Abstract: A dialogue act estimation method includes acquiring learning data including a first sentence to be estimated in the form of text data of a first uttered sentence uttered at a first time point, a second sentence which is text data of a second uttered sentence uttered, at a time point before the first time point, successively after the first uttered sentence, act information indicating an act associated to the first sentence, property information indicating a property information associated to the first sentence, and dialogue act information indicating a dialogue act in the form of a combination of an act and a property associated to the first sentence, making a particular model learn three or more tasks at the same time using the learning data, and storing a result of the learning as learning result information in a memory.

Abstract: A method for controlling identification includes obtaining first text, which is text in a first language, obtaining second text, which is text in a second language obtained by translating the first text into the second language, obtaining correct labels, which indicate content of the first text, inputting the first text and the second text to an identification model common to the first and second languages, and updating the common identification model such that labels identified by the common identification model from the first text and the second text match the correct labels.

Abstract: A subject estimation system includes a convolutional neural network to estimate a subject label of a dialog. The convolution neural network includes: one or more topic-dependent convolutional layers and one topic-independent convolutional layer, each of the one or more topic-dependent convolutional layers performing, on an input of a word-string vector sequence corresponding to dialog text transcribed from a dialog, a convolution operation dependent on a topic, and the topic-independent convolutional layer performing, on the input of the word-string vector sequence, a convolution operation not dependent on the topic; a pooling layer performing pooling process on outputs of the convolutional layer; and a fully connected layer performing full connection process on outputs of the pooling layer.

Abstract: A decision tree generating apparatus includes an information gain calculator and a decision tree generator. When a classification target data set including a plurality of pieces of classification target data respectively having different attributes with attribute values assigned thereto is segmented into subsets in a form of a decision tree, the information gain calculator calculates an amount of entropy reduction on each attribute, and calculates an information gain, based on the amount of reduction in the entropy and reliability of a user's answer responsive to an inquiry asking about the attribute. The decision tree generator successively determines an attribute having a maximum information gain to be a node of the decision tree by recursively iterating the segmentation of the pre-segmentation data set, and generates the decision tree that is to be used to determine an order of the inquiries.

Abstract: An information processing method in an interactive apparatus that questions a user's symptom through interaction with a user includes: outputting first question information of a first type concerning the user's symptom to a display or a speaker connected to the interactive apparatus, receiving first answer information indicating an answer to the question in the first question information from a keyboard, a touch panel, or a microphone connected to the interactive apparatus, outputting second question information of the first type concerning the user's symptom to the display or the speaker when it is determined that the answer in the first answer information does not include a word in a negative expression, and outputting third question information of a second type concerning the user's symptom to the display or the speaker when it is determined that the answer in the first answer information includes the word in the negative expression.

Abstract: A meaning generation method, in a meaning generation apparatus, includes acquiring meaning training data including text data of a sentence that can be an utterance sentence and meaning information indicating a meaning of the sentence and associated with the text data of the sentence, acquiring restatement training data including the text data of the sentence and text data of a restatement sentence of the sentence, and learning association between the utterance sentence and the meaning information and the restatement sentence. The learning includes learning of a degree of importance of a word included in the utterance sentence, and the learning is performed by applying the meaning training data and the restatement training data to a common model, and storing a result of the learning as learning result information.

Abstract: A method is provided for controlling an operation of a target device using a plurality of input devices, including a speech input device. The method includes acquiring, from the speech input device, speech information, including i) environmental sound around the speech input device, and ii) a speech instruction indicating an operation to be performed on the target device. The method also includes calculating a level of noise included in the speech information, and recognizing the operation. The method further includes informing a user of a second input device as a recommended input device based on the calculated noise level and the recognized operation instruction, wherein the second input device does not include a speech input device.

Abstract: A method is provided for controlling electric equipment according to a user's speech in a speech-based equipment control system. The method includes receiving first speech information that expresses an operating instruction causing the electric equipment to operate for a first operating time. The method also includes transmitting to the electric equipment a first control command for executing a first operating process. When receiving second speech information expressing an operating instruction causing the electric equipment to operate for a second operating time, different from the first operating time before the first operating process is complete, the method further includes detecting an elapsed operating time of the electric equipment, comparing the detected elapsed operating time to the second operating time, and conditionally transmitting a second control command to the electric equipment aborting the first operating process and executing a second operating process.

Abstract: A method includes determining a content of a speech of a user on the basis of text data including a word string acquired as a recognition result of the speech, selecting a correction method suitable for the determined content of the speech from among multiple correction methods for correcting false recognition contained in the text data, and correcting the false recognition contained in the text data using the selected correction method.

Abstract: A method for controlling an operation of a target device using a plurality of input devices is disclosed. The method comprises: receiving from one of the plurality of the input devices a first operation instruction issued to the target device, with a first data format; recognizing the first operation instruction and the first data format; determining that the one of the plurality of the input devices is a first input device corresponding to the first data format; and providing to a user of the target device a recommendation for a second input device, a type of the second input device being different from a type of the first input device, when it is determined that a type of the first operation instruction is identical to a type of a second operation instruction received from the second input device earlier than the reception of the first operation instruction.

Abstract: A subject estimation system includes a convolutional neural network to estimate a subject label of a dialog. The convolution neural network includes: one or more topic-dependent convolutional layers and one topic-independent convolutional layer, each of the one or more topic-dependent convolutional layers performing, on an input of a word-string vector sequence corresponding to dialog text transcribed from a dialog, a convolution operation dependent on a topic, and the topic-independent convolutional layer performing, on the input of the word-string vector sequence, a convolution operation not dependent on the topic; a pooling layer performing pooling process on outputs of the convolutional layer; and a fully connected layer performing full connection process on outputs of the pooling layer.

