WO2018179219A1 - Computer system, method for diagnosing animal, and program - Google Patents

Computer system, method for diagnosing animal, and program Download PDF

Info

Publication number
WO2018179219A1
WO2018179219A1 PCT/JP2017/013252 JP2017013252W WO2018179219A1 WO 2018179219 A1 WO2018179219 A1 WO 2018179219A1 JP 2017013252 W JP2017013252 W JP 2017013252W WO 2018179219 A1 WO2018179219 A1 WO 2018179219A1
Authority
WO
WIPO (PCT)
Prior art keywords
animal
image
result
analysis
information
Prior art date
Application number
PCT/JP2017/013252
Other languages
French (fr)
Japanese (ja)
Inventor
俊二 菅谷
佳雄 奥村
Original Assignee
株式会社オプティム
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社オプティム filed Critical 株式会社オプティム
Priority to PCT/JP2017/013252 priority Critical patent/WO2018179219A1/en
Priority to JP2018522159A priority patent/JPWO2018179219A1/en
Publication of WO2018179219A1 publication Critical patent/WO2018179219A1/en

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis

Definitions

  • the present invention relates to a computer system, an animal diagnosis method, and a program for diagnosing an animal.
  • Non-Patent Document 1 It is known to diagnose animals by image analysis (see Non-Patent Document 1). Such diagnosis performs image analysis using a visible light image, an infrared image, an X-ray image, an ultrasonic image, or the like to diagnose pregnancy or a disease.
  • Non-Patent Document 1 pregnancy and illness are determined based only on acquired image data, and a plurality of data resources are not analyzed and predicted.
  • the present invention is a computer system that analyzes a correlation between possible prediction results (for example, estrus period and disease) from image analysis and a plurality of data resources, and performs prediction with higher accuracy than analysis of a single image,
  • An object is to provide an animal diagnosis method and program.
  • the present invention provides the following solutions.
  • the present invention is a computer system for diagnosing an animal, Animal image obtaining means for obtaining an animal image of the animal; Animal image analysis means for image analysis of the acquired animal image; Animal information acquisition means for acquiring animal information of the animal; Animal information analysis means for analyzing the acquired animal information; Correlation analysis means for analyzing the correlation between the image analysis result and the analysis result; An animal diagnostic means for diagnosing the animal based on the analyzed correlation result; A computer system is provided.
  • a computer system for diagnosing an animal acquires an animal image of the animal, performs image analysis on the acquired animal image, acquires animal information on the animal, and analyzes the acquired animal information. The correlation between the image analysis result and the analysis result is analyzed, and the animal is diagnosed based on the analyzed correlation result.
  • the present invention is a computer system category, but also in other categories such as animal diagnosis methods and programs, the same actions and effects according to the category are exhibited.
  • a computer system for analyzing a correlation between possible prediction results from image analysis and a plurality of data resources, and performing prediction with higher accuracy than analysis of a single image. It becomes possible to provide.
  • FIG. 1 is a diagram showing an outline of the animal diagnosis system 1.
  • FIG. 2 is an overall configuration diagram of the animal diagnosis system 1.
  • FIG. 3 is a functional block diagram of the computer 10.
  • FIG. 4 is a flowchart showing the image analysis learning process executed by the computer 10.
  • FIG. 5 is a flowchart showing the learning process for animal information analysis executed by the computer 10.
  • FIG. 6 is a flowchart showing animal diagnosis processing executed by the computer 10. It is.
  • FIG. 1 is a diagram for explaining an outline of an animal diagnosis system 1 which is a preferred embodiment of the present invention.
  • the animal diagnosis system 1 includes a computer 10 and is a computer system that diagnoses animals.
  • the animal diagnosis system 1 is a computer system that diagnoses cattle.
  • the computer 10 stores, measures, and inspects various imaging devices such as a visible light camera, an infrared camera, an X-ray camera, a CT (Computed Tomography), an ultrasonic camera, and the like, which are not shown, and external resources different from images.
  • imaging devices such as a visible light camera, an infrared camera, an X-ray camera, a CT (Computed Tomography), an ultrasonic camera, and the like, which are not shown, and external resources different from images.
  • various devices to be performed various sensors for measuring environmental data such as animal step count data, livestock charts that are history data of diseases and estrus, BCS (Body Condition Score), not shown computers, various tests such as blood tests Is a computing device communicably connected to an inspection device or the like that performs the above.
  • the computer 10 acquires an animal image of an animal (step S01).
  • the computer 10 acquires at least one of a visible light image, an infrared image, an X-ray image, a CT scan image, or an ultrasonic image as an animal image. In the following description, it demonstrates as what acquired the visible light image of the cow.
  • the computer 10 performs image analysis on the acquired animal image (step S02).
  • the computer 10 analyzes the feature amount of the animal image (estrus sign, characteristic behavior at the time of estrus, estrus mucus, etc.). For example, the computer 10 analyzes the characteristic amount of the cow from the visible light image, and follows, rides, discipline during rest, thrusting during lying, allowance of riding, mucus outflow, alignment, fight, jaw rest, frame , Analyze the riding detection instrument.
  • the computer 10 learns by associating the animal image stored in advance with the diagnosis result performed on the animal image, and based on the learned result, image analysis is performed on the animal image acquired this time. Good.
  • the computer 10 acquires animal information of animals (step S03).
  • the computer 10 acquires, as animal information, at least one of environmental data such as step count data measured by various sensors, livestock charts that are history data of diseases and estrus, blood test results, or BCS. In the following description, it is assumed that step count data has been acquired.
  • the computer 10 analyzes the acquired animal information (step S04).
  • the computer 10 analyzes whether or not an animal corresponds to, for example, estrus, respiratory disease, wound disease, parasitic disease, reproduction disorder, gastrointestinal disease, metabolic disease, and the like.
  • the computer 10 may learn by associating previously stored animal information and a diagnosis result performed on the animal information, and analyze the animal information acquired this time based on the learned result.
  • the computer 10 analyzes the correlation between the image analysis result and the analysis result (step S05). For example, as a result of image analysis, the computer 10 obtains results such as cow movement, estrus mucus from the vulva, and cows lined up in one example, and as a result of analysis, estrus from pedometer data or livestock charts. These correlations are analyzed when stage symptoms are acquired.
  • the computer 10 diagnoses an animal based on the analyzed correlation result (step S06). For example, the computer 10 determines that the cow is in the estrus period based on the analyzed correlation result.
  • FIG. 2 is a diagram showing a system configuration of the animal diagnosis system 1 which is a preferred embodiment of the present invention.
  • the animal diagnosis system 1 is composed of a computer 10 and a public network (Internet network, third generation, fourth generation communication network, etc.) 5 and is a computer system for diagnosing animals.
  • the computer 10 is the above-described computing device having the functions described later.
  • FIG. 3 is a functional block diagram of the computer 10.
  • the computer 10 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), etc. as the control unit 11, and a device for enabling communication with other devices as the communication unit 12. For example, a WiFi (Wireless Fidelity) compatible device compliant with IEEE 802.11 is provided.
  • the computer 10 also includes a data storage unit such as a hard disk, a semiconductor memory, a recording medium, or a memory card as the storage unit 13. Further, the computer 10 includes, as the processing unit 14, a device for executing various processes such as image processing, state diagnosis, and learning process.
  • control unit 11 reads a predetermined program, thereby realizing an animal image acquisition module 20, a diagnosis result acquisition module 21, and an animal information acquisition module 22 in cooperation with the communication unit 12. Further, in the computer 10, the control unit 11 reads a predetermined program, thereby realizing the storage module 30 in cooperation with the storage unit 13. Further, in the computer 10, the control unit 11 reads a predetermined program, so that the learning module 40, the image analysis module 41, the animal information analysis module 42, the correlation analysis module 43, and the diagnosis module cooperate with the processing unit 14. 44 is realized.
  • FIG. 4 is a flowchart of the image analysis learning process executed by the computer 10. Processing executed by each module described above will be described together with this processing.
  • the animal image acquisition module 20 acquires animal images of animals (step S10).
  • the animal image acquired by the animal image acquisition module 20 is, for example, at least one of a visible light image, an infrared image, an X-ray image, a CT scan image, or an ultrasonic image.
  • the animal image acquisition module 20 may acquire these animal images from a corresponding imaging device, or may acquire via a computer or the like (not shown). In the following description, the animal image acquisition module 20 will be described as acquiring a visible light image of a cow as an animal image.
  • the animal image acquisition module 20 may acquire animal images from a database or the like stored in an external computer (not shown).
  • the storage module 30 stores animal images (step S11).
  • the storage module 30 identifies the identifier of the animal that acquired the animal image this time (animal name, management number, preset reference number, identifier that can uniquely identify other animals, etc.), animal image, Are stored in association with each other. Note that the storage module 30 may store only animal images.
  • the diagnosis result acquisition module 21 acquires the diagnosis result of the animal corresponding to the animal image acquired this time (step S12).
  • the diagnosis result acquisition module 21 acquires a diagnosis result from, for example, an external computer (not shown) that stores livestock records or the like, a terminal device held by a veterinarian or a livestock related person, and the like.
