Abstract: Techniques for transcription of an audio stream are provided. A request for transcription of a first audio stream from a first device is received. A request for transcription of a second audio stream from a second device is received. It is determined that the first and second audio streams are the same. One of the first and second audio streams are selected for transcription. Transcription of the selected audio stream is requested.

Abstract: A method, system and computer program product for correlating objects of interest based on difference and similarities analysis is disclosed. The method includes receiving input that a human user is focused on a portion of a first image during a first period of time, and also focused on a portion of a second image during a second period of time. In response to the input being received, a first analytics-based action may be initiated when certain similarity/difference conditions are met, or a second analytics-based action may be initiated when certain other similarity/difference conditions are met.

Abstract: Techniques for management of commercial virtual assistant services are provided. The techniques include receiving a query from a user within an organization. The techniques include determining if generating at least a portion of a response to the query will require use of a paid service and determining if at least one other virtual assistant within the organization has cached information usable to generate the at least a portion of the response to the query that requires use of the paid service. The techniques further include determining if the information cached by the at least one other virtual assistant is valid based in part on the query and receiving the information from the at least one other virtual assistant when the cached information is valid and include generating the at least a portion of the response to the query that requires use of the paid service using the received information.

Abstract: Methods and systems for coordinating task zones at a public safety incident scene. One system includes an electronic computing device that includes an electronic processor configured to determine a first task to be performed by a first public safety officer and a second task to be performed by a second public safety officer. The electronic processor establishes a first geofence for the first task and a second geofence for the second task. In response to determining that the second geofence at least partially overlaps with the first geofence, the electronic processor determines whether the first task conflicts with the second task. In response to determining that the first task conflicts with the second task, the electronic processor modifies the first task and provides an instruction to a communication device of the first public safety officer to indicate that the first task has been modified.

Abstract: A method, system and computer program product for reducing learning time for a newly installed camera is disclosed. The method includes generating a new unusual activity model for the newly installed camera, based on portion(s) of existing and established unusual activity model(s) built for different older camera(s), where the existing and established unusual activity model(s) relate to at least one same static object appearing within Fields Of Views (FOVs) of the new and older cameras.

Abstract: A method, system and computer program product for event summarization facilitated by emotions/reactions of people near an event location is disclosed. The method includes generating a query based at least in part on reaction information and at least in part on primary video metadata. Based on the query, at least one possible event summarization match for the one or more events is retrieved from a database.

Abstract: A method, system and computer program product for reducing learning time for a newly installed camera is disclosed. The method includes generating a new unusual activity model for the newly installed camera, based on portion(s) of existing and established unusual activity model(s) built for different older camera(s), where the existing and established unusual activity model(s) relate to at least one same static object appearing within Fields Of Views (FOVs) of the new and older cameras.

Abstract: A device, system and method for controlling environmental devices at a smart building to assist a first responder is provided. A public-safety computing device determiners a context of a first responder at a smart building. The public-safety computing device is in communication with a smart-building control device. The context comprises one or more of: an objective to be achieved by the first responder in the smart building; and an object-of-interest in the smart building for which evidence is to be collected. The public-safety computing device communicates with the smart-building control device, to control environmental devices at the smart building to assist the first responder with respect to the context.

Abstract: Secure communication in a geographic incident area is disclosed. Computer-implemented methods are also disclosed, one of which is for restricting access to a resource and includes generating a key and splitting it into N key parts (where N is an integer greater than two). The method also includes encrypting the N key parts. The method also includes transmitting, over a network, to a device: the N encrypted key parts; and identifying information for N secret objects expected to be visible within the area. Each of the N encrypted key parts is decryptable based on at least one video analytics-discernable object attribute for each respective secret object of the N secret objects. The method also includes allowing an additional entity to access the resource only by presentation of a complete key formed from decrypted versions of less than all of the N key parts.

Abstract: A method and apparatus for preventing access to an IoT device is provided herein. During operation an apparatus will inquire about current and/or past connections to an IoT device. A list of identities of current and/or past apparatuses that were connected to the IoT device will be provided, and a determination on whether or not to allow access to the IoT device will be based on the identities of current and/or past apparatuses that are accessing, or have accessed the IoT device.

Abstract: A method and apparatus for displaying and controlling user interface elements is provided herein. During operation, when a user interface element is expanded and covers other user interface elements, the expanded user interface element will have embedded text or user interface elements (e.g., buttons) that show what is covered, and/or allow quick access to various functions for what is covered. Hovering over the text or embedded user interface elements, or clicking on them engages the covered user interface element.

