed, environmental sampling detection information, historical medication information, feeding information, temperature and humidity information, etc. In practical applications, these basic information can be stored in open source or non-open source databases such as Oracle and PostgreSQL, or in cloud databases. Here, the environmental sampling detection information is the information obtained by sampling, detecting and identifying the strains in the pen where the target pig herd is located. Historical medication information is the medication information of the target pig herd before this, which may include the name of the disease, strain type, drug name, drug dosage and sensitive drugs, etc. Sensitive drugs refer to drugs that have achieved better therapeutic effects when treating a certain disease of the target pig herd. Feeding information may include feeding times, feeding times, feeding amounts and feed intake. Temperature and humidity information may include temperature values ​​and humidity values ​​of the pen where the target pig herd is located.

[0034] In one implementation scenario, the preset model may be a MobileNet model, which may output the posture of each pig as the posture detection result of the target pig group by performing a posture detection operation on each pig mark in the target image. In one embodiment, the posture may include but is not limited to standing, lying on the side, curled up, prone, and dog sitting. Standing and lying on the side are normal postures for pigs. Standing refers to a standing posture with the limbs of the pig upright and facing downwards, and lying on the side refers to a lying state of the pig with the head and torso on one side touching the ground, and the limbs on one side of the body and stretched out.

[0035] On the contrary, crouching, lying prone and dog sitting are abnormal postures for pigs. Figure 2 Understand the abnormal posture of pigs. Figure 2 As shown, Figure 2 The "a" in the figure stands for curled up position. In this position, the pig lies with one side of its trunk on the ground, but its forelimbs or limbs are curled up and bent on the chest and abdomen. Figure 2 The b in the figure stands for prone position. In this position, the pig lies with its chest or abdomen on the ground, and its limbs are under its body or stretched out in front and behind its body. Figure 2 The c in the figure is dog sit, in which the pig is lying with its front limbs stretched out for support and its hips and hind limbs on the ground.

[0036] Based on this, the target abnormal posture can be any one of curled up, prone and dog sitting. The first proportion is equal to the ratio of the number of pigs with the target abnormal posture to the total number of pigs in the target pig group. In one embodiment, when there are more than one type of abnormal posture in the posture detection result, each abnormal posture can be used as the target abnormal posture, and then the first proportion of pigs with each abnormal posture in the target pig group is determined, so that multiple first proportions can be obtained.

[0037] Given that different diseases may cause different adverse feelings to pigs, the abnormal postures presented by the pigs will also be different. Therefore, there may be a corresponding relationship between abnormal postures and diseases, that is, different abnormal postures may correspond to different diseases. Furthermore, the first proportion of pigs with abnormal postures in the pig herd can indicate the severity of the disease. Therefore, when determining the disease state of the target pig herd based on the first proportion, the name of the disease can be determined according to the target abnormal posture, and the severity can be determined according to the first proportion.

[0038] Generally, the larger the first proportion is, the more serious the disease is, and the smaller the first proportion is, the milder the disease is. In an implementation scenario, multiple thresholds (e.g., the first threshold, the second threshold, and the third threshold) for judging the severity of the disease can be pre-set according to actual needs, and different thresholds can be set for different diseases. Thus, when the first proportion is less than the first threshold, the severity of the disease can be determined to be normal; when the first proportion is greater than or equal to the first threshold and less than the second threshold, the severity of the disease can be determined to be mild; when the first proportion is greater than or equal to the second threshold and less than the third threshold, the severity of the disease can be determined to be moderate; when the first proportion is greater than or equal to the third threshold, the severity of the disease can be determined to be severe.

[0039] As an example, when the target abnormal posture is curled up, the disease name can be determined to be fever. Further, when the first proportion of curled up pigs in the pig herd is less than 5%, the pig herd can be determined to be normal; when the first proportion of curled up pigs in the pig herd is greater than or equal to 5% and less than 10%, the pig herd can be determined to have a mild fever; when the first proportion of curled up pigs in the pig herd is greater than or equal to 10% and less than 15%, the pig herd can be determined to have a moderate fever; when the first proportion of curled up pigs in the pig herd is greater than or equal to 15%, the pig herd can be determined to have a severe fever.

