Abstract: A method for integrating a machine learning (ML) model that impacts different factor groups for generating a dynamic recommendation to collectively optimize an objective factor is provided.

Abstract: A system and method for automatically predicting deviation on a metric of a use-case and deriving interconnections between metrics for generating action recommendations is provided. The system includes a deviation management system 104 which captures data from a plurality of external sources and internal sources and comprises of a deviation management platform 106 and a deviation management environment 108. The system includes various computation modules which work the deviation management platform 106 to provide a deviation management service to a set of clients that are associated with that service. The service and its users are specific to use-case, wherein the use-case is specified by a client device 116 inside the system. The system comprises of external data which is horizontal across a plurality of deviation management services and internal data which is specific to every deviation management service.

Abstract: A graph data structure for an artificial intelligence knowledge base includes a plurality of user-centric facts associated with a user. Each user-centric fact has an application-agnostic data format and includes a subject graph node, an object graph node, and an edge connecting the subject graph node to the object graph node. The graph data structure is designed to accommodate facts from different application-specific data providers using the same application-agnostic data format even when the different application-specific data providers use different native data formats.

Abstract: An AI platform to enable one or more users to design and create AI enabled applications is provided. The AI platform comprises a data module configured to condition data received from a plurality of data sources to generate a corresponding data pipeline; wherein the data module comprises a plurality of reusable data components. The AI platform further comprises an intelligent processing module configured to process a plurality of datasets received on the data pipeline and generate a corresponding artificial intelligence (AI) pipeline; wherein the intelligent processing module comprises a plurality of reusuable data processing components.

Abstract: A method for estimating metric forecasts associated with a plurality of related entities with more accuracy by training and applying a metric forecast entity relationship machine learning (ML) model is provided. The method includes obtaining a first primary and a first secondary entity metric forecast based on historical data of a primary entity metric obtained from primary entity metric device and historical data of secondary entity metric obtained from secondary entity metric device at different instances of time, training metric forecast entity relationship ML model based on relationship between first primary and first secondary entity metric forecast to obtain a trained metric entity relationship ML model that accounts for the relationship between the first primary entity metric forecast and the first secondary entity metric forecast, and estimating a second primary entity metric forecast and a second secondary entity metric forecast based on the trained metric entity relationship ML model.

Abstract: A system and method for automatically predicting deviation on a metric of a use-case and deriving interconnections between metrics for generating action recommendations is provided. The system includes a deviation management system 104 which captures data from a plurality of external sources and internal sources and comprises of a deviation management platform 106 and a deviation management environment 108. The system includes various computation modules which work the deviation management platform 106 to provide a deviation management service to a set of clients that are associated with that service. The service and its users are specific to use-case, wherein the use-case is specified by a client device 116 inside the system. The system comprises of external data which is horizontal across a plurality of deviation management services and internal data which is specific to every deviation management service.

Abstract: An AI platform to enable one or more users to design and create AI enabled applications is provided. The AI platform comprises a data module configured to condition data received from a plurality of data sources to generate a corresponding data pipeline; wherein the data module comprises a plurality of reusable data components. The AI platform further comprises an intelligent processing module configured to process a plurality of datasets received on the data pipeline and generate a corresponding artificial intelligence (AI) pipeline; wherein the intelligent processing module comprises a plurality of reusuable data processing components.

Abstract: A messaging service is disclosed that provides access to data center event data for physical infrastructure assets via dynamically configurable custom tags defined by customers. For example, a network services exchange provider or co-location provider deploys a data center monitoring system that monitors physical infrastructure assets that enable system operation within a data center for events. The system implements an API which applies custom tags defined by customers to the assets, wherein each custom tag defines attributes of the assets. The system receives subscription requests that describe events and custom tags applied to the assets. The data center infrastructure monitoring system publishes a subscription of event data related to the events for the assets to which the custom tags are applied. Further, a feed manager receives updates to asset equipment and changes to metadata describing the assets and automatically updates the subscription to account for the changes.

