Abstract: An information processing apparatus (1) includes: an acquisition unit (101) configured to acquire an object image including an object; and a prediction unit (102) configured to predict various attributes relating to the object by applying a learning model to the object image acquired by the acquisition unit, wherein the learning model is a learning model that is shared between a plurality of different objects including the object and includes a plurality of estimation layers that estimate a plurality of attribute values for a plurality of attributes relating to the plurality of different objects.

Abstract: The information processing device obtains a character string image which includes a plurality of characters, and which includes the characters arranged in an arrangement direction, obtains a probability image representing a probability of an existence of a character in each of the pixel included in the character string image, obtains a plurality of character regions in which the characters are estimated to respectively exist in the character string image based on the probability image, obtains an additional character region which is located in the character string image, and which does not overlap the plurality of character regions based on a determination result on whether or not a pixel of a non-background color exists in a direction perpendicular to the arrangement direction at every position in the arrangement direction in the character string image, and recognizes the plurality of characters from the character regions and the additional character region.

Abstract: Input information acquisition means (101, 201) of an authentication system (S) acquires input information, which accompanies a card possessed by a user, and has been input from a user terminal through use of reading means (33A) or photographing means (36). Identification information acquisition means (102, 202) acquires identification information that enables identification of the card. Registered information acquisition means (105, 203) acquires registered information, which accompanies the card, and has been registered in a server in association with the identification information in advance. Authentication means (103) executes authentication based on the input information and the registered information.

Abstract: To easily and correctly determine substantial identity of a plurality of images in each of which an object is placed, provided is an image judgement method including steps of obtaining first object data from a first image with a use of an R-CNN 12, which is a first machine learning model, where the first object data indicates an attribute and a layout of an object in the first image, obtaining second object data from a second image with a use of the R-CNN 12, where the second object data indicates an attribute and a layout of an object in the second image, and determining substantial identity of the first image and the second image based on the first object data and the second object data with a use of a CNN, which is a second machine learning model.

Abstract: A control device (500) includes a selector (550) that selects one of a first vehicle and a second vehicle as a remaining vehicle that stores a first article and a second article and that remains at a receiving location where the first article and the second article are to be received, and selects another of the first vehicle and the second vehicle as a departing vehicle that departs from the receiving location, when the second vehicle storing the second article arrives at the receiving location while the first vehicle storing the first article stays at the receiving location. Additionally, the control device (500) includes a storage controller (560) that identifies the first article or the second article stored in the selected departing vehicle as a transfer article to be transferred from the departing vehicle to the remaining vehicle, and causes the identified transfer article to be stored in the remaining vehicle.

Abstract: Information processing system S acquires sensing data obtained through sensing downward from the sky by an UAV 1 flying in a specific zone, and identifies flood-damaged area where flood damage has occurred in the specific zone on the basis of the acquired sensing data.

Abstract: The present disclosure relates to improving recommendations for small shops on an ecommerce platform while maintaining accuracy for larger shops by retraining a machine-learning recommendation model to reduce sample selection bias using a meta-learning process. The retraining process comprises identifying a sample subset of shops on the ecommerce platform, and then creating shop-specific versions of the recommendation model for each of the shops in the subset by optimizing the baseline model to predict user-item interactions in a first training dataset for the applicable shop. Each of the shop-specific models is then tested using a second training dataset for the shop. A loss is calculated for each shop-specific model based on the model's predicted user-item interactions and the actual user-item interactions in the second training dataset for the shop. A global loss is calculated based on each of the shop-specific losses, and the baseline model is updated to minimize the global loss.

Abstract: An information processing apparatus (100) includes: an acquisition unit configured to acquire a content-to-content similarity that is a similarity between a target content and one or more pieces of other content, and a user-to-user similarity that is a similarity between a target user and one or more other users; an estimation unit configured to estimate a prior distribution of expected rewards obtained as a result of execution processing performed by the target user on the target content, based on the content-to-content similarity and the user-to-user similarity; and a derivation unit configured to derive a posterior distribution of the expected rewards, using the prior distribution.

Abstract: An input data generation unit is configured to generate, based on log data indicating a log of a behavior of a user with respect to a given computer resource for each period, input data for the period, which is associated with the log data. A user probability data generation unit is configured to generate user probability data based on output obtained from a trained machine learning model when the input data is input to the trained machine learning model. An anomaly determination unit is configured to determine whether an anomaly has occurred in the behavior of the user during a latest period based on the user probability data generated based on the input data for the latest period and the user probability data generated based on the input data for a period before the latest period.