[0040] As another example, when the target abnormal posture is lying prone, the disease name can be determined to be cough. Further, when the first proportion of lying pigs in the pig herd is less than 3%, the pig herd can be determined to be normal; when the first proportion of lying pigs in the pig herd is greater than or equal to 3% and less than 5%, the pig herd can be determined to have a mild cough; when the first proportion of lying pigs in the pig herd is greater than or equal to 5% and less than 8%, the pig herd can be determined to have a moderate cough; when the first proportion of lying pigs in the pig herd is greater than or equal to 8%, the pig herd can be determined to have a severe cough.

[0041] Combined with the above description, it can be seen that when the embodiment of the present application monitors the pig herd for diseases, it no longer relies on the experience of the breeder, but detects and analyzes the posture of the target pig herd by using a preset model, so that the proportion of pigs with abnormal posture in the target pig herd can be determined, and the disease state of the target pig herd can be determined based on the proportion. Furthermore, the treatment plan for the target pig herd can be determined in combination with the age and weight of the target pig herd. Based on this, the disease that causes abnormal posture of the pig herd can be identified as early as possible, and a reasonable treatment plan can be given, which can not only reduce the health risks of the pig herd, improve the survival rate of the pig herd, and reduce the economic losses of the enterprise, but also help to improve production efficiency and expand the scale of production.

[0042] Figure 3 FIG. 3 is an exemplary flowchart showing the operation 300 performed by the apparatus for disease monitoring of a pig herd according to an embodiment of the present application. Figure 3 As shown in FIG. 3 , at step S301 , basic information of a target pig group and a target image containing the target pig group may be acquired.

[0043] Next, at step S302, the target image can be input into a preset model for posture detection operation to output the posture of each pig as the posture detection result of the target pig group. In order to reduce the influence of adjacent pigs on the accuracy of the posture detection result, a deep learning model can be used to locate and identify the pigs in the target image, and the pig image in the target image can be segmented and cropped according to the bounding box in the recognition result to obtain a sub-image containing only the complete outline of a single pig. In addition, the position of each sub-image in the target image can also be stored so that the posture detection result of the sub-image can be mapped back to the target image for summary analysis. In one embodiment, the deep learning model used to locate and identify the pigs in the target image can be a YOLOv model.

[0044] After obtaining a sub-image containing only the complete outline of a single pig, the posture detection result of a single pig can be obtained by inputting the sub-image into a preset model for posture monitoring operation. By summarizing and analyzing the posture detection results of all pigs in the target image, the posture detection results of the target pig group can be obtained.

[0045] In addition, in order to integrate multi-dimensional data to accurately determine the disease state of the target pig group, at step S303, the hair state and back state of the target pig group can also be obtained. Further, at step S304, the disease state of the target pig group can be determined based on the posture detection results, hair state and / or back state. Specifically, based on the posture detection results, hair state and / or back state, the second proportion of pigs with a target abnormal posture, a target abnormal hair state and / or an abnormal back state in the target pig group can be determined. Then the disease state of the target pig group is determined based on the second proportion.

[0046] In one embodiment, the above sub-images can be respectively input into the pre-trained hair state detection model and back state detection model to obtain the hair state and back state of a single pig. By summarizing and analyzing the hair state and back state of all pigs in the target image, the hair state and back state of the target pig group can be obtained. In practical applications, the hair state detection model and the back state detection model can be deep learning classification models, such as multilayer perceptron (MLP), convolutional neural network (CNN), recurrent neural network (RNN), EfficientNet model and MobileNet model, etc.

[0047] Abnormal hair conditions of pigs may include but are not limited to frizzy hair and ruffled hair. Rizzled hair indicates a condition where the hair is long, coarse, white, but in a straight line; ruffled hair indicates a condition where the hair is long, coarse, white, but in a disordered direction. Abnormal back conditions of pigs include but are not limited to exposed bones, hunched back, and exposed shoulders. Exposed bones indicate a condition where the spine or joints of the back are visible; hunched back indicates a condition where the back is arched and normally flat; exposed shoulders indicate a condition where the shoulder blades are clearly visible.

[0048] In the scheme of the present application, similar to the above process of determining the disease state of the target pig group based on the first ratio, when determining the disease state of the target pig group based on the second ratio, the name of the disease can be determined according to the target abnormal posture, target abnormal hair state and / or target abnormal back state, and the severity can also be determined according to the second ratio. Additionally or optionally, at least one threshold value can be pre-set according to actual needs to determine the severity of the disease.

