Nippon Telegraph and Telephone Corporation

Ntt Corporation

Oki Semiconductor Co., Ltd.

Hiroyuki Toda

Takeshi Kurashima

Shuhei Yamamoto

Masahiro Kojima

Tatsushi Matsubayashi

Takuya Nishimura

Masami Takahashi

Yasunori Akagi

Yusuke Tanaka

Daisuke Sato

Yoshiaki Takimoto

Tomu Tominaga

Maya Okawa

Yuya Hikima

Noriko Yokoyama

Yasuhito Yoshida

An action-sequence generation unit of an information presentation device generates, based on an action log representing a target action of a user and an action history of the user, an action sequence representing a sequence of actions including the target action. A permission-level calculation unit calculates, based on the action log and a permission log, about the actions, a permission level representing a difference between a time period when the actions included in the action log were performed and a time period when the actions included in the permission log are permitted. An action specifying unit specifies, based on the action sequence and the permission level, out of the actions in the action sequence, an action, the permission level of which is equal to or larger than a threshold concerning the permission level, as a trigger action among the actions included in the action sequence.

Information presentation device, information acquisition device, information presentation method, information acquisition method and information presentation program

The present invention relates to a parameter estimation system, a parameter estimation method, and a program, and more particularly to a parameter estimation system, a parameter estimation method, and a program that efficiently estimate parameters of machine learning and simulation, etc. An objective of the present invention is to provide a parameter estimation system and a parameter estimation method that may rapidly determine the optimum input parameter.

Parameter estimation device, method and program

A learning device includes: a psychological state data preprocessing unit that calculates a duration of a psychological state from psychological state sequence data, and generates preprocessed psychological state sequence data including the psychological state and the duration; and a learning unit that learns a psychological state sequence prediction model, using input sequence data including behavior sequence data and the preprocessed psychological state sequence data, and correct sequence data that is preprocessed psychological state sequence data at a time later than the input sequence data.

Learning apparatus, mental state sequence prediction apparatus, learning method, mental state sequence prediction method and program

A hazard estimation unitestimates a likelihood of an occurrence of an event according to a hazard function, with respect to each of a plurality of pieces of time-series data that are a series of multiple pieces of data to which an event occurrence time relevant to the data is given in advance and that include time-series data in which the event did not occur and time-series data in which the event occurred. A parameter estimation unitestimates a parameter of the hazard function so as to optimize a likelihood function expressed by including the event occurrence time given with respect to each of the plurality of pieces of time-series data and the likelihood of the occurrence of the event estimated with respect to each of the plurality of pieces of time-series data.

Event occurrence time learning device, event occurrence time estimation device, event occurrence time learning method, event occurrence time estimation method, event occurrence time learning program, and event occurrence time estimation program

An intersection determination is made regarding whether or not a traffic route included in map information intersects a boundary between areas on a basis of the traffic route and an area shape between areas that are adjacent in the map information, the intersection determination being made for each pair of adjacent areas. On a basis of a weight determined for the boundary in a case where the intersection determination is made that no intersection exists, a movement cost graph expressing a movement cost for each area that accounts for the weight is constructed. A corrected shortest distance between areas is calculated on a basis of the movement cost graph. A human mobility between areas is estimated for each timestep, the timestep being the length of a predetermined time interval, according to a predetermined function for estimating the human mobility between areas on a basis of the corrected shortest distance between areas and a population of each of the areas at different predetermined times.

Moving number estimating device, moving number estimating method, and moving number estimating program

The present disclosure enables vehicle dispatch in consideration of individual differences of each orderer for a price and a required time by a computer executing an input procedure to input parameters for a distance matrix relating to a distance between a taxi and an orderer giving a taxi dispatch order, a travel distance for an order, an opportunity cost parameter for a taxi driver, and an acceptance probability function of the orderer, and a calculation procedure to calculate a price and a required time to be presented to the orderer by solving an optimization problem formulated using the parameters.

Calculation method, calculation apparatus and program

A personal remaining movement estimation unit () estimates information relating to a remaining movement of a user on the move based on a movement trajectory of the user on the move, a personal destination estimation unit () predicts a destination of the user on the move based on information estimated by the personal remaining movement estimation unit () and information indicating the number of people moving between areas of a plurality of users stored in a movement trend information storage unit (), and it is thereby possible to predict a destination even for a user having no information on past movement trajectories.

Device, method, and program for predicting destination

A prediction device includes: a normal prediction unit configured to predict first prediction values for target ranges of respective models, based on respective pieces of spatio-temporal observation data including observation values for respective observation locations and respective observation times observed for a given time period and the respective models for predicting variations of the pieces of spatio-temporal observation data for the respective target ranges defined for at least one of an observation location or a period; a residual extraction unit configured to extract, based on residuals between the respective pieces of spatio-temporal observation data being observed and the models corresponding to the respective pieces of spatio-temporal observation data based on the pieces of spatio-temporal observation data and the models, the respective pieces of spatio-temporal observation data with residuals greater than or equal to a threshold value, as spatio-temporal residual data; a residual prediction unit configured to predict, based on the spatio-temporal residual data, second prediction values for the target ranges corresponding to the spatio-temporal residual data in accordance with a predetermined prediction technique; and a synthesis unit configured to output prediction values obtained by synthesizing the first prediction values and the second prediction values.

Prediction device, prediction method, and prediction program

An observation streamlining apparatus includes one or more computers each including a memory and a processor configured to discriminate between an observation-necessary time slot and an observation-unnecessary time slot with an intervention measure including at least a time when a predetermined intervention is performed on a user as an input, the observation-necessary time slot indicating a time slot when a user's action or state needs to be observed, and the observation-unnecessary time slot indicating a time slot when the user's action or state does not need to be observed; and execute predetermined processing for observing the user's action or state when the observation-necessary time slot arrives.

Observation streamlining apparatus, observation streamlining method and program

A moving state analysis device improves accuracy of moving state recognition by including a detection unit configured to detect, from image data associated with a frame, an object and a region of the object, for each of frames that constitute first video data captured in a course of movement of a first moving body, and a learning unit configured to learn a DNN model that takes video data and sensor data as input and that outputs a probability of each moving state, based on the first video data, a feature of first sensor data measured in relation to the first moving body and corresponding to a capture of the first video data, a detection result of the object and the region of the object, and information that indicates a moving state associated with the first video data.

Moving state analysis device, moving state analysis method, and program

A movement state recognition multitask DNN model training sectiontrains a parameter of a DNN model based on an image data time series and a sensor data time series, and based on first annotation data, second annotation data, and third annotation data generated for the image data time series and the sensor data time series. Training is performed such that a movement state recognized by the DNN model in a case in which input with the image data time series and the sensor data time series matches movement states indicated by the first annotation data, the second annotation data, and the third annotation data. This thereby enables information to be efficiently extracted and combined from both video data and sensor data, and also enables movement state recognition to be implemented with high precision for a data set including data that does not fall in any movement state class.

Movement state recognition model training device, movement state recognition device, methods and programs therefor

A high frequency signal detection circuit includes an input terminal for a high frequency signal to be detected, a switch transferring the high frequency signal as intermittent ringing signal to a first node in response to a pulse signal whose frequency is lower than that of the high frequency signal, a transistor amplifying the signal at the first node, and outputting to a second node, a bias generator generating a bias voltage by which the transistor is operated in its weak inversion region, a resonant circuit outputting the bias voltage to the first node, and resonating the high frequency signal, a capacitor removing a high frequency component of the signal at the second node; and a judgment circuit judging whether or not the high frequency signal is inputted by detecting the signal at the second node, which has the same frequency as the pulse signal.

Growing community of inventors

Tokyo, Japan

Hiroyuki Toda