CN112562846A

CN112562846A - Animal disease diagnosis device

Info

Publication number: CN112562846A
Application number: CN201910911602.5A
Authority: CN
Inventors: 李奥; 刘永生
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2019-09-25
Filing date: 2019-09-25
Publication date: 2021-03-26

Abstract

The application discloses an animal disease diagnosis device, relates to the field of animal medical treatment, and is used for animal disease diagnosis. The animal disease diagnosis device comprises a monitoring unit, a diagnosis unit and a control unit, wherein the monitoring unit acquires various physiological data of an animal; the artificial intelligence unit carries out preprocessing according to the physiological data acquired by the monitoring unit to obtain symptoms; judging whether the animal is ill according to the symptoms, if so, obtaining animal disease types according to the symptoms and obtaining a treatment scheme and a feeding scheme according to the animal disease types. The embodiment of the application is applied to animal disease diagnosis.

Description

Animal disease diagnosis device

Technical Field

The application relates to the field of animal medical treatment, in particular to an animal disease diagnosis device.

Background

With the improvement of living standard of people, animals as pets have gone into thousands of households, and have established profound emotion with people, so that the animals become indispensable components of numerous families. While enjoying the joy brought by animals, the following problems also happen:

1. the animal is difficult to find the illness in time, and further the illness state can be delayed, and irreparable influence is generated.

2. Veterinarians are few and expensive to charge, and animal medical resources are under strain.

Disclosure of Invention

The embodiment of the application provides an animal disease diagnosis device, which is used for solving the problems that animals are difficult to find diseases in time and the medical resources of the animals are in shortage.

In order to achieve the above purpose, the embodiment of the present application adopts the following technical solutions:

the embodiment of the application provides an animal disease diagnosis device, and the device includes monitoring unit and artificial intelligence unit, specifically is used for:

the monitoring unit acquires various physiological data of the animal;

the artificial intelligence unit carries out preprocessing according to the physiological data acquired by the monitoring unit to obtain symptoms; judging whether the animal is ill according to the symptoms, if so, obtaining animal disease types according to the symptoms and obtaining a treatment scheme and a feeding scheme according to the animal disease types.

According to the animal disease diagnosis device provided by the embodiment of the application, the monitoring unit acquires various physiological data of an animal; the artificial intelligence unit carries out preprocessing according to the physiological data acquired by the monitoring unit to obtain symptoms; judging whether the animal is ill according to the symptoms, if so, obtaining animal disease types according to the symptoms and obtaining a treatment scheme and a feeding scheme according to the animal disease types. The animal disease diagnosis device has the advantages that a user can monitor the animal monitoring condition through the animal disease diagnosis device, diseases are found and treated in time, the delay of animal diseases is avoided, and the problem that the animals are ill and are difficult to find in time is solved. On the other hand, the animal disease diagnosis device can generate a corresponding treatment scheme and a feeding scheme according to the disease of the animal, so that a user can obtain the treatment scheme and the feeding scheme at home without looking at a veterinarian, thereby solving the problem of shortage of medical resources of the animal.

Drawings

Fig. 1 is a schematic view of a system according to an embodiment of the present application, wherein the system is related to an animal disease diagnosis device;

fig. 2 is a first schematic structural diagram of an animal disease diagnosis device provided in an embodiment of the present application;

fig. 3 is a schematic structural diagram ii of an animal disease diagnosis device provided in an embodiment of the present application;

fig. 4 is a first flowchart illustrating steps performed by the animal disease diagnosis apparatus according to the embodiment of the present application;

fig. 5 is a second schematic flowchart illustrating steps executed by the animal disease diagnosis apparatus according to the embodiment of the present application;

fig. 6 is a third schematic flowchart illustrating steps executed by the animal disease diagnosis apparatus according to the embodiment of the present application.

Detailed Description

As shown in fig. 1, the system of the animal disease diagnosis apparatus provided by the present application includes an animal disease diagnosis apparatus 101 and a user terminal 102.

The animal disease diagnosis apparatus 101 includes at least the following functions: acquiring various physiological data of animals; preprocessing the acquired physiological data to obtain symptoms; judging whether the animal is ill according to the symptoms, if so, obtaining animal disease types according to the symptoms and obtaining a treatment scheme and a feeding scheme according to the animal disease types.

