Abstract: Disclosed is an image processing apparatus including a receiving section that receives a captured image of a target object, a recognizing section that performs recognition of the target object by extracting feature points of the target object on the basis of the captured image, a recommending section that gives recommendation regarding an imaging direction on the basis of a type of the target object, and an instruction section that gives an instruction on a specific direction to capture an image of the target object, on the basis of a result of the recognition and a result of the recommendation.
Abstract: A control device 200 includes at least one memory configured to store a program code, and at least one processor configured to access the program code and operate as instructed by the program code. The program code includes an acquisition code configured to cause the at least one processor to acquire a request for requesting determination as to whether or not a target area is usable for a predetermined purpose, and a control code configured to cause the at least one processor to perform control to cause a first flying object to fly to the target area. The acquisition code is configured to cause the at least one processor to further acquire sensing data that is data obtained by optical sensing of the target area by the first flying object. The program code further comprises a determination code configured to cause the at least one processor to determine, based on the acquired sensing data, whether or not the target area is usable for the predetermined purpose.
Abstract: The center server 3 determines, for each take-off/landing port 2, any one of charging of the UAV 1, discharging of the UAV 1, operation of the UAV 1 for article delivery, and standby of the UAV 1 as a action to be implemented in the take-off/landing port 2 on the basis of delivery schedule information related to a schedule for article delivery and battery information of the UAV 1 deployed in each of the plurality of take-off/landing ports 2.
Abstract: The information processing server 2 communicates with the user terminal 3 of the recipient of the article delivered by the delivery machine 1, specifies content that is content according to the delivery waiting time until the delivery machine 1 arrives at the delivery destination of the article and that can be output on the user terminal 3 during the delivery waiting time, and provides the specified content to the user terminal 3 during the delivery waiting time.
Abstract: Disclosed herein is an information processing apparatus, comprising: a data set acquisition unit configured to acquire a first training data set that stores training data in which a first natural language sequence is correlated to a second natural language sequence; an analysis unit configured to extract a segment indicating either non-honorific or honorific expressions from the second natural language sequence in the first training data set, and analyze the extracted segment; and a data set conversion unit configured to convert, based on an analysis result of the segment, the first training data set into a second training data set that is different from the first training data set and in which the honorific expression in the second natural language sequence is enriched over the non-honorific expression with respect to the first training data set.
Abstract: A dialogue control system, comprising at least one processor configured to: acquire remark information about a remark of a user; control a plurality of dialogue generators each for generating, when the remark information is acquired, reply information about a reply to be made in response to the remark indicated by the remark information; and output the reply information generated by at least one of a plurality of dialogue generators, wherein the acquisition of the remark information and the output of the reply information are repeated so that a dialogue progresses, and wherein each of the plurality of dialogue generators is configured to generate new reply information based on the reply information that has been generated and output by another of the plurality of dialogue generators.
Abstract: An UAV 1 performs a detachment control to detach a cargo supported by a support portion 117 or connected a connecting portion 118, and thereafter, performs a load detection process of detecting a mechanical load applied to the support portion 117 or the connecting portion 118. And then An UAV 1 performs different control according to the mechanical load, with respect to a movement of the UAV 1 after the detection of the mechanical load.
Abstract: A bidding assistance device includes a ratio calculation unit configured to calculate a ratio of an actual advertising cost index to a goal advertising cost index, the actual advertising cost index being based on an advertising delivery performance at a bidding time in an advertising period, the goal advertising cost index being requested by an advertiser in the advertising period, an adjustment factor calculation unit configured to calculate an adjustment factor from the ratio and from a relationship between the advertising period and the bidding time, the adjustment factor being used to adjust a bid price of an advertisement, and a determination unit configured to determine the bid price at the bidding time using the adjustment factor calculated by the adjustment factor calculation unit, the goal advertising cost index, and a forecast effectiveness index forecast from advertising effectiveness, the advertising effectiveness being obtained from the advertising delivery performance.
Abstract: Photographed image acquisition means (201) of an information processing device (20) acquires a photographed image photographed by photographing means (25) capable of photographing a target image including predetermined information. Reference means (202) refers to storage means (200) for storing the target image photographed in the past and information extracted from the target image in the past, in association with each other. Determination means (207) determines whether or not the target image photographed in the past has been captured in the photographed image. Processing execution means (211) executes, when the target image photographed in the past has been captured in the photographed image, predetermined processing based on the information associated with the target image.
Abstract: The article transfer system S selects an article transfer candidate on the basis of first sensing information obtained from first sensing performed by the unmanned aerial vehicle in flight, performs a movement control of the unmanned ground vehicle on the basis of position information of the selected article transfer candidate, and determines an article transfer place with reference to the selected article transfer candidate on the basis of second sensing information obtained from second sensing performed by the unmanned ground vehicle.
