Abstract: Described herein are techniques that may be used to provide automatic adjustment of image selection for image generation. In some embodiments, such techniques may comprise receiving, at an image capture device, raw image data that comprises information about a number of pixels, receiving, at the image capture device, sensor data comprising information about a position of the image capture device, determining, based at least in part on the received sensor data, an offset value, selecting, based on the determined offset value, a portion of the raw image data to be included within an image, and generating the image from the portion of the raw image data.

Abstract: A data model computing device receives a first data model with a first set of attributes, a first margin of error, a first set of predictions, and an underlying data set. Subsequently, the data model computing device receives a second data model with a second set of attributes, as the test data for a machine learning module. Based on the first and second data model, the machine learning function generates a second set of predictions and a second margin of error. The data model computing device performs a statistical analysis on the first and second set of predictions and the first and second margin of error to determine if the second set of predictions converge with the first set of predictions and second margin of error is narrower than the first margin of error, to determine if the second data model improves the prediction results of the machine learning module.

Abstract: This disclosure describes techniques for improving CSB platforms (or CSB applications) that manages cloud services for different clients and different environments. In one example, the CSB platforms may be interconnected and configured to act as a proxy for the cloud services. The interconnected CSB platforms may perform spontaneous updating of stored service instance addresses when a service instance is tracked to trigger a strong consistency in the interconnected CSB platforms. Alternatively, the interconnected CSB platforms may perform delayed updating of stored service instance addresses when a service instance is tracked to trigger a weak consistency in the interconnected CSB platforms. Regulation of a frequency and scope of updating may improve the use of power resources in the CSB platforms.

Abstract: A data aggregation implementation includes self-configuring drivers. From the viewpoint of a Network Operation Center (NOC), a plurality of heterogenous content sources provide content that may be of a variety of different types and formats. All of this content must be ingested and stored for retrieval and reporting, analysis, and/or presentation despite many differences in their collection, format, transmission, and quality. In some embodiments, the NOC includes or cooperates with one or more servers to, among other functions, receive content from content sources, request object reflection by the driver of each content source, receive driver attributes in response, and map the metadata of the content for each content source to a universal schema, thereby self-configuring the driver.

Abstract: This disclosure describes techniques that enable a parallel execution controller to execute partitioned segments of a data model in parallel and on different network resources. The resultant processed data from each partitioned segment may be combined to form an aggregated set of results data. The parallel execution controller may identify model attributes of a data model and determine whether the data model is partitionable, based on the model attributes. If the data model is partitionable, the parallel execution controller may partition the data model, initiate a parallel execution of the individual partitioned segments on available network resources, and combine the corresponding results data into an aggregated set of results data.

Abstract: A video processing engine may receive a request for a video communication session, via a network to produce a video file key that is routed to the video camera. If the video camera is communicatively connected to a Wi-Fi 6 compatible wireless access point, it routes a high-quality video file to the Network Operation Center (NOC). Alternatively, using the video key file, the video camera generates message digests and watermarks that are embedded in a video camera generated high-quality video file and a degraded quality video file. The video camera routes, via the network, the degraded quality video file to the NOC, while the high-quality video file is uploaded to the NOC later. Subsequently, a video processing engine extracts the watermarks from the message digests of the video files and compares them to ensure that the high-quality video file correlates to the degraded quality video file.

Abstract: A Network Operation Center may receive video data, sensor data and third-party data for a situation that a police officer or security service personnel has been called to. Using the video data, a sentiment analysis engine may generate a sentiment data file that contains the sentiment of at least one individual involved in the situation. Using the video data, sensor data, third party data and the sentiment data file, the sentiment analysis engine may generate a safety quality value for the situation. Subsequently, the safety quality value is compared to a predetermined sentiment value to establish a safety rating and confidence interval for the situation. Furthermore, the sentiment analysis engine may generate a situational awareness file, that contains the safety rating and confidence interval, and route it to the field computing device of the officer for evaluation and implementation.

Abstract: This disclosure describes techniques for creating a universal schema with default fields that support sensor formats of different devices. In one example, the universal schema supports substantial equivalents between data fields in different sensor formats. Further, a sensor format may be configured to support inheritance and aggregation of sensor formats in prior devices. Accordingly, the mapping of sensor formats that supports inheritance and aggregation in the universal schema may provide several advantages such as capturing a mapping of substantive equivalents between the fields in different sensor formats.

Abstract: A content management system (CMS) manages content for trained machine learning (ML) models. The CMS may develop first, second, and third trained ML models from corresponding datasets, to output respective values of dependent variables derived from data underlying the datasets as independent variables, the respective outputs having statistical confidences in the accuracy of their predictions. The third dataset results from combining the first and second datasets, and the third trained ML model is derived from training on the third dataset. The datasets and ML models are stored in a data store, with the trained ML models associated with respective datasets, the datasets with respective underlying data, the trained ML models with respective statistical confidences and corresponding thresholds, and the trained ML models with metadata indicating independent and dependent variables. The datasets and ML models can be versioned and the provenance of the datasets tracked for future ML modeling.

Abstract: This disclosure describes techniques that enable a safety detection controller to analyze and infer a likelihood of a safety concern impacting a monitored individual at a real-time event. More specifically, a safety detection controller may receive sensor data from a monitored device associated with a particular individual. The sensor data may be captured from the environment that is proximate to the monitored device. The safety detection controller is further configured to analyze the sensor data to infer the identities of third-party individuals proximate to the monitored device and determine whether those individuals pose a safety concern to the monitored individual.

