Abstract:
An information processing device obtains skeletal information which includes a location of joint in each of users who acted on a product. Then, the information processing device generates a feature quantity that characterizes an action of each of the users on a basis of the location of joint included in the skeletal information of each of the users. Then, the information processing device generates a determination index for determining a user interested in a product, by using the feature quantity of each of the users. After that, the information processing device detects a customer service target from visiting users, by using the determination index.
Abstract:
An information processing program causes a computer to execute a process including: specifying, from an image that is captured by a camera, a person and a plurality of objects, generating, by inputting the image of the person into a machine learning model, skeleton information on the person, identifying, based on the plurality of objects and the skeleton information, a first feature value associated with one or more first motions of the person who retrieves an object from among the plurality of objects, identifying a second feature value associated with one or more objects registered to a first terminal by the person from among the plurality of object, and generating, based on a difference between the first feature value and the second feature value, an alert indicates that an object retrieved by the person is not registered in the first terminal.
Abstract:
A non-transitory computer-readable recording medium has stored therein a distribution program that causes a computer to execute a process, the process including, extracting a person and a product from a video of an inside of a store, tracking the extracted person, identifying a behavior that is performed by the tracked person with respect to a product in the store, identifying a first behavior type that is led by the behavior that is performed by the tracked person with respect to the product among a plurality of behavior types that define transition of a process of the behavior since entrance into the store until purchase of a product in the store, and distributing information on a product indicating the first behavior type to the tracked person when the identified first behavior type is at a predetermined level or higher and the tracked person has not yet purchased the product.
Abstract:
A concealed data matching method for a computer including: registering a first concealed vector obtained by concealing registered data and key data based on a first random number and a linear combination of row vectors of a determination matrix; acquiring a second concealed vector; calculating a remainder vector indicating a remainder obtained by dividing the difference between the first concealed vector and the second concealed vector; determining the similarity between the registered data and the matching data based on the remainder vector; extracting the key data from the remainder vector if it is determined they are similar; calculating an inter-vector distance between the registered data and the matching data; and determining the similarity between the registered data and the matching data based on the magnitude of the inter-vector distance.
Abstract:
A non-transitory computer-readable recording medium stores an information output program for causing a computer to execute processing including: acquiring a video of an inside of a store; specifying, by analyzing the acquired video, a first area that includes a store clerk, a second area that includes an object customer who purchases a product, and a first relationship that identifies an interaction between the store clerk and the customer, from the video; determining that the store clerk included in the first area has performed service behavior with respect to the customer included in the second area based on the specified first relationship; and outputting a result of the determination to a display device.
Abstract:
A non-transitory computer-readable recording medium stores therein an information processing program that causes a computer to execute a process including, acquiring a video image in which an inside of a store in which each commodity product is arranged is captured, specifying a relationship between a plurality of persons who visit the inside of the store by analyzing the acquired video image in which the inside of the store is captured, grouping the plurality of persons when the specified relationship between the plurality of persons satisfies a predetermined condition, specifying, by analyzing the acquired video image in which the inside of the store is captured, a behavior exhibited with respect to the commodity product by each of the plurality of grouped persons, and associating the behavior exhibited with respect to the commodity product with a group to which the person who exhibits the behavior with respect to the commodity product belongs.
Abstract:
A computer-readable recording medium has stored therein a program that causes a computer to execute a process including: learning, for multiple forecasting models that perform demand forecasting based on sales performance data, multiple error forecasting models that estimate forecasting errors of the respective forecasting models based on product information and a result of forecasts by the respective forecasting models based on sales performance data on a first period; generating weight information on the multiple forecasting models from forecasting errors of multiple forecasted values by the multiple forecasting models, which are forecasting errors generated using the multiple error forecasting models and based on the sales performance data on a second period, which is a period after the first period, and the product information; and performing demand forecasting based on the result of forecasts by the multiple forecasting models that are combined according to the weight information.
Abstract:
A vein authentication device converts pixel values of an image, which captures an authentication site including veins, into frequency components. Moreover, the vein authentication device performs filtering of the frequency components, which are obtained by conversion of the pixel values, using a filter stored in a filter storing unit for reducing frequency components, from among low-frequency components having a lower spatial frequency than the spatial frequency of the veins and high-frequency components having a higher spatial frequency than the spatial frequency of the veins, corresponding to surface reflection of an illumination used for the authentication site. Furthermore, the vein authentication device converts the frequency components, which are subjected to filtering, back into an image. Moreover, the vein authentication device extracts vein data representing a vascular pattern of veins from the image obtained by reverse conversion. Furthermore, the vein authentication device performs vein authentication using the vein data that is extracted.