  • the diagnosis result in the present embodiment is, for example, the presence or absence of estrus, identification of a disease, identification of necessary treatment, and the like.
  • the learning module 40 learns the animal image stored in the storage module 30 and the diagnosis result acquired by the diagnosis result acquisition module 21 in association with each other (step S13). In step S13, the learning module 40 learns at least one of the above-described visible light image, infrared image, X-ray image, CT scan image, or ultrasonic image in association with the diagnosis result.
  • the storage module 30 stores the learned result (step S14).
  • the animal diagnosis system 1 executes the above-described image analysis learning process a sufficient number of times and stores the learning result.
  • FIG. 5 is a flowchart of animal information analysis learning processing executed by the computer 10. Processing executed by each module described above will be described together with this processing.
  • the animal information acquisition module 22 acquires animal information of animals (step S20).
  • the animal information acquired by the animal information acquisition module 22 includes, for example, environmental data such as step count data measured by various sensors, livestock medical records that are history data of diseases and estrus, blood test results, or at least BCS results.
  • environmental data such as step count data measured by various sensors, livestock medical records that are history data of diseases and estrus, blood test results, or at least BCS results.
  • the animal information acquisition module 22 may acquire such animal information from various corresponding devices or the like, or may acquire it via a computer or the like (not shown). In the following description, the animal information acquisition module 22 will be described as acquiring step count data as animal information.
  • the storage module 30 stores animal information (step S21).
  • the storage module 30 associates the identifier of the animal that acquired the animal information this time (the name of the animal, the management number, a preset reference number, an identifier that can uniquely identify other animals, etc.) and the animal information.
  • the storage module 30 may store only animal information.
  • the diagnosis result acquisition module 21 acquires the diagnosis result of the animal corresponding to the animal information acquired this time (step S22).
  • the diagnosis result acquisition module 21 acquires a diagnosis result from, for example, an external computer (not shown) that stores livestock records or the like, a terminal device held by a veterinarian or a livestock related person, and the like.
  • the diagnosis result in the present embodiment is, for example, the presence or absence of estrus, identification of a disease, identification of necessary treatment, and the like.
  • the learning module 40 learns by associating the animal information stored in the storage module 30 with the diagnosis result acquired by the diagnosis result acquisition module 21 (step S23). In step S23, the learning module 40 associates at least one of environmental data such as step count data measured by the various sensors described above, livestock charts that are history data of diseases and estrus, blood test results, or BCS with the diagnosis results. To learn.
  • environmental data such as step count data measured by the various sensors described above, livestock charts that are history data of diseases and estrus, blood test results, or BCS with the diagnosis results.
  • the storage module 30 stores the learned result (step S24).
  • the animal diagnosis system 1 executes the above-described learning process for animal information analysis a sufficient number of times and stores the learning result.
  • the above is the learning process for animal information analysis.
  • FIG. 6 is a flowchart of the animal diagnosis process executed by the computer 10. Processing executed by each module described above will be described together with this processing. In the following description, the animal diagnosis system 1 will be described as diagnosing a cow based on the visible light image of the cow and the number of steps data.
  • the animal image acquisition module 20 acquires animal images of animals (step S30).
  • the animal image acquired by the animal image acquisition module 20 is, for example, at least one of a visible light image, an infrared image, an X-ray image, a CT scan image, or an ultrasound image.
  • the animal image acquisition module 20 may acquire these animal images from a corresponding imaging device, or may acquire via a computer or the like (not shown).
  • the image analysis module 41 performs image analysis on the acquired animal image (step S31).
  • step S31 an animal image is image-analyzed based on the result learned by the learning module 40.
  • the image analysis module 41 analyzes the feature amount of the animal image acquired this time (estrus sign, characteristic behavior at the time of estrus, estrus mucus, etc.).
  • the image analysis module 41 analyzes a plurality of candidates such as image parts and features necessary for making a diagnosis from the learning result.
  • the image analysis module 41 extracts, for example, a feature amount of a cow from an animal image, follows, rides, riding, discipline during rest, thrusting behavior during lying, allowance of riding, mucus outflow, alignment, fight, jaw rest, Analyze flamen and norigami detectors.
  • the image analysis module 41 is not necessarily limited to identifying estrus or disease as a result of image analysis, but may only obtain information for diagnosis described later. For example, the image analysis module 41 may obtain preliminary information for diagnosis from the result of image analysis.
  • the animal information acquisition module 22 acquires animal information of animals (step S32).
  • the animal information acquisition module 22 acquires, as animal information, at least one of environmental data such as step count data measured by various sensors, livestock charts that are history data of diseases and estrus, blood test results, or BCS. To do.
  • the animal information acquisition module 22 may acquire such animal information from various corresponding devices or the like, or may acquire it via a computer or the like (not shown).
  • the animal information analysis module 42 analyzes the acquired animal information (step S33).
  • step S33 the animal information analysis module 42 analyzes the animal information based on the result learned by the learning module 40.
  • the animal information analysis module 42 analyzes a plurality of candidates for animal information necessary for making a diagnosis from the learned result.
  • the animal information analysis module 42 analyzes whether or not an animal corresponds to, for example, estrus, respiratory disease, wound disease, parasitic disease, reproductive disorder, gastrointestinal disease, metabolic disease or the like.
  • the animal information analysis module 42 acquires step count data as animal information, and analyzes that there is a suspicion of the estrus period as a symptom corresponding to the step count data.
  • the animal information analysis module 42 is not necessarily limited to the one that identifies estrus and disease as a result of the analysis, and may only obtain information for diagnosis described later. For example, the animal information analysis module 42 may obtain preliminary information for diagnosis from the analysis result.
  • the correlation analysis module 43 analyzes the correlation between the result of image analysis by the image analysis module 41 and the result of analysis by the animal information analysis module 42 (step S34).
  • step S34 for example, the correlation analysis module 43 analyzes the result of image analysis by the image analysis module 41, the analysis result that the cow's movement, the estrus mucus flowed out from the vulva, and the cows are lined up, As a result of the analysis by the information analysis module 42, the correlation with the analysis result that the estrus period is suspected is analyzed.
  • the correlation analysis module 43 analyzes the correlation as a score. That is, the correlation analysis module 43 evaluates as a score how much the diagnosis obtained from the analysis result and the diagnosis obtained from the analysis result have a correlation.
  • the correlation analysis module 43 evaluates the degree of correlation between the diagnosis results of the respective items obtained as a result of the analysis and the diagnosis results of the respective items obtained as a result of the analysis.
  • the correlation analysis module 43 evaluates a high correlation as a high score, and evaluates a low correlation as a low score.
  • the diagnosis module 44 diagnoses an animal based on the analyzed correlation result (step S35).
  • the diagnosis module 44 identifies the estrus or disease of the animal based on the combination of the diagnosis results with the highest score as the result of the analyzed correlation. For example, the diagnosis module 44 specifies that the current animal is in the estrus period based on the above-described image analysis result, the above-described animal information analysis result, and the correlation analysis result.
  • the learning module 40 learns the current diagnosis result in association with the animal image and the animal information (step S36).
  • the storage module 30 stores the learned result (step S37).
  • the computer 10 performs a diagnosis in consideration of the result learned this time at the subsequent diagnosis.
  • the computer 10 may transmit the diagnosis result to a terminal device or the like held by a veterinarian or animal husbandry not shown.
  • the diagnosis result may be transmitted to this terminal device.
  • a specific method of treatment information such as a map and contact information of the nearest corresponding facility, and various types of information such as a risk level may be transmitted together.
  • the terminal device that has received the various types of information may notify the various types of information by display or voice.
  • the above is animal diagnosis processing.
  • the means and functions described above are realized by a computer (including a CPU, an information processing apparatus, and various terminals) reading and executing a predetermined program.
  • the program is provided, for example, in a form (SaaS: Software as a Service) provided from a computer via a network.
  • the program is provided in a form recorded on a computer-readable recording medium such as a flexible disk, CD (CD-ROM, etc.), DVD (DVD-ROM, DVD-RAM, etc.).
  • the computer reads the program from the recording medium, transfers it to the internal storage device or the external storage device, stores it, and executes it.
  • the program may be recorded in advance in a storage device (recording medium) such as a magnetic disk, an optical disk, or a magneto-optical disk, and provided from the storage device to a computer via a communication line.