Optionally, the animal disease diagnostic device 101 may be an intelligent cat nest, an intelligent dog nest, an intelligent birdcage, an intelligent barn, an intelligent cowshed, an intelligent pigsty, or the like.

Alternatively, the animal disease diagnosis apparatus 101 may transmit the health condition, the treatment plan, and the feeding plan of the animal to the user terminal 102. Wherein, the health condition comprises various physiological data, symptoms, disease and disease types.

The user terminal 102 comprises at least the following functions: receives the animal health condition and the coping process transmitted from the animal disease diagnosis apparatus 101 and adds or deletes symptoms according to a user instruction and transmits them to the animal disease diagnosis apparatus 101.

As shown in fig. 2, the embodiment of the present application provides a schematic structural diagram of an animal disease diagnosis device. The animal disease diagnostic device 200 may include at least one processor 201, a communication line 202, a memory 203, a camera 205, and a sensor 206. Specifically, the method comprises the following steps:

a processor 201 for executing the computer executed instructions stored in the memory 203, thereby implementing the steps or actions of each network element or device in the embodiments described below in the present application. The processor 201 may be a chip. For example, the Field Programmable Gate Array (FPGA) may be an Application Specific Integrated Circuit (ASIC), a system on chip (SoC), a Central Processing Unit (CPU), a Network Processor (NP), a digital signal processing circuit (DSP), a Micro Controller Unit (MCU), a Programmable Logic Device (PLD) or other integrated chips.

A communication line 202 for transmitting information between the processor 201 and the memory 203.

The memory 203 is used for storing computer execution instructions for executing the scheme of the application and is controlled by the processor 201 to execute. The memory 203 may be separate and coupled to the processor via the communication line 202. The memory 203 may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), double data rate SDRAM, enhanced SDRAM, SLDRAM, Synchronous Link DRAM (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory of the systems and apparatus described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

The camera 205 is used for acquiring facial features (including eye droppings, canthus inflammation, nose head state and the like) of the animal. Optionally, the facial features may be automatically identified by an identification algorithm of the camera, or the image may be sent to a user terminal to allow the user to make a label, and the identification algorithm of the camera performs learning to improve the identification algorithm according to the label made by the user.

The sensor 206 is configured to acquire data of animal weight, body temperature, and heartbeat (the heartbeat of the animal is recorded within 15 minutes and multiplied by 4 to obtain the respiration times per minute of the animal), where the sensor includes a weight sensor, an infrared temperature sensor, a humidity sensor, a heart rate sensor, and the like.

Optionally, the animal disease diagnosis apparatus 200 further comprises at least one communication interface 204 for communicating with other devices or a communication network. The communication network may be an ethernet, a Radio Access Network (RAN), or a Wireless Local Area Network (WLAN).

Examples 1,

The embodiment of the present application provides an animal disease diagnosis device 300, as shown in fig. 3, the animal disease diagnosis device includes a monitoring unit 301, an artificial intelligence unit 302, a control unit 303, and a communication unit 304, as shown in fig. 4, the animal disease diagnosis device 300 specifically executes steps including:

s401, various physiological data of the animal are obtained, and the physiological data are sent to the artificial intelligent unit.

Wherein step S401 is performed by the monitoring unit 301.

Wherein the physiological data comprises: body weight, body temperature, heart beat, respiration rate, hair color, facial features, etc.

Optionally, the monitoring unit 301 sends the physiological data to a management module in a mobile phone software (APP) running in the user terminal through the communication unit 304.

And S402, preprocessing according to the physiological data to obtain symptoms.

Wherein step S402 is performed by the artificial intelligence unit 302.

Wherein the preprocessing comprises removing obvious noise data and repeated data and filling up the missing value data.

Optionally, the artificial intelligence unit 302 receives, through the communication unit 304, the physiological data filled by the user, sent by the management module through the wireless communication module in the APP run by the user terminal.