Abstract: Provided is a ranking determination system including at least one processor configured to: acquire a plurality of second classifications relating to second data based on a first model which has learned a relationship between first data and a first classification relating to the first data; acquire, for each of the second classifications, a second score relating to a validity of a combination of the second data and the second classification based on a second model which has learned a validity of a combination of third data and a third classification relating to the third data; and determine a second ranking for each of the plurality of second classifications based on the second score of each second classification.

Abstract: Authentication means (101) of an authentication system (S) performs authentication based on input authentication information. Determination means (102) determines, based on the input authentication information, whether there are a plurality of users for which there is a possibility of successful authentication. Input request means (104) requests, when it is determined that there are the plurality of users, input of additional authentication information that is based on a difference in user information on each of the plurality of users. Additional authentication means (105) performs additional authentication based on the input additional authentication information.

Abstract: An operation guidance corresponding to a user is output. A server (10) of a logistics management system (1) sets, based on user setting information associated with users, an output mode of an operation guidance that is output by an unmanned ground vehicle (30) that carries a package, generates a notification code for a package subject to carrying, associates the generated notification code with a user who picks up or deposits the package, sends the generated notification code to a user device used by the user, obtains an authentication code which includes the notification code and which the user has entered into the unmanned vehicle (30), specifies, based on the notification code included in the obtained authentication code, the output mode of the operation guidance corresponding to the user who has entered the authentication code, causes the unmanned vehicle (30) to output the operation guidance using the specified output mode.

Abstract: An information processing apparatus acquires a plurality of images related to a specified article, decides suitability of each of the plurality of images for estimating a state of the article, and outputs state information indicating an estimated state of the specified article based on a result of the decision and at least a part of the plurality of images.

Abstract: An information processing system configured to provide an electronic commerce platform. An information processing system is configured to acquire a descriptive text related to an item and at least one image related to the item; identify an object from the descriptive text; detect an object from each of the at least one image; and generate correspondence information based on correspondence between the object identified from the descriptive text and the object detected from the image.

Abstract: A logistics management system includes a memory that stores operation record information indicating a record of each of users operating an unmanned vehicle and a circuitry. The circuitry is configured to specify, when the unmanned vehicle moves on a carrying route that includes carrying points, a user who operates the unmanned vehicle at each of the carrying points, obtain the operation record information corresponding to the specified user, and specify, based on the operation record information, an estimated operation time for each of the users to operate the unmanned vehicle and determine a carrying sequence using the estimated operation time. The carrying sequence is a sequence in which the unmanned vehicle moves between the carrying points on the carrying route.

Abstract: An information processing apparatus includes an acquiring unit configured to acquire an object image that includes an object, and a predicting unit configured to predict a class of the object by applying the object image acquired by the acquiring unit to a learning model. The learning model includes a main network (201) that extracts feature amounts regarding hierarchical classes of the object based on the object image, and a sub network (202) that outputs hierarchical classes of the object based on the feature amounts. The main network (201) includes extractors that extract the feature amounts. The sub network (202) includes classifiers that output classes of the object based on the feature amounts, and in the sub network, a higher-level classifier has a connection to one or more lower-level classifiers.

Abstract: A control device (100) includes an acquirer (110) that acquires transport article information expressing a characteristic of an article to be transported, and a generator (130) that generates, on the basis of the characteristic expressed in the acquired transport article information, transport control information that causes an unmanned vehicle to transport the article.

Abstract: An information processing apparatus (1) includes: an acquisition unit (101) configured to acquire an object image that contains a target object; a generation unit (102;103;104;105) configured to generate a plurality of feature vectors for the object by applying the object image to a plurality of learning models; a concatenation unit (106) configured to concatenate and embed the plurality of feature vectors into a common feature space to generate a compounded feature vector in the feature space; and a search unit (107) configured to search for a similar image that is similar to the object image, using the compounded feature vector.

Abstract: An information processing apparatus (10): sets a plurality of styles that each indicate a moving-image composition of a moving image which relates to a predetermined item and in which a plurality of pieces of image content corresponding to the predetermined item are used; acquires an attribute of a target user; estimates the most-suitable style for the target user among the plurality of styles based on the plurality of pieces of image content and the attribute of the target user; and provides a moving image that is in accordance with the estimated style to the user.

Abstract: An authentication system, comprising at least one processor configured to: execute first authentication for a first user when the first user is present at a first place or arrives at a first place; predict a predicted period in which a second user who has a possibility of being authenticated as the first user by the first authentication is not expected to be present at the first place or arrive at the first place, based on at least one type of information out of second-time information about a second time at which the second user has been present at a second place or has arrived at a second place and second-place information about the second place; and execute first processing for the first user based on the first authentication executed in the predicted period.