Abstract: An exemplary electronic device is in a housing to be gripped by a right hand and a left hand of a user, and has a plurality of manipulable portions. The electronic device includes: electrodes placed at positions which come in contact with the right hand and left hand of the user gripping the housing; an extractor for extracting an electrocardiographic component of the user from a potential difference between the electrodes; a determination section for determining whether the extracted electrocardiographic component is in a positive direction or a negative direction by referring to a prestored criterion; and a change section for, in accordance with a result of determination by the determination section, changing assignment between each of the plurality of manipulable portions and a manipulation signal generated in response to a manipulation.

Abstract: A method includes acquiring a first corpus, including first text of a first sentence including a first word and described in a natural language, and second text of a second sentence including a second word different in meaning from the first word, a second word distribution of the second word being similar to a first word distribution of the first word, acquiring a second corpus including third text of a third sentence, including a third word identical to the first word and/or the second word, a third word distribution of the third word being not similar to the first word distribution, based on an arrangement of a word string in the first corpus and the second corpus, assigning to the first word a first vector representing a meaning of the first word and assigning to the second word a second vector representing a meaning of the second word.

Abstract: A cloud server extracts voiceprint data from voice data of a user, and distinguishes the user. The cloud server identifies a task which the user instructs, from the voice data of the user. If contexts required to execute the task have not been amassed, the cloud server registers the distinguished user as a task owner, and notifies the user with a reply sentence to cause the user to speak the required context. If the voiceprint data of the voice data which the user has uttered matches the voiceprint data of the user A, and all required contexts are amassed, the cloud server causes a device to execute the task.

Abstract: An exemplary electronic device is in a housing to be gripped by both hands, and measures the potentials of first and second fingers of respectively different hands. The device includes: a first electrode group provided in a position to come in contact with the first finger, including a first main electrode and at least one first auxiliary electrode provided in a position away from the first main electrode; a second electrode group provided in a position to come in contact with the second finger, including a second main electrode and at least one second auxiliary electrode provided in a position away from the second main electrode; a biological signal processor for, from potential values measured at the first and second electrode groups, determining respective contact states concerning the first and second fingers; and a transmission circuit for presenting information concerning a finger contact state based on a result of determination.

Abstract: In a running control method of a running apparatus, person moving direction and speed are estimated based on a person position history for predetermined time. It is decided whether contact with a person is likely to be made based on the estimation and running information about the running apparatus. When it is decided that the contact is likely to be made, a first route where the running apparatus avoids the person is generated for controlling running of the running apparatus therealong. It is decided whether the person has the intention to contact with the running apparatus based on the decision in the contact possibility deciding unit after the running along the first route. When it is decided that the person has the contact intention, a second route where the running apparatus approaches the person is generated for controlling the running of the running apparatus therealong.

Abstract: In a case of receiving, from an audio input device, instruction information including first audio information indicating operation instructions for a cooking appliance when first and second cooking units are executing first and second cooking programs, respectively, operation instructions are recognized from the first audio information. In a case where it is determined that the instruction information includes second audio information related to the first cooking menu information or the second cooking menu information, a control command is transmitted to the cooking appliance to cause the cooking appliance to execute a process corresponding to the operation instructions, without executing a process according to the first cooking program or the second cooking program corresponding to one of the first cooking menu information or the second cooking menu information to which the second audio information is related.

Abstract: A movement information calculator calculates a moving direction and a speed of the moving person from a position history database. An approach time calculator calculates an approach time at which an autonomous running apparatus and the moving person approach to each other within a predetermined distance from the moving person's position, moving direction, and speed, and the running information. A gaze position obtaining unit obtains a moving person's gaze position from the moving person's position and moving direction, and the position of an obstacle recorded in an obstacle database. A gaze region calculator calculates a moving person's gaze region from the moving person's position, moving direction, and gaze position. A running information generator generates running information for making the autonomous running apparatus run to the gaze region at a predetermined time earlier than the approach time from the obstacle's position, the approach time, and the gaze region.

Abstract: A method for controlling an operation of a target device using a plurality of input devices is disclosed. The method comprises: receiving from one of the plurality of the input devices a first operation instruction issued to the target device, with a first data format; recognizing the first operation instruction and the first data format; determining that the one of the plurality of the input devices is a first input device corresponding to the first data format; and providing to a user of the target device a recommendation for a second input device, a type of the second input device being different from a type of the first input device, when it is determined that a type of the first operation instruction is identical to a type of a second operation instruction received from the second input device earlier than the reception of the first operation instruction.

Abstract: A movement information calculator calculates a moving direction and a speed of the moving person from a position history database. An approach time calculator calculates an approach time at which an autonomous running apparatus and the moving person approach to each other within a predetermined distance from the moving person's position, moving direction, and speed, and the running information. A gaze position obtaining unit obtains a moving person's gaze position from the moving person's position and moving direction, and the position of an obstacle recorded in an obstacle database. A gaze region calculator calculates a moving person's gaze region from the moving person's position, moving direction, and gaze position. A running information generator generates running information for making the autonomous running apparatus run to the gaze region at a predetermined time earlier than the approach time from the obstacle's position, the approach time, and the gaze region.