Abstract: A computer system document according to one embodiment includes a generation unit and an update unit. The generation unit performs first machine learning on a target document, as input data, to which a correct path in a tree structure where each node indicates a document category is given, and thereby generates a classification model indicating a right path to a leaf node for the target document. The update unit performs second machine learning that applies, to the classification model, the target document to which the correct path is not given, and when a path from an Nth level node to an (N+1)th level node is different from the correct path, updates the classification model by setting a modified path from the (N+1)th level node to an (N+2)th level node different from a child node of the (N+1)th level node based on the correct path.
Abstract: The present disclosure relates to a new method for cross-modal retrieval via deep binary hashing and quantization. In a training phase, the system simultaneously learns to generate feature vectors, binary codes, and quantization codes for data across two or more modalities that preserves the semantic similarity correlations in the original data. In a prediction phase, the system retrieve a data item in a database that is semantically similar to a query item of a different modality. To identify the database item closest in semantic meaning to the query item, the system first narrows the database search space based on binary hash code distances between each of the database items and the query item. The system then measures the quantization distances between the query items and the database items in the smaller search space. The system identifies database item have the closest quantization distance to the query item as the closest semantic match to the query item.
Abstract: A system for avoiding an access conflict between a plurality of devices that access an IC module. The system includes a first device and a second device that can access an IC module used in an electronic money system. The second device has the function of detecting waves having a predetermined pattern to indicate that the first device is accessing the IC module. These waves may be continuously generated from the first device or may be continuously generated from another device installed near the first device, and when the second device detects the waves having the predetermined pattern, the second device refrains from accessing the IC module. This allows the system to implement autonomous conflict control between a plurality of devices that access the IC module that does not have an adequate conflict control function without providing a special control circuit.
Abstract: A device searches a file being recorded that includes lines sorted in accordance with keys included in the lines to find a line that matches a pattern. When the device receives a pattern, it initializes upper and lower limits of a search range and calculates a middle position between the limits. It acquires, from the file, a middle line that starts at or before the middle position and ends after it. If the key included in the middle line matches the pattern, it outputs the middle line and re-sets the upper or lower limit based on whether the key included in the middle line is greater or less than the pattern and, if there is a distance greater than a length of a newline between the limits, repeats the procedure starting from the middle position. Otherwise, it outputs a result to the effect that no matching line has been found.
Abstract: An unmanned aerial vehicle, including: a propelling device configured to generate a downward airstream; a package carrier; and wheels arranged so as to allow the package carrier to stand alone. The package carrier includes: vertical members which surround a package in a horizontal direction to prevent falling of the package; support members configured to support a load of the package at positions; and a coupling device configured to hold vertical members so as to enable relative horizontal movement. The support members are each fixed to a corresponding one of the vertical members. The wheels are each mounted to the corresponding one of the vertical members, and enable the relative horizontal movement of the vertical members under a state in which the wheels are on the ground. Through the relative horizontal movement of the vertical members, the package is separable from the support members.
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: An aerial vehicle according to the present invention includes: at least one rotor configured to generate an air flow for lifting; and at least one sound producing structure having an opening and configured to produce sound for scaring birds and animals when the air flow generated by the rotor causes air to flow into the opening.
Abstract: An unmanned aerial vehicle is caused to fly by avoiding a no-fly zone, which changes as a moving object moves. Provided is an unmanned aerial vehicle control system, including: moving object position acquisition means for acquiring moving object position information on a current position of a moving object moving above a surface of an earth; zone setting means for setting a no-fly zone in which a flight of an unmanned aerial vehicle is inhibited based on the moving object position information; and flight control means for controlling the flight of the unmanned aerial vehicle so that the unmanned aerial vehicle avoids the no-fly zone set based on the moving object position information.
Abstract: The delivery system S acquires sensing information sensed in a transfer area by a sensor mounted on UAV 1 that delivers an article, and determines whether visibility in the transfer area is good on the basis of the sensing information. Then, in a case where it is determined that the visibility is not good, the delivery system S performs a first notification processing for stopping a recipient who is going to receive the article from heading for the area, while in a case where it is determined that the visibility is good, the delivery system S performs a second notification processing for directing the recipient to head for the area.
Abstract: The UAV 1a includes a dust sensor 16 and a dust-preventing function 17 and performs a processing for a different UAV 1b not provided with a dust-preventing function on the basis of a dust amount detected by the dust sensor 16 during a flight of the UAV 1a.