Optionally, the artificial intelligence unit 302 sends the symptom to the user terminal through the communication unit 304; the artificial intelligence unit 302 receives, through the communication unit 304, the modified symptoms (such as inflammation, tear mark, etc.) sent by the management module in APP running in the user terminal through the wireless communication module. Wherein, the user modification is specifically that the user deletes or adds symptoms according to the actual condition of the animal.

And S403, judging whether the animal suffers from the disease according to the symptoms, if so, obtaining the disease type of the animal according to the symptoms, and obtaining a treatment scheme and a feeding scheme according to the disease type of the animal.

Wherein step S403 is performed by the artificial intelligence unit 302.

Optionally, the artificial intelligence unit 302 sends the information about whether the animal is ill, the type of disease of the animal, the treatment scheme and the feeding scheme to the APP management module running in the user terminal through the communication unit 304.

Specifically, as shown in fig. 5, step S403 includes:

s4031, inputting the symptoms into the second model to obtain whether the disease is caused.

Wherein the second model is a two-classification decision tree model established according to the first model.

Wherein the first model is a knowledge base.

Wherein the first model building process comprises:

and obtaining a first association rule of symptoms and whether the animal is ill or not by making a crawler on the Internet.

And obtaining a second association rule of symptoms and animal disease types by making a crawler on the Internet.

Illustratively, the second association rule includes:

infectious peritonitis-anorexia, infectious peritonitis-weight loss, infectious peritonitis-persistent fever, infectious peritonitis-mental condition beginning to worsen, etc.

And calculating the support degree and the confidence degree of the first association rule.

The support degree is a set of all high-frequency items, the support degree excludes unimportant symptoms, and the support degree is the sum of the number of related objects/the number mined; and generating an association rule in the high-frequency item set of the confidence coefficient, wherein the confidence coefficient is used for mining the relation between the symptom and whether the symptom is ill, and the confidence coefficient is the number of the associated objects/the number of the one of the mined associated objects. According to the support degree and the confidence degree, two kinds of things which are not related at ordinary times are related.

And calculating the support degree and the confidence degree of the second association rule.

Screening out the first association rules with the support degree larger than a first threshold and the confidence degree larger than a second threshold.

And screening out second association rules with the support degree larger than a third threshold and the confidence degree larger than a fourth threshold.

Wherein the third threshold may be the same as the first threshold and may be different from the first threshold, and the fourth threshold may be the same as the second threshold and may be different from the second threshold.

The purpose of screening according to the support degree and the confidence degree is to find out the most relevant symptoms of each disease and screen out the symptoms with low relevance.

And excluding the wrong first association rule, wherein the wrong first association rule at the exclusion is performed by an animal expert.

The erroneous second association rule is excluded. Wherein the second association rule excluding the error is performed by an animal specialist.

And constructing the first model according to the first association rule and the second association rule.

Optionally, the knowledge base may be constructed by using Structured Query Language (SQL), or may be constructed by using a relational or non-relational database such as non-structured query language (NoSQL).

Optionally, rule mining may be performed by using a correlation analysis algorithm (apriori), a frequent pattern growth algorithm (FP-growth), a fast update algorithm (FUP), and the like.

Wherein the second model building process comprises:

according to the first modelAnd calculating the information entropy of all symptoms according to the probability of whether the animal is ill in the first association rule corresponding to all symptoms. The entropy is a measure of the ordering of the system, and the more chaotic the system, the larger the entropy. Entropy of information

If a random variable X is X ═ { X1, X2, …, xn }, the probability of each of the random variables X is { p1, p2, …, pn }.

And calculating the information entropy of the first symptom according to the probability of the animal suffering from the disease in the first association rule corresponding to the first symptom.

For example, assuming that there are 5 types of symptom first association rules, the information entropy of the association rule of each symptom is calculated, and 5 information entropies are calculated.

And calculating the information gain of the first symptom according to the information entropies of all the symptoms and the information entropy of the first symptom. Wherein the information gain

The information gain is the difference value of the information before and after attribute selection and division of the decision tree, and the larger the information gain is, the stronger the ability of distinguishing samples is, and the more representative the information gain is.