Abstract

[Problem] The purpose of the present invention is to provide: a computer system that analyzes, from image analysis and multiple data resources, correlations between possible prediction results and executes a prediction with higher precision than that achieved by analysis of a single image; a method for diagnosing an animal; and a program. [Solution] A computer system for diagnosing an animal acquires an image of the animal, performs image analysis on the acquired animal image, acquires animal information about the animal, analyzes the acquired animal information, analyzes the correlation between the result of the image analysis and the result of the animal information analysis, and then diagnoses the animal on the basis of the result of the correlation analysis.

Description

コンピュータシステム、動物診断方法及びプログラムComputer system, animal diagnosis method and program
　本発明は、動物を診断するコンピュータシステム、動物診断方法及びプログラムに関する。 The present invention relates to a computer system, an animal diagnosis method, and a program for diagnosing an animal.
　近年、画像解析により動物を診断することが知られている（非特許文献１参照）。このような診断は、可視光画像、赤外線画像、レントゲン画像又は超音波画像等を用いた画像解析を行い、妊娠や疾病を診断する。 Recently, it is known to diagnose animals by image analysis (see Non-Patent Document 1). Such diagnosis performs image analysis using a visible light image, an infrared image, an X-ray image, an ultrasonic image, or the like to diagnose pregnancy or a disease.
　しかしながら、非特許文献１の構成では、取得できた画像データのみで妊娠や疾病を判定するものであり、複数のデータリソースを解析して、予測を行うものではなかった。 However, in the configuration of Non-Patent Document 1, pregnancy and illness are determined based only on acquired image data, and a plurality of data resources are not analyzed and predicted.
　本発明は、画像解析と複数のデータリソースとから、起こりえる予測結果（例えば、発情期や疾病）の相関関係を解析し、単体の画像の解析よりも高度な精度の予測を行うコンピュータシステム、動物診断方法及びプログラムを提供することを目的とする。 The present invention is a computer system that analyzes a correlation between possible prediction results (for example, estrus period and disease) from image analysis and a plurality of data resources, and performs prediction with higher accuracy than analysis of a single image, An object is to provide an animal diagnosis method and program.
　本発明では、以下のような解決手段を提供する。 The present invention provides the following solutions.
　本発明は、動物を診断するコンピュータシステムであって、
　前記動物の動物画像を取得する動物画像取得手段と、
　取得した前記動物画像を画像解析する動物画像解析手段と、
　前記動物の動物情報を取得する動物情報取得手段と、
　取得した前記動物情報を分析する動物情報分析手段と、
　前記画像解析した結果と、前記分析した結果との相関関係を分析する相関関係分析手段と、
　分析した前記相関関係の結果に基づいて、前記動物を診断する動物診断手段と、
　を備えることを特徴とするコンピュータシステムを提供する。 The present invention is a computer system for diagnosing an animal,
Animal image obtaining means for obtaining an animal image of the animal;
Animal image analysis means for image analysis of the acquired animal image;
Animal information acquisition means for acquiring animal information of the animal;
Animal information analysis means for analyzing the acquired animal information;
Correlation analysis means for analyzing the correlation between the image analysis result and the analysis result;
An animal diagnostic means for diagnosing the animal based on the analyzed correlation result;
A computer system is provided.
　本発明によれば、動物を診断するコンピュータシステムは、前記動物の動物画像を取得し、取得した前記動物画像を画像解析し、前記動物の動物情報を取得し、取得した前記動物情報を分析し、前記画像解析した結果と、前記分析した結果との相関関係を分析し、分析した前記相関関係の結果に基づいて、前記動物を診断する。 According to the present invention, a computer system for diagnosing an animal acquires an animal image of the animal, performs image analysis on the acquired animal image, acquires animal information on the animal, and analyzes the acquired animal information. The correlation between the image analysis result and the analysis result is analyzed, and the animal is diagnosed based on the analyzed correlation result.
　本発明は、コンピュータシステムのカテゴリであるが、動物診断方法及びプログラム等の他のカテゴリにおいても、そのカテゴリに応じた同様の作用・効果を発揮する。 The present invention is a computer system category, but also in other categories such as animal diagnosis methods and programs, the same actions and effects according to the category are exhibited.
　本発明によれば、画像解析と複数のデータリソースとから、起こりえる予測結果の相関関係を解析し、単体の画像の解析よりも高度な精度の予測を行うコンピュータシステム、動物診断方法及びプログラムを提供することが可能となる。 According to the present invention, a computer system, an animal diagnosis method, and a program for analyzing a correlation between possible prediction results from image analysis and a plurality of data resources, and performing prediction with higher accuracy than analysis of a single image. It becomes possible to provide.
図１は、動物診断システム１の概要を示す図である。FIG. 1 is a diagram showing an outline of the animal diagnosis system 1. 図２は、動物診断システム１の全体構成図である。FIG. 2 is an overall configuration diagram of the animal diagnosis system 1. 図３は、コンピュータ１０の機能ブロック図である。FIG. 3 is a functional block diagram of the computer 10. 図４は、コンピュータ１０が実行する画像解析用学習処理を示すフローチャートである。FIG. 4 is a flowchart showing the image analysis learning process executed by the computer 10. 図５は、コンピュータ１０が実行する動物情報分析用学習処理を示すフローチャートである。FIG. 5 is a flowchart showing the learning process for animal information analysis executed by the computer 10. 図６は、コンピュータ１０が実行する動物診断処理を示すフローチャートである。である。FIG. 6 is a flowchart showing animal diagnosis processing executed by the computer 10. It is.
　以下、本発明を実施するための最良の形態について図を参照しながら説明する。なお、これはあくまでも一例であって、本発明の技術的範囲はこれに限られるものではない。 Hereinafter, the best mode for carrying out the present invention will be described with reference to the drawings. This is merely an example, and the technical scope of the present invention is not limited to this.
　［動物診断システム１の概要］
　本発明の好適な実施形態の概要について、図１に基づいて説明する。図１は、本発明の好適な実施形態である動物診断システム１の概要を説明するための図である。動物診断システム１は、コンピュータ１０から構成され、動物を診断するコンピュータシステムである。本実施形態において、動物診断システム１は、牛を診断するコンピュータシステムである。 [Outline of Animal Diagnosis System 1]
An outline of a preferred embodiment of the present invention will be described with reference to FIG. FIG. 1 is a diagram for explaining an outline of an animal diagnosis system 1 which is a preferred embodiment of the present invention. The animal diagnosis system 1 includes a computer 10 and is a computer system that diagnoses animals. In the present embodiment, the animal diagnosis system 1 is a computer system that diagnoses cattle.
　コンピュータ１０は、図示していない可視光カメラ、赤外線カメラ、Ｘ線カメラ、ＣＴ（Ｃｏｍｐｕｔｅｄ　Ｔｏｍｏｇｒａｐｈｙ）、超音波カメラ等の各種撮像装置等や、画像とは異なる外部リソースを記憶、計測、検査等を行う各種装置、動物の歩数データ等の環境データを計測する各種センサ、疾病や発情の履歴データである畜産カルテやＢＣＳ（Ｂｏｄｙ　Ｃｏｎｄｉｔｉｏｎ　Ｓｃｏｒｅ）を記憶する図示していないコンピュータ、血液検査等の各種検査を実行する検査装置等に通信可能に接続された計算装置である。 The computer 10 stores, measures, and inspects various imaging devices such as a visible light camera, an infrared camera, an X-ray camera, a CT (Computed Tomography), an ultrasonic camera, and the like, which are not shown, and external resources different from images. Various devices to be performed, various sensors for measuring environmental data such as animal step count data, livestock charts that are history data of diseases and estrus, BCS (Body Condition Score), not shown computers, various tests such as blood tests Is a computing device communicably connected to an inspection device or the like that performs the above.
　はじめに、コンピュータ１０は、動物の動物画像を取得する（ステップＳ０１）。コンピュータ１０は、動物画像として、可視光画像、赤外線画像、レントゲン画像、ＣＴスキャン画像又は超音波画像の少なくとも一つを取得する。以下の説明において、牛の可視光画像を取得したものとして説明する。 First, the computer 10 acquires an animal image of an animal (step S01). The computer 10 acquires at least one of a visible light image, an infrared image, an X-ray image, a CT scan image, or an ultrasonic image as an animal image. In the following description, it demonstrates as what acquired the visible light image of the cow.
　コンピュータ１０は、取得した動物画像を画像解析する（ステップＳ０２）。コンピュータ１０は、動物画像の特徴量（発情兆候、発情時における特徴的な行動、発情粘液等）を解析する。コンピュータ１０は、例えば、可視光画像から牛の特徴量を分析し、追従、乗駕、休息中の規律、横臥中の突き行動、乗駕許容、粘液の流出、並び、争い、顎休め、フレーメン、乗駕検出器具を解析する。なお、コンピュータ１０は、予め記憶した動物画像と、この動物画像に対して行われた診断結果とを対応付けて学習し、学習した結果に基づいて、今回取得した動物画像を画像解析してもよい。 The computer 10 performs image analysis on the acquired animal image (step S02). The computer 10 analyzes the feature amount of the animal image (estrus sign, characteristic behavior at the time of estrus, estrus mucus, etc.). For example, the computer 10 analyzes the characteristic amount of the cow from the visible light image, and follows, rides, discipline during rest, thrusting during lying, allowance of riding, mucus outflow, alignment, fight, jaw rest, frame , Analyze the riding detection instrument. The computer 10 learns by associating the animal image stored in advance with the diagnosis result performed on the animal image, and based on the learned result, image analysis is performed on the animal image acquired this time. Good.
