KR-20260064147-A - System for monitoring dogs and method thereof

KR20260064147AKR 20260064147 AKR20260064147 AKR 20260064147AKR-20260064147-A

Abstract

The present invention relates to a dog monitoring system and a method thereof. According to the present invention, a dog monitoring system comprises: a collection unit that collects wearable data in real time through a wearable sensor attached to a part of the dog's body; a prediction unit that predicts abnormal signs of the dog by applying a learned monitoring model to the wearable data collected in real time; and a control unit that transmits an alarm to a guardian in real time when there are abnormal signs of the dog. The system may further include: a preprocessing unit that refines a plurality of dog breed-specific wearable data and converts them according to a preset method to train the monitoring model; and a learning unit that trains the monitoring model to predict the health status of the dog using the preprocessed dog breed-specific wearable data. As such, according to the present invention, the behavioral patterns of a pet dog can be accurately analyzed using biometric data collected in real time, and abnormal signs in the pet dog can be detected early based on the behavioral patterns.

Inventors

박종일
강승호
최웅환

Assignees

박종일
강승호
최웅환

Dates

Publication Date: 20260507
Application Date: 20241031

Claims (12)

A collection unit that collects wearable data in real time through a wearable sensor attached to a part of a pet dog's body; A prediction unit that predicts abnormal signs of the pet dog by applying a learned monitoring model to the wearable data collected in real time; and A pet dog monitoring system comprising a control unit that transmits an alarm to the guardian in real time if there are abnormal signs in the pet dog.
In paragraph 1, A preprocessing unit that refines multiple dog breed-specific wearable data and converts them according to a preset method to train the above monitoring model; and A dog monitoring system further comprising a learning unit that trains the monitoring model to predict the health status of the dog using the preprocessed dog-specific wearable data.
In paragraph 1, The above wearable data is, A dog monitoring system including the dog's activity and activity level.
In paragraph 2, The above breed-specific wearable data is, A dog monitoring system including current health status, affected area, activity or activity level for dogs of different breeds, healthy dogs, and dogs with at least one part of the body affected.
In paragraph 1, The above control unit is, A dog monitoring system that recommends preventive measures or schedules appointments with a veterinarian based on prediction results.
In paragraph 5, The above control unit is, A dog monitoring system that sends a real-time alarm to the guardian when there are abnormal signs in the dog, recommends a veterinary clinic within a pre-set radius based on the dog's location, or connects the guardian with at least one of the registered veterinarians to provide remote consultation.
A step in which a collection unit collects wearable data in real time through a wearable sensor attached to a part of the dog's body; A step in which a prediction unit predicts abnormal signs of the pet dog by applying a trained monitoring model to the wearable data collected in real time; and A method for monitoring a dog, comprising the step of a control unit transmitting an alarm to a guardian in real time if there are abnormal signs in the dog.
In Paragraph 7, A preprocessing unit that refines multiple breed-specific wearable data and converts them according to a preset method to train the monitoring model; and A dog monitoring method comprising the step of further training the monitoring model to predict the health status of the dog using the preprocessed wearable data for each dog breed.
In Paragraph 7, The above wearable data is, A method for monitoring a dog, including the dog's activity and activity level.
In paragraph 8, The above breed-specific wearable data is, A method for monitoring companion dogs, including current health status, affected area, activity or activity level, for dogs of different breeds that are healthy and dogs that are sick with at least one part of their body.
In Paragraph 7, The step of transmitting the above alarm is, A dog monitoring method that recommends preventive measures or schedules appointments with a veterinarian based on prediction results.
In Paragraph 11, The step of transmitting the above alarm is, A dog monitoring method that sends a real-time alarm to the guardian when there are abnormal signs in the dog, recommends a veterinary clinic within a pre-set radius based on the dog's location, or connects the dog to at least one of the registered veterinarians to provide remote consultation.

Description

System for monitoring dogs and method thereof The present invention relates to a dog monitoring system and a method thereof, and more specifically, to a dog monitoring system and a method thereof that collects data in real time through a wearable sensor attached to a part of the dog’s body and monitors the condition of the dog based on the collected data. According to the 2022 National Survey on Animal Protection released by the Ministry of Agriculture, Food and Rural Affairs, as of 2022, the number of households raising pets in Korea was 6.02 million, and with 75.6% of these households raising dogs, the number of pet dogs is estimated at 5.45 million. As such, the pet-related market is growing in line with the increase in the pet-owning population. However, due to the diversity of pet species and the distinct characteristics of each individual, it is difficult for pet owners to visually assess their pets' health status; consequently, when abnormal symptoms appear, they often visit multiple veterinary clinics to have them checked. In addition, because pet diseases cannot be clearly identified, there are problems such as abandonment or failure to provide timely health care, resulting in missing the golden time. Therefore, there is a need for technology to monitor the health status of pets in real time. The technology forming the background of the present invention is described in Korean Registered Patent No. 10-2052601 (published Dec. 05, 2019). FIG. 1 is a configuration diagram of a pet dog monitoring system according to one embodiment of the present invention. FIG. 2 is a flowchart of a dog monitoring method according to another embodiment of the present invention. FIG. 3 is a drawing illustrating an example of predicting abnormal signs according to another embodiment of the present invention. FIG. 4 is a drawing illustrating an example of performing membership registration according to another embodiment of the present invention. FIG. 5 is a drawing illustrating the modification of member information and basic pet information according to another embodiment of the present invention. FIG. 6 is a drawing illustrating an example of providing a community function according to another embodiment of the present invention. FIG. 7 is a drawing illustrating an example of providing a chat function to a guardian according to another embodiment of the present invention. FIG. 8 is a drawing illustrating an example of providing a chat function to a veterinarian according to another embodiment of the present invention. Preferred embodiments according to the present invention will be described in detail below with reference to the attached drawings. In this process, the thickness of lines or the size of components shown in the drawings may be exaggerated for clarity and convenience of explanation. Furthermore, the terms described below are defined in consideration of their functions within the present invention, and these may vary depending on the intent or practice of the user or operator. Therefore, the definitions of these terms should be based on the content throughout this specification. FIG. 1 is a configuration diagram of a pet dog monitoring system according to one embodiment of the present invention. As illustrated in FIG. 1, the pet dog monitoring system (100) may include a collection unit (110), a preprocessing unit (120), a learning unit (130), a prediction unit (140), and a control unit (150). First, the collection unit (110) can collect wearable data in real time through a wearable sensor attached to a part of the dog's body. At this time, the wearable sensor may be a 6-axis tilt sensor including a 3-axis accelerometer and a 3-axis gyroscope. Specifically, the collection unit (110) can collect wearable data including the dog's activity (e.g., walking, running, sitting, lying down, lying down, etc.) or activity level (e.g., heart rate, water content, stress, etc.) in real time through a wearable sensor attached to a part of the dog's body. In addition, the collection unit (110) can collect physical information of the dog (e.g., weight, back length, breed, age, gender, etc.). Next, the preprocessing unit (120) can refine and convert multiple dog breed-specific wearable data according to a preset method to train a monitoring model. Specifically, the preprocessing unit (120) can refine the wearable data collected by breed by performing noise removal, missing value processing, outlier detection, etc., and can convert the refined wearable data by breed to be suitable for input to a trained monitoring model by applying a pre-set method (time stamp alignment, data scaling, standardization work, etc.). At this time, the wearable data by breed is data including the current health status, the affected area, activity (e.g., walking, running, sitting, lying down, lying down, etc.) or activity amount (e.g., heart rate, water content, stress, etc.) for dogs in a healthy state and dogs in a state where at least one part of