Abstract: Disclosed is a process for performance monitoring and feedback for facial recognition systems. A first image for image matching from a camera capture device at a first location is received for purposes of image matching. A highest match confidence score of the first image to a particular stored enrollment image is determined. One or more image or user characteristics associated with the first image or first user is identified. The identified image or user characteristics and highest match confidence score are added to a facial recognition monitoring and feedback model. Subsequently, a particular one of the stored image or user characteristics consistently associated with a below-threshold highest match confidence score is identified, and a notification is displayed or transmitted including an indication of an identified facial recognition low match pattern and identifying the particular one of the stored image characteristics or user characteristics.

Abstract: A device, system and method for role based data collection and public-safety incident response is provided. A computing device receives a call to report a public-safety incident. The computing device determines a role of a caller on the call, the role of the caller being relative to the public-safety incident. The computing device retrieves, from one or more memories, data dependent on the role of the caller. The computing device controls a notification device to provide the data dependent on the role of the caller.

Abstract: Systems and methods for broadband failover in land mobile radio networks. One method includes operating a first communication interface of a converged communication device to execute a first communication between the device and a first network using an LMR modality. The method includes determining a plurality of radio communication characteristic values for each of a plurality of sites of the first network and generating a fallback threshold for a home site of the device based on the plurality of radio communications characteristics. The method includes determining whether a current radio communication characteristic value associated with a home site of the device exceeds the fallback threshold, and, when the current radio communication characteristic value does not exceed the fallback threshold, operating a second communication interface of the converged communication device to execute a second communication between the device and a second network using a non-LMR modality.

Abstract: A device, system and method for transmitting notifications based on indications of effectiveness for previous notifications is provided. A public-safety answering point (PSAP) device transmits, to first communication devices, a first notification of a given type, associated with a first public-safety incident. The PSAP device, subsequent to transmitting the first notification, tracks indications of effectiveness of the first notification determined from one or more of: PSAP call traffic; locations and/or responses of the first communication devices and/or PSAP-related data retrieved from one or more servers external or internal to a PSAP system. The PSAP device transmits, to second communication devices, a second notification of the given type, the second notification associated with a second public-safety incident; one or more of the second notification and transmitting of the second notification being modified, relative to the first notification, based on the one or more indications of effectiveness.

Abstract: A device, system, and method for selecting a public safety answering point server to include on a call is provided. A first communication device associated with a first responder, during a call with a second communication device, provides first and second input mechanisms to select a public-safety answering point (PSAP) to include on the call, respectively based on an association with the first communication device or based on a location of the second communication device. In response to detecting activation of the first or second input mechanism, the first communication device respectively provides, to a network server: information to identify the association with the first communication device or the location of the second communication device. Subsequently, first and second communication devices communicate on the call with a PSAP as selected by the network server.

Abstract: A process of requesting and providing an anonymization service for sharing images or videos capturing identity of persons. An anonymization server receives a request including information corresponding to an identifier identifying the image or the video, a region within the image or video in which an identity of a person is captured, an encryption key used to encrypt the region of the image or the video, and contact information of the person. When the anonymization server receives a request from the second agency to share an encryption key for decrypting the region, the server transmits a request to the person to provide a permission to deanonymize the identity of the person captured in the image or video. The anonymization server transmits a response including the encryption key to the second agency when a response indicating a permission is received from the person.

Abstract: A device, system and method for modifying actions associated with an emergency call is provided. A mobile device operates a virtual assistant application, which connects to an emergency call that includes a dispatcher and a caller communicating on the emergency call. The mobile device monitors, using the virtual assistant application, the emergency call to determine context information of the emergency call. The mobile device receives, at the virtual assistant application, sensor data from sensors associated with the mobile device. The mobile device correlates, using the virtual assistant application, the context information with the sensor data. The mobile device causes, using the virtual assistant application, a modification of an action associated with the emergency call based on a correlation between the context information with the sensor data.

Abstract: Methods, systems, and techniques for performing a facet search include receiving facet search commencement user input indicating that a search for a facet is to commence; in response to the facet search commencement user input, searching one or more video recordings for the facet; and displaying, on a display, facet image search results depicting the facet, wherein the facet image search results are selected from the one or more video recordings. An artificial neural network may be used for the facet search, and that network may be trained by generating a facet image training set that comprises training images, with the training images depicting a type of facet common to the training images; and training, by using the facet image training set, that neural network to classify the type of facet when a sample image comprising the type of facet is input to that network.

Abstract: A device, system and process for controlling document access using hierarchical paths is provided. A query, received from a requesting device, comprises: a search string for searching a document database; and an identifier associated with a user. A security permissions database is accessed using the identifier to receive permissible hierarchical document access paths indicating document access permissions associated with the identifier. A modified query includes the permissible hierarchical document access paths. The modified query used to access an index of the document database, the index comprising: a searchable content portion, and corresponding hierarchical document access paths, of a document. Document identifiers are received that identify only the documents having: respective searchable content portions that include the search string of the modified query; and at least one respective corresponding hierarchical document access path encompassed by the permissible hierarchical document access paths.