Abstract: This disclosure describes techniques for continuous improvement of machine learning models (also called data models) in a Content Management System (CMS). In one example, a CMS may store a set of data models for each application such as plate number recognition, facial recognition, a determination of likelihood of assault to a law enforcement officer in a traffic violation or robbery scenario, and car identification. In an example embodiment, a predictive model may be used to select a data model from the plurality of data models. The selected data model may be further improved or trained to a new sample of data features to generate an output pattern (e.g., likelihood of assault to a law enforcement officer).

Abstract: This disclosure describes techniques for a consumer application that integrates a model-controller-view (MCV) design pattern with an event streaming platform such as an Apache Kafka™ in a network operation center (NOC) server to support NOC workspace interoperability. The MCV design pattern may include a pattern that divides an application into three main logical components (e.g., model component, controller component, and view component) to handle specific aspects of the application. In one example, the model component decouples the telemetry data streams from an event stream platform, and the controller component filters a queried set of decoupled telemetry data streams to dynamically control views to be rendered in the view component.

Abstract: This disclosure describes techniques for improving CSB platforms (or CSB applications) that manages cloud services for different clients and different environments. In one example, the CSB platforms may be interconnected and configured to act as a proxy for the cloud services. The interconnected CSB platforms may perform spontaneous updating of stored service instance addresses when a service instance is tracked to trigger a strong consistency in the interconnected CSB platforms. Alternatively, the interconnected CSB platforms may perform delayed updating of stored service instance addresses when a service instance is tracked to trigger a weak consistency in the interconnected CSB platforms. Regulation of a frequency and scope of updating may improve the use of power resources in the CSB platforms.

Abstract: A method and system of correlating annotations of media files. A first media file is received from a first media recording device. A file record for the first media file is created in the file table. A determination is made whether the first media file belongs to an existing matter group. Upon determining that the first media file belongs to an existing matter group: the file record is related with the existing matter group in the file table; annotations of the first media file that are flagged to be shared, are related to all media files of the existing matter group; and annotations of all the media files of the existing matter group to the first media file are related. Upon determining that the first media file does not belong to an existing matter group, a new matter group is created for the first media file in the matter table of the central server.

Abstract: A subscriber device may perform a key exchange with a network operation center (NOC) computing device to receive a secret key. A list of group identifiers of personal devices for which the subscriber device is to handle events may be received at the subscriber device. The subscriber device may receive an encrypted event packet from a personal device via a direct communication connection. The subscriber device may decrypt the encrypted event packet at the subscriber device using the secret key to generate a decrypted event packet and extract a group identifier from the decrypted event packet. In response to determining that the group identifier is included in the list of group identifiers received from the NOC computing device, an event handler of a plurality of handlers stored in the subscriber device that corresponds to an event included in the decrypted event packet may be identified to handle the event.

Abstract: A method and system of correlating annotations of media files. A first media file is received from a first media recording device. A file record for the first media file is created in the file table. A determination is made whether the first media file belongs to an existing matter group. Upon determining that the first media file belongs to an existing matter group: the file record is related with the existing matter group in the file table; annotations of the first media file that are flagged to be shared, are related to all media files of the existing matter group; and annotations of all the media files of the existing matter group to the first media file are related. Upon determining that the first media file does not belong to an existing matter group, a new matter group is created for the first media file in the matter table of the central server.

Abstract: This disclosure describes a portable recording device that is configured to capture real-time multimedia data from a surrounding environment. The portable recording device may comprise one or more sensors to capture the real-time multimedia data, a category selector to selectively toggle between preset positions that designate a category classification to the real-time data, and an activation button to trigger one or more actions relating to the capture of the real-time multimedia data.

Abstract: This disclosure describes an apparatus and system for classifying audio and video data captured by a portable recording device. The portable recording device may comprise a camera system enclosure that captures audio and video data that reflects a user's point-of-view perception of their surroundings. The video and/or audio data may be transmitted in real-time, or near real-time, to a Central Multimedia Management (CMM) System at a Network Operations Center, or one or more mobile computing devices, via one or more networks. Alternatively, or additionally, the video and/or audio data may be stored within memory of the portable recording device. This disclosure further describes a CMM system that may act as a central repository of multimedia data from one or more portable recording device(s). The CMM system may further generate and assign incident report forms for each individual instance of real-time data that is recorded by a portable recording device.

Abstract: Techniques for providing target coverage using mobile assets are described, including techniques for dynamically adjusting routing of mobile assets to cover targets when a disruption occurs in the original routing and target coverage plans. Mobile assets are assigned routes to cover target areas and adherence to the routes is monitored. If a first mobile asset experiences a route interruption, other mobile assets are automatically re-routed to cover the target areas originally covered by the route of the first mobile asset.

Abstract: Techniques for providing target coverage using mobile assets are described, including techniques for dynamically adjusting routing of mobile assets to cover targets when a disruption occurs in the original routing and target coverage plans. Mobile assets are assigned routes to cover target areas and adherence to the routes is monitored. If a first mobile asset experiences a route interruption, other mobile assets are automatically re-routed to cover the target areas originally covered by the route of the first mobile asset.