摘要:
A speech receiving unit receives a user ID, a speech obtained at a terminal, and an utterance duration, from the terminal. A proximity determining unit calculates a correlation value expressing a correlation between speeches received from plural terminals, compares the correlation value with a first threshold value, and determines that the plural terminals that receive the speeches whose correlation value is calculated are close to each other, when the correlation value is larger than the first threshold value. A dialog detecting unit determines whether a relationship between the utterance durations received from the plural terminals that are determined to be close to each other within an arbitrarily target period during which a dialog is to be detected fits a rule. When the relationship is determined to fit the rule, the dialog detecting unit detects dialog information containing the target period and the user ID.
摘要:
A speech receiving unit receives a user ID, a speech obtained at a terminal, and an utterance duration, from the terminal. A proximity determining unit calculates a correlation value expressing a correlation between speeches received from plural terminals, compares the correlation value with a first threshold value, and determines that the plural terminals that receive the speeches whose correlation value is calculated are close to each other, when the correlation value is larger than the first threshold value. A dialog detecting unit determines whether a relationship between the utterance durations received from the plural terminals that are determined to be close to each other within an arbitrarily target period during which a dialog is to be detected fits a rule. When the relationship is determined to fit the rule, the dialog detecting unit detects dialog information containing the target period and the user ID.
摘要:
A moving context and a moving time of a user are specified by acceleration information while the user is moving. The moving context represents the user's moving status. The acceleration information is measured by an acceleration sensor carried with the user. The moving context and the moving time are stored in time series. The moving context and the moving time between a moving start time and an arrival time are set as a moving pattern. A tag is set to the moving context in the moving pattern. The tag identifies a function to be executed for the moving context. A moving estimation pattern is generated as the moving pattern having the moving context and the moving time specified by acceleration information measured when the user is newly moving. The function identified by the tag is executed, when the moving context set with the tag in the moving estimation pattern coincides with a moving context specified by acceleration information measured while the user is newly moving.
摘要:
A moving context and a moving time of a user are specified by acceleration information while the user is moving. The moving context represents the user's moving status. The acceleration information is measured by an acceleration sensor carried with the user. The moving context and the moving time are stored in time series. The moving context and the moving time between a moving start time and an arrival time are set as a moving pattern. A tag is set to the moving context in the moving pattern. The tag identifies a function to be executed for the moving context. A moving estimation pattern is generated as the moving pattern having the moving context and the moving time specified by acceleration information measured when the user is newly moving. The function identified by the tag is executed, when the moving context set with the tag in the moving estimation pattern coincides with a moving context specified by acceleration information measured while the user is newly moving.
摘要:
In general, embodiments provide an inter-facility movement estimation apparatus including: a movement map which stores location information about facilities and movement times therebetween; a positioning unit which obtains user's location information when starting a movement; a movement candidate list which stores given movement path candidates; a movement situation estimating unit which estimates a user's movement situation; a movement path estimating unit which selects, whenever the movement situation is changed, estimated movement path candidates from the given movement path candidates based on the nearest facility and the user's movement situation; and an adjusting unit which changes the likelihoods of the estimated movement path candidates, wherein one of the estimated movement path candidates having a highest likelihood thereamong is specified as an actual movement path of the user.
摘要:
In one embodiment, a motion determination apparatus includes: a basic motion determination module determining a basic motion of a user, based on a sensor signal for detecting a motion of the user; a basic motion recording module recording the basic motion in a temporal sequence; a motion scene determination table configured to store the basic motion and a condition under which the basic motion occurs, for each motion scene; a motion scene determination module determining that the basic motion recorded in the temporal sequence corresponds to a certain motion scene, based on the motion scene determination table; a detailed label determination table storing a detailed label indicating a detailed motion in the motion scene, for each motion scene; and a detailed label determination module determining that the basic motion included in the motion scene corresponds to a certain detailed label, based on the detailed label determination table.
摘要:
A portable terminal includes a body movement sensor configured to detect a movement of a user; a normal moving pattern storage unit configured to store, in advance, a normal moving pattern; a moving state determination unit configured to determine the moving state from the movement; a normal moving certainty calculation unit configured to calculate a normal moving certainty indicating a degree of coincidence between the normal moving pattern and the moving state determined at time of detecting the movement; a position measurement interval controller configured to calculate a position measurement interval depending on the normal moving certainty; and a positioning unit configured to measure a current position of the portable terminal at the position measurement interval.
摘要:
In one embodiment, a motion determination apparatus includes: a basic motion determination module determining a basic motion of a user, based on a sensor signal for detecting a motion of the user; a basic motion recording module recording the basic motion in a temporal sequence; a motion scene determination table configured to store the basic motion and a condition under which the basic motion occurs, for each motion scene; a motion scene determination module determining that the basic motion recorded in the temporal sequence corresponds to a certain motion scene, based on the motion scene determination table; a detailed label determination table storing a detailed label indicating a detailed motion in the motion scene, for each motion scene; and a detailed label determination module determining that the basic motion included in the motion scene corresponds to a certain detailed label, based on the detailed label determination table.
摘要:
In general, embodiments provide an inter-facility movement estimation apparatus including: a movement map which stores location information about facilities and movement times therebetween; a positioning unit which obtains user's location information when starting a movement; a movement candidate list which stores given movement path candidates; a movement situation estimating unit which estimates a user's movement situation; a movement path estimating unit which selects, whenever the movement situation is changed, estimated movement path candidates from the given movement path candidates based on the nearest facility and the user's movement situation; and an adjusting unit which changes the likelihoods of the estimated movement path candidates, wherein one of the estimated movement path candidates having a highest likelihood thereamong is specified as an actual movement path of the user.
摘要:
A context estimation rule is applied to spare time on a user's schedule, and contexts are estimated. On the basis of a task template, an input task is divided into plural subtasks. A task recommendation rule for recommending tasks to do from the relation between contexts and metadata of tasks is applied to the spare time of the user, and tasks to do in the spare time are recommended on the basis of the contexts of the spare time and the metadata of the subtasks. The recommended tasks are managed as schedules.