[0049] As an example, when the target abnormal posture is curled up and the target abnormal hair state is protruding hair, it can be further determined whether the second proportion is greater than 50%. In the case where the second proportion is greater than 50%, the disease name can be determined to be blue ear, and the severity is severe. As another example, when the target abnormal posture is curled up, the target abnormal hair state is protruding hair, and the target abnormal back state is exposed, it can be further determined whether the second proportion is greater than 35%. In the case where the second proportion is greater than 35%, the disease name can be determined to be diarrhea, and the severity is severe.

[0050] It is understandable that there may be multiple pathogens for a disease. For example, the pathogenic bacteria of cough may be Mycoplasma or Pasteurella, and for another example, the pathogenic bacteria of diarrhea may be Escherichia coli or Clostridium, and the sensitive drugs for different pathogens may also be different. Based on this, after determining the disease state of the target pig herd, in order to obtain the accurate cause of the disease and then formulate a more accurate treatment plan for the target pig herd, at step S305, the type of bacteria corresponding to the disease state can be determined according to the above-mentioned environmental sampling detection information. Then, at step S306, the treatment plan for the target pig herd can be determined based on the age, weight, disease state and bacterial type of the target pig herd.

[0051] Furthermore, there may be multiple therapeutic drugs for a disease, but different pig groups may be sensitive to different drugs. Therefore. At step S306, the treatment plan for the target pig group can also be determined based on the age, weight, disease state, strain type and historical medication information of the target pig group. More specifically, the name and dosage of the medication for the target pig group can be determined based on the age, weight, disease state, strain type and historical medication information of the target pig group.

[0052] In addition, in order to improve the comfort of the target pig group and help the target pig group recover as soon as possible, the temperature and humidity of the pen where the target pig group is located can also be adjusted, and the feeding plan of the target pig group can also be adjusted. In an implementation scenario, the feeding information of the target pig group and the temperature and humidity information of the pen where the target pig group is located can be obtained first. Then, based on the feeding information, the feeding adjustment plan of the target pig group is determined, and the feeding adjustment plan can identify the adjustment amount of the number of feedings, feeding time, and feeding amount. Next, the temperature adjustment amount and humidity adjustment amount of the target pig group can also be determined based on the temperature and humidity information. In this way, the comfort of the target pig group can be improved from both the diet and living environment aspects, helping the target pig group to recover as soon as possible.

[0053] After determining a treatment plan for a certain disease of the target pig herd, in order to determine whether the treatment plan is effective for the target pig herd, the above-mentioned device can also perform the following operations to achieve continuous disease monitoring of the target pig herd: obtain a new target image containing the target pig herd after a preset time interval; input the new target image into a preset model for posture detection operation to output the posture of each pig as a new posture detection result of the target pig herd; determine the proportion of pigs with target abnormal posture in the target pig herd based on the new posture detection result (for the purpose of distinction, it can be called the third proportion); determine whether the third proportion is less than the above-mentioned first proportion; when the third proportion is less than the above-mentioned first proportion, it indicates that the above-mentioned treatment plan is effective for the target pig herd. At this time, the treatment plan can be kept unchanged, and the operation of obtaining a new target image containing the target pig herd after a preset time interval is continued, so as to continue to observe the treatment effect of the treatment plan on the target pig herd.

[0054] On the contrary, when the third proportion is greater than or equal to the first proportion, it indicates that the above treatment plan has a poor treatment effect on the target pig group, and the treatment plan can be adjusted to obtain a new treatment plan. Furthermore, the operation of obtaining a new target image containing the target pig group after a preset time interval can be continued to determine the treatment effect of the new treatment plan on the target pig group.

[0055] In addition, before determining whether the third proportion is less than the first proportion, it is also possible to determine whether the third proportion is less than the first threshold value mentioned above to determine whether the target pig herd has returned to a normal state. When the third proportion is less than the first threshold value, it can be determined that the target pig herd has returned to a normal state. On the contrary, when the third proportion is greater than or equal to the first threshold value, it indicates that the target pig herd has not returned to a normal state, and it is possible to determine whether the third proportion is less than the first proportion to determine whether the treatment plan is effective for the target pig herd.

[0056] Figure 4 is an exemplary structural block diagram of a device 400 for disease monitoring of a pig herd according to an embodiment of the present application. It is understood that the device 400 may include the apparatus of the embodiment of the present application, and the device implementing the solution of the present application may be a single device (such as a computing device) or a multifunctional device including various peripheral devices.

