Abstract: The present invention extends to methods, systems, and computer program products for detecting events from ingested data. Data is ingested. A first score is computed from a portion of the data. The first score indicates a likelihood of the data including event information. Computing resources are allocated to further process the data based on the first score indicating that further processing is warranted. A second score is computed from parameters of the data. An event is detected based on the second score.

Abstract: The present invention extends to methods, systems, and computer program products for classifying video. In one aspect, a model is trained to classify video. A reference model capable of identifying signals from a plurality of signals classes is used along with tagged training data to train a signal class specific model. The signal class specific model uses less resources to identify the specific signal class model relative to the reference model. The signal class specific model can be deployed to an event detection infrastructure or other device. Frames from video streams can be classified using the signal class specific model.

Abstract: The present invention extends to methods, systems, and computer program products for ingesting streaming signals. Signal ingestion modules sample a frame from a raw streaming signal. A preliminary severity or possible event type is computed from the sampled frame. A deeper inspection request is triggered of the raw streaming signal or of another raw streaming signal. Segments of content from the raw streaming signal or the other raw streaming signal are inspected. An actual severity or actual event type is computed from the inspected content. The actual severity or actual event type can be included in a normalized signal.

Abstract: The present invention extends to methods, systems, and computer program products for event detection from signal data removing private information. A signal is ingested. A portion of the signal is selected from within the signal. A first score is computed from the selected portion. The first score indicates a likelihood of the signal including information related to an event type. It is determined that processing of another signal is warranted based on the indicated likelihood. Resources are allocated to process the other signal. The other signal is ingested. Parameters associated with the other signal are accessed. A second score is computed from the parameters utilizing the allocated resources. A previously unidentified event of the event type is identified based on the second score and utilizing the allocated resources. A privacy infrastructure spans signal ingestion, event detection, and event notification and protects the integrity of private information.

Abstract: The present invention extends to systems and methods for notifying entities of relevant events. A boundary geometry, a user event truthfulness preference, a first event type, a second event type, and an area are combined into a rule formula. The first event type and a first event truthfulness associated with a detected event are accessed. The second event type and a second event truthfulness associated with another detected event are accessed. It is determined that the first event type and the second event type occurred in combination in the area within a boundary defined by the boundary geometry and that the first event truthfulness and the second event truthfulness both satisfy the user event truthfulness preference. An entity is automatically electronically notified in accordance with notification preferences that the rule formula was satisfied.

Abstract: The present invention extends to methods, systems, and computer program products for event detection removing private information. In one aspect, an event detection infrastructure determines that characteristics of multiple signals, when considered collectively, indicate an event of interest to one or more parties. In another aspect, an evaluation module determines that characteristics of one or more signals indicate a possible event of interest to one or more parties. A validator then determines that characteristics of one or more other signals validate the possible event as an actual event of interest to the one or more parties. Signal features can be used to compute probabilities of events occurring. A privacy infrastructure spans signal ingestion, event detection, and event notification and protects the integrity of private information.

Abstract: The present invention extends to methods, systems, and computer program products for estimating color of vehicles on a roadway. The color can be at least estimated from captured imagery, such as, frames of a video stream. The captured imagery can be captured by variably configured traffic cameras, other public cameras, private cameras (e.g., CCTV), or virtually any other camera, etc., which may have different operating conditions. Color confidence scores can be derived based on image characteristics.

Abstract: The present invention extends to methods, systems, and computer program products for validating and supplementing emergency call information removing private information. A probability that an emergency call originated from a location is derived from features of a normalized signal version of the emergency call. An additional normalized signal is accessed within a specified distance of the location. The location is validated from features of the additional signal. An event is detected from the features of the normalized signal version of the emergency call based on the validated location. The validated location is associated with an obtained event truthfulness probability for the event. The event is sent to a Public Safety Answering Point (PSAP). A privacy infrastructure spans signal ingestion, event detection, and event notification and protects the integrity of private information.

Abstract: The present invention extends to systems and methods for notifying entities of relevant events. An entity defines a rule formula that is triggered when one or more detected events match the rule formula including defining one or more event types and one or more locations types. A boundary associated with a selected location type is also received along with a monitoring area. The received elements are combined into the rule formula notification preferences are associated with the defined rule. One or more events are detected and then compared to the rule formula to determine if the combination of one or more event types occurred within the boundary of the one or more location types within the area.

Abstract: A method for dynamic event detection based on content from a set of social networking systems including receiving content from the set of social networking systems, identifying a plurality of content associated with a geofence, the content that was generated within a predetermined time period, determining feature values from the plurality of content for each of a set of features, determining an event probability for the geofence based on the feature values, and detecting an event within the geofence in response to the event probability exceeding a threshold event probability.