And (4) taking the symptom with the maximum information gain as a root node, taking the rest symptoms as non-leaf nodes, and taking whether the animal is ill as a leaf node to construct a second model. The symptom with the largest information gain is used as a root node, so that the hierarchy of the decision tree is reduced, the calculation complexity is reduced, and the efficiency is saved.

Optionally, the second model may be constructed by using a random forest, a gradient decision tree (GBDT), a classification and regression tree (CART), or the like.

S4032, if the animal is ill, inputting the symptoms into the third model to obtain the animal disease type.

Wherein the third model is a multi-classification decision tree model established according to the first model.

Wherein the third model building process comprises:

calculating the information entropy of all symptoms according to the probability of each animal disease type in the second association rule corresponding to all symptoms in the first model; the entropy is a measure of the ordering of the system, and the more chaotic the system, the larger the entropy. Entropy of information

And calculating the information entropy of the second symptom according to the probability of each animal disease type in the second association rule corresponding to the second symptom.

For example, assuming that there are 5 types of symptom second association rules, the information entropy of the association rule of each symptom is calculated, and 5 information entropies are calculated.

And calculating the information gain of the second symptom according to the information entropies of all the symptoms and the information entropy of the second symptom. Wherein the information gain

And (4) constructing a third model by taking the symptom with the maximum information gain as a root node, taking the rest symptoms as non-leaf nodes and taking the animal disease types as leaf nodes. The symptom with the largest information gain is used as a root node, so that the hierarchy of the decision tree is reduced, the calculation complexity is reduced, and the efficiency is saved.

Optionally, the third model may be constructed by using random forest, GBDT, CART and other similar algorithms

S4033, inputting animal disease types into the fourth model to obtain a treatment scheme and a feeding scheme.

Wherein the fourth model is a knowledge base.

Wherein the fourth model building process comprises:

and acquiring the animal disease types and a third association rule of the treatment scheme by making a crawler on the Internet.

And acquiring the animal disease types and the fourth association rule of the feeding scheme by making a crawler on the Internet. Feeding regimens include, among other things, recommendations for the brand and type of animal food (e.g., therapeutic food for a particular disease), recommendations for water intake, recommendations for exercise capacity, and the like.

And calculating the support degree and the confidence degree of the third association rule.

And calculating the support degree and the confidence degree of the fourth association rule.

And screening out a third association rule with the support degree larger than a fifth threshold and the confidence degree larger than a sixth threshold, wherein the fifth threshold is possibly the same as or different from the first threshold or the third threshold, and the sixth threshold is possibly the same as or different from the second threshold or the fourth threshold.

And screening out a fourth association rule with the support degree larger than a seventh threshold and the confidence degree larger than an eighth threshold, wherein the seventh threshold may be the same as or different from the first threshold, or the third threshold or the fifth threshold, and the eighth threshold may be the same as or different from the second threshold, or the fourth threshold or the sixth threshold.

And excluding the wrong third association rule, wherein the third association rule excluding the mistake is performed by the animal specialist.

And excluding the wrong fourth association rule, wherein the fourth association rule excluding the error is performed by the animal specialist.

And constructing a fourth model according to the third association rule and the fourth association rule, wherein the animal disease category is used as an input node, and the treatment scheme and the feeding scheme are used as output nodes.

Alternatively, rules may be mined using apriori, FP-growth, FUP, and the like.

Optionally, the knowledge base may be constructed by SQL, or by relational or non-relational databases such as unstructured query language NoSQL.

Optionally, the fourth model is updated periodically.

Optionally, as shown in fig. 6, the animal disease diagnosis apparatus performs the steps further including:

s404, adjusting the environmental temperature and the environmental humidity according to whether the animal is sick or not or the disease type of the animal.

Wherein step S404 is performed by the control unit 303.

Optionally, the control unit 303 adjusts the management module that sends the environmental temperature and environmental humidity adjustment policy to the APP running in the user terminal through the communication unit 304 before, and the control unit 303 receives and executes the adjustment policy of the environmental temperature and the environmental humidity after the user modification sent by the APP running in the user terminal through the wireless communication module through the communication unit 304.