[0057] like Figure 4As shown in , the device of the present application may also include a central processing unit or central processing unit ("CPU") 411, which may be a general-purpose CPU, a dedicated CPU, or other information processing and program execution unit. Further, the device 400 may also include a large-capacity memory 412 and a read-only memory ("ROM") 413, wherein the large-capacity memory 412 may be configured to store various types of data, including basic information of the target pig group, target images, posture detection results, disease status and treatment plans, algorithm data, intermediate results, and various programs required to run the device 400. ROM 413 may be configured to store data and instructions required for power-on self-test of the device 400, initialization of various functional modules in the system, drivers for the basic input / output of the system, and booting the operating system.

[0058] Optionally, the device 400 may also include other hardware platforms or components, such as the tensor processing unit ("TPU") 414, the graphics processing unit ("GPU") 415, the field programmable gate array ("FPGA") 416, and the machine learning unit ("MLU") 417 shown. It is understood that although a variety of hardware platforms or components are shown in the device 400, they are merely exemplary and not restrictive, and those skilled in the art may add or remove corresponding hardware according to actual needs. For example, the device 400 may only include a CPU, related storage devices, and interface devices to implement the operations performed by the present application for disease monitoring of a pig herd.

[0059] In some embodiments, in order to facilitate the transmission and interaction of data with an external network, the device 400 of the present application further includes a communication interface 418, so that it can be connected to a local area network / wireless local area network ("LAN / WLAN") 405 through the communication interface 418, and then connected to a local server 406 or to the Internet ("Internet") 407 through the LAN / WLAN. Alternatively or additionally, the device 400 of the present application can also be directly connected to the Internet or a cellular network through the communication interface 418 based on wireless communication technology, such as wireless communication technology based on the third generation ("3G"), the fourth generation ("4G") or the fifth generation ("5G") of the third generation ("3G"), the fourth generation ("4G") or the fifth generation ("5G") of the third generation ("3G"), the fourth generation ("4G") or the fifth generation ("5G") of the third generation ("3G"), the fourth generation ("4G") or the fifth generation ("5G") of the third generation ("3G") of the third generation ("3G"), the fourth generation ("4G") or the fifth generation ("5G") of the third generation ("3G") of the third generation ("3G") of the fourth generation ("4G") or the fifth generation ("5G") of the third generation ("3G") of the fourth generation ("4G") of the fourth generation ("4G") of the fourth generation ("4G") of the fourth generation ("5 ...

[0060] The peripheral devices of the device 400 may include a display device 402, an input device 403, and a data transmission interface 404. In one embodiment, the display device 402 may, for example, include one or more speakers and / or one or more visual displays, which are configured to perform voice prompts and / or image video display for disease monitoring of pigs in the present application. The input device 403 may include other input buttons or controls such as a keyboard, a mouse, a microphone, a gesture capture camera, etc., which are configured to receive input and / or user instructions of audio data. The data transmission interface 404 may include, for example, a serial interface, a parallel interface or a universal serial bus interface ("USB"), a small computer system interface ("SCSI"), a serial ATA, a FireWire ("FireWire"), a PCI Express, and a high-definition multimedia interface ("HDMI"), etc., which are configured for data transmission and interaction with other devices or systems. According to the solution of the present application, the data transmission interface 404 can receive a target image of a target pig group collected by an image acquisition device, and transmit data or results including a target image or various other types to the device 400.

[0061] The CPU 411, mass storage 412, ROM 413, TPU 414, GPU 415, FPGA 416, MLU 417 and communication interface 418 of the device 400 of the present application can be interconnected through a bus 419, and data interaction with peripheral devices can be achieved through the bus. In one embodiment, through the bus 419, the CPU 411 can control other hardware components in the device 400 and its peripheral devices.

[0062] Combination of the above Figure 4 The device for disease monitoring of pigs that can be used to implement the present application is described. It should be understood that the device structure or architecture here is only exemplary, and the implementation method and implementation entity of the present application are not limited thereto, but can be changed without departing from the spirit of the present application.

[0063] According to the above description in combination with the accompanying drawings, those skilled in the art can also understand that the embodiments of the present application can also be implemented by software programs. Therefore, the present application also provides a computer-readable storage medium, on which computer-readable instructions for disease monitoring of pigs are stored. When the computer-readable instructions are executed by one or more processors, they can be used to implement the present application in combination with the accompanying drawings. Figure 3 The operations performed by the described apparatus for disease monitoring of a herd of pigs.

