WO2023026439A1 - Animal health management system - Google Patents

Animal health management system Download PDF

Info

Publication number
WO2023026439A1
WO2023026439A1 PCT/JP2021/031395 JP2021031395W WO2023026439A1 WO 2023026439 A1 WO2023026439 A1 WO 2023026439A1 JP 2021031395 W JP2021031395 W JP 2021031395W WO 2023026439 A1 WO2023026439 A1 WO 2023026439A1
Authority
WO
WIPO (PCT)
Prior art keywords
animal
learning model
answer
management system
question
Prior art date
Application number
PCT/JP2021/031395
Other languages
French (fr)
Japanese (ja)
Inventor
純 岡崎
Original Assignee
株式会社Peco
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Peco filed Critical 株式会社Peco
Priority to PCT/JP2021/031395 priority Critical patent/WO2023026439A1/en
Priority to JP2022504232A priority patent/JP7049030B1/en
Priority to JP2022042617A priority patent/JP2023033080A/en
Publication of WO2023026439A1 publication Critical patent/WO2023026439A1/en

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01K—ANIMAL HUSBANDRY; CARE OF BIRDS, FISHES, INSECTS; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
    • A01K29/00—Other apparatus for animal husbandry
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01K—ANIMAL HUSBANDRY; CARE OF BIRDS, FISHES, INSECTS; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
    • A01K67/00—Rearing or breeding animals, not otherwise provided for; New breeds of animals
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry

Definitions

  • the present invention relates to an animal health management system.
  • the present invention was made in view of such a background, and aims to provide a technology that allows breeders to quickly ascertain the health condition of animals.
  • the main invention of the present invention for solving the above problems is a system for managing the health of animals, wherein the answer to a first question related to the health condition of the animal is used as input data, and a veterinary medical worker designates A learning model storage unit that stores a learning model created by machine learning using a second question to be asked after the first question as teacher data, and an inquiry transmission unit that transmits the first question to the owner terminal , an answer receiving unit that receives the answer to the first question from the owner terminal, and an inference unit that gives the answer to the learning model to ask for the second question.
  • the breeder can grasp the health condition of the animal at an early stage.
  • FIG. 3 is a diagram showing an example hardware configuration of a management server 20;
  • FIG. 3 is a diagram showing an example of software configuration of a management server 20;
  • FIG. It is a figure explaining operation
  • a system for managing animal health comprising: It was created by machine learning using the answers to the first question related to the health condition of the animal as input data and the second question to be asked after the first question specified by the veterinarian as teacher data.
  • An animal health management system comprising: [Item 2] The animal health management system according to item 1, The learning model storage unit stores the learning model for each animal species, the reasoning unit providing the answer to the learning model corresponding to the animal species of the animal; An animal health management system characterized by: [Item 3] The animal health management system according to item 2, The learning model storage unit stores the learning model in association with at least one of animal species, breed, body weight, body weight rank, age and generation, the reasoning unit providing the answer to the learning model corresponding to the animal species of the animal and at least one of the breed, weight, weight rank, age, and age group of the animal; An animal health management system characterized by: [Item 4] The animal health management system according to item 1, The learning model is learned using the answers and animal species as the input data, the reasoning
  • a periodic medical examination system according to an embodiment of the present invention will be described below.
  • the regular check-up system of this embodiment is intended to support regular check-ups of animals.
  • the veterinary institution side periodically asks the owner of the animal such as a pet to determine the health condition of the animal, especially the necessity of visiting the hospital (triage). It is.
  • AI can be used to automatically determine the content of the medical interview.
  • the AI can be, for example, a classifier that determines which of the pre-prepared questions to ask next.
  • the AI can use a learning model trained on questions manually determined by a veterinarian, such as a veterinarian.
  • a learning model is created for each animal species, but it is also possible to provide animal species as input data for AI learning.
  • an owner can give an image of a specific part of an animal as input data.
  • FIG. 1 is a diagram showing an example of the overall configuration of the regular medical examination system of this embodiment.
  • the regular check-up system of this embodiment includes a management server 20 .
  • the management server 20 is communicably connected to each of the owner terminal 10 and the medical institution terminal 30 via the communication network 40 .
  • the communication network 40 is, for example, the Internet, and is constructed by a public telephone line network, a mobile telephone line network, a wireless communication path, Ethernet (registered trademark), or the like.
  • the owner terminal 10 is a computer operated by an animal caregiver (owner or person taking care of the animal).
  • Owner terminal 10 is, for example, a smart phone, a tablet computer, a personal computer, or the like. It is assumed that the owner terminal 10 has a camera (not shown) and is capable of taking pictures.
  • the medical institution terminal 30 is a computer operated by veterinary medical personnel (such as nurses and doctors at veterinary hospitals) at veterinary medical institutions.
  • Medical institution terminal 30 is, for example, a tablet computer.
  • the medical institution terminal 30 can be, for example, any computer such as a smart phone or a personal computer.
  • the management server 20 is a computer that conducts regular medical interviews and determines whether animal patients need to visit the hospital.
  • the management server 20 may be a general-purpose computer such as a workstation or personal computer, or a virtual computer logically implemented by cloud computing.
  • FIG. 2 is a diagram showing a hardware configuration example of the management server 20. As shown in FIG. Note that the illustrated configuration is an example, and other configurations may be employed.
  • the management server 2 includes a CPU 201 , a memory 202 , a storage device 203 , a communication interface 204 , an input device 205 and an output device 206 .
  • the storage device 203 is, for example, a hard disk drive, solid state drive, flash memory, etc., which stores various data and programs.
  • the communication interface 204 is an interface for connecting to the communication network 3, and includes, for example, an adapter for connecting to Ethernet (registered trademark), a modem for connecting to a public telephone network, and a wireless communication device for performing wireless communication.
  • the input device 205 is, for example, a keyboard, mouse, touch panel, button, microphone, etc. for inputting data.
  • the output device 206 is, for example, a display, printer, speaker, or the like that outputs data.
  • Each functional unit of the management server 20, which will be described later, is implemented by the CPU 201 reading a program stored in the storage device 203 into the memory 202 and executing it. is implemented as part of the storage provided by
  • FIG. 3 is a diagram showing a software configuration example of the management server 20.
  • the management server 20 includes an inquiry transmission unit 211, an answer reception unit 212, a hospital visit necessity transmission unit 214, a hospital visit necessity acquisition unit 215, a learning processing unit 216, an owner information storage unit 231, an animal information storage unit 232, and a question storage unit 233. , an inquiry storage unit 234 , an answer history storage unit 235 , a triage history storage unit 236 , and a learning model storage unit 237 .
  • the owner information storage unit 231 stores information (hereinafter referred to as owner information) regarding the owner of an animal (patient animal) undergoing veterinary medical care.
  • the owner information includes an owner ID that identifies the owner, name, address, and contact information. Information about the owner other than name, address and contact information may be included.
  • the animal information storage unit 232 stores information about patient animals (hereinafter referred to as animal information).
  • the animal information includes the name, species, and breed of the patient animal in association with an owner ID indicating the owner of the patient animal and an animal ID identifying the patient animal.
  • Animal information can also include age, weight and preventive history. The age may be calculated by including the date of birth instead of the age.
  • body weight and preventive history (whether or not vaccination such as vaccines and medicines have been taken within a predetermined period) can be obtained, for example, from the medical record information related to medical care and examination of the patient animal. can.
  • the management server 20 can periodically access a chart server that manages chart information, obtain body weight and preventive history, and update animal information.
  • the animal information can include various attributes of the patient animal.
  • the question storage unit 233 stores information related to questions about the animal's health condition (hereinafter referred to as question information).
  • the question information can include the content of the question in association with the question ID specifying the question and the animal species to which the question corresponds.
  • the content of the questions includes questions to be answered in free text, questions to be answered by selecting one or more from two or three or more choices, and answers with values (real numbers or integers) within a predetermined range. It can include questions such as scheduling questions.
  • the questions can be text data, for example, and can include images and sounds.
  • the question includes a question to be answered with an image of a specific site.
  • the medical inquiry storage unit 234 stores the transmitted information regarding one medical inquiry (hereinafter referred to as medical inquiry information).
  • the medical inquiry information includes, in association with the medical inquiry ID identifying the medical inquiry, the date and time when the medical inquiry was sent, the animal ID indicating the animal to be medically examined, and the question ID indicating the question to be included in the medical inquiry.
  • a plurality of question IDs may be set for one inquiry ID.
  • the answer history storage unit 235 stores the history of answers from the owner to questions related to medical interviews.
  • the answer history stored by the answer history storage unit 235 includes a question ID indicating a question and an answer to the question in association with an interview ID, an animal ID, and the date and time when the interview was conducted (or the answer was received). be It should be noted that sets of question IDs and answers corresponding to the number of questions can be registered for one inquiry ID.
  • the triage history storage unit 236 stores a history (hereinafter referred to as triage history).
  • the diagnosis history includes an interview ID, necessity of visiting the hospital, actions, and comments. Whether a visit to the hospital is necessary or not is either necessary or unnecessary.
  • the action is intervention information for the animal, and is information indicating actions that the animal should take, such as "Let's take a walk" and "Let's feed”. Action options can be preconfigured. The action may include that a hospital visit is required.
  • the comment is a comment on the interview result by the veterinarian.
  • a comment can be text data, for example. Comments may include possible illnesses.
  • the learning model storage unit 237 stores a learning model for determining the next interview content (questions to be included in the interview) based on the interview results.
  • the learning model storage unit 237 can store learning models in association with animal species.
  • the animal species may be given as input data (feature amount) of the learning model.
  • the learning model storage unit 237 can also store learning models in association with animal species and breeds. For example, even for the same dog, the question to be asked may differ between a large dog and a small dog. Therefore, learning models can be stored in association with weight ranks (ranges determined by maximum and minimum) in addition to or in place of animal species and breeds. In addition to or in place of at least one of animal species and breeds and body weight, learning models can also be stored in association with ages (age ranges).
  • the animal species and breed may be given as input data (feature amounts) of the learning model.
  • at least one of weight, weight rank, age, and generation may be included as a feature value to be given to the learning model.
  • past interview results can be included as a feature quantity to be given to the learning model.
  • a time lag time information indicating how long ago the interview was or how many days ago from the present time
  • Questions to ask next determined by veterinarians can be employed as training data provided to train the learning model. That is, it is possible to use machine learning to learn the content of the next question to be asked according to the answers to the past questions, which were determined by the veterinary medical staff, and use it as a learning model.
  • the learning model is created and updated by the learning processing unit 216, which will be described later.
  • the inquiry transmission unit 211 periodically transmits an inquiry to the owner terminal 10.
  • the inquiry sending unit 211 can create one inquiry by selecting one or a plurality of questions stored in the question storage unit 233 corresponding to the animal species of the patient animal.
  • the medical inquiry sending unit 211 can, for example, randomly select a predetermined number of questions that satisfy the presentation conditions from among the questions corresponding to the animal species of the patient animal.
  • the medical inquiry sending unit 211 may select a question according to a predetermined rule set in advance, for example.
  • the answer receiving unit 212 receives answers to each medical interview question from the owner terminal 10 .
  • the answer receiving unit 212 can accept uploading of an image when the question includes a question to be answered with an image of a specific part.
  • the reply receiving section 212 can register the received reply in the reply history storage section 235 .
  • the hospital visit necessity acquisition unit 215 can send a message to the medical institution terminal 30 requesting a determination of the necessity of a hospital visit.
  • the hospital visit necessity determination unit 213 can include the result of medical examination (answers to questions, that is, selection results of options, images, etc.) in a message and transmit it to the medical institution terminal 30 .
  • the medical institution terminal 30 can output the medical interview result and accept input from medical personnel such as a veterinarian as to whether or not a visit to the hospital is necessary. In the medical institution terminal 30, it is also possible to input intervention information (actions) and comments for the animal according to the interview results.
  • the hospital visit necessity acquisition unit 215 can create a triage history including the hospital visit necessity acquired from the medical institution terminal 30 and an interview ID indicating an interview corresponding to the interview result, and register the triage history in the triage history storage unit 236. can. Further, when actions and comments are transmitted from the medical institution terminal 30, the actions and comments can be included in the triage history.
  • the hospital visit necessity transmission unit 214 transmits to the owner terminal 10 the necessity of a hospital visit determined based on the results of the interview.
  • the learning processing unit 216 creates and updates a learning model for determining the inquiry content. For example, if the interview storage unit 234 stores an interview prepared by a veterinarian, the learning processing unit 216 reads out the interview content (question information) corresponding to each animal species. As input data, machine learning is performed using the question ID corresponding to the inquiry sent next to the inquiry (the oldest date and time among the inquiry information with the same animal ID and later date and time) as teacher data. A learning model created or updated through learning can be registered in the learning model storage unit 237 . Since a medical interview can include a plurality of questions, learning can be performed using each of the questions included in the following medical interview after a certain medical interview as teacher data.
  • the learning processing unit 216 can update the learning model periodically or at timing determined by a predetermined rule. In this case, the learning processing unit 216 can transmit the content of the interview and its answer to the medical institution terminal 30, receive input of the content of the next question (question ID) to be asked from the veterinary medical staff, and input the answer. Machine learning can be performed using the question ID input by the veterinarian as teacher data to update the learning model.
  • FIG. 4 is a diagram for explaining the operation of the periodic medical examination system of this embodiment.
  • the management server 20 creates an inquiry (S301).
  • the medical interview can be prepared by reading out a predetermined number of questions that correspond to the animal species of the patient animal and satisfy the provision conditions among the questions stored in the question storage unit 233 .
  • the management server 20 transmits the created medical interview to the owner terminal 10 (S302).
  • An interview is displayed on the owner terminal 10.
  • the medical interview may be conducted, for example, in a chat format, or may be conducted using a form on a web page.
  • a camera included in the owner terminal 10 can be activated to obtain an image captured by the camera as an answer.
  • the owner terminal 10 transmits the inputted answer to the management server 20 .
  • the management server 20 can receive a response from the owner terminal 10 (S303) and register the received response in the response history storage unit 235 (S304).
  • the management server 20 transmits a message with an answer set to the medical institution terminal 30, and inquires whether or not it is necessary to visit the hospital (S305).
  • the medical institution terminal 30 receives an input of whether or not to visit the hospital from the medical personnel such as a veterinarian, and transmits the input to the management server 20.
  • the management server 20 receives the necessity of visiting the hospital from the medical institution terminal 30, and determines whether or not to visit the hospital.
  • the information is registered in the triage history storage unit 236 (S306), and the necessity of visiting the hospital is transmitted to the owner terminal 10 (S307).
  • the management server 20 periodically repeats the processing from S301 until the period for sending periodic medical interviews ends (S308: NO). Before proceeding to S301, the management server 20 can give the answer to the medical inquiry to the learning model corresponding to the animal species, determine the question to be sent for the next medical inquiry, and register it in the medical inquiry storage unit 234 (S309).
  • the medical inquiry information may not set the date and time, or may set the date and time when the next medical inquiry is scheduled to be sent.
  • the veterinary institution can proactively send medical interviews to the breeders of patient animals periodically to confirm the health condition of the patient animals.
  • AI learning model
  • AI can be used to automatically determine the content of the next inquiry based on the result of the inquiry.
  • a learning model is created for each animal species, but one or more learning models may be used as a whole, and the animal species may be given as a feature amount.
  • the learning model can include an image captured by the owner terminal 10 in the feature amount of the learning model.
  • the learning model can include an image captured by the owner terminal 10 in the feature amount of the learning model.
  • test results at veterinary medical institutions may be given as input data (feature values) for the learning model.
  • the medical chart information is managed by the management server 20, or the medical chart server that manages the medical chart information is accessed to obtain the test results included in the medical chart information. can.
  • the time lag can be used as input data together with the inspection results.
  • the learning model is a classifier that determines the question to be sent next from among the given questions. or a transformer.
  • a classifier for determining the necessity of visiting the hospital can be stored in the learning model storage unit for each animal species.
  • a classifier using animal species as input data (feature amount) may be stored.
  • the input data (feature amount) of the hospital visit necessity classifier can be an answer to an interview.

Abstract

[Problem] To make it possible for an owner to recognize the health status of an animal at an early stage. [Solution] A system for managing animal health characterized in comprising: a learning model storage unit storing a learning model created by machine learning using a response to a first question related to the health status of an animal as input data, and a second question to be asked after the first question specified by a veterinary worker as teacher data; a questionnaire submission unit submitting the first question to an owner terminal; a response reception unit receiving a response to the first question from the owner terminal; and an inference unit providing the response to the learning model to obtain the second question.

