Nec Corporation

Satoshi Morinaga

Ryohei Fujimaki

Shinji Nakadai

Kenji Aoki

Riki Eto

Hironori Mizuguchi

Satoshi Nakazawa

Yukitaka Kusumura

Yousuke Motohashi

Manabu Kusumoto

Yoshio Kameda

Takeo Nozaki

Yuki Chiba

Kazuyo Narita

Yuki Kosaka

Yoshinobu Kawahara

Kaori Yamada

Daisuke Komura

Shunsuke Hirose

Aiko Kumano

Maki Komamine

Yosuke Motohashi

Michinari Momma

Ayumi Endo

The target setting unitsets a target state of the self-driving vehicle. The planned route creating unitcreates a planned route of the self-driving vehiclefor realizing the target state. The transmission unittransmits the planned route to another vehicle. The response receiving unitreceives, from another vehicle, a notification indicating agreement with the planned route or disagreement with the planned route as a response to the planned route. The traveling control unitcontrols the self-driving vehicleso as to cause the self-driving vehicleto travel along the planned route when the response receiving unithas received the notification indicating agreement with the planned route.

Vehicle control system, self-driving vehicle, vehicle control method, and program

The non-traveling area plan creating unitcreates a plan of the non-traveling area, which is an area where the self-driving vehiclecan travel and which is an area set as an area where the self-driving vehicledoes not travel. The negotiation area information receiving unitreceives, from another vehicle, information on one or more negotiation areas each of which is an area other than the non-traveling area and is a subject of negotiation to be included in the non-traveling area. The permissible area determining unitcalculates, for each negotiation area, the first value which is the value of the negotiation area indicated by the information for the self-driving vehicle, and determines one negotiation area permissible to be included in the non-traveling area, or determines not to include any negotiation area in the non-traveling area.

A prediction data input unitinputs prediction data that is one or more explanatory variables that are information likely to affect future sales. An exposure pattern generation unitgenerates an exposure pattern which is an explanatory variable indicating the content of a commercial message scheduled to be performed during a period from predicted time to future prediction target time. A component determination unitdetermines the component used for predicting the sales, on the basis of a hierarchical latent structure that is a structure in which latent variables are represented by a tree structure and components representing probability models are located at nodes of a lowest level of the tree structure, gating functions for determining a branch direction in the nodes of the hierarchical latent structure, and the prediction data and the exposure pattern. A sales prediction unitpredicts the sales on the basis of the component determined by the component determination unitand of the prediction data and the exposure pattern.

Commercial message planning assistance system and sales prediction assistance system

The planned route creating unitcreates a planned route of the self-driving vehicle. The non-traveling area plan creating unitcreates a plan of the non-traveling area, which is an area where the self-driving vehiclecan travel and which is an area set as an area where the self-driving vehicledoes not travel. The non-traveling area plan creating unitcreates a plan of the non-traveling area at a frequency lower than the frequency at which the planned route creating unitcreates a planned route. The transmission unittransmits the plan of the non-traveling area to the other vehicle each time the plan of the non-traveling area is created.

An apparatus that extracts an explanatory variable used as a condition from a classification model classified by the condition for selecting a component used for prediction, displays the explanatory variable in association with any of dimensional axes of a multi-dimensional space in which a prediction value is displayed, specifies the component that corresponds to a position in the multi-dimensional space specified by each of the explanatory variables associated with the dimensional axis, displays the prediction value calculated based on the specified component, on the same position and displays the multi-dimensional space that corresponds to the position in which the prediction value is displayed, in a mode that corresponds to the component used for calculating the prediction value.

Prediction result display system, prediction result display method, and prediction result display program

A method of extracting a combination of a drug and an adverse event related to the drug includes: for each of positive example combinations, negative example combinations and combinations that are neither positive examples nor negative examples, which are combinations of drug and disease, extracting medical events from medical information data about a patient and generating attribute data based on time-series information about the medical events; and learning a discriminant model based on attribute data of the positive and negative examples; and inputting attribute data corresponding to the combinations that are neither positive examples nor negative examples to the discriminant model to determine scores.

Drug adverse event extraction method and apparatus

An information processing device according to the present invention, includes: an information accumulation unit which receives and accumulates control-target information that includes information related to a control target and an environment including the control target; a prediction-equation-set learning and generation unit which learns and generates a prediction-equation set to be used for determination of an operation quantity of the control target based on the control-target information accumulated in the information accumulation unit; and an operation-quantity determination unit which receives input information needed for determination of an operation quantity of the control target, constructs a predictive-control model of the control target based on the prediction-equation set, the control-target information accumulated in the information accumulation unit, the control-target information received, and the input information, and determines an operation quantity used for control of the control target.

Information processing device, predictive control method, and recording medium

A visualization device includes: an evaluation index calculation unitwhich calculates the value of an evaluation index representing a feature degree for each of combinations of a first attribute group and a second attribute group in terms of data on the second attribute group including one or more attributes and conditioned with the first attribute group including one or more attributes among high-dimensional data to be visualized; and a visualization processing unitwhich generates image information for presenting combinations of the first attribute group and the second attribute group, which are determined to have large evaluation index values based on a predetermined criterion.

Visualization device, visualization method and visualization program

A hierarchical latent structure setting unitsets a hierarchical latent structure that is a structure in which latent variables are represented by a tree structure and components representing probability models are located at nodes of a lowest level of the tree structure. A variational probability computation unitcomputes a variational probability of a path latent variable that is a latent variable included in a path linking a root node to a target node in the hierarchical latent structure. A component optimization unitoptimizes each of the components for the computed variational probability. A gating function optimization unitoptimizes a gating function model that is a model for determining a branch direction according to the multivariate data in a node of the hierarchical latent structure, based on the variational probability of the latent variable in the node.

Hierarchical latent variable model estimation device, hierarchical latent variable model estimation method, supply amount prediction device, supply amount prediction method, and recording medium

An abnormality score calculating means calculates abnormality scores which are information indicating abnormality of medical data, based on specificity of the medical data. An abnormality score vector generating means creates at least one or more abnormality score vectors which are information obtained by integrating the abnormality scores. Further, a side effect detecting means which decides a likelihood of a side effect indicated by the abnormality score vector, based on a predetermined rule, and detects an abnormality score vector the likelihood of which is set in advance and which satisfies conditions as information indicating the side effect.

Device, method, and program for extracting abnormal event from medical information

To provide a latent variable model estimation apparatus capable of implementing the model selection at high speed even if the number of model candidates increases exponentially as the latent state number and the kind of the observation probability increase. A variational probability calculating unitcalculates a variational probability by maximizing a reference value that is defined as a lower bound of an approximation amount, in which Laplace approximation of a marginalized log likelihood function is performed with respect to an estimator for a complete variable. A model estimation unitestimates an optimum latent variable model by estimating the kind and a parameter of the observation probability with respect to each latent state. A convergence determination unitdetermines whether a reference value, which is used by the variational probability calculating unitto calculate the variational probability, converges.

Latent variable model estimation apparatus, and method

To provide an information spread scale prediction device capable of accurately predicting the number of future contributions for a specific topic in SNS and the like. The information spread scale prediction device includes: a learning text data input unit which acquires learning text data from a specific website; a node influence learning unit which calculates the influence for the number of statements by each group to which a node specifying a single specific user belongs for the topic from the number of statements by each classified topic, and stores it as learning data; a prediction text data input unit which acquires prediction text data from the specific website after storing the learning data; and a future contribution number prediction unit which predicts and outputs the number of contributions at a specific future time of the topic based on the number of statements of each topic and the learning data.

Information spread scale prediction device, information spread scale prediction method, and information spread scale prediction program

A hierarchical latent structure setting unitsets a hierarchical latent structure that is a structure in which latent variables are represented by a tree structure and components representing probability models are located at nodes of a lowest level of the tree structure. A variational probability computation unitcomputes a variational probability of a path latent variable that is a latent variable included in a path linking a root node to a target node in the hierarchical latent structure. A component optimization unitoptimizes each of the components for the computed variational probability. A gating function optimization unitoptimizes a gating function model that is a model for determining a branch direction according to the multivariate data in a node of the hierarchical latent structure, on the basis of the variational probability of the latent variable in the node.

Hierarchical latent variable model estimation device, hierarchical latent variable model estimation method, and recording medium

To provide a discriminant model learning device capable of efficiently learning a discriminant model on which domain knowledge indicating user's knowledge or analysis intention for a model is reflected while keeping fitting to data. A query candidate storage meansstores candidates of a query as a model to be given with domain knowledge indicating a user's intention. A regularization function generation meansgenerates a regularization function indicating compatibility with domain knowledge based on the domain knowledge to be given to the query candidates. A model learning meanslearns a discriminant model by optimizing a function defined by a loss function and the regularization function predefined per discriminant model.

Discriminant model learning device, method and program

A loss distribution calculation system including: a section that performs at least one of upside and downside discretizations for a scale distribution; a section that calculates, after dividing all events, a probability value of a cumulative sum of losses for a portion out of all events in order to calculate at least one of upside and downside sub-composite distributions, the upside sub-composite distribution being calculated based on the frequency distribution and the upside-discretized scale distribution, and the downside sub-composite distribution being calculated based on the frequency distribution and the downside-discretized scale distribution; a section that calculates upper and lower bounds of a loss distribution function based on at least one of the upside and downside sub-composite distributions, calculates a function, as an approximate value of the loss distribution function, based on at least one of the upside and downside sub-composite distributions, and calculates an accuracy of the approximate value.

Growing community of inventors

Tokyo, Japan

Satoshi Morinaga