[0064] It should be noted that although the operations of the method of the present application are described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flow chart can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0065] Although the implementation methods of the present application are as above, the contents described are only examples adopted to facilitate the understanding of the present application, and are not intended to limit the scope and application scenarios of the present application. Any technician in the technical field described in the present application can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present application, but the scope of patent protection of the present application shall still be subject to the scope defined in the attached claims.

[0066] In addition, the collection and acquisition of various data in this application complies with relevant laws and regulations and is authorized by the data provider. Any organization or individual that needs to obtain external data must obtain authorization in accordance with the law and ensure data security. It is not allowed to illegally collect, use, process, or transmit unauthorized or unprotected data, or to illegally buy, sell, provide, or disclose unauthorized or unprotected data.

Claims

1. A device for disease monitoring of pigs, characterized in that: include: processor; A memory having program instructions for disease monitoring of a pig herd stored therein, wherein when the program instructions are executed by the processor, the device implements the following operations: Acquire basic information of a target pig group and a target image containing the target pig group, wherein the basic information at least includes age and weight; Inputting the target image into a preset model to perform a posture detection operation, so as to output the posture of each pig as a posture detection result of the target pig group; Determining a first proportion of pigs having a target abnormal posture in the target pig group based on the posture detection result, and determining a disease state of the target pig group based on the first proportion; and Based on the age, weight and disease status, a treatment plan for the target pig group is determined to achieve disease monitoring of the target pig group.

2. The device according to claim 1, characterized in that When the program instructions are executed by the processor, the device further performs the following operations to determine the disease status of the target pig group: Obtaining the hair condition and back condition of the target pig group; and The disease state of the target pig group is determined based on the posture detection result, the hair state and / or the back state.

3. The device according to claim 2, characterized in that When the program instructions are executed by the processor, the device further performs the following operations to determine the disease state of the target pig group based on the posture detection result, the hair state and / or the back state: Based on the posture detection result, the hair state and the back state, determining a second proportion of pigs having a target abnormal posture, a target abnormal hair state and / or an abnormal back state in the target pig group; and The disease status of the target pig herd is determined based on the second proportion.

4. The device according to claim 1 or 2, characterized in that: The basic information also includes environmental sampling detection information, and when the program instructions are executed by the processor, the device further performs the following operations to determine the treatment plan for the target pig group: Determining the bacterial species type corresponding to the disease state according to the environmental sampling detection information; and The treatment plan for the target pig herd is determined based on the age, weight, disease status and bacterial strain type.

5. The device according to claim 4, characterized in that The basic information also includes historical medication information, and when the program instructions are executed by the processor, the device further performs the following operations to determine the treatment plan for the target pig group: Based on the age, weight, disease status, bacterial strain type and historical medication information, a treatment plan for the target pig herd is determined.

6. The device according to claim 5, characterized in that When the program instructions are executed by the processor, the device further performs the following operations to determine a treatment plan for the target pig group: Obtaining feeding information of the target pig group and temperature and humidity information of the pen where the target pig group is located; Determine the name and dosage of the medication for the target pig herd based on the age, weight, disease status, bacterial strain type, and historical medication information; Determine a feeding adjustment plan for the target pig group based on the feeding information; as well as The temperature adjustment amount and humidity adjustment amount of the target pig group are determined based on the temperature and humidity information.

7. The device according to claim 1, characterized in that When the program instructions are executed by the processor, the device further performs the following operations to achieve disease monitoring of the target pig herd: After a preset time interval, a new target image including the target pig group is acquired; Inputting the new target image into the preset model to perform a posture detection operation, so as to output the posture of each pig as a new posture detection result of the target pig group; Determine, based on the new posture detection result, a third proportion of pigs having the target abnormal posture in the target pig group; Determining whether the third proportion is less than the first proportion; When the third proportion is greater than or equal to the first proportion, the treatment plan is adjusted, and the treatment plan is continued to be executed after the preset interval time to obtain a new target image containing the target pig group.

8. The device according to claim 7, characterized in that When the program instructions are executed by the processor, the device further performs the following operations to achieve disease monitoring of the target pig herd: When the third proportion is less than the first proportion, the treatment plan is kept unchanged, and the new target image containing the target pig group is acquired after the preset interval is continued.

9. A computer-readable storage medium, characterized in that: Computer-readable instructions for disease monitoring of a pig herd are stored thereon, and when the computer-readable instructions are executed by one or more processors, the operations performed by the device as described in any one of claims 1-8 are implemented.

Images