Description

動物健康管理システムanimal health management system
　本発明は、動物健康管理システムに関する。 The present invention relates to an animal health management system.
　ネットワークを介して問診を行うことが行われている（特許文献１参照）。 Medical interviews are conducted via networks (see Patent Document 1).
国際公開２００４／１０４８８０号WO 2004/104880
　一般に問診は患者が自覚症状を感じたときに行われる。しかしながら、獣医療においては飼育者が健康状態を把握する必要がある。 In general, an interview is conducted when the patient feels subjective symptoms. However, in veterinary medicine, it is necessary for breeders to grasp their health conditions.
　本発明はこのような背景を鑑みてなされたものであり、飼育者が動物の健康状態を早期に把握することができる技術を提供することを目的とする。 The present invention was made in view of such a background, and aims to provide a technology that allows breeders to quickly ascertain the health condition of animals.
　上記課題を解決するための本発明の主たる発明は、動物の健康を管理するシステムであって、前記動物の健康状態に関連する第１の質問に対する回答を入力データとし、獣医療従事者が指定した前記第１の質問の次に行うべき第２の質問を教師データとして機械学習により作成された学習モデルを記憶する学習モデル記憶部と、前記第１の質問を飼い主端末に送信する問診送信部と、前記飼い主端末から前記第１の質問に対する前記回答を受信する回答受信部と、前記回答を前記学習モデルに与えて前記第２の質問を求める推論部と、を備えることを特徴とする。 The main invention of the present invention for solving the above problems is a system for managing the health of animals, wherein the answer to a first question related to the health condition of the animal is used as input data, and a veterinary medical worker designates A learning model storage unit that stores a learning model created by machine learning using a second question to be asked after the first question as teacher data, and an inquiry transmission unit that transmits the first question to the owner terminal , an answer receiving unit that receives the answer to the first question from the owner terminal, and an inference unit that gives the answer to the learning model to ask for the second question.
　その他本願が開示する課題やその解決方法については、発明の実施形態の欄及び図面により明らかにされる。 Other problems disclosed by the present application and their solutions will be clarified in the section of the embodiment of the invention and the drawings.
　本発明によれば、飼育者が動物の健康状態を早期に把握することができる。 According to the present invention, the breeder can grasp the health condition of the animal at an early stage.
本実施形態の定期検診システムの全体構成例を示す図である。BRIEF DESCRIPTION OF THE DRAWINGS It is a figure which shows the whole structural example of the periodical medical examination system of this embodiment. 管理サーバ２０のハードウェア構成例を示す図である。3 is a diagram showing an example hardware configuration of a management server 20; FIG. 管理サーバ２０のソフトウェア構成例を示す図である。3 is a diagram showing an example of software configuration of a management server 20; FIG. 本実施形態の定期検診システムの動作を説明する図である。It is a figure explaining operation|movement of the periodical medical examination system of this embodiment.
＜発明の概要＞
　本発明の実施形態の内容を列記して説明する。本発明は、たとえば、以下のような構成を備える。
［項目１］
　動物の健康を管理するシステムであって、
　前記動物の健康状態に関連する第１の質問に対する回答を入力データとし、獣医療従事者が指定した前記第１の質問の次に行うべき第２の質問を教師データとして機械学習により作成された学習モデルを記憶する学習モデル記憶部と、
　前記第１の質問を飼い主端末に送信する問診送信部と、
　前記飼い主端末から前記第１の質問に対する前記回答を受信する回答受信部と、
　前記回答を前記学習モデルに与えて前記第２の質問を求める推論部と、
　を備えることを特徴とする動物健康管理システム。
［項目２］
　項目１に記載の動物健康管理システムであって、
　前記学習モデル記憶部は、動物種ごとに前記学習モデルを記憶し、
　前記推論部は、前記動物の前記動物種に対応する前記学習モデルに対して前記回答を与えること、
　を特徴とする動物健康管理システム。
［項目３］
　項目２に記載の動物健康管理システムであって、
　前記学習モデル記憶部は、動物種と、品種、体重、体重ランク、年齢及び年代の少なくともいずれかとに対応付けて前記学習モデルを記憶し、
　前記推論部は、前記動物の前記動物種と、前記動物の前記品種、前記体重、前記体重ランク、前記年齢及び前記年代の少なくともいずれかとに対応する前記学習モデルに対して前記回答を与えること、
　を特徴とする動物健康管理システム。
［項目４］
　項目１に記載の動物健康管理システムであって、
　前記学習モデルは、前記回答及び動物種を前記入力データとして学習されたものであり、
　前記推論部は、前記動物の前記動物種と前記回答とを前記学習モデルに与えること、
　を特徴とする動物健康管理システム。
［項目５］
　項目４に記載の動物健康管理システムであって、
　前記学習モデルは、前記回答と、前記動物種と、品種、体重、体重ランク、年齢及び年代の少なくともいずれかとを前記入力データとして学習されたものであり、
　前記推論部は、前記動物の前記動物種と、前記回答と、前記動物の前記品種、前記体重、前記体重ランク、前記年齢及び前記年代の少なくともいずれかとを前記学習モデルに与えること、
　を特徴とする動物健康管理システム。
［項目６］
　項目１ないし５のいずれか１項に記載の動物健康管理システムであって、
　前記学習モデルは、前記獣医療従事者が判断した前記動物の前記健康状態をさらに前記入力データに加えて学習されたものであり、
　前記回答を前記獣医療従事者に対して出力し、前記獣医療従事者から前記健康状態の入力を受け付ける健康状態取得部をさらに備え、
　前記推論部は、前記学習モデルに、入力された前記健康状態をさらに与えること、
　を特徴とする動物健康管理システム。
［項目７］
　項目１ないし６のいずれか１項に記載の動物健康管理システムであって、
　前記学習モデルは、前記動物についての検査結果をさらに前記入力データに加えて学習されたものであり、
　前記動物についての前記検査結果を取得する検査結果取得部をさらに備え、
　前記推論部は、前記学習モデルに、取得した前記検査結果をさらに与えること、
　を特徴とする動物健康管理システム。
［項目８］
　項目１ないし７のいずれか１項に記載の動物健康管理システムであって、
　前記飼い主端末から受信した前記回答を記憶する回答履歴記憶部をさらに備え、
　前記学習モデルは、タイムラグを含む前記回答を前記入力データに含んで学習されたものであり、
　前記推論部は、前記回答履歴記憶部に記憶されている前記回答及び現時点からの前記タイムラグを前記学習モデルに与えること、
　を特徴とする動物健康管理システム。 <Overview of the invention>
The contents of the embodiments of the present invention are listed and explained. The present invention has, for example, the following configurations.
[Item 1]
A system for managing animal health, comprising:
It was created by machine learning using the answers to the first question related to the health condition of the animal as input data and the second question to be asked after the first question specified by the veterinarian as teacher data. a learning model storage unit that stores learning models;
an inquiry transmission unit that transmits the first question to the owner terminal;
an answer receiving unit that receives the answer to the first question from the owner terminal;
a reasoning unit that provides the answer to the learning model to ask the second question;
An animal health management system comprising:
[Item 2]
The animal health management system according to item 1,
The learning model storage unit stores the learning model for each animal species,
the reasoning unit providing the answer to the learning model corresponding to the animal species of the animal;
An animal health management system characterized by:
[Item 3]
The animal health management system according to item 2,
The learning model storage unit stores the learning model in association with at least one of animal species, breed, body weight, body weight rank, age and generation,
the reasoning unit providing the answer to the learning model corresponding to the animal species of the animal and at least one of the breed, weight, weight rank, age, and age group of the animal;
An animal health management system characterized by:
[Item 4]
The animal health management system according to item 1,
The learning model is learned using the answers and animal species as the input data,
the reasoning unit providing the species of the animal and the answer to the learning model;
An animal health management system characterized by:
[Item 5]
The animal health management system according to item 4,
The learning model is learned using at least one of the answer, the animal species, breed, weight, weight rank, age and age group as the input data,
The reasoning unit provides the animal species of the animal, the answer, and at least one of the breed, the weight, the weight rank, the age, and the age group of the animal to the learning model;
An animal health management system characterized by:
[Item 6]
The animal health management system according to any one of items 1 to 5,
The learning model is learned by adding the health condition of the animal determined by the veterinarian to the input data,
further comprising a health condition acquisition unit that outputs the answer to the veterinary medical staff and receives an input of the health condition from the veterinary medical staff;
The inference unit further provides the input health condition to the learning model;
An animal health management system characterized by:
[Item 7]
The animal health management system according to any one of items 1 to 6,
The learning model is learned by adding test results of the animal to the input data,
further comprising a test result acquisition unit that acquires the test results of the animal;
The inference unit further provides the acquired inspection result to the learning model;
An animal health management system characterized by:
[Item 8]
The animal health management system according to any one of items 1 to 7,
further comprising an answer history storage unit that stores the answer received from the owner terminal;
The learning model is learned by including the answer including the time lag in the input data,
the inference unit providing the answer stored in the answer history storage unit and the time lag from the current time to the learning model;
An animal health management system characterized by:
＜システムの概要＞
　以下、本発明の一実施形態に係る定期検診システムについて説明する。本実施形態の定期検診システムは、動物の定期検診を支援しようとするものである。 <Overview of the system>
A periodic medical examination system according to an embodiment of the present invention will be described below. The regular check-up system of this embodiment is intended to support regular check-ups of animals.
