Abstract: A method of automatically improving artificial intelligence (AI) model performance is provided. The method includes: collecting image data including at least one item; performing pre-training based on self-supervised training for a pre-training model by using the image data; and setting initial values of the AI model and performing fine-tuning by using the pre-training model.

Abstract: A method for analyzing fashion attributes using large amounts of pieces of image data is provided. The method includes: collecting image data including at least one item; statistically analyzing on the image data based on an attribute classification AI model; and visualizing the results of the statistical analysis, wherein the attribute classification AI model is a model for detecting said at least one item included in the image data, and for recognizing, labeling and classifying fashion attributes of the at least one item.

Abstract: A method of creating training data for model training is provided. The method includes: receiving image data including at least one fashion item; performing location box labeling on an item location box which indicates a location of an item included in the image data by using an item location detection model; calculating a location box labeling result value and a location box labeling confidence value; receiving a user's location box review value for the location box labeling result value; determining a location noise value of the location box review value by using the item location detection model; and determining the location box review value as location box training data if the location noise value meets a predetermined first criterion.

Abstract: A method of searching for similar products using a multi-task learning (MTL) model is provided. The method includes: converting, by using a multi-task learning model utilizing a unified backbone network, each of an original image including a fashion item into a single vector including at least one multi-task attribute; and generating a visual search database by storing the original image and the single vector of the original image together.

Abstract: A method for measuring influence on a social network is provided. The method includes collecting social network service (SNS) data from an SNS, measuring a user influence index based on user account information among the SNS data and content information associated with the user account information, measuring an attribute influence value for an attribute included in image information based on the image information among the SNS data, measuring a product influence value for product information based on the user influence coefficient and the attribute influence value with respect to content including the product information, and curating the content including the product information based on the product influence value.

Abstract: A method for measuring influence on a social network is provided. The method includes collecting social network service (SNS) data from an SNS, measuring a user influence index based on user account information among the SNS data and content information associated with the user account information, measuring an attribute influence value for an attribute included in image information based on the image information among the SNS data, measuring a product influence value for product information based on the user influence coefficient and the attribute influence value with respect to content including the product information, and curating the content including the product information based on the product influence value.