　コンピュータ１０は、動物の動物情報を取得する（ステップＳ０３）。コンピュータ１０は、動物情報として、各種センサが計測した歩数データ等の環境データ、疾病や発情の履歴データである畜産カルテ、血液検査の結果又はＢＣＳの少なくとも一つを取得する。以下の説明において、歩数データを取得したものとして説明する。 The computer 10 acquires animal information of animals (step S03). The computer 10 acquires, as animal information, at least one of environmental data such as step count data measured by various sensors, livestock charts that are history data of diseases and estrus, blood test results, or BCS. In the following description, it is assumed that step count data has been acquired.
　コンピュータ１０は、取得した動物情報を分析する（ステップＳ０４）。コンピュータ１０は、例えば、発情期、呼吸器疾患、創傷性疾患、寄生虫病、繁殖障害、胃腸性疾患、代謝病等に動物が該当するか否かを分析する。なお、コンピュータ１０は、予め記憶した動物情報とこの動物情報に対して行われた診断結果とを対応付けて学習し、学習した結果に基づいて、今回取得した動物情報を分析してもよい。 The computer 10 analyzes the acquired animal information (step S04). The computer 10 analyzes whether or not an animal corresponds to, for example, estrus, respiratory disease, wound disease, parasitic disease, reproduction disorder, gastrointestinal disease, metabolic disease, and the like. Note that the computer 10 may learn by associating previously stored animal information and a diagnosis result performed on the animal information, and analyze the animal information acquired this time based on the learned result.
　コンピュータ１０は、画像解析した結果と、分析した結果との相関関係を分析する（ステップＳ０５）。コンピュータ１０は、例えば、画像解析の結果として、牛の動き、外陰部から発情粘液が流出、牛が一例に並んでいる等の結果を取得し、分析した結果として、歩数データや畜産カルテから発情期の症状を取得した場合、これらの相関関係を分析する。 The computer 10 analyzes the correlation between the image analysis result and the analysis result (step S05). For example, as a result of image analysis, the computer 10 obtains results such as cow movement, estrus mucus from the vulva, and cows lined up in one example, and as a result of analysis, estrus from pedometer data or livestock charts. These correlations are analyzed when stage symptoms are acquired.
　コンピュータ１０は、分析した相関関係の結果に基づいて、動物を診断する（ステップＳ０６）。コンピュータ１０は、例えば、分析した相関関係の結果に基づいて、牛が発情期であると決定する。 The computer 10 diagnoses an animal based on the analyzed correlation result (step S06). For example, the computer 10 determines that the cow is in the estrus period based on the analyzed correlation result.
　以上が、動物診断システム１の概要である。 The above is the outline of the animal diagnosis system 1.
　［動物診断システム１のシステム構成］
　図２に基づいて、本発明の好適な実施形態である動物診断システム１のシステム構成について説明する。図２は、本発明の好適な実施形態である動物診断システム１のシステム構成を示す図である。動物診断システム１は、コンピュータ１０、公衆回線網（インターネット網や、第３、第４世代通信網等）５から構成され、動物を診断するコンピュータシステムである。 [System configuration of animal diagnosis system 1]
Based on FIG. 2, the system configuration | structure of the animal diagnosis system 1 which is suitable embodiment of this invention is demonstrated. FIG. 2 is a diagram showing a system configuration of the animal diagnosis system 1 which is a preferred embodiment of the present invention. The animal diagnosis system 1 is composed of a computer 10 and a public network (Internet network, third generation, fourth generation communication network, etc.) 5 and is a computer system for diagnosing animals.
　コンピュータ１０は、後述の機能を備えた上述した計算装置である。 The computer 10 is the above-described computing device having the functions described later.
　［各機能の説明］
　図３に基づいて、本発明の好適な実施形態である動物診断システム１の機能について説明する。図３は、コンピュータ１０の機能ブロック図を示す図である。 [Description of each function]
Based on FIG. 3, the function of the animal diagnosis system 1 which is a preferred embodiment of the present invention will be described. FIG. 3 is a functional block diagram of the computer 10.
　コンピュータ１０は、制御部１１として、ＣＰＵ（Ｃｅｎｔｒａｌ　Ｐｒｏｃｅｓｓｉｎｇ　Ｕｎｉｔ）、ＲＡＭ（Ｒａｎｄｏｍ　Ａｃｃｅｓｓ　Ｍｅｍｏｒｙ）、ＲＯＭ（Ｒｅａｄ　Ｏｎｌｙ　Ｍｅｍｏｒｙ）等を備え、通信部１２として、他の機器と通信可能にするためのデバイス、例えば、ＩＥＥＥ８０２．１１に準拠したＷｉＦｉ（Ｗｉｒｅｌｅｓｓ　Ｆｉｄｅｌｉｔｙ）対応デバイスを備える。また、コンピュータ１０は、記憶部１３として、ハードディスクや半導体メモリ、記録媒体、メモリカード等によるデータのストレージ部を備える。また、コンピュータ１０は、処理部１４として、画像処理、状態診断、学習処理等の各種処理を実行するためのデバイス等を備える。 The computer 10 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), etc. as the control unit 11, and a device for enabling communication with other devices as the communication unit 12. For example, a WiFi (Wireless Fidelity) compatible device compliant with IEEE 802.11 is provided. The computer 10 also includes a data storage unit such as a hard disk, a semiconductor memory, a recording medium, or a memory card as the storage unit 13. Further, the computer 10 includes, as the processing unit 14, a device for executing various processes such as image processing, state diagnosis, and learning process.
　コンピュータ１０において、制御部１１が所定のプログラムを読み込むことにより、通信部１２と協働して、動物画像取得モジュール２０、診断結果取得モジュール２１、動物情報取得モジュール２２を実現する。また、コンピュータ１０において、制御部１１が所定のプログラムを読み込むことにより、記憶部１３と協働して、記憶モジュール３０を実現する。また、コンピュータ１０において、制御部１１が所定のプログラムを読み込むことにより、処理部１４と協働して、学習モジュール４０、画像解析モジュール４１、動物情報分析モジュール４２、相関関係分析モジュール４３、診断モジュール４４を実現する。 In the computer 10, the control unit 11 reads a predetermined program, thereby realizing an animal image acquisition module 20, a diagnosis result acquisition module 21, and an animal information acquisition module 22 in cooperation with the communication unit 12. Further, in the computer 10, the control unit 11 reads a predetermined program, thereby realizing the storage module 30 in cooperation with the storage unit 13. Further, in the computer 10, the control unit 11 reads a predetermined program, so that the learning module 40, the image analysis module 41, the animal information analysis module 42, the correlation analysis module 43, and the diagnosis module cooperate with the processing unit 14. 44 is realized.
　［画像解析用学習処理］
　図４に基づいて、動物診断システム１が実行する画像解析用学習処理について説明する。図４は、コンピュータ１０が実行する画像解析用学習処理のフローチャートを示す図である。上述した各モジュールが実行する処理について、本処理に併せて説明する。 [Learning processing for image analysis]
Based on FIG. 4, the learning process for image analysis which the animal diagnosis system 1 performs is demonstrated. FIG. 4 is a flowchart of the image analysis learning process executed by the computer 10. Processing executed by each module described above will be described together with this processing.
　動物画像取得モジュール２０は、動物の動物画像を取得する（ステップＳ１０）。ステップＳ１０において、動物画像取得モジュール２０が取得する動物画像とは、例えば、可視光画像、赤外線画像、レントゲン画像、ＣＴスキャン画像又は超音波画像の少なくとも一つである。動物画像取得モジュール２０は、これらの動物画像を、対応する撮像装置から取得してもよいし、図示していないコンピュータ等を介して取得してもよい。以下の説明において、動物画像取得モジュール２０は、動物画像として、牛の可視光画像を取得するものとして説明する。 The animal image acquisition module 20 acquires animal images of animals (step S10). In step S10, the animal image acquired by the animal image acquisition module 20 is, for example, at least one of a visible light image, an infrared image, an X-ray image, a CT scan image, or an ultrasonic image. The animal image acquisition module 20 may acquire these animal images from a corresponding imaging device, or may acquire via a computer or the like (not shown). In the following description, the animal image acquisition module 20 will be described as acquiring a visible light image of a cow as an animal image.
　なお、動物画像取得モジュール２０は、図示していない外部コンピュータ等に記憶されたデータベース等から、動物画像を取得してもよい。 The animal image acquisition module 20 may acquire animal images from a database or the like stored in an external computer (not shown).
　記憶モジュール３０は、動物画像を記憶する（ステップＳ１１）。ステップＳ１１において、記憶モジュール３０は、今回動物画像を取得した動物の識別子（動物の名称、管理番号、予め設定された整理番号、その他の動物を一意に特定可能な識別子等）と、動物画像とを対応付けて記憶する。なお、記憶モジュール３０は、動物画像のみを記憶してもよい。 The storage module 30 stores animal images (step S11). In step S11, the storage module 30 identifies the identifier of the animal that acquired the animal image this time (animal name, management number, preset reference number, identifier that can uniquely identify other animals, etc.), animal image, Are stored in association with each other. Note that the storage module 30 may store only animal images.
　診断結果取得モジュール２１は、今回取得した動物画像に該当する動物の診断結果を取得する（ステップＳ１２）。ステップＳ１２において、診断結果取得モジュール２１は、例えば、畜産カルテ等を記憶する図示していない外部コンピュータや、獣医師又は畜産関係者が保有する端末装置等から、診断結果を取得する。本実施形態における診断結果とは、例えば、発情の有無、疾病の特定、必要な処置の特定等である。 The diagnosis result acquisition module 21 acquires the diagnosis result of the animal corresponding to the animal image acquired this time (step S12). In step S12, the diagnosis result acquisition module 21 acquires a diagnosis result from, for example, an external computer (not shown) that stores livestock records or the like, a terminal device held by a veterinarian or a livestock related person, and the like. The diagnosis result in the present embodiment is, for example, the presence or absence of estrus, identification of a disease, identification of necessary treatment, and the like.