　本実施形態の定期検診システムは、獣医療機関側からペット等の動物の飼い主に対して定期的な問診を行うことにより、動物の健康状態、とくに来院の要否（トリアージ）を判断しようとするものである。本実施形態では、ＡＩを用いて問診の内容を自動的に決定することができる。ＡＩは、例えば、事前に準備されている質問のうち次に行うべき質問を決定する分類器とすることができる。ＡＩには、獣医師等の獣医療従事者が手動で決定した質問を学習した学習モデルを用いることができる。また、本実施形態の定期検診システムでは、学習モデルは動物種ごとに作成されるものとするが、ＡＩの学習にあたり動物種を入力データとして与えるようにすることもできる。また、ＡＩの学習にあたり、飼い主が動物の特定部位を撮影した画像を入力データとして与えることができる。 In the regular medical examination system of this embodiment, the veterinary institution side periodically asks the owner of the animal such as a pet to determine the health condition of the animal, especially the necessity of visiting the hospital (triage). It is. In this embodiment, AI can be used to automatically determine the content of the medical interview. The AI can be, for example, a classifier that determines which of the pre-prepared questions to ask next. The AI can use a learning model trained on questions manually determined by a veterinarian, such as a veterinarian. In addition, in the periodic medical examination system of this embodiment, a learning model is created for each animal species, but it is also possible to provide animal species as input data for AI learning. Also, when AI learns, an owner can give an image of a specific part of an animal as input data.
　図１は、本実施形態の定期検診システムの全体構成例を示す図である。本実施形態の定期検診システムは、管理サーバ２０を含んで構成される。管理サーバ２０は、飼い主端末１０および医療機関端末３０とのそれぞれに対して通信ネットワーク４０を介して通信可能に接続される。通信ネットワーク４０は、たとえばインターネットであり、公衆電話回線網や携帯電話回線網、無線通信路、イーサネット（登録商標）などにより構築される。 FIG. 1 is a diagram showing an example of the overall configuration of the regular medical examination system of this embodiment. The regular check-up system of this embodiment includes a management server 20 . The management server 20 is communicably connected to each of the owner terminal 10 and the medical institution terminal 30 via the communication network 40 . The communication network 40 is, for example, the Internet, and is constructed by a public telephone line network, a mobile telephone line network, a wireless communication path, Ethernet (registered trademark), or the like.
　飼い主端末１０は、動物の介護者（飼い主または世話をしている人）が操作するコンピュータである。飼い主端末１０は、たとえば、スマートフォンやタブレットコンピュータ、パーソナルコンピュータなどである。飼い主端末１０は、カメラ（不図示）を備え、撮影が可能となっていることを想定する。 The owner terminal 10 is a computer operated by an animal caregiver (owner or person taking care of the animal). Owner terminal 10 is, for example, a smart phone, a tablet computer, a personal computer, or the like. It is assumed that the owner terminal 10 has a camera (not shown) and is capable of taking pictures.
　医療機関端末３０は、獣医療機関での獣医療関係者（動物病院の看護師や医師などが）が操作するコンピュータである。医療機関端末３０は、たとえば、タブレットコンピュータである。医療機関端末３０は、たとえば、スマートフォンやパーソナルコンピュータなど、任意のコンピュータとすることができる。 The medical institution terminal 30 is a computer operated by veterinary medical personnel (such as nurses and doctors at veterinary hospitals) at veterinary medical institutions. Medical institution terminal 30 is, for example, a tablet computer. The medical institution terminal 30 can be, for example, any computer such as a smart phone or a personal computer.
　管理サーバ２０は、定期的な問診を行い、動物患者の来院要否を判断するコンピュータである。管理サーバ２０は、たとえばワークステーションやパーソナルコンピュータのような汎用コンピュータとしてもよいし、あるいはクラウド・コンピューティングによって論理的に実現される仮想コンピュータとしてもよい。 The management server 20 is a computer that conducts regular medical interviews and determines whether animal patients need to visit the hospital. The management server 20 may be a general-purpose computer such as a workstation or personal computer, or a virtual computer logically implemented by cloud computing.
　図２は、管理サーバ２０のハードウェア構成例を示す図である。なお、図示された構成は一例であり、これ以外の構成を有していてもよい。管理サーバ２は、ＣＰＵ２０１、メモリ２０２、記憶装置２０３、通信インタフェース２０４、入力装置２０５、出力装置２０６を備える。記憶装置２０３は、各種のデータやプログラムを記憶する、例えばハードディスクドライブやソリッドステートドライブ、フラッシュメモリなどである。通信インタフェース２０４は、通信ネットワーク３に接続するためのインタフェースであり、例えばイーサネット（登録商標）に接続するためのアダプタ、公衆電話回線網に接続するためのモデム、無線通信を行うための無線通信機、シリアル通信のためのＵＳＢ（Universal Serial Bus）コネクタやＲＳ２３２Ｃコネクタなどである。入力装置２０５は、データを入力する、例えばキーボードやマウス、タッチパネル、ボタン、マイクロフォンなどである。出力装置２０６は、データを出力する、例えばディスプレイやプリンタ、スピーカなどである。後述する管理サーバ２０の各機能部は、ＣＰＵ２０１が記憶装置２０３に記憶されているプログラムをメモリ２０２に読み出して実行することにより実現され、管理サーバ２０の各記憶部は、メモリ２０２及び記憶装置２０３が提供する記憶領域の一部として実現される。 FIG. 2 is a diagram showing a hardware configuration example of the management server 20. As shown in FIG. Note that the illustrated configuration is an example, and other configurations may be employed. The management server 2 includes a CPU 201 , a memory 202 , a storage device 203 , a communication interface 204 , an input device 205 and an output device 206 . The storage device 203 is, for example, a hard disk drive, solid state drive, flash memory, etc., which stores various data and programs. The communication interface 204 is an interface for connecting to the communication network 3, and includes, for example, an adapter for connecting to Ethernet (registered trademark), a modem for connecting to a public telephone network, and a wireless communication device for performing wireless communication. , USB (Universal Serial Bus) connector and RS232C connector for serial communication. The input device 205 is, for example, a keyboard, mouse, touch panel, button, microphone, etc. for inputting data. The output device 206 is, for example, a display, printer, speaker, or the like that outputs data. Each functional unit of the management server 20, which will be described later, is implemented by the CPU 201 reading a program stored in the storage device 203 into the memory 202 and executing it. is implemented as part of the storage provided by
＜管理サーバ２０のソフトウェア構成＞
　図３は、管理サーバ２０のソフトウェア構成例を示す図である。管理サーバ２０は、問診送信部２１１、回答受信部２１２、来院要否送信部２１４、来院要否取得部２１５、学習処理部２１６、飼い主情報記憶部２３１、動物情報記憶部２３２、質問記憶部２３３、問診記憶部２３４、回答履歴記憶部２３５、トリアージ履歴記憶部２３６、学習モデル記憶部２３７を備える。 <Software Configuration of Management Server 20>
FIG. 3 is a diagram showing a software configuration example of the management server 20. As shown in FIG. The management server 20 includes an inquiry transmission unit 211, an answer reception unit 212, a hospital visit necessity transmission unit 214, a hospital visit necessity acquisition unit 215, a learning processing unit 216, an owner information storage unit 231, an animal information storage unit 232, and a question storage unit 233. , an inquiry storage unit 234 , an answer history storage unit 235 , a triage history storage unit 236 , and a learning model storage unit 237 .
　飼い主情報記憶部２３１は、獣医療機関を受診する動物（患者動物）の飼い主に関する情報（以下、飼い主情報という。）を記憶する。飼い主情報には、飼い主を特定する飼い主ＩＤ、氏名、住所、連絡先を含む。氏名、住所、連絡先以外の飼い主に関する情報を含めてもよい。 The owner information storage unit 231 stores information (hereinafter referred to as owner information) regarding the owner of an animal (patient animal) undergoing veterinary medical care. The owner information includes an owner ID that identifies the owner, name, address, and contact information. Information about the owner other than name, address and contact information may be included.
　動物情報記憶部２３２は、患者動物に関する情報（以下、動物情報という。）を記憶する。動物情報には、患者動物の飼い主を示す飼い主ＩＤおよび患者動物を特定する動物ＩＤに対応付けて、患者動物の名前、動物種、品種が含まれる。また、動物情報には、年齢、体重、予防履歴を含めることができる。年齢に代えて生年月日を含めるようにして年齢を算出可能としてもよい。また、体重及び予防履歴（所定期間内にワクチン等の予防接種を受けたり薬を飲んだりしたか否か）は、例えば、当該患者動物の診療、検査に関するカルテ情報から取得するようにすることもできる。例えば、管理サーバ２０が定期的にカルテ情報を管理するカルテサーバにアクセスして、体重及び予防履歴を取得して動物情報を更新するようにすることができる。なお、動物情報には、患者動物の各種属性を含めることができる。 The animal information storage unit 232 stores information about patient animals (hereinafter referred to as animal information). The animal information includes the name, species, and breed of the patient animal in association with an owner ID indicating the owner of the patient animal and an animal ID identifying the patient animal. Animal information can also include age, weight and preventive history. The age may be calculated by including the date of birth instead of the age. In addition, body weight and preventive history (whether or not vaccination such as vaccines and medicines have been taken within a predetermined period) can be obtained, for example, from the medical record information related to medical care and examination of the patient animal. can. For example, the management server 20 can periodically access a chart server that manages chart information, obtain body weight and preventive history, and update animal information. The animal information can include various attributes of the patient animal.
　質問記憶部２３３は、動物の健康状態についての質問に係る情報（以下、質問情報という。）を記憶する。質問情報には、質問を特定する質問ＩＤと、当該質問が該当する動物種とに対応付けて、質問内容を含めることができる。質問内容には、フリーテキストでの回答を予定する質問、２択または３択以上の選択肢から１つ以上を選択する回答を予定する質問、所定の範囲内での値（実数または整数）の回答を予定する質問などを含めることができる。質問は、例えば、テキストデータとすることができ、画像や音声を含めるようにすることもできる。本実施形態では、質問には、特定の部位を撮影した画像により回答するべき質問が含まれるものとする。 The question storage unit 233 stores information related to questions about the animal's health condition (hereinafter referred to as question information). The question information can include the content of the question in association with the question ID specifying the question and the animal species to which the question corresponds. The content of the questions includes questions to be answered in free text, questions to be answered by selecting one or more from two or three or more choices, and answers with values (real numbers or integers) within a predetermined range. It can include questions such as scheduling questions. The questions can be text data, for example, and can include images and sounds. In this embodiment, the question includes a question to be answered with an image of a specific site.