Abstract: The invention extends to methods, systems, and computer program products for deriving signal location information. A raw signal is ingested and normalized, including deriving a partially normalized signal. The partially normalized signal can be a signal including a Time, a Context and possibly a non-dispositive location hint. A list of one or more geo cells where the raw signal potentially originated is accessed. In one aspect, the one or more geo cells are accessed based on the non-dispositive location hint. A location annotation identifying a geo cell from among the one or more geo cells is formulated. The partially normalized signal can be annotated with the location annotation. A location in a two dimensional space is determined from the location annotation. The location is inserted into the partially normalized signal forming a fully normalized signal. The fully normalized signal can include a Time, a Location, and a Context.

Abstract: The present invention extends to systems and methods for notifying entities of relevant events. An entity defines a rule formula that is triggered when one or more detected events match the rule formula including defining one or more event types and one or more locations types. A boundary associated with a selected location type is also received along with a monitoring area. The received elements are combined into the rule formula notification preferences are associated with the defined rule. One or more events are detected and then compared to the rule formula to determine if the combination of one or more event types occurred within the boundary of the one or more location types within the area.

Abstract: The present invention extends to methods, systems, and computer program products for detecting events from features derived from ingested signals. In one aspect, an event detection infrastructure determines that characteristics of multiple (and possibly private and/or non-private) signals, when considered collectively, indicate an event of interest to one or more parties. In another aspect, an evaluation module determines that characteristics of one or more (possibly private and/or non-private) signals indicate a possible event of interest to one or more parties. A validator then determines that characteristics of one or more other (possibly private and/or non-private) signals validate the possible event as an actual event of interest to the one or more parties. Signal features can be used to compute probabilities of events occurring.

Abstract: The present invention extends to methods, systems, and computer program products for validating and supplementing emergency call information. A Public Safety Answering Point receives an emergency (e.g., 911) call from a mobile device. Parts of the emergency call are processed to identify an emergency call location. Characteristics of the emergency call are combined with characteristics of other signals to identify and emergency call event, including the emergency call location. The emergency call event is sent to the Public Safety Answering Point. Prior to receiving phase II data and possibly even prior to receiving phase I data, the Public Safety Answering Point receives the event. The Public Safety Answering Point tailors dispatch of emergency resources responding to the emergency call based on characteristics of the event, including the originating location.

Abstract: Embodiments of a method and/or system for facilitating event-based vehicle operation can include determining a vehicle route; determining geographic regions for the vehicle route; monitoring the determined geographic regions for events; determining an event of interest from the detected events; and/or dynamically facilitating modification of vehicular operation of the vehicle based on the event of interest, such as in response to determination of the event of interest. In one aspect, a vehicle is routed towards an event of interest and assists in remediating the event (or an impact thereof).

Abstract: The present invention extends to methods, systems, and computer program products for storing and validating the integrity of event related information. To facilitate auditing and traceability, raw signals, normalized signals, detected events, event expirations, and event notifications can be stored in a queryable distributed ledger (e.g., a blockchain). Personal information can be stripped (or otherwise rendered inert, for example, unrecognizable, unreproducible, etc.) prior to storage into the distributed ledger minimizing the possibility of a person being identified. Ledger data can be used to verify actual data as well as for forensics purposes, such as, to audit data, recreate events, etc., in view of an error or inconsistency to investigate, diagnose, remediate, etc.

Abstract: Embodiments of a method and/or system for facilitating event-based vehicle operation can include determining a vehicle route; determining geographic regions for the vehicle route; monitoring the determined geographic regions for events; determining an event of interest from the detected events; and/or dynamically facilitating modification of vehicular operation of the vehicle based on the event of interest, such as in response to determination of the event of interest.

Abstract: The present invention extends to systems and methods for notifying entities of relevant events. An entity defines a rule formula that is triggered when one or more detected events match the rule formula including defining one or more event types and one or more locations types. A boundary associated with a selected location type is also received along with a monitoring area. The received elements are combined into the rule formula notification preferences are associated with the defined rule. One or more events are detected and then compared to the rule formula to determine if the combination of one or more event types occurred within the boundary of the one or more location types within the area.

Abstract: The present invention extends to methods, systems, and computer program products for validating and supplementing emergency call information. A Public Safety Answering Point receives an emergency (e.g., 911) call from a mobile device. Parts of the emergency call are processed to identify an emergency call location. Characteristics of the emergency call are combined with characteristics of other signals to identify and emergency call event, including the emergency call location. The emergency call event is sent to the Public Safety Answering Point. Prior to receiving phase II data and possibly even prior to receiving phase I data, the Public Safety Answering Point receives the event. The Public Safety Answering Point tailors dispatch of emergency resources responding to the emergency call based on characteristics of the event, including the originating location.

Abstract: The present invention extends to methods, systems, and computer program products for detecting events from signal data. A signal is ingested. A portion of the signal is selected from within the signal. A first score is computed from the selected portion. The first score indicates a likelihood of the signal including information related to an event type. It is determined that processing of another signal is warranted based on the indicated likelihood. Resources are allocated to process the other signal. The other signal is ingested. Parameters associated with the other signal are accessed. A second score is computed from the parameters utilizing the allocated resources. A previously unidentified event of the event type is identified based on the second score and utilizing the allocated resources.