　学習モジュール４０は、記憶モジュール３０が記憶した動物画像と、診断結果取得モジュール２１が取得した診断結果とを対応付けて学習する（ステップＳ１３）。ステップＳ１３において、学習モジュール４０は、上述した、可視光画像、赤外線画像、レントゲン画像、ＣＴスキャン画像又は超音波画像の少なくとも一つを診断結果と対応付けて学習する。 The learning module 40 learns the animal image stored in the storage module 30 and the diagnosis result acquired by the diagnosis result acquisition module 21 in association with each other (step S13). In step S13, the learning module 40 learns at least one of the above-described visible light image, infrared image, X-ray image, CT scan image, or ultrasonic image in association with the diagnosis result.
　記憶モジュール３０は、学習した結果を、記憶する（ステップＳ１４）。 The storage module 30 stores the learned result (step S14).
　動物診断システム１は、上述した画像解析用学習処理を、十分な回数実行し、学習した結果を記憶する。 The animal diagnosis system 1 executes the above-described image analysis learning process a sufficient number of times and stores the learning result.
　以上が、画像解析用学習処理である。 The above is the image analysis learning process.
　［動物情報分析用学習処理］
　図５に基づいて、動物診断システム１が実行する動物情報分析用学習処理について説明する。図５は、コンピュータ１０が実行する動物情報分析用学習処理のフローチャートを示す図である。上述した各モジュールが実行する処理について、本処理に併せて説明する。 [Animal information analysis learning process]
Based on FIG. 5, the learning process for animal information analysis which the animal diagnosis system 1 performs is demonstrated. FIG. 5 is a flowchart of animal information analysis learning processing executed by the computer 10. Processing executed by each module described above will be described together with this processing.
　動物情報取得モジュール２２は、動物の動物情報を取得する（ステップＳ２０）。ステップＳ２０において、動物情報取得モジュール２２が取得する動物情報とは、例えば、各種センサが計測した歩数データ等の環境データ、疾病や発情の履歴データである畜産カルテ、血液検査の結果又はＢＣＳの少なくとも一つである。動物情報取得モジュール２２は、これらの動物情報を、対応する各種装置等から取得してもよいし、図示していないコンピュータ等を介して取得してもよい。以下の説明において、動物情報取得モジュール２２は、動物情報として、歩数データを取得するものとして説明する。 The animal information acquisition module 22 acquires animal information of animals (step S20). In step S20, the animal information acquired by the animal information acquisition module 22 includes, for example, environmental data such as step count data measured by various sensors, livestock medical records that are history data of diseases and estrus, blood test results, or at least BCS results. One. The animal information acquisition module 22 may acquire such animal information from various corresponding devices or the like, or may acquire it via a computer or the like (not shown). In the following description, the animal information acquisition module 22 will be described as acquiring step count data as animal information.
　記憶モジュール３０は、動物情報を記憶する（ステップＳ２１）。記憶モジュール３０は、今回動物情報を取得した動物の識別子（動物の名称、管理番号、予め設定された整理番号、その他の動物を一意に特定可能な識別子等）と、動物情報とを対応付けて記憶する。なお、記憶モジュール３０は、動物情報のみを記憶してもよい。 The storage module 30 stores animal information (step S21). The storage module 30 associates the identifier of the animal that acquired the animal information this time (the name of the animal, the management number, a preset reference number, an identifier that can uniquely identify other animals, etc.) and the animal information. Remember. Note that the storage module 30 may store only animal information.
　診断結果取得モジュール２１は、今回取得した動物情報に該当する動物の診断結果を取得する（ステップＳ２２）。ステップＳ２２において、診断結果取得モジュール２１は、例えば、畜産カルテ等を記憶する図示していない外部コンピュータや、獣医師又は畜産関係者が保有する端末装置等から、診断結果を取得する。本実施形態における診断結果とは、例えば、発情の有無、疾病の特定、必要な処置の特定等である。 The diagnosis result acquisition module 21 acquires the diagnosis result of the animal corresponding to the animal information acquired this time (step S22). In step S22, the diagnosis result acquisition module 21 acquires a diagnosis result from, for example, an external computer (not shown) that stores livestock records or the like, a terminal device held by a veterinarian or a livestock related person, and the like. The diagnosis result in the present embodiment is, for example, the presence or absence of estrus, identification of a disease, identification of necessary treatment, and the like.
　学習モジュール４０は、記憶モジュール３０が記憶した動物情報と、診断結果取得モジュール２１が取得した診断結果とを対応付けて学習する（ステップＳ２３）。ステップＳ２３において、学習モジュール４０は、上述した各種センサが計測した歩数データ等の環境データ、疾病や発情の履歴データである畜産カルテ、血液検査の結果又はＢＣＳの少なくとも一つを診断結果と対応付けて学習する。 The learning module 40 learns by associating the animal information stored in the storage module 30 with the diagnosis result acquired by the diagnosis result acquisition module 21 (step S23). In step S23, the learning module 40 associates at least one of environmental data such as step count data measured by the various sensors described above, livestock charts that are history data of diseases and estrus, blood test results, or BCS with the diagnosis results. To learn.
　記憶モジュール３０は、学習した結果を、記憶する（ステップＳ２４）。 The storage module 30 stores the learned result (step S24).
　動物診断システム１は、上述した動物情報分析用学習処理を、十分な回数実行し、学習した結果を記憶する。 The animal diagnosis system 1 executes the above-described learning process for animal information analysis a sufficient number of times and stores the learning result.
　以上が、動物情報分析用学習処理である。 The above is the learning process for animal information analysis.
　［動物診断処理］
　図６に基づいて、動物診断システム１が実行する動物診断処理について説明する。図６は、コンピュータ１０が実行する動物診断処理のフローチャートを示す図である。上述した各モジュールが実行する処理について、本処理に併せて説明する。なお、以下の説明において、動物診断システム１は、牛の可視光画像及び歩数データに基づいて、牛を診断するものとして説明する。 [Animal diagnosis processing]
Based on FIG. 6, the animal diagnosis process which the animal diagnosis system 1 performs is demonstrated. FIG. 6 is a flowchart of the animal diagnosis process executed by the computer 10. Processing executed by each module described above will be described together with this processing. In the following description, the animal diagnosis system 1 will be described as diagnosing a cow based on the visible light image of the cow and the number of steps data.
　動物画像取得モジュール２０は、動物の動物画像を取得する（ステップＳ３０）。ステップＳ３０において、動物画像取得モジュール２０が取得する動物画像とは、例えば、可視光画像、赤外線画像、レントゲン画像、ＣＴスキャン画像又は超音波画像の少なくとも一つである。動物画像取得モジュール２０は、これらの動物画像を、対応する撮像装置から取得してもよいし、図示していないコンピュータ等を介して取得してもよい。 The animal image acquisition module 20 acquires animal images of animals (step S30). In step S30, the animal image acquired by the animal image acquisition module 20 is, for example, at least one of a visible light image, an infrared image, an X-ray image, a CT scan image, or an ultrasound image. The animal image acquisition module 20 may acquire these animal images from a corresponding imaging device, or may acquire via a computer or the like (not shown).
　画像解析モジュール４１は、取得した動物画像を画像解析する（ステップＳ３１）。ステップＳ３１において、学習モジュール４０が学習した結果に基づいて、動物画像を画像解析する。画像解析モジュール４１は、今回取得した動物画像の特徴量（発情兆候、発情時における特徴的な行動、発情粘液等）を解析する。画像解析モジュール４１は、学習した結果から、診断を下すために必要な画像の部位や特徴等の複数の候補を解析する。画像解析モジュール４１は、例えば、動物画像から牛の特徴量を抽出し、追従、乗駕、休息中の規律、横臥中の突き行動、乗駕許容、粘液の流出、並び、争い、顎休め、フレーメン、乗駕検出器具を解析する。画像解析モジュール４１は、画像解析の結果として、必ずしも発情や疾病の特定を行うものに限らず、後述する診断のための情報を得ることのみであってもよい。例えば、画像解析モジュール４１は、診断のための予備情報を画像解析の結果から得てもよい。 The image analysis module 41 performs image analysis on the acquired animal image (step S31). In step S31, an animal image is image-analyzed based on the result learned by the learning module 40. The image analysis module 41 analyzes the feature amount of the animal image acquired this time (estrus sign, characteristic behavior at the time of estrus, estrus mucus, etc.). The image analysis module 41 analyzes a plurality of candidates such as image parts and features necessary for making a diagnosis from the learning result. The image analysis module 41 extracts, for example, a feature amount of a cow from an animal image, follows, rides, riding, discipline during rest, thrusting behavior during lying, allowance of riding, mucus outflow, alignment, fight, jaw rest, Analyze flamen and norigami detectors. The image analysis module 41 is not necessarily limited to identifying estrus or disease as a result of image analysis, but may only obtain information for diagnosis described later. For example, the image analysis module 41 may obtain preliminary information for diagnosis from the result of image analysis.