　問診記憶部２３４は、送信された１回の問診に関する情報（以下、問診情報という。）を記憶する。問診情報には、問診を識別する問診ＩＤに対応付けて、問診が送信された日時、問診対象とした動物を示す動物ＩＤ、及び問診に含める質問を示す質問ＩＤを含む。１つの問診ＩＤに対して質問ＩＤは複数設定されてよい。 The medical inquiry storage unit 234 stores the transmitted information regarding one medical inquiry (hereinafter referred to as medical inquiry information). The medical inquiry information includes, in association with the medical inquiry ID identifying the medical inquiry, the date and time when the medical inquiry was sent, the animal ID indicating the animal to be medically examined, and the question ID indicating the question to be included in the medical inquiry. A plurality of question IDs may be set for one inquiry ID.
　回答履歴記憶部２３５は、問診に係る質問に対する飼い主からの回答の履歴を記憶する。回答履歴記憶部２３５が記憶する回答履歴には、問診ＩＤ、動物ＩＤ及び問診を行った（又は回答を受け付けた）日時に対応付けて、質問を示す質問ＩＤと、当該質問に対する回答とが含まれる。なお、１つの問診ＩＤに対して、質問の数だけ質問ＩＤ及び回答のセットが登録されうる。 The answer history storage unit 235 stores the history of answers from the owner to questions related to medical interviews. The answer history stored by the answer history storage unit 235 includes a question ID indicating a question and an answer to the question in association with an interview ID, an animal ID, and the date and time when the interview was conducted (or the answer was received). be It should be noted that sets of question IDs and answers corresponding to the number of questions can be registered for one inquiry ID.
　トリアージ履歴記憶部２３６は、問診結果（質問に対する回答）に対して獣医療従事者（本実施形態では獣医師を想定する。）が判断した動物患者の来院要否の判断に係る履歴（以下、トリアージ履歴）を記憶する。診断履歴には、問診ＩＤ、来院要否、アクション及びコメントが含まれる。来院要否は、必要又は不要のいずれかである。アクションは、動物に対する介入情報であり、例えば、「散歩をさせましょう」「食事をさせましょう」といった、動物が取るべき行動を示す情報である。アクションの選択肢は事前に設定しておくことができる。アクションに来院が必要であることを含めるようにしてもよい。コメントは、獣医師による問診結果に対するコメントである。コメントは、例えば、テキストデータとすることができる。コメントには、可能性のある病気を含めるようにしてもよい。 The triage history storage unit 236 stores a history (hereinafter referred to as triage history). The diagnosis history includes an interview ID, necessity of visiting the hospital, actions, and comments. Whether a visit to the hospital is necessary or not is either necessary or unnecessary. The action is intervention information for the animal, and is information indicating actions that the animal should take, such as "Let's take a walk" and "Let's feed". Action options can be preconfigured. The action may include that a hospital visit is required. The comment is a comment on the interview result by the veterinarian. A comment can be text data, for example. Comments may include possible illnesses.
　学習モデル記憶部２３７は、問診結果に基づいて次の問診内容（問診に含める質問事項）を決定するための学習モデルを記憶する。学習モデル記憶部２３７は、動物種に対応付けて学習モデルを記憶することができる。なお、学習モデルの入力データ（特徴量）として動物種を与えるようにしてもよい。また、学習モデル記憶部２３７は、動物種及び品種に対応付けて学習モデルを記憶することもできる。例えば、同じ犬であっても、大型犬と小型犬では問うべき問診内容が変化しうる。そこで、動物種及び品種に加えて又はいずれかに代えて、体重のランク（最大最小で決定される範囲）に対応づけて学習モデルを記憶することもできる。また、動物種及び品種、体重に加えて又はこれらの少なくともいずれかに代えて、年代（年齢の範囲）に対応付けて学習モデルを記憶することもできる。また、学習モデルの入力データ（特徴量）として動物種と品種とを与えるようにしてもよい。また、学習モデルに与える特徴量として、体重、体重ランク、年齢、及び年代の少なくともいずれかを含めるようにしてもよい。また、学習モデルに与える特徴量として、過去の問診結果を含めることができる。過去の問診結果にはタイムラグ（何回前の問診であるか、または現時点から何日前の問診であるかを示す時間情報）を付帯させて特徴量とすることができる。学習モデルを学習するに与えられる教師データとして、獣医療従事者により決定された次に聞くべき質問項目を採用することができる。すなわち、獣医療従事者が決定していた、過去の問診に対する回答に応じて次に聞くべき問診の内容を機械学習により学習して学習モデルとすることができる。学習モデルは、後述する学習処理部２１６により作成及び更新される。 The learning model storage unit 237 stores a learning model for determining the next interview content (questions to be included in the interview) based on the interview results. The learning model storage unit 237 can store learning models in association with animal species. The animal species may be given as input data (feature amount) of the learning model. The learning model storage unit 237 can also store learning models in association with animal species and breeds. For example, even for the same dog, the question to be asked may differ between a large dog and a small dog. Therefore, learning models can be stored in association with weight ranks (ranges determined by maximum and minimum) in addition to or in place of animal species and breeds. In addition to or in place of at least one of animal species and breeds and body weight, learning models can also be stored in association with ages (age ranges). Also, the animal species and breed may be given as input data (feature amounts) of the learning model. Also, at least one of weight, weight rank, age, and generation may be included as a feature value to be given to the learning model. In addition, past interview results can be included as a feature quantity to be given to the learning model. A time lag (time information indicating how long ago the interview was or how many days ago from the present time) can be attached to the past medical interview result and used as a feature amount. Questions to ask next determined by veterinarians can be employed as training data provided to train the learning model. That is, it is possible to use machine learning to learn the content of the next question to be asked according to the answers to the past questions, which were determined by the veterinary medical staff, and use it as a learning model. The learning model is created and updated by the learning processing unit 216, which will be described later.
　問診送信部２１１は、問診を定期的に飼い主端末１０に送信する。問診送信部２１１は、患者動物の動物種に対応する質問記憶部２３３に記憶されている質問事項を１つ又は複数選択して１つの問診を作成することができる。問診送信部２１１は、患者動物の動物種に対応する質問事項のうち、提示条件が満たされているものを、例えば、ランダムに所定数選択することができる。また、問診送信部２１１は、例えば、事前に設定された所定のルールに従って質問を選択するようにしてもよい。 The inquiry transmission unit 211 periodically transmits an inquiry to the owner terminal 10. The inquiry sending unit 211 can create one inquiry by selecting one or a plurality of questions stored in the question storage unit 233 corresponding to the animal species of the patient animal. The medical inquiry sending unit 211 can, for example, randomly select a predetermined number of questions that satisfy the presentation conditions from among the questions corresponding to the animal species of the patient animal. In addition, the medical inquiry sending unit 211 may select a question according to a predetermined rule set in advance, for example.
　回答受信部２１２は、問診の各質問に対する回答を飼い主端末１０から受信する。回答受信部２１２は、質問事項に、特定の部位を撮影した画像により回答するべき質問が含まれていた場合には、画像のアップロードを受け付けることができる。回答受信部２１２は、受信した回答を回答履歴記憶部２３５に登録することができる。 The answer receiving unit 212 receives answers to each medical interview question from the owner terminal 10 . The answer receiving unit 212 can accept uploading of an image when the question includes a question to be answered with an image of a specific part. The reply receiving section 212 can register the received reply in the reply history storage section 235 .
　来院要否取得部２１５は、医療機関端末３０に対して来院要否の判断を求めるメッセージを送信することができる。来院要否判定部２１３は、問診結果（質問に対する回答、すなわち、選択肢の選択結果や画像などを含めることができる。）をメッセージに含めて医療機関端末３０に送信することができる。医療機関端末３０では、問診結果を出力して、獣医等の医療関係者から来院要否の判断の入力を受け付けることができる。医療機関端末３０では、問診結果に応じた動物に対する介入情報（アクション）及びコメントを入力することもできる。 The hospital visit necessity acquisition unit 215 can send a message to the medical institution terminal 30 requesting a determination of the necessity of a hospital visit. The hospital visit necessity determination unit 213 can include the result of medical examination (answers to questions, that is, selection results of options, images, etc.) in a message and transmit it to the medical institution terminal 30 . The medical institution terminal 30 can output the medical interview result and accept input from medical personnel such as a veterinarian as to whether or not a visit to the hospital is necessary. In the medical institution terminal 30, it is also possible to input intervention information (actions) and comments for the animal according to the interview results.
　来院要否取得部２１５は、医療機関端末３０から取得した来院要否と、問診結果に対応する問診を示す問診ＩＤとを含むトリアージ履歴を作成して、トリアージ履歴記憶部２３６に登録することができる。また、医療機関端末３０からアクション及びコメントが送信された場合には、トリアージ履歴にアクション及びコメントを含めることもできる。 The hospital visit necessity acquisition unit 215 can create a triage history including the hospital visit necessity acquired from the medical institution terminal 30 and an interview ID indicating an interview corresponding to the interview result, and register the triage history in the triage history storage unit 236. can. Further, when actions and comments are transmitted from the medical institution terminal 30, the actions and comments can be included in the triage history.
　来院要否送信部２１４は、問診結果に基づいて判断された来院要否を飼い主端末１０に送信する。 The hospital visit necessity transmission unit 214 transmits to the owner terminal 10 the necessity of a hospital visit determined based on the results of the interview.