Abstract: A device, method and system for changing content of live broadcast media is provided. The device associated with a given location, and analyzes live broadcast media to determine presence of one or more of a person of interest (POI) and an event of interest (EOI), the live broadcast media being provided at one or more display screens at the given location, the live broadcast media originating external to the given location. The device analyzes one or more images captured by one or more cameras located at the given location to determine whether one or more of the POI and the EOI meets a condition for causing harm to one or more persons indicated in the one or more images. The device, responsive to the POI or the EOI meeting the condition, changes content of the live broadcast media.

Abstract: A device, method and system for determining a primary location of a public-safety unit is provided. An example device receives, from a plurality of devices associated with a public-safety unit, a plurality of locations associated with the public-safety unit, the public-safety unit comprising the plurality of devices and one or more public-safety personnel. The example device determines a context associated with the public-safety unit. The example device selects a single location, from the plurality of locations, that represents a primary location of the public-safety unit based on the context as determined. The example device one or more of: causes the primary location to be provided at an electronic map; and provides the primary location to one or more of a computer-aided dispatch (CAD) device and a public-safety server.

Abstract: A method, system and apparatus for image capture, analysis and transmission are provided. A link aggregation method involves identifying controller network ports to a source connected to the same subnetwork; producing packets associating corresponding controller network ports selected by the source CPU for substantially uniform selection; and transmitting the packets to their corresponding network ports. An image analysis method involves producing by a camera an indication whether a region of an image differs by a threshold extent from a corresponding region of a reference image; transmitting the indication and image data to a controller via a communications network; and storing at the controller the image data and the indication in association therewith. The controller may perform operations according to positive indications.

Abstract: A computer apparatus, such as a validator node, for validating incident-related data records in a distributed electronic ledger is configured to receive a request from an agent to add a proposed incident-related data record associated with an incident to the distributed electronic ledger. In response to the proposed incident-related data record, the computer apparatus determines, from the distributed electronic ledger, one or more attributes of the agent or incident. The computer apparatus determines whether the proposed incident-related data record satisfies validation criteria based at least partially on the one or more attributes of the agent or incident. Once validated, the computer apparatus may then append the proposed incident-related data record to the distributed electronic ledger. Alternatively, the proposed incident-related data record may be appended regardless of validity, but an indication of validity may be appended if the proposed incident-related data record is validated.

Abstract: Devices and systems for providing cross-agency communications at an incident are described. An incident manager determines attributes of devices to be used at the incident, negotiating the devices and device attributes with each first responder agency from which devices are to be dispatched to the incident. The manager controls lifecycles of network slices to provide communication services for the incident. The lifecycle is controlled based on communication from each UE indicating arrival to and departure from the incident, as well as the attributes of the UE.

Abstract: A method and apparatus for correcting a wrongly-translated word in a device employing speech recognition is provided herein. During operation, a device will use a second language to correct a wrongly-translated word that was wrongly translated using a first language. More particularly, after speech recognition is performed using the first language, when a user selects text to be corrected, the user will utter the speech again using the second language that differs from the first language. Both the first and the second language can be used by the device to determine a best translation of the speech.

Abstract: A method and system to preserve group call audio during a cloud-based group call service upgrade are provided. Audio duplication requests are received and managed through a message broker and instances of an audio distribution service. When a determination is made that an audio distribution service needs to be upgraded, the group call is preserved by generating new instances of the audio distribution service. The new instances of the audio distribution service are added to a queue of the message broker, and old instance of the audio duplication service are gracefully shutdown. Each new instance of the audio distribution service is used to route an audio stream associated with each of the original audio duplication requests, while the olds instances of the audio duplication service are being gracefully shutdown.

Abstract: Automated processing, enforcement and intelligent management of vehicle operation violations is disclosed. A method, that is also disclosed, includes obtaining at least one image within which is shown at least a portion of a vehicle. The method also includes receiving image data for the at least one image, and analyzing the image data to generate a violation score for each of one or more potential vehicle operation violations for the vehicle. When the violation score is in-between an upper violation threshold and a lower consideration threshold, user input is obtained that either affirms or rejects existence of a violation and then, once the user input is obtained, a violation notification is generated only when the user input affirms the existence of the violation. When the violation score is higher than the violation threshold, the violation notification is generated without the user input being obtained.

Abstract: A process of assigning video analytics tasks to computing devices. In operation, an electronic computing device obtains predicted scene data associated with a scene corresponding to which video data is to be captured at a particular time period using a video camera. The electronic computing device then estimates, based on the predicted scene data, an edge computing cost to be incurred to complete execution of a video analytics task at one or more edge computing devices and a cloud computing cost to be incurred to complete execution of the same video analytics task at one or more cloud computing devices. If the edge computing cost is lower than the cloud computing cost, then the electronic computing device assigns the video analytics task to the edge computing devices. Otherwise, then the electronic computing device assigns the video analytics task to the cloud computing devices.

Abstract: A battery module includes a first load terminal, a second load terminal, a first charger terminal, a charger enable terminal, and a battery having a first battery terminal coupled to the first load terminal and a second terminal coupled to the second load terminal. A first isolation device is coupled between the first load terminal and the first charger terminal and has an enable terminal coupled to the charger enable terminal. A first protection circuit includes a second isolation device coupled between the second battery terminal and the second load terminal and a first sensing circuit configured to enable the second isolation device responsive to detecting a failure of the first isolation device.