Ntt Docomo, Inc.

Yusuke Fukazawa

Keiichi Ochiai

Shoji Kurakake

Takefumi Naganuma

Satoshi Kawasaki

Naoki Yamamoto

Anna Oonishi

Takashi Hamatani

Masato Yamada

Hidetoshi Ueno

Haruka Kikuchi

Masashi Onogi

Midori Onogi

Shigeki Tanaka

Mirai Hara

Kunihiro Fujii

Masatoshi Kimoto

Akiya Inagaki

Putri Fatina

Shin Ishiguro

Yoshitaka Inoue

Noriaki Hirokawa

Taku Itou

Tsukasa Demizu

A prediction interpretation apparatus, comprising: a data storage unit configured to store data of a plurality of users; a model storage unit configured to store a prediction model learned from data of the whole of the plurality of users; a vicinity user search unit configured to extract vicinity users for the target user from the data storage unit; a linear regression model learning unit configured to learn a linear regression model approximated to the prediction model for the vicinity users; and an interpretation result output unit configured to output an interpretation result of prediction for the target user based on a partial regression coefficient of the linear regression model, wherein the vicinity user search unit extracts the vicinity user by narrowing vicinity user candidates extracted based on distance between users based on a prediction direction of the target user by the prediction model.

Prediction interpretation apparatus and prediction interpretation method

A system of generating a model for estimation is a system that generates the model for estimation used for estimation based on information about musical pieces, the system including: a learning data acquiring unit configured to acquire learning information in which information about audio data of a plurality of musical pieces having sequences is aligned in a dimension of the sequences in order of the sequences that is learning data used for machine learning; and a model generating unit configured to generate the model for estimation by performing machine learning using the learning information as an input to the model for estimation performing convolution using a kernel in the dimension of the sequences.

System of generating model for estimation, and estimation system

A state estimation device includes a sensor information acquisition unit that acquires time-series sensor data, a state allocation unit that provisionally allocates a state label to sensor data, a first model learning unit that calculates a feature parameter of sensor data to which the same state label is allocated and performs learning of a state estimation model that classifies the sensor data at each time into any one of states, a second model learning unit that performs learning of a state transition model whose input is transition of state labels before a transition reference time and whose output is a state label at a time subsequent to the transition reference time, a state allocation update unit that updates a state label allocated to each time based on the state at each time estimated, and an output unit that outputs the state estimation model and the state transition model.

State estimation device, state estimation program, estimation model, and state estimation method

A type estimation model generation system is a system that generates a type estimation model used for type estimation of estimating one of a plurality of types to which a user belongs, the system including: a learning data acquiring unit configured to acquire learning time series information that is information of a time series about a plurality of used musical pieces and learning type information representing types to which users who have used the plurality of musical pieces belong that are learning data used for machine learning; and a model generating unit configured to generate the type estimation model by performing machine learning using information based on the learning time series information as an input for the type estimation model in units of musical pieces in order of the time series and information based on the learning type information as an output of the type estimation model.

Type estimation model generation system and type estimation system

A POI popularity derivation device () includes: a dictionary generation unit () that assigns a feature word used as a co-occurrence word of a POI name to each popularity-assigned POI name serving as a popularity assignment target to generate a popularity-assigned POI dictionary in which a popularity-assigned POI name and a feature word are associated with each other; an extraction unit () that extracts posted data serving as a search target from posted data on the basis of predetermined criteria; and a popularity derivation unit () that searches for the posted data on the basis of a predetermined rule regarding feature words while referring to the popularity-assigned POI dictionary, to extract posted data linked to the popularity-assigned POI name, and derives the popularity of each popularity-assigned POI name on the basis of the number of pieces of extracted posted data for each popularity-assigned POI name.

POI popularity derivation device

A learning system includes a learning data acquisition unit that generates a neural network included in a single forecast model for performing a forecast of demand for a service through machine learning and acquires, as learning data, an actual demand value of the service and a feature amount for learning for each mesh associated with a past period, the feature amount for learning including the number of demands for the service in each mesh in each period as a feature amount, a learning data normalization unit that normalizes at least the number of demands in the feature amount for learning for each mesh, and a generation unit that performs machine learning on the basis of an actual demand value and a demand forecast value obtained by inputting the feature amount for learning including the normalized number of demands to the neural network, and generates the neural network.

Learning and using a single forecast model for demand forecasting

A popularity estimation device includes: an acquisition unit configured to acquire a first map image including a first particular point and to acquire a plurality of second map images including a second particular point which is a particular point; a generation unit configured to generate a first feature vector and a second feature vector by inputting the first map image and the second map images to a geographical feature generation model with a map image as an input and with a feature vector indicating geographical features of the map image as an output; a score calculating unit configured to calculate a popularity score of the first particular point from a popularity score of the second particular point based on a degree of similarity between the first feature vector and the second feature vector; and an output unit configured to output the popularity score of the first particular point.

Popularity evaluation system and geographical feature generation model

Provided is a re-ranking device that enables a re-ranking process with less possibility of decrease in accuracy due to shortage of data. A re-ranking deviceincludes an input unitthat receives a search query from one user, a re-ranking model storage unitthat stores a plurality of re-ranking models prepared in accordance with common information of a plurality of users, a search unitthat performs a search on the basis of the search query and obtains a search result, and a re-ranking processing unitthat selects one re-ranking model on the basis of common information of the one user and performs a re-ranking process on the search result using the one re-ranking model.

Re-ranking device

A server includes a first statistic processor configured to calculate, for each of different types of screens displayed on a display; a first statistic value of display time of a screen of each type display on the display, to generate first statistic values corresponding to the different types of screens; a first determiner configured to determine, for each type of the screens, whether a user is concentrating on a screen of each type, based on, from among the first statistic values, a first statistic value calculated for the screen of each type; and a generator configured to generate a list including screen identification information for identifying, from among the different types of screens, a type of screen for which a corresponding determination result from the first determiner is affirmative.

Information generation apparatus and control system

An information generation apparatus includes a feature information generator that generates feature information on transition to a first screen based on a log including a transition timepoint and identification information, the transition timepoint being a timepoint when a foreground screen transitioned from a second screen to the first screen among a plurality of screens displayed by a plurality of program modules that differ from each other, and the identification information identifying from among the program modules a first program module for displaying the first screen, an index value generator that generates an index value indicative of a degree to which the first screen draws attention from a user based on the feature information, and a determiner that determines based on the index value whether to use the identification information that identifies the first program module in a process of estimating the state of the user.

Information processing apparatus

A feature extraction device is a device that extracts a feature quantity to be input to a state estimation model for estimating a state related to a terminal where the activity is executed or a user of the terminal, which includes an acquisition unit that acquires activity history information indicating an execution history of the activity in a specified period of time and including time-series activity logs, an extraction unit that extracts co-occurrence relationship information indicating a co-occurrence relationship of activities in a specified period of time based on the activity history information, a generation unit that aggregates activity feature quantities indicating a feature of each activity based on the co-occurrence relationship information and generates an activity history feature quantity indicating a feature of the activity history information, and an output unit that outputs the activity history feature quantity as a feature quantity to be input to the state estimation model.

Feature extraction device and state estimation system

A visiting destination prediction device includes: a user position information acquiring unit configured to acquire user position information indicating a position of a user; an action history acquiring unit configured to acquire information on an action history of the user; and a visiting POI estimating unit configured to estimate a visiting POI which is a visiting destination of the user on the basis of a relationship between an acquired user position and a previously stored POI position and a relationship between the acquired action history of the user in a predetermined period and previously stored POI relevant information.

Visiting destination prediction device and visiting destination prediction method

A visiting destination prediction device includes: a user position information acquiring unit configured to acquire user position information indicating a position of a user; a stationary position deriving unit configured to derive a stationary position of the user on the basis of the acquired user position information; and a visiting POI estimating unit configured to estimate a visiting POI which is a visiting destination of the user on the basis of a relationship between the derived stationary position of the user and a predetermined POI position of a POI which is able to be the visiting destination of the user. The stationary position deriving unit derives the stationary position which is expressed by an area on the basis of an error and a degree of dispersion of a series of pieces of the acquired user position information.

A determination deviceincludes: a history storage unitconfigured to accumulate and store use history information in which application identification information, position information indicating a position of a user, and user identification information are correlated with each other; a use region UU number totaling unitconfigured to total a UU number for each of a plurality of regions on the basis of the use history information for a specific application; a use region number totaling unitconfigured to total the number of regions on the basis of the use history information for the specific application; a score calculating unitconfigured to calculate a regionality score for each of the plurality of regions on the basis of the UU number and the number of regions for the specific application; and a determination unitconfigured to determine whether there is regionality for the specific application on the basis of the regionality score.

Determination device

A POI (Point Of Interest) information updating device () includes an input unit () configured to input POI identification information for identifying a POI, an acquisition unit () configured to acquire event information on an event performed at a target POI identified by the POI identification information input by the input unit, a search unit () configured to search for similar event information similar to the event information acquired by the acquisition unit (), and an updating unit () configured to update information on the target POI on the basis of information on a POI at which an event indicated by the similar event information searched for by the search unit () has been performed.

Growing community of inventors

Chiyoda-ku, Japan

Yusuke Fukazawa