　学習処理部２１６は、問診内容を決定するための学習モデルを作成及び更新する。例えば、問診記憶部２３４には獣医療従事者が作成した問診が記憶されている場合に、学習処理部２１６は、動物種ごとに、当該動物種に対応する問診内容（質問情報）を読み出して入力データとし、当該問診の次に送信された問診（動物ＩＤが同一であり日時が後の問診情報のうち、日時が最も古いもの）に対応する質問ＩＤを教師データとして機械学習を行い、機械学習により作成又は更新された学習モデルを学習モデル記憶部２３７に登録することができる。問診には複数の質問が含まれうるため、ある問診の次の問診に含まれる質問のそれぞれを教師データとして学習を行うことができる。 The learning processing unit 216 creates and updates a learning model for determining the inquiry content. For example, if the interview storage unit 234 stores an interview prepared by a veterinarian, the learning processing unit 216 reads out the interview content (question information) corresponding to each animal species. As input data, machine learning is performed using the question ID corresponding to the inquiry sent next to the inquiry (the oldest date and time among the inquiry information with the same animal ID and later date and time) as teacher data. A learning model created or updated through learning can be registered in the learning model storage unit 237 . Since a medical interview can include a plurality of questions, learning can be performed using each of the questions included in the following medical interview after a certain medical interview as teacher data.
　学習処理部２１６は、定期的に、又は、所定のルールにより決定されるタイミングに、学習モデルを更新することができる。この場合、学習処理部２１６は、問診内容及びその回答を医療機関端末３０に送信し、獣医療従事者から次に質問するべき問診内容（質問ＩＤ）の入力を受け付けることができ、回答を入力データとし、獣医療従事者から入力された質問ＩＤを教師データとして機械学習を行い学習モデルを更新することができる。 The learning processing unit 216 can update the learning model periodically or at timing determined by a predetermined rule. In this case, the learning processing unit 216 can transmit the content of the interview and its answer to the medical institution terminal 30, receive input of the content of the next question (question ID) to be asked from the veterinary medical staff, and input the answer. Machine learning can be performed using the question ID input by the veterinarian as teacher data to update the learning model.
＜動作＞
　図４は、本実施形態の定期検診システムの動作を説明する図である。 <Action>
FIG. 4 is a diagram for explaining the operation of the periodic medical examination system of this embodiment.
　管理サーバ２０は、問診を作成する（Ｓ３０１）。問診は、質問記憶部２３３に記憶されている質問のうち、患者動物の動物種に対応し、提供条件が満たされているものを所定数読み出すことにより作成することができる。管理サーバ２０は、作成した問診を飼い主端末１０に送信する（Ｓ３０２）。 The management server 20 creates an inquiry (S301). The medical interview can be prepared by reading out a predetermined number of questions that correspond to the animal species of the patient animal and satisfy the provision conditions among the questions stored in the question storage unit 233 . The management server 20 transmits the created medical interview to the owner terminal 10 (S302).
　飼い主端末１０では問診が表示される。問診は例えばチャット形式により行うようにしてもよいし、Ｗｅｂページのフォームにより行うようにしてもよい。また、画像により回答することが求められている質問については、飼い主端末１０が備えるカメラ（不図示）を起動してカメラの撮影画像を回答として取得することもできる。飼い主端末１０は、入力された回答を管理サーバ２０に送信する。 An interview is displayed on the owner terminal 10. The medical interview may be conducted, for example, in a chat format, or may be conducted using a form on a web page. In addition, for a question that requires an answer with an image, a camera (not shown) included in the owner terminal 10 can be activated to obtain an image captured by the camera as an answer. The owner terminal 10 transmits the inputted answer to the management server 20 .
　管理サーバ２０は、飼い主端末１０から回答を受信し（Ｓ３０３）、受信した回答を回答履歴記憶部２３５に登録することができる（Ｓ３０４）。管理サーバ２０は、回答を設定したメッセージを医療機関端末３０に送信して、来院要否を問い合わせる（Ｓ３０５）。医療機関端末３０では、獣医等の医療関係者から来院要否の入力を受け付けて管理サーバ２０に送信し、管理サーバ２０は、医療機関端末３０から来院要否を受信して、来院要否をトリアージ履歴記憶部２３６に登録し（Ｓ３０６）、来院要否を飼い主端末１０に送信する（Ｓ３０７）。 The management server 20 can receive a response from the owner terminal 10 (S303) and register the received response in the response history storage unit 235 (S304). The management server 20 transmits a message with an answer set to the medical institution terminal 30, and inquires whether or not it is necessary to visit the hospital (S305). The medical institution terminal 30 receives an input of whether or not to visit the hospital from the medical personnel such as a veterinarian, and transmits the input to the management server 20. The management server 20 receives the necessity of visiting the hospital from the medical institution terminal 30, and determines whether or not to visit the hospital. The information is registered in the triage history storage unit 236 (S306), and the necessity of visiting the hospital is transmitted to the owner terminal 10 (S307).
　管理サーバ２０は、定期的な問診の送信を行う期間が終了するまで（Ｓ３０８：ＮＯ）、定期的にＳ３０１からの処理を繰り返す。Ｓ３０１に進む前に、管理サーバ２０は、問診に対する回答を、動物種に対応する学習モデルに与えて次の問診に送信する質問を決定して問診記憶部２３４に登録することができる（Ｓ３０９）。なお、ここで問診情報には日時を設定しないようにしてもよいし、次に問診を送信する予定の日時を設定するようにしてもよい。 The management server 20 periodically repeats the processing from S301 until the period for sending periodic medical interviews ends (S308: NO). Before proceeding to S301, the management server 20 can give the answer to the medical inquiry to the learning model corresponding to the animal species, determine the question to be sent for the next medical inquiry, and register it in the medical inquiry storage unit 234 (S309). . Here, the medical inquiry information may not set the date and time, or may set the date and time when the next medical inquiry is scheduled to be sent.
　以上のようにして、本実施形態の定期検診システムでは、獣医療機関側が主体的に、定期的に問診を患者動物の飼育者に対して送信し、患者動物の健康状態を確認することができる。また、ＡＩ（学習モデル）を用いて問診結果に基づいて次の問診内容を自動的に決定することができる。 As described above, in the regular medical examination system of the present embodiment, the veterinary institution can proactively send medical interviews to the breeders of patient animals periodically to confirm the health condition of the patient animals. . In addition, AI (learning model) can be used to automatically determine the content of the next inquiry based on the result of the inquiry.
　以上、本実施形態について説明したが、上記実施形態は本発明の理解を容易にするためのものであり、本発明を限定して解釈するためのものではない。本発明は、その趣旨を逸脱することなく、変更、改良され得ると共に、本発明にはその等価物も含まれる。 Although the present embodiment has been described above, the above embodiment is intended to facilitate understanding of the present invention, and is not intended to limit and interpret the present invention. The present invention can be modified and improved without departing from its spirit, and the present invention also includes equivalents thereof.
　例えば、本実施形態では、動物種ごとに学習モデルを作成するものとしたが、全体で１つ又は複数の学習モデルを用いるようにして、特徴量として動物種を与えるようにしてもよい。 For example, in this embodiment, a learning model is created for each animal species, but one or more learning models may be used as a whole, and the animal species may be given as a feature amount.
　また、学習モデルには飼い主端末１０において撮影した画像を学習モデルの特徴量に含めることができる。これにより、例えば、皮膚病などの発症部位を撮影した写真や動画等に基づいて、次に聞くべき質問内容を決定することができ、動物の状態に応じた必要な観察を行うことができる。 In addition, the learning model can include an image captured by the owner terminal 10 in the feature amount of the learning model. As a result, for example, it is possible to determine the content of the question to be asked next based on a photograph or a moving image of an onset site such as a skin disease, and to perform necessary observation according to the condition of the animal.
　また、学習モデルの入力データ（特徴量）として、来院要否を与えるようにしてもよい。 In addition, as input data (feature amount) of the learning model, the necessity of visiting the hospital may be given.
　また、学習モデルの入力データ（特徴量）として、獣医療機関における検査結果を与えるようにしてもよい。この場合、例えば、カルテ情報を管理サーバ２０が管理するようにして、あるいは、カルテ情報を管理しているカルテサーバにアクセスするようにして、カルテ情報に含まれている検査結果を取得することができる。この場合にも、タイムラグを検査結果とともに入力データとすることができる。 Also, test results at veterinary medical institutions may be given as input data (feature values) for the learning model. In this case, for example, the medical chart information is managed by the management server 20, or the medical chart server that manages the medical chart information is accessed to obtain the test results included in the medical chart information. can. In this case as well, the time lag can be used as input data together with the inspection results.
　また、本実施形態では、学習モデルは所与の質問の中から次に送信するべきものを決定する分類器であるものとしたが、これに限らず、次に行うべき質問を生成する生成器やトランスフォーマなどとしてもよい。 In addition, in the present embodiment, the learning model is a classifier that determines the question to be sent next from among the given questions. or a transformer.
　また、本実施形態では、来院要否を獣医療従事者に問い合わせるものとしたが、これに限らず、例えば、来院要否をＡＩにより決定するようにすることもできる。この場合、来院要否を決定する分類器を、動物種ごとに学習モデル記憶部に記憶しておくようにすることができる。あるいは、動物種を入力データ（特徴量）とした分類器を記憶しておくようにしてもよい。来院要否の分類器の入力データ（特徴量）は問診に対する回答とすることができる。
In addition, in this embodiment, the veterinary medical staff is asked about the necessity of visiting the hospital, but the present invention is not limited to this. In this case, a classifier for determining the necessity of visiting the hospital can be stored in the learning model storage unit for each animal species. Alternatively, a classifier using animal species as input data (feature amount) may be stored. The input data (feature amount) of the hospital visit necessity classifier can be an answer to an interview.
　　１０　　飼い主端末
　　２０　　管理サーバ
　　３０　　医療機関端末 10 owner terminal 20 management server 30 medical institution terminal

