Search

KR-102961721-B1 - A METHOD FOR OPTIMIZING ARTIFICIAL INTELLIGENCE MODEL AND PREDICTING A DISEASE THAT REFLECTS A CONDITION OF PET, AND A COMPUTING DEVICE AND SYSTEM IMPLEMENTING SUCH METHOD

KR102961721B1KR 102961721 B1KR102961721 B1KR 102961721B1KR-102961721-B1

Abstract

According to one embodiment of the present disclosure, a method of operation of an electronic device may be provided, comprising the operation of acquiring input data including quantitative data according to a PCR test result and additional information related to the health or disease of a pet by at least one processor included in the electronic device, the operation of calling a first artificial intelligence model for calculating a health score, and the operation of inputting the input data into the first artificial intelligence model to calculate a health score representing the health status of the pet.

Inventors

  • 이재훈
  • 지대경
  • 이강영

Assignees

  • 제너바이오 주식회사

Dates

Publication Date
20260511
Application Date
20231023

Claims (10)

  1. By at least one processor included in an electronic device, An operation to acquire input data including quantitative data based on PCR test results and additional information related to the health or disease of the pet; The action of loading the first artificial intelligence model to calculate the health score; The operation of calculating a first risk level caused by pathogenic microorganisms by performing regression analysis on quantitative values for each pathogen included in the above quantitative data; An operation to calculate a second risk level by analyzing information related to the health or disease of the pet based on the additional information above; An operation to adjust at least one weight of the first artificial intelligence model based on the first risk level and the second risk level; and The operation includes inputting the above input data into the first artificial intelligence model to calculate a health score representing the health status of the pet, and The above second risk level is: A method of operating an electronic device comprising one or more of the following: a risk based on the age of the pet, a risk based on the BCS of the pet, or a risk based on the disease history of the pet.
  2. In Article 1, The above additional information is obtained by receiving it from at least one of user input or a pre-stored database, in a method of operating an electronic device.
  3. In Article 1, A method of operation of an electronic device in which the above-mentioned first artificial intelligence model is implemented to include at least one weight for extracting at least one feature value corresponding to the input data.
  4. In Article 1, The operation of calculating the above health score is, An operation of applying at least one weight based on the input data through at least one layer of the first artificial intelligence model; and A method of operation of an electronic device comprising the operation of outputting a health score through at least one layer of a first artificial intelligence model.
  5. In Article 1, A method of operation of an electronic device further comprising the operation of preprocessing the above input data to adjust at least one weight of the first artificial intelligence model.
  6. delete
  7. delete
  8. In Article 1, A method of operation of an electronic device further comprising the operation of additionally training the first artificial intelligence model based on the above input data and the above health score.
  9. Memory; and It includes at least one processor electronically connected to the memory; and The above-mentioned at least one processor is, Acquire input data including quantitative data based on PCR test results and additional information related to the pet's health or disease, and Load the first artificial intelligence model to calculate the health score, and Calculate the first risk level caused by pathogenic microorganisms by performing regression analysis on the quantitative values for each pathogen included in the above quantitative data, and Based on the above additional information, the information related to the health or disease of the pet is analyzed to calculate a second risk level, and Adjusting at least one weight of the first artificial intelligence model based on the first risk level and the second risk level, and The above input data is input into the above first artificial intelligence model to calculate a health score representing the health status of the pet, and The above second risk level is: A computing device comprising one or more of the risk based on the age of the pet, the risk based on the BCS of the pet, or the risk based on the disease history of the pet.
  10. A server including a computing device according to paragraph 9; and A system comprising at least one user device that obtains health information or disease information of the pet based on a communication connection with the server.

Description

A method for optimizing an artificial intelligence model reflecting the condition of a pet and predicting a disease, and a computing device and system implementing such method The present disclosure relates to an electronic device comprising an artificial intelligence model. More specifically, it relates to an electronic device that uses an artificial intelligence model to predict the health and disease status of a companion animal (pet) and recommends suitable food according to the pet's health and disease. As the companion animal market grows explosively, the size of the pet healthcare market is also expanding rapidly. In particular, a significant number of pet diseases are infectious. Pet diseases are caused by infection with pathogens (e.g., germs, bacteria, microorganisms, etc.). However, the biggest problem in treating pet diseases is that pets cannot verbally express their pain. Consequently, the reality is that pet diseases are often treated only after the disease has progressed significantly following onset. Recently, the cost of raising pets has been skyrocketing, with the fact that treatment expenses account for more than half of the total cost acting as a major contributing factor. Under these circumstances, there is a need for technology that can closely monitor a pet's current condition and predict infectious diseases in advance. Disease prediction has so far been carried out in a very non-quantitative manner. The purpose of this disclosure is to indirectly predict the current health status and diseases of companion animals by utilizing data obtained from qualitatively and quantitatively analyzing the genes of pathogens possessed by companion animals, and to use a preventive solution for this. FIG. 1 is a drawing illustrating a pet diagnostic system according to various embodiments. FIG. 2 is a drawing for explaining the configuration of an electronic device according to various embodiments. FIG. 3 is a drawing for illustrating an electronic device including an artificial intelligence model learned based on training data associated with a pet, according to various embodiments. Figure 4 is a diagram illustrating an example of PCR quantitative data. FIG. 5 is a diagram illustrating a method in which an electronic device, according to various embodiments, obtains output data based on input data using an artificial intelligence model. FIG. 6 is a diagram illustrating a method in which an electronic device predicts the probability of disease occurrence in a pet based on PCR data according to various embodiments. Figure 7 is a diagram illustrating the correlation between pathogenic microorganisms and diseases. FIG. 8 is a flowchart illustrating an embodiment in which an electronic device obtains a disease score according to various embodiments. FIG. 9 is a diagram illustrating a specific method for an electronic device to determine a predicted target disease according to various embodiments. FIG. 10 is a flowchart illustrating another embodiment in which an electronic device obtains a disease score according to various embodiments. FIG. 11 is a flowchart illustrating another embodiment in which an electronic device obtains a disease score according to various embodiments. FIG. 12 is a diagram illustrating a method for an electronic device to calculate a health score according to various embodiments. FIG. 13 is a flowchart illustrating a method for an electronic device to obtain a health score according to various embodiments. FIG. 14 is a diagram illustrating an embodiment of adjusting the weights of an artificial intelligence model based on input data according to various embodiments. FIG. 15 is a flowchart illustrating an embodiment of additionally training an artificial intelligence model based on input data according to various embodiments. FIG. 16 is a flowchart illustrating an example of an operation for providing pet-customized recommended food according to various embodiments. FIG. 17 is a drawing for illustrating an example of improvement information and food information according to various embodiments. FIG. 18 is a flowchart illustrating an example of an operation to obtain improvement information according to various embodiments. FIG. 19 is a flowchart illustrating another example of an operation to obtain improvement information according to various embodiments. FIG. 20 is a flowchart illustrating an example of an operation to determine at least one food according to various embodiments. FIG. 21 is a flowchart illustrating another example of an operation to determine at least one food according to various embodiments. FIG. 22 is a flowchart illustrating another example of an operation to determine at least one food according to various embodiments. FIG. 23 is a drawing for illustrating an example of a user interface according to various embodiments. The embodiments described in this specification are intended to clearly explain the concept of the invention to those skilled in the art to