Abstract: A graph data structure for an artificial intelligence knowledge base includes a plurality of user-centric facts associated with a user. Each user-centric fact has an application-agnostic data format and includes a subject graph node, an object graph node, and an edge connecting the subject graph node to the object graph node. The graph data structure is designed to accommodate facts from different application-specific data providers using the same application-agnostic data format even when the different application-specific data providers use different native data formats.

Abstract: Intelligent capture, storage, and retrieval of information for task completion are provided. A user can explicitly request to capture information, or user information is implicitly captured from one or more data streams. Semantic understanding of captured information is provided, wherein offline processes are run that analyze captured information to bucket them into a set of pre-defined high value scenarios. Whenever a capture falls into such scenarios, additional structured information about the capture is extracted. Further, aspects provide for storing and indexing information in a data repository. Users are enabled to explicitly retrieve the stored information using a natural language interface, or stored information can be proactively provided to the user based on context to enable task completion.

Abstract: Intelligent capture, storage, and retrieval of information for task completion are provided. A user can explicitly request to capture information, or user information is implicitly captured from one or more data streams. Semantic understanding of captured information is provided, wherein offline processes are run that analyze captured information to bucket them into a set of pre-defined high value scenarios. Whenever a capture falls into such scenarios, additional structured information about the capture is extracted. Further, aspects provide for storing and indexing information in a data repository. Users are enabled to explicitly retrieve the stored information using a natural language interface, or stored information can be proactively provided to the user based on context to enable task completion.

Abstract: A system and method for real time video streaming from a device through a website to a designated group for security, personal, entertainment or commercial applications and to enable responses from those recipients comprises a server operable to bi-directionally communicate with the device and other devices, which are operable to bi-directionally communicate with the server and a module on the server operable to receive notice of an upstream from the device and authenticate a log-in of the device, e.g., a user, transmit content of the upstream to the website, transmit the notice of the upstream to either Designated Recipient Groups or pre-determined recipients, display the content of the upstream on the website, in response to requests, enable placement of information such as advertising and publicity in the content, and enable responses to the content, such as communicating with the user, posting comments, conducting electronic commerce, making appointments and making reservations.

Abstract: A system and method for generating security alerts for a facility is presented. The system can comprise a server, cameras operable to stream video to the server or other storage location and to a surveillance center of the facility, input devices, a first module operable to assign one or more codes to the facility, associate one or more cameras with each code, and associate response guidelines with each code; and a second module operable to receive one code of the one or more codes from one of the one or more input devices, notify the facility assigned to the one code based on the response guidelines, stream video from the one or more cameras associated with the one code to the surveillance center of the facility, and generate the security alert based on the video stream. In one aspect, a user can send a video feed along with the code.

Abstract: Disclosed herein is a method and system for determining class, attributes, and identity of an occupant in an occupancy space. An infra-red image of the occupant in the occupancy space is captured. The infra-red image information of the captured image is digitized to obtain a thermal signature of the occupant. The thermal signature of the occupant is compared with thermal signatures, characteristics, and attributes common to a class of occupants stored in a thermal signature database to determine the class, the attributes, and the identity of the occupant. The determination of the class and the attributes may, for example, comprise distinguishing between an animate occupant and an inanimate occupant, analyzing gait of the animate occupant for distinguishing between human motion and non-human motion, and enumerating occupants in the occupancy space using an edge detection algorithm.

Abstract: The present disclosure discloses a network device and/or method for enhanced VLAN pooling assignments in a wireless network. The disclosed network device receives a message from a wireless client in the wireless network. The network device identifies a virtual local area network (VLAN) based at least on a size of the VLAN and a number of active wireless clients associated with the VLAN. Next, the network device assigns the wireless client to the identified VLAN. In some embodiments, the network device assigns a wireless client to a VLAN if the radio between the number of active wireless clients and the size of the VLAN does not exceed a predetermined value. In some embodiments, the network device assigns a wireless