Claims (8)

  1. 　動物の健康を管理するシステムであって、
    　前記動物の健康状態に関連する第１の質問に対する回答を入力データとし、獣医療従事者が指定した前記第１の質問の次に行うべき第２の質問を教師データとして機械学習により作成された学習モデルを記憶する学習モデル記憶部と、
    　前記第１の質問を飼い主端末に送信する問診送信部と、
    　前記飼い主端末から前記第１の質問に対する前記回答を受信する回答受信部と、
    　前記回答を前記学習モデルに与えて前記第２の質問を求める推論部と、
    　を備えることを特徴とする動物健康管理システム。     A system for managing animal health, comprising:
    It was created by machine learning using the answers to the first question related to the health condition of the animal as input data and the second question to be asked after the first question specified by the veterinarian as teacher data. a learning model storage unit that stores learning models;
    an inquiry transmission unit that transmits the first question to the owner terminal;
    an answer receiving unit that receives the answer to the first question from the owner terminal;
    a reasoning unit that provides the answer to the learning model to ask the second question;
    An animal health management system comprising:
  2. 　請求項１に記載の動物健康管理システムであって、
    　前記学習モデル記憶部は、動物種ごとに前記学習モデルを記憶し、
    　前記推論部は、前記動物の前記動物種に対応する前記学習モデルに対して前記回答を与えること、
    　を特徴とする動物健康管理システム。     The animal health management system of claim 1,
    The learning model storage unit stores the learning model for each animal species,
    the reasoning unit providing the answer to the learning model corresponding to the animal species of the animal;
    An animal health management system characterized by:
  3. 　請求項２に記載の動物健康管理システムであって、
    　前記学習モデル記憶部は、動物種と、品種、体重、体重ランク、年齢及び年代の少なくともいずれかとに対応付けて前記学習モデルを記憶し、
    　前記推論部は、前記動物の前記動物種と、前記動物の前記品種、前記体重、前記体重ランク、前記年齢及び前記年代の少なくともいずれかとに対応する前記学習モデルに対して前記回答を与えること、
    　を特徴とする動物健康管理システム。     An animal health management system according to claim 2,
    The learning model storage unit stores the learning model in association with at least one of animal species, breed, body weight, body weight rank, age and generation,
    the reasoning unit providing the answer to the learning model corresponding to the animal species of the animal and at least one of the breed, weight, weight rank, age, and age group of the animal;
    An animal health management system characterized by:
  4. 　請求項１に記載の動物健康管理システムであって、
    　前記学習モデルは、前記回答及び動物種を前記入力データとして学習されたものであり、
    　前記推論部は、前記動物の前記動物種と前記回答とを前記学習モデルに与えること、
    　を特徴とする動物健康管理システム。     The animal health management system of claim 1,
    The learning model is learned using the answers and animal species as the input data,
    the reasoning unit providing the species of the animal and the answer to the learning model;
    An animal health management system characterized by:
  5. 　請求項４に記載の動物健康管理システムであって、
    　前記学習モデルは、前記回答と、前記動物種と、品種、体重、体重ランク、年齢及び年代の少なくともいずれかとを前記入力データとして学習されたものであり、
    　前記推論部は、前記動物の前記動物種と、前記回答と、前記動物の前記品種、前記体重、前記体重ランク、前記年齢及び前記年代の少なくともいずれかとを前記学習モデルに与えること、
    　を特徴とする動物健康管理システム。     An animal health management system according to claim 4,
    The learning model is learned using at least one of the answer, the animal species, breed, weight, weight rank, age and age group as the input data,
    The reasoning unit provides the animal species of the animal, the answer, and at least one of the breed, the weight, the weight rank, the age, and the age group of the animal to the learning model;
    An animal health management system characterized by:
  6. 　請求項１ないし５のいずれか１項に記載の動物健康管理システムであって、
    　前記学習モデルは、前記獣医療従事者が判断した前記動物の前記健康状態をさらに前記入力データに加えて学習されたものであり、
    　前記回答を前記獣医療従事者に対して出力し、前記獣医療従事者から前記健康状態の入力を受け付ける健康状態取得部をさらに備え、
    　前記推論部は、前記学習モデルに、入力された前記健康状態をさらに与えること、
    　を特徴とする動物健康管理システム。     The animal health management system according to any one of claims 1 to 5,
    The learning model is learned by adding the health condition of the animal determined by the veterinarian to the input data,
    further comprising a health condition acquisition unit that outputs the answer to the veterinary medical staff and receives an input of the health condition from the veterinary medical staff;
    The inference unit further provides the input health condition to the learning model;
    An animal health management system characterized by:
  7. 　請求項１ないし６のいずれか１項に記載の動物健康管理システムであって、
    　前記学習モデルは、前記動物についての検査結果をさらに前記入力データに加えて学習されたものであり、
    　前記動物についての前記検査結果を取得する検査結果取得部をさらに備え、
    　前記推論部は、前記学習モデルに、取得した前記検査結果をさらに与えること、
    　を特徴とする動物健康管理システム。     The animal health management system according to any one of claims 1 to 6,
    The learning model is learned by adding test results of the animal to the input data,
    further comprising a test result acquisition unit that acquires the test results of the animal;
    The inference unit further provides the acquired inspection result to the learning model;
    An animal health management system characterized by:
  8. 　請求項１ないし７のいずれか１項に記載の動物健康管理システムであって、
    　前記飼い主端末から受信した前記回答を記憶する回答履歴記憶部をさらに備え、
    　前記学習モデルは、タイムラグを含む前記回答を前記入力データに含んで学習されたものであり、
    　前記推論部は、前記回答履歴記憶部に記憶されている前記回答及び現時点からの前記タイムラグを前記学習モデルに与えること、
    　を特徴とする動物健康管理システム。     The animal health management system according to any one of claims 1 to 7,
    further comprising an answer history storage unit that stores the answer received from the owner terminal;
    The learning model is learned by including the answer including the time lag in the input data,
    the inference unit providing the answer stored in the answer history storage unit and the time lag from the current time to the learning model;
    An animal health management system characterized by:
PCT/JP2021/031395 2021-08-26 2021-08-26 Animal health management system WO2023026439A1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/JP2021/031395 WO2023026439A1 (en) 2021-08-26 2021-08-26 Animal health management system
JP2022504232A JP7049030B1 (en) 2021-08-26 2021-08-26 Animal health management system
JP2022042617A JP2023033080A (en) 2021-08-26 2022-03-17 animal health management system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/031395 WO2023026439A1 (en) 2021-08-26 2021-08-26 Animal health management system

