Abstract: A training data confirmation support device according to the present disclosure includes a label inference unit that infers inference labels that are labels corresponding to elements included in training data in which elements and correct labels corresponding to the elements are associated with each other using a model that is learned using the training data and infers labels corresponding to the elements, and an evaluation unit that generates evaluation results of the training data creators on the basis of comparison between correct labels corresponding to elements included in the training data and inference labels of the elements.

Abstract: A word selection support device according to the present disclosure includes processing circuitry configured to derive, for each extracted unknown word that is a term that is extracted from a target corpus and is not registered in dictionary data, statistical information regarding the extracted unknown word in a plurality of corpuses including the target corpus, and calculate appropriateness as a registered unknown word possibility that is a possibility of an unknown word to be registered in the dictionary data for each of the extracted unknown word on the basis of the statistical information.

Abstract: A support device according to the present disclosure includes a label inference unit that infers inference labels that are labels corresponding to elements included in training data in which elements and correct labels corresponding to the elements are associated with each other using a model that is learned using the training data and infers labels corresponding to the elements, and an evaluation unit that generates training data confirmation screens including elements included in the training data, correct labels of the elements, and inference labels of the elements.

Abstract: A learning device (10) according to the present disclosure includes a data set division unit (11) as a training data processing unit and a divided data set learning unit (12) as a model learning unit. The data set division unit (11) divides a new training data set into a plurality of divided data sets on the basis of attribute information. After performing model learning processing using an existing model as a learning target model, the divided data set learning unit (12) creates a new model by repeating the model learning processing until all the divided data sets are learned using a learned model created by the model learning processing as a new learning target model.

Abstract: Provided is an endoluminal device system including: an elongated and flexible endoluminal device; a wire that is disposed in the endoluminal device; a first sensor that detects tension of the wire; a second sensor that detects displacement of the wire; a driving device capable of pulling the wire; and a processor. The processor is configured to: cause the driving device to execute a relaxing operation for relaxing the wire, acquire the tension and the displacement of the wire during the relaxing operation, which are detected by the first sensor and the second sensor, respectively, and adjust a control parameter of the endoluminal device based on a rate of change in the tension with respect to the displacement.

Abstract: A manipulator system includes: a manipulator including a bending portion and a bending wire configured to bend the bending portion; a driving portion configured to pull and loosen the bending wire; and a control device configured to control the driving portion, wherein the control device controls the driving portion to perform an initialization operation that alternately repeats pulling and loosening of the bending wire so that an amount of change in a bending shape of the bending portion compared to when the initialization operation is started falls within a predetermined range.

Abstract: A method for calibrating an endoscope, the endoscope including a curved portion that can be driven to bend and a flexible portion through which a bending wire that bends the curved portion is inserted, includes: arranging the curved portion and the flexible portion of the endoscope so that they have a predetermined shape; bending the curved portion; measuring first shape information, which is information about a shape of the curved portion; and updating a control parameter for the endoscope to drive the curved portion based on the measured first shape information.

Abstract: An endoscope system includes: an endoscope including an insertion portion having a joint and first and second wires fixed on both sides of the joint; a drive device that is connected to the endoscope and bends the joint by driving the first and second wires; and a processor that controls the drive device. The processor can perform position control that controls traction amount or delivery amount of one of the first and second wires based on target position for bending the joint, and tension control that controls traction amount or delivery amount so that tension of the other of the first and second wires matches a specified set value, and execute a drive mode in which one of the first and second wires is controlled by the position control and the other of the first and second wires is controlled by the tension control.