Abstract: A method is provided that provides information exchange between mobile devices that are near each other. Upon determining that a first mobile device is located near a second mobile device, information is exchanged between a first virtual personal assistant associated with the first mobile device and a second virtual personal assistant associated with the second mobile device. The information is compared to identify an overlapping topic in the information. If there is overlapping information, the users of the mobile devices are alerted to the overlapping topic.

Abstract: A method, system and computer program product for event summarization facilitated by emotions/reactions of people near an event location is disclosed. The method includes generating a query based at least in part on reaction information and at least in part on primary video metadata. Based on the query, at least one possible event summarization match for the one or more events is retrieved from a database.

Abstract: A process for responding to location-variable group electronic digital assistant requests includes monitoring audio communications transmitted between a plurality of communication devices (CDs) on a group communication channel (CC) and detecting an audio inquiry from a first CD of the plurality of CDs. A location of each CD is determined, including different first and second determined locations of the first and second CDs. The audio inquiry is processed and it is determined that a response will vary based on the different first and second locations. Two different first and second responses to the audio inquiry are generated as a function of the determined locations and are caused to be provide to respective ones of the first and second CDs via one of (i) two private call CCs, (ii) one individual private call CC and the group CC, and (iii) the group CC and a second group CC.

Abstract: Techniques for management of commercial virtual assistant services are provided. The techniques include receiving a query from a user within an organization. The techniques include determining if generating at least a portion of a response to the query will require use of a paid service and determining if at least one other virtual assistant within the organization has cached information usable to generate the at least a portion of the response to the query that requires use of the paid service. The techniques further include determining if the information cached by the at least one other virtual assistant is valid based in part on the query and receiving the information from the at least one other virtual assistant when the cached information is valid and include generating the at least a portion of the response to the query that requires use of the paid service using the received information.

Abstract: Methods and systems for coordinating task zones at a public safety incident scene. One system includes an electronic computing device that includes an electronic processor configured to determine a first task to be performed by a first public safety officer and a second task to be performed by a second public safety officer. The electronic processor establishes a first geofence for the first task and a second geofence for the second task. In response to determining that the second geofence at least partially overlaps with the first geofence, the electronic processor determines whether the first task conflicts with the second task. In response to determining that the first task conflicts with the second task, the electronic processor modifies the first task and provides an instruction to a communication device of the first public safety officer to indicate that the first task has been modified.

Abstract: A method and apparatus for sharing information used to identify an object/person by a camera (e.g., a body-worn camera) is provided herein. During operation the apparatus will determine a set of characteristics that can be used to identify the object/person. The apparatus then analyzes the body-worn camera's FOV (or potential FOV) and removes characteristics from the set of characteristics to produce a minimal set of characteristics that can be used to identify the object/person in the body-worn cameras FOV. The minimal set of characteristics is then sent to the officer's body-worn camera for detection.

Abstract: A method and apparatus for bypassing a virtual partner is provided herein. During operation a device will have knowledge of a status of sensors connected to form a personal-area network (PAN) and/or have knowledge of a current incident type assigned to a user. The device will then bypass digital-assistant functionality based on the status of associated PAN devices and/or the incident type. Thus, virtual-partner functionality will be bypassed based on a fact that a public-safety event has occurred. As discussed, the public-safety event may comprise a current incident assigned to a user, or a status of at least one device/sensor connected to form a PAN.

Abstract: A process for responding to location-variable group electronic digital assistant requests includes monitoring audio communications transmitted between a plurality of communication devices (CDs) on a group communication channel (CC) and detecting an audio inquiry from a first CD of the plurality of CDs. A location of each CD is determined, including different first and second determined locations of the first and second CDs. The audio inquiry is processed and it is determined that a response will vary based on the different first and second locations. Two different first and second responses to the audio inquiry are generated as a function of the determined locations and are caused to be provide to respective ones of the first and second CDs via one of (i) two private call CCs, (ii) one individual private call CC and the group CC, and (iii) the group CC and a second group CC.

Abstract: A method and apparatus for bypassing a virtual partner is provided herein. During operation a device will have knowledge of a status of sensors connected to form a personal-area network (PAN) and/or have knowledge of a current incident type assigned to a user. The device will then bypass digital-assistant functionality based on the status of associated PAN devices and/or the incident type. Thus, virtual-partner functionality will be bypassed based on a fact that a public-safety event has occurred. As discussed, the public-safety event may comprise a current incident assigned to a user, or a status of at least one device/sensor connected to form a PAN.