Specifically, the functions/implementation processes of the monitoring unit 301, the artificial intelligence unit 302, the control unit 303 and the communication unit 304 in fig. 3 can be implemented by the processor 201 shown in fig. 2 calling the computer execution instructions stored in the memory 203 through the communication line 202. The communication unit 304 in fig. 3 communicates with the user terminal through the communication interface 204 in fig. 2. The monitoring unit 301 in fig. 3 acquires physiological data in the camera 205 and the sensor 206 through the communication line 202 in fig. 2.

The above units may be individually configured processors, or may be implemented by being integrated into one of the processors of the controller, or may be stored in a memory of the controller in the form of program codes, and the functions of the above units may be called and executed by one of the processors of the controller. The processor described herein may be a CPU, or an ASIC, or one or more integrated circuits configured to implement embodiments of the present application.

It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing embodiments of the apparatuses, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus, and device may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

Claims

1. An animal disease diagnostic device, comprising:

the monitoring unit acquires various physiological data of the animal;

2. The animal disease diagnostic device of claim 1, wherein the artificial intelligence unit is specifically configured to:

inputting the symptoms into a second model to obtain whether the disease is ill, wherein the second model is a decision tree model established according to the first model;

if the animal is ill, inputting the symptoms into a third model to obtain the animal disease category, wherein the third model is a decision tree model established according to the first model;

inputting said animal disease category into a fourth model to obtain a treatment regimen and a feeding regimen, wherein said fourth model is a knowledge base.

3. The animal disease diagnosis apparatus according to claim 2, wherein the first model construction process comprises:

obtaining a first association rule of symptoms and whether an animal is ill or not by making a crawler on the Internet;

obtaining a second association rule of symptoms and animal disease types by making a crawler on the Internet;

calculating the support degree and the confidence degree of the first association rule;

calculating the support degree and the confidence degree of the second association rule;

screening out the first association rules with the support degree larger than a first threshold and the confidence degree larger than a second threshold;

screening out the second association rules with the support degree larger than a third threshold and the confidence degree larger than a fourth threshold;

excluding the erroneous first association rule;

excluding the second association rule being erroneous;

and constructing a first model according to the first association rule and the second association rule.

4. The animal disease diagnosis apparatus according to claim 2, wherein the second model construction process comprises:

calculating the information entropy of all symptoms according to the probability of whether the animals in the first association rule corresponding to all symptoms in the first model are ill or not;

calculating the information entropy of the first symptom according to the probability of the animal suffering from the disease in the first association rule corresponding to the first symptom;

calculating the information gain of the first symptom according to the information entropies of all symptoms and the information entropy of the first symptom;

and (4) taking the symptom with the maximum information gain as a root node, taking the rest symptoms as non-leaf nodes, and taking whether the animal is ill as a leaf node to construct a second model.

5. The animal disease diagnosis apparatus according to claim 2, wherein the third model construction process comprises:

calculating the information entropy of all symptoms according to the probability of each animal disease type in the second association rule corresponding to all symptoms in the first model;

calculating the information entropy of the second symptom according to the probability of each animal disease type in the second association rule corresponding to the second symptom;

calculating the information gain of the second symptom according to the information entropies of all the symptoms and the information entropy of the second symptom;

and (4) constructing a third model by taking the symptom with the maximum information gain as a root node, taking the rest symptoms as non-leaf nodes and taking the animal disease types as leaf nodes.

6. The animal disease diagnosis apparatus according to claim 2, wherein the fourth model construction process comprises:

obtaining animal disease types and a third association rule of a treatment scheme by making a crawler on the Internet;

obtaining animal disease types and fourth association rules of feeding schemes by making crawlers on the Internet;

calculating the support degree and the confidence degree of the third association rule;

calculating the support degree and the confidence degree of the fourth association rule;

screening out the third association rule with the support degree larger than a fifth threshold and the confidence degree larger than a sixth threshold;

screening out the fourth association rule with the support degree larger than a seventh threshold and the confidence degree larger than an eighth threshold;

excluding the third association rule that is erroneous;

excluding the wrong fourth association rule;

7. The animal disease diagnosis device according to any one of claims 1 to 6, wherein the device further comprises:

and the control unit is used for adjusting the environmental temperature and the environmental humidity according to whether the animal is sick or not or the disease type of the animal.