　動物情報取得モジュール２２は、動物の動物情報を取得する（ステップＳ３２）。ステップＳ３２において、動物情報取得モジュール２２は、動物情報として、各種センサが計測した歩数データ等の環境データ、疾病や発情の履歴データである畜産カルテ、血液検査の結果又はＢＣＳの少なくとも一つを取得する。動物情報取得モジュール２２は、これらの動物情報を、対応する各種装置等から取得してもよいし、図示していないコンピュータ等を介して取得してもよい。 The animal information acquisition module 22 acquires animal information of animals (step S32). In step S32, the animal information acquisition module 22 acquires, as animal information, at least one of environmental data such as step count data measured by various sensors, livestock charts that are history data of diseases and estrus, blood test results, or BCS. To do. The animal information acquisition module 22 may acquire such animal information from various corresponding devices or the like, or may acquire it via a computer or the like (not shown).
　動物情報分析モジュール４２は、取得した動物情報を分析する（ステップＳ３３）。ステップＳ３３において、動物情報分析モジュール４２は、学習モジュール４０が学習した結果に基づいて、動物情報を分析する。動物情報分析モジュール４２は、学習した結果から、診断を下すために必要な動物情報の複数の候補を分析する。動物情報分析モジュール４２は、例えば、発情期、呼吸器疾患、創傷性疾患、寄生虫病、繁殖障害、胃腸性疾患、代謝病等に動物が該当するか否かを分析する。動物情報分析モジュール４２は、例えば、動物情報として、歩数データを取得し、この歩数データに該当する症状として、発情期の疑いがあると分析する。動物情報分析モジュール４２は、分析の結果として、必ずしも、発情や疾病の特定を行うものに限らず、後述する診断のための情報を得ることのみであってもよい。例えば、動物情報分析モジュール４２は、診断のための予備情報を分析の結果から得てもよい。 The animal information analysis module 42 analyzes the acquired animal information (step S33). In step S33, the animal information analysis module 42 analyzes the animal information based on the result learned by the learning module 40. The animal information analysis module 42 analyzes a plurality of candidates for animal information necessary for making a diagnosis from the learned result. The animal information analysis module 42 analyzes whether or not an animal corresponds to, for example, estrus, respiratory disease, wound disease, parasitic disease, reproductive disorder, gastrointestinal disease, metabolic disease or the like. For example, the animal information analysis module 42 acquires step count data as animal information, and analyzes that there is a suspicion of the estrus period as a symptom corresponding to the step count data. The animal information analysis module 42 is not necessarily limited to the one that identifies estrus and disease as a result of the analysis, and may only obtain information for diagnosis described later. For example, the animal information analysis module 42 may obtain preliminary information for diagnosis from the analysis result.
　相関関係分析モジュール４３は、画像解析モジュール４１が画像解析した結果と、動物情報分析モジュール４２が分析した結果との相関関係を分析する（ステップＳ３４）。ステップＳ３４において、例えば、相関関係分析モジュール４３は、画像解析モジュール４１が画像解析した結果として、牛の動き、外陰部から発情粘液が流出、牛が一列に並んでいるとの解析結果と、動物情報分析モジュール４２が分析した結果として、発情期の疑いがあるとの分析結果との相関関係を分析する。ここで、相関関係分析モジュール４３は、相関関係をスコアとして分析する。すなわち、相関関係分析モジュール４３は、解析結果から得られた診断と、分析結果から得られた診断とがどの程度相関があるかをスコアとして評価する。相関関係分析モジュール４３は、上述した画像解析の結果得られた各項目の診断結果の其々に対して、分析の結果得られた各項目の診断結果との相関の程度を評価する。相関関係分析モジュール４３は、相関関係が高いものを高スコアとして評価し、相関関係が低いものを低スコアとして評価する。 The correlation analysis module 43 analyzes the correlation between the result of image analysis by the image analysis module 41 and the result of analysis by the animal information analysis module 42 (step S34). In step S34, for example, the correlation analysis module 43 analyzes the result of image analysis by the image analysis module 41, the analysis result that the cow's movement, the estrus mucus flowed out from the vulva, and the cows are lined up, As a result of the analysis by the information analysis module 42, the correlation with the analysis result that the estrus period is suspected is analyzed. Here, the correlation analysis module 43 analyzes the correlation as a score. That is, the correlation analysis module 43 evaluates as a score how much the diagnosis obtained from the analysis result and the diagnosis obtained from the analysis result have a correlation. The correlation analysis module 43 evaluates the degree of correlation between the diagnosis results of the respective items obtained as a result of the analysis and the diagnosis results of the respective items obtained as a result of the analysis. The correlation analysis module 43 evaluates a high correlation as a high score, and evaluates a low correlation as a low score.
　診断モジュール４４は、分析した相関関係の結果に基づいて、動物を診断する（ステップＳ３５）。ステップＳ３５において、診断モジュール４４は、分析した相関関係の結果として、スコアが最も高い評価の診断結果の組み合わせに基づいて、動物の発情や疾病を特定する。例えば、診断モジュール４４は、上述した画像解析の結果と、上述した動物情報の分析の結果と、その相関関係の分析の結果とに基づいて、今回の動物は、発情期であると特定する。 The diagnosis module 44 diagnoses an animal based on the analyzed correlation result (step S35). In step S35, the diagnosis module 44 identifies the estrus or disease of the animal based on the combination of the diagnosis results with the highest score as the result of the analyzed correlation. For example, the diagnosis module 44 specifies that the current animal is in the estrus period based on the above-described image analysis result, the above-described animal information analysis result, and the correlation analysis result.
　学習モジュール４０は、今回の診断結果を動物画像と動物情報とに対応付けて学習する（ステップＳ３６）。 The learning module 40 learns the current diagnosis result in association with the animal image and the animal information (step S36).
　記憶モジュール３０は、学習した結果を記憶する（ステップＳ３７）。コンピュータ１０は、次以降の診断の際に、今回学習した結果も加味した診断を行う。 The storage module 30 stores the learned result (step S37). The computer 10 performs a diagnosis in consideration of the result learned this time at the subsequent diagnosis.
　なお、コンピュータ１０は、診断結果を、図示してない獣医師又は畜産関係者が保有する端末装置等に送信してもよい。この場合、予め登録された端末装置からの要求や診断の結果、異常が発見された場合等において、この端末装置に対して、診断結果を送信すればよい。このとき、診断結果とともに、具体的な処置の方法、最寄りの対応施設の地図や連絡先等の情報、危険度等の各種情報を合わせて送信してもよい。この各種情報を受信した端末装置は、各種情報を表示又は音声等により通知してもよい。 Note that the computer 10 may transmit the diagnosis result to a terminal device or the like held by a veterinarian or animal husbandry not shown. In this case, when an abnormality is found as a result of a request or diagnosis from a previously registered terminal device, the diagnosis result may be transmitted to this terminal device. At this time, along with the diagnosis result, a specific method of treatment, information such as a map and contact information of the nearest corresponding facility, and various types of information such as a risk level may be transmitted together. The terminal device that has received the various types of information may notify the various types of information by display or voice.
　以上が、動物診断処理である。 The above is animal diagnosis processing.
　上述した手段、機能は、コンピュータ（ＣＰＵ、情報処理装置、各種端末を含む）が、所定のプログラムを読み込んで、実行することによって実現される。プログラムは、例えば、コンピュータからネットワーク経由で提供される（ＳａａＳ：ソフトウェア・アズ・ア・サービス）形態で提供される。また、プログラムは、例えば、フレキシブルディスク、ＣＤ（ＣＤ－ＲＯＭなど）、ＤＶＤ（ＤＶＤ－ＲＯＭ、ＤＶＤ－ＲＡＭなど）等のコンピュータ読取可能な記録媒体に記録された形態で提供される。この場合、コンピュータはその記録媒体からプログラムを読み取って内部記憶装置又は外部記憶装置に転送し記憶して実行する。また、そのプログラムを、例えば、磁気ディスク、光ディスク、光磁気ディスク等の記憶装置（記録媒体）に予め記録しておき、その記憶装置から通信回線を介してコンピュータに提供するようにしてもよい。 The means and functions described above are realized by a computer (including a CPU, an information processing apparatus, and various terminals) reading and executing a predetermined program. The program is provided, for example, in a form (SaaS: Software as a Service) provided from a computer via a network. The program is provided in a form recorded on a computer-readable recording medium such as a flexible disk, CD (CD-ROM, etc.), DVD (DVD-ROM, DVD-RAM, etc.). In this case, the computer reads the program from the recording medium, transfers it to the internal storage device or the external storage device, stores it, and executes it. The program may be recorded in advance in a storage device (recording medium) such as a magnetic disk, an optical disk, or a magneto-optical disk, and provided from the storage device to a computer via a communication line.
　以上、本発明の実施形態について説明したが、本発明は上述したこれらの実施形態に限るものではない。また、本発明の実施形態に記載された効果は、本発明から生じる最も好適な効果を列挙したに過ぎず、本発明による効果は、本発明の実施形態に記載されたものに限定されるものではない。 As mentioned above, although embodiment of this invention was described, this invention is not limited to these embodiment mentioned above. The effects described in the embodiments of the present invention are only the most preferable effects resulting from the present invention, and the effects of the present invention are limited to those described in the embodiments of the present invention. is not.
　１　動物診断システム１０　コンピュータ 1 Animal diagnosis system 10 Computer