Publications (1)

Publication Number Publication Date
WO2023026439A1 true WO2023026439A1 (en) 2023-03-02

Family

ID=81259178

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/031395 WO2023026439A1 (en) 2021-08-26 2021-08-26 Animal health management system

Country Status (2)

Country Link
JP (2) JP7049030B1 (en)
WO (1) WO2023026439A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7220822B1 (en) 2022-03-23 2023-02-10 大塚製薬株式会社 Program, information processing device, and information processing method
JP7152822B1 (en) 2022-04-26 2022-10-13 株式会社Emyu Pet medical consultation support system, pet medical consultation support method and program

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002132918A (en) * 2000-10-26 2002-05-10 Matsushita Electric Ind Co Ltd System for managing pet information
JP2003242248A (en) * 2002-02-18 2003-08-29 Ip Corporation:Kk Doctor's question determination method and doctor's question determination system
JP2019079503A (en) * 2017-10-26 2019-05-23 株式会社メディアコンテンツファクトリー Interview system and program thereof

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002132918A (en) * 2000-10-26 2002-05-10 Matsushita Electric Ind Co Ltd System for managing pet information
JP2003242248A (en) * 2002-02-18 2003-08-29 Ip Corporation:Kk Doctor's question determination method and doctor's question determination system
JP2019079503A (en) * 2017-10-26 2019-05-23 株式会社メディアコンテンツファクトリー Interview system and program thereof

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ARITA RYUTARO, TETSUHIRO YOSHINO, YUKO HORIBA, HIROAKI HIKIAMI, YUTAKA SHIMADA, TAKAO NAMIKI, EIICHI TAHARA, KIYOSHI MINAMIZAWA, : "Problem Extraction of Browser-Based Questionnaire System and its Solution for a Patient-Centered System", KAMPO MED., vol. 69, no. 1, 1 January 2018 (2018-01-01), pages 82 - 90, XP093039893, DOI: 10.3937/kampomed.69.82 *

Also Published As

Publication number Publication date
JP2023033080A (en) 2023-03-09
JPWO2023026439A1 (en) 2023-03-02
JP7049030B1 (en) 2022-04-06

Similar Documents

Publication Publication Date Title
WO2023026439A1 (en) Animal health management system
Teller et al. Veterinary telemedicine: a literature review
JP2022009351A (en) Animal medical examination support system, animal medical examination support server, and animal medical examination support program
WO2023007690A1 (en) Animal health management system
JP7118488B1 (en) animal health management system
JP7260943B1 (en) animal health management system
JP7207805B1 (en) animal health management system
WO2023037425A1 (en) Animal health management system
US20080162175A1 (en) System and method for enabling informed decisions
Robinson Use of sentinel practices to obtain data regarding common clinical conditions and presentations in small animal consultations
Ouyang Health Informatics in Veterinary Medicine: State of the Literature, Day-1 Competencies, Perceptions of Telemedicine and Application of Predictive Modeling
JP7321615B1 (en) Veterinary Medical Support System, Veterinary Medical Support Program, Veterinary Medical Support Method
WO2023162111A1 (en) Veterinary medical assistance system, veterinary medical assistance method, and program
JP7132669B1 (en) Veterinary Medical Support System, Veterinary Medical Support Method and Program
JP7149665B2 (en) How to provide electronic medical records for animal patients
JP7157506B1 (en) Veterinary Medical Support System, Veterinary Medical Support Method and Program
Lumbis et al. Veterinary nutritional assessment: the importance of an interprofessional approach
WO2023162110A1 (en) Veterinary care assistance system, veterinary care assistance method, and program
WO2023026440A1 (en) Notification system, notification program, and notification method
JP6994800B1 (en) Electronic medical record system for animal patients, programs and information sharing support methods
WO2023228421A1 (en) Veterinary medical support system, veterinary medical support method, and program
Lumbis Developing an interprofessional nutrition programme: Roles and responsibilities
JP2022163326A (en) pet protection system
Graham The potential impact of artificial intelligence in equine practice
Caddiell et al. Qualitative Exploration of the Hidden Curriculum in Communicating Dog Breed Stereotypes During Veterinary Clinical Training

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2022504232

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: 21955051

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE