Abstract:
In an aspect, a client device detects a set of proximate client devices. The client device classifies, for each respective proximate client device in the set of proximate client devices, a relationship relative to an operator of the client device based on a local evaluation of one or more interactions between the client device and at least one proximate client device from the set of proximate client devices in response to the detecting. The client device determines whether to automatically trigger a communicative action with one or more proximate client devices from the set of proximate client devices based on the classifying.
Abstract:
The disclosure relates to creating a time-sensitive grammar. A device receives a plurality of data points, identifies a plurality of time gaps associated with the plurality of data points, each of the plurality of time gaps representing a dwell time or a frequency of occurrence of a data point of the plurality of data points, generates a generic time factor representing a multiple of the plurality of time gaps, and combines the generic time factor with the plurality of data points to create a time-sensitive sequence of data points. The generic time factor may be inserted into the time-sensitive sequence a number of times representing the dwell time or the frequency of occurrence of a corresponding data point of the plurality of data points.
Abstract:
Systems and methods for generating a grammar describing activities of a user are disclosed. An aspect receives log data for the user, clusters the log data around a plurality of cluster centroids, assigns one or more semantic labels to each of the plurality of cluster centroids based on determining that a threshold number of log data points have been assigned to each of the plurality of cluster centroids, determines a sequence in which the log data points were clustered around the plurality of cluster centroids, generates one or more grammars representing a sequence of possible activities of the user based on the sequence in which the log data points were clustered around the plurality of cluster centroids and the one or more semantic labels of each of the plurality of cluster centroids, and filters the assigned one or more semantic labels for each of the plurality of cluster centroids.
Abstract:
In an embodiment, an apparatus receives report(s) of raw motion data detected in IoT environment, and also receives report(s) indicating user-initiated event(s) detected by a set of IoT devices within the IoT environment. The apparatus scans the raw motion data within a threshold period of time preceding particular detected user-initiated events to identify motion sequence(s) within the IoT environment that occurred during the threshold period of time. Certain motion sequence(s) are correlated with user-initiated event(s) based on a confidence level that the user-initiated event(s) will follow the motion sequence(s). Upon detection of the motion sequence(s) at some later point in time, the correlated event(s) is preemptively triggered without user interaction.
Abstract:
An aspect enables context aware actions among heterogeneous Internet of Things (IoT) devices. An IoT device receives data representing a context of each of a first set of IoT devices, receives data representing a current state of each of a second set of IoT devices, and determines an action to perform at a target IoT based on the received data. An aspect verifies an implied relationship between a first user and a second user by detecting an interaction between a first user device belonging to the first user and a second user device belonging to the second user, storing information related to the interaction in a first interaction table associated with the first user device, assigning a relationship identifier to the second user based, at least in part, on the information related to the interaction, and determining whether or not the assigned relationship identifier is correct.
Abstract:
Systems and methods are disclosed for determining a context-dependent virtual distance based on stigmergic interference. The method may include obtaining environmental status information relating to an environment in proximity to a client device, calculating, based on the obtained environmental status information, the context-dependent virtual distance between the client device and a user of the client device, and controlling a user signaling pattern of the client device based on the calculated context-dependent virtual distance.
Abstract:
Methods and systems for receiving an offer from an entrusting device to access one or more devices are disclosed. A trust model module of a first device receives the offer from the entrusting device to provide the first device with permission to access the one or more devices, and determines whether or not to accept the offer from the entrusting device to provide the permission to access the one or more devices, wherein the first device determines whether or not to accept the permission to access the one or more devices based on a relationship between the first device and the entrusting device and/or a relationship between the first device and the one or more devices.
Abstract:
Mechanisms to trigger commands on target devices when source devices broadcast certain notifications to thereby automate common, routine, or otherwise related activities among heterogeneous devices are provided. For example, when a source device broadcasts a notification that arrives at a control device, a trigger that links the notification to a command on the target device may be defined and stored at the control device, which may then automatically invoke the command on the target device when the source device broadcasts the notification again in the future. In other use cases, the trigger and the linked command may be pushed to the broadcasting source device, which may then invoke the command on the target device when broadcasting the notification in the future, or a listener may be configured on the target device such that the target device may invoke the command in response to locally detecting the notification linked thereto.
Abstract:
The disclosure is related to calculating a relative distance between a first node and a second node in a wireless network. An aspect of the disclosure includes detecting a plurality of transitions of a user device from the first node to the second node, determining a relationship between the first node and the second node based on the plurality of transitions, and calculating the relative distance between the first node and the second node based on the determined relationship.
Abstract:
The disclosure is directed to controlling of Internet of Things (IoT) devices based on detecting a device and obtaining control information and associated rules for controlling the device. The control functions available to a smart controller can vary based on the condition of the various rules and/or the interaction of the various devices detected.