Storage medium and information processing device

1 . A non-transitory computer-readable storage medium storing an information processing program that causes at least one computer to execute a process, the process comprising:

acquiring video data of a product placed on a scale included in a registration machine;

extracting, by a first machine learning model that analyzes the acquired video data, an appearance attribute of the product;

specifying an attribute regarding an appearance of the product, by inputting the acquired video data into a first machine learning model;

acquiring information regarding a measured weight of the product, from the registration machine that has measured a weight of the product placed on the scale; and

performing machine learning of a second machine learning model distinct from the first machine learning model, the performing the machine learning including using the extracted appearance attribute as an input feature and the acquired measured weight as a corresponding ground truth label to train the second machine learning model to estimate a weight of a product from an appearance attribute.

2 . The non-transitory computer-readable storage medium according to claim 1 , wherein the attribute regarding the appearance of the product is one of a color of the product, a size of the product, and a shape of the product.

3 . The non-transitory computer-readable storage medium according to claim 1 , wherein the performing the machine learning includes performing machine learning of the second machine learning model, by using each of the specified image data of the product and the attribute of the product as training data and the information regarding the weight of the product as correct answer data.

4 . The non-transitory computer-readable storage medium according to claim 1 , wherein the performing the machine learning includes:

acquiring product information selected by a user, from among items related to products displayed on a display of the registration machine; and

performing machine learning of the second machine learning model, by using each of the acquired product information and the attribute of the product as training data and the information regarding the weight of the product as correct answer data.

5 . The non-transitory computer-readable storage medium according to claim 1 , wherein the process further comprising:

detecting an abnormal behavior of the person who operates the registration machine, based on the information regarding the weight of the product imaged in the video data estimated by using the second machine learning model.

6 . An information processing device comprising:

one or more memories; and

one or more processors coupled to the one or more memories and the one or more processors configured to:

acquire video data of a product placed on a scale included in a registration machine,

extracting, by a first machine learning model that analyzes the acquired video data, an appearance attribute of the product;

specify an attribute regarding an appearance of the product, by inputting the acquired video data into a first machine learning model,

acquire information regarding a measured weight of the product, from the registration machine that has measured a weight of the product placed on the scale, and

perform machine learning of a second machine learning model distinct from the first machine learning model, the performing the machine learning including using the extracted appearance attribute as an input feature and the acquired measured weight as a corresponding ground truth label to train the second machine learning model to estimate a weight of a product from an appearance attribute.