Claims (6)

  1. 　動物を診断するコンピュータシステムであって、
    　前記動物の動物画像を取得する動物画像取得手段と、
    　取得した前記動物画像を画像解析する動物画像解析手段と、
    　前記動物の動物情報を取得する動物情報取得手段と、
    　取得した前記動物情報を分析する動物情報分析手段と、
    　前記画像解析した結果と、前記分析した結果との相関関係を分析する相関関係分析手段と、
    　分析した前記相関関係の結果に基づいて、前記動物を診断する動物診断手段と、
    　を備えることを特徴とするコンピュータシステム。     A computer system for diagnosing animals,
    Animal image obtaining means for obtaining an animal image of the animal;
    Animal image analysis means for image analysis of the acquired animal image;
    Animal information acquisition means for acquiring animal information of the animal;
    Animal information analysis means for analyzing the acquired animal information;
    Correlation analysis means for analyzing the correlation between the image analysis result and the analysis result;
    An animal diagnostic means for diagnosing the animal based on the analyzed correlation result;
    A computer system comprising:
  2. 　前記動物画像解析手段は、予め記憶した動物画像と診断結果とを対応付けて学習し、学習した結果に基づいて、前記動物画像を画像解析する、
    　ことを特徴とする請求項１に記載のコンピュータシステム。     The animal image analysis means learns by associating a pre-stored animal image with a diagnosis result, and performs image analysis of the animal image based on the learned result.
    The computer system according to claim 1.
  3. 　前記動物情報分析手段は、予め記憶した動物情報と診断結果とを対応付けて学習し、学習した結果に基づいて、前記動物情報を分析する、
    　ことを特徴とする請求項１に記載のコンピュータシステム。     The animal information analysis means learns by associating previously stored animal information and diagnosis results, and analyzes the animal information based on the learned results.
    The computer system according to claim 1.
  4. 　前記動物画像解析手段は、予め記憶した可視光画像、赤外線画像、レントゲン画像、ＣＴスキャン画像又は超音波画像の少なくとも一つを診断結果と対応付けて学習し、
    　前記動物情報分析手段は、予め記憶した歩数データ、畜産カルテ、血液検査又はＢＣＳの少なくとも一つを診断結果と対応付けて学習する、
    　ことを特徴とする請求項１に記載のコンピュータシステム。     The animal image analysis means learns at least one of a pre-stored visible light image, infrared image, X-ray image, CT scan image or ultrasonic image in association with a diagnostic result,
    The animal information analysis means learns by associating at least one of prestored step count data, livestock chart, blood test or BCS with a diagnosis result,
    The computer system according to claim 1.
  5. 　動物を診断する動物診断方法であって、
    　前記動物の動物画像を取得するステップと、
    　取得した前記動物画像を画像解析するステップと、
    　前記動物の動物情報を取得するステップと、
    　取得した前記動物情報を分析するステップと、
    　前記画像解析した結果と、前記分析した結果との相関関係を分析するステップと、
    　分析した前記相関関係の結果に基づいて、前記動物を診断するステップと、
    　を備えることを特徴とする動物診断方法。     An animal diagnostic method for diagnosing an animal,
    Obtaining an animal image of the animal;
    Analyzing the acquired animal image; and
    Obtaining animal information of the animal;
    Analyzing the acquired animal information;
    Analyzing the correlation between the image analysis result and the analysis result;
    Diagnosing the animal based on the analyzed correlation results;
    An animal diagnostic method comprising:
  6. 　動物を診断するコンピュータシステムに、
    　前記動物の動物画像を取得するステップ、
    　取得した前記動物画像を画像解析するステップ、
    　前記動物の動物情報を取得するステップ、
    　取得した前記動物情報を分析するステップ、
    　前記画像解析した結果と、前記分析した結果との相関関係を分析するステップ、
    　分析した前記相関関係の結果に基づいて、前記動物を診断するステップ、
    　を実行させるためのプログラム。     Computer systems for diagnosing animals
    Obtaining an animal image of the animal;
    Image analysis of the obtained animal image;
    Obtaining animal information of the animal;
    Analyzing the acquired animal information;
    Analyzing the correlation between the image analysis result and the analysis result;
    Diagnosing the animal based on the analyzed correlation results;
    A program for running
PCT/JP2017/013252 2017-03-30 2017-03-30 Computer system, method for diagnosing animal, and program WO2018179219A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2017/013252 WO2018179219A1 (en) 2017-03-30 2017-03-30 Computer system, method for diagnosing animal, and program
JP2018522159A JPWO2018179219A1 (en) 2017-03-30 2017-03-30 Computer system, animal diagnosis method and program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2017/013252 WO2018179219A1 (en) 2017-03-30 2017-03-30 Computer system, method for diagnosing animal, and program

Publications (1)

Publication Number Publication Date
WO2018179219A1 true WO2018179219A1 (en) 2018-10-04

Family

ID=63677266

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2017/013252 WO2018179219A1 (en) 2017-03-30 2017-03-30 Computer system, method for diagnosing animal, and program

Country Status (2)

Country Link
JP (1) JPWO2018179219A1 (en)
WO (1) WO2018179219A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021085313A1 (en) * 2019-10-28 2021-05-06 アニコムホールディングス株式会社 Disease prediction system, insurance fee calculation system, and disease prediction method
WO2023191043A1 (en) * 2022-03-31 2023-10-05 古河電気工業株式会社 Animal behavior recording device, animal behavior recording method, and program
WO2023191045A1 (en) * 2022-03-31 2023-10-05 古河電気工業株式会社 Information processing device, information processing method, and program

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013001678A1 (en) * 2011-06-30 2013-01-03 パナソニック株式会社 Apparatus for searching for analogous cases and apparatus for preparing relevance database, as well as method for searching for analogous cases and method for preparing relevance database
JP2015202208A (en) * 2014-04-14 2015-11-16 サイバーワオン合同会社 Portable terminal health condition examination device with camera

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006042962A (en) * 2004-08-02 2006-02-16 Matsushita Electric Ind Co Ltd Portable terminal equipment, interactive medical examination system using portable terminal equipment and medical examination data communication method
JP4599520B2 (en) * 2004-09-17 2010-12-15 オリンパス株式会社 Multispectral image processing method
CN101854855B (en) * 2007-09-25 2012-11-14 国立大学法人岐阜大学 Magnetic resonance imaging apparatus and its operating method, and diagnostic imaging system
JP2010256219A (en) * 2009-04-27 2010-11-11 Shiseido Co Ltd Risk evaluating method of "pimple"
CN105592792B (en) * 2013-10-23 2018-08-17 麦克赛尔控股株式会社 Surface state measures analytical information management system and surface state measures analysis approaches to IM

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013001678A1 (en) * 2011-06-30 2013-01-03 パナソニック株式会社 Apparatus for searching for analogous cases and apparatus for preparing relevance database, as well as method for searching for analogous cases and method for preparing relevance database
JP2015202208A (en) * 2014-04-14 2015-11-16 サイバーワオン合同会社 Portable terminal health condition examination device with camera

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
NIMURA YUKITAKA ET AL.: "A study on quantifying emphysema severity by using multi-class classifier based on combining CT image and spirometric m", IEICE TECHNICAL REPORT, vol. 110, no. 121, 2 July 2010 (2010-07-02), pages 57 - 62 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021085313A1 (en) * 2019-10-28 2021-05-06 アニコムホールディングス株式会社 Disease prediction system, insurance fee calculation system, and disease prediction method
EP4053762A4 (en) * 2019-10-28 2023-10-11 Anicom Holdings, Inc. Disease prediction system, insurance fee calculation system, and disease prediction method
WO2023191043A1 (en) * 2022-03-31 2023-10-05 古河電気工業株式会社 Animal behavior recording device, animal behavior recording method, and program
WO2023191045A1 (en) * 2022-03-31 2023-10-05 古河電気工業株式会社 Information processing device, information processing method, and program

Also Published As

Publication number Publication date
JPWO2018179219A1 (en) 2019-04-04

Similar Documents

Publication Publication Date Title
KR102243830B1 (en) System for providing integrated medical diagnostic service and method thereof
KR102289277B1 (en) Medical image diagnosis assistance apparatus and method generating evaluation score about a plurality of medical image diagnosis algorithm
WO2018179219A1 (en) Computer system, method for diagnosing animal, and program
US10832410B2 (en) Computer system, method, and program for diagnosing subject
JP6900345B2 (en) Diagnostic support device, diagnostic support system, display control device, diagnostic support method, and diagnostic support program
CN113990500A (en) Vital sign parameter monitoring method and device and storage medium
WO2018211687A1 (en) Computer system, subject diagnosis method, and support program
US20200160517A1 (en) Priority judgement device, method, and program
US20230084267A1 (en) System and a control method thereof
KR102534158B1 (en) Method and system for providing artificial intelligence diagnosis information for companion animals
WO2023095989A1 (en) Method and device for analyzing multimodality medical images for cerebral disease diagnosis
Elabbas et al. Classification of Otitis Media Infections using Image Processing and Convolutional Neural Network
KR102360615B1 (en) Medical image diagnosis assistance apparatus and method using a plurality of medical image diagnosis algorithm for endoscope images
JP7084357B2 (en) Diagnostic support device, diagnostic support method, and diagnostic support program
WO2018179419A1 (en) Computer system, animal diagnosis method, and program
Ikermane et al. Web-based autism screening using facial images and convolutional neural network
EP4230144A1 (en) Apparatus and method for providing dementia diagnosis assistance information
KR20240014123A (en) Apparatus and method for assisting sexually transmitted infections testing based on artificial intelligence and rapid diagnostic kit convergence
Dell A mobile point-of-care diagnostic system for low-resource settings
KR20240014122A (en) Apparatus and method for colorectal cancer screening using fecal occult blood test based on artificial intelligence and rapid diagnosis kit convergence
KR20240014128A (en) Apparatus and operation method for predicting and analyzing individual or collective immunity based on AI-Rapid Antigen Kit convergence
Hyde et al. The future of AI for livestock veterinary practice
KR20240014634A (en) Method of providing visual artificial intelligence diagnosis service of in vitro diagnostic kit and recording medium thereof
KR20240014126A (en) Apparatus and method for urine analysis based on artificial intelligence-quick diagnosis kit convergence
KR20240014124A (en) Apparatus and operation method for myocardial infarction prognosis based on artificial intelligence and rapid diagnosis kit convergence

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2018522159

Country of ref document: JP

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17902803

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17902803

Country of ref document: EP

Kind code of ref document: A1