Fujitsu Corporation

Cong Chen

Kanji Uchino

Ajay Chander

Technologies are described to provide autonomous speech and language assessments. In some examples, a method to conduct an autonomous speech and language assessment includes facilitating authoring of an autonomous speech and language assessment. The autonomous speech and language assessment may be interactions between one or more of a conversational module, an analytical module, and a control module, and the interaction may be specified using a visual programming language. The method may also include modeling the autonomous speech and language assessment as a graph using a conversation markup language, and conducting the autonomous speech and language assessment utilizing a conversational virtual agent.

Autonomous speech and language assessment

A method includes acquiring individual assessment data that includes behavior from player of a construction toy. The construction toy includes at least one sensor to detect an activity of the player with the construction toy. The method further includes determining a goal for the player based on the individual assessment data and a set of group assessment data. The method also includes providing a teaching based on the goal. The method includes permitting the player to play with the construction toy with reduced monitoring or intervention by the processing device during a free play period. The method further includes in response to a determination that free play period is over, prompting the player to perform an activity based on the goal. The method also includes in response to a determination that the player has completed the activity, providing a first reinforcement message to the player.

Behavior shaping using a construction toy

A system includes a memory and a processor operatively coupled to the memory. The processor being configured to execute instructions to monitor a behavior of a player of a first construction toy. The first construction toy includes at least one sensor to detect a first construction made by the player between the first construction toy and a second construction toy. The processor being further configured to record the first construction made by the player between the first construction toy and the second construction toy. The processor also being configured to identify a preexisting second construction that is similar to the first construction. The processor being configured to group all the constructions. The processor being further configured to determine a behavior variability and a complexity level for the player based on the construction operations and structures.

Behavior variability and complexity modeling using a construction toy

A method of smart notification scheduling and modality selection includes identifying a notification. The method includes extracting context pertaining to the notification or a user of the client device in response to receiving the notification. The method further includes determining a priority for the notification based on the context. The method also includes determining a delivery schedule for the notification based on the priority. The method includes determining a notification delivery plan based on at least one of the context, priority or delivery schedule. The method further includes transmitting the notification to a display device.

Growing community of inventors

Cupertino, CA, United States of America

Cong Chen