Pet health management service platform based on artificial intelligence learning

A computer implemented method for predicting pet health executed by a pet healthcare service platform server, the method comprising:

• (a) obtaining, by the pet healthcare service platform server, pet information about a managed pet, comprising animal attribute information of at least one of breed, sex, and age, and health history information of at least one of disease history, examination history, and symptom history from a user device associated with an owner of the managed pet;
• (b) establishing, by the pet healthcare service platform server, based on at least one of the animal attribute information and the health history information collected about the managed pet, a pet comparison group comprising at least one other pet from a pre-built pet database to which the managed pet is to be clustered and compared,
• wherein the step (b) comprises:
• extracting, by the pet healthcare service platform server, from the pet database, a first dataset of the disease history, the examination history, and the symptom history for each of other pets of a same-breed group as the managed pet;
• extracting, by the pet healthcare service platform server, from the pet database, a second dataset of the disease history, the examination history, and the symptom history for each of other pets of a same-gender group as the managed pet;
• extracting, by the pet healthcare service platform server, from the pet database, a third dataset of the disease history, the examination history, and the symptom history of each of other pets in a same-age group as the managed pet;
• extracting, by the pet healthcare service platform server, from the pet database, a fourth dataset of the disease history, the examination history, and the symptom history for each of other pets in a different-breed group that are not of the same breed as the managed pet;
• extracting, by the pet healthcare service platform server, from the pet database, a fifth dataset of the disease history, the examination history, and the symptom history for each of other pets in a different-gender group that are not of the same gender as the managed pet;
• extracting, by the pet healthcare service platform server, from the pet database, a sixth dataset of the disease history, the examination history, and the symptom history for each of other pets in a different-age group that are not of the same age as the managed pet;
• inputting, by the pet healthcare service platform server, the first dataset into a pre-trained artificial intelligence learning model for pets;
• obtaining a first classification result that quantifies a correlation of disease items by breed, a correlation of examination items by breed, and a correlation of symptom items by breed, respectively;
• inputting, by the pet healthcare service platform server, the second dataset into the artificial intelligence learning model for pets;
• obtaining a second classification result that quantifies a correlation of disease items by gender, a correlation of examination items by gender, and a correlation of symptom items by gender, respectively;
• inputting, by the pet healthcare service platform server, the third dataset into the artificial intelligence learning model for pets;
• obtaining a third classification result that quantifies a correlation of disease items by age, a correlation of examination items by age, and a correlation of symptom items by age, respectively,
• inputting, by the pet healthcare service platform server, the fourth dataset into the artificial intelligence learning model for pets;
• obtaining a fourth classification result that quantifies a correlation of disease items by different breeds, a correlation of examination items by different breeds, and a correlation of symptom items by different breeds, respectively;
• inputting, by the pet healthcare service platform server, the fifth dataset into the artificial intelligence learning model for pets;
• obtaining a fifth classification result that quantifies a correlation of disease items by different genders, a correlation of examination items by different genders, and a correlation of symptom items by different genders, respectively;
• inputting, by the pet healthcare service platform server, the sixth dataset into the artificial intelligence learning model for pets;
• obtaining a sixth classification result that quantifies a correlation of disease items by different ages, a correlation of examination items by different ages, and a correlation of symptom items by different ages, respectively,
• comparing, by the pet healthcare service platform server, the first classification result and the fourth classification result for individual item by:
• determining a dominant item exists when an itemized value according to the first classification result is higher than an itemized value according to the fourth classification result by a predetermined threshold,
• extracting the dominant item, and
• selecting the extracted dominant item as a breed-specific item that maps to one of a breed-specific disease item, a breed-specific examination item, and a breed-specific symptom item based on an item classification;
• comparing, by the pet healthcare service platform server, the second classification result and the fifth classification result for individual item by:
• determining a dominant item exists when in which an itemized value according to the second classification result is higher than an itemized value according to the fifth classification result by a predetermined threshold,
• extracting the dominant item, and
• selecting the extracted dominant item as a gender-specific item that maps to one of a gender-specific disease item, a gender-specific examination item, and a gender-specific symptom item based on an item classification;
• comparing, by the pet healthcare service platform server, the third classification result and the sixth classification result for individual item by:
• determining a dominant item in which an itemized value according to the third classification result is higher than an itemized value according to the sixth classification result by more than a predetermined threshold,
• extracting the dominant item, and
• selecting the extracted dominant item as an age-specific item that maps to one of an age-specific disease item, an age-specific examination item, and an age-specific symptom item based on the item classification;
• classifying, by the pet healthcare service platform server, for disease items, examination items, and symptom items that do not correspond to the breed-specific items, the gender-specific items, and the age-specific items, them as non-specific items that are not related to animal attribute information;
• extracting, by the pet healthcare service platform server, from the pet database, other pets that are of the same breed as the managed pet and include a history for the breed-specific item when the breed specific item exists in the disease history, the examination history or the symptom history of the managed pet;
• setting, by the pet healthcare server platform server, the extracted other pets having the same breed and the history of the breed-specific item as a first pet comparison group;
• extracting, by the pet healthcare service platform server, from the pet database, other pets that are of the same gender as the managed pet and include a history for the gender-specific item when the gender-specific item exists in the disease history, the examination history, or the symptom history of the managed pet;
• setting, by the pet healthcare server platform server, the extracted other pets having the same gender and the history of the gender-specific item as a second pet comparison group;
• extracting, by the pet healthcare service platform server, from the pet database, other pets that are of the same age as the managed pet and include a history for the age-specific item when the age specific item exists in the disease history, the examination history, or the symptom history of the managed pet;
• setting, by the pet healthcare server platform server, the extracted other pets having the same age and the history of the age-specific item as a third pet comparison group;
• extracting, by the pet healthcare service platform server, from the pet database, other pets that include a history for the non-specific item when the non-specific item exists in the disease history, the examination history, or the symptom history of the managed pet;
• setting the extracted other pets having the history of the non-specific item as a fourth pet comparison group;
• (c) predicting, by the pet healthcare service platform server, using the health history information of at least one other pet in said pet comparison group, a change in a health condition that is likely to occur in the managed pet in a future,
• wherein the step (c) comprises:
• selecting, by the pet healthcare service platform server, a dataset of each of the first pet comparison group, the second pet comparison group, the third pet comparison group, and the fourth pet comparison group, and inputting the dataset of health history information into the artificial intelligence learning model for pets to predict a change in a health condition likely to occur in the managed pet in the future;
• and
• (d) transmitting, by the pet healthcare service platform server, the predicted change in the health condition to the user device associated with the owner of the managed pet, wherein the predicted change in the health condition refers to probability of the managed pet developing one or more diseases and a recommendation of items to be checked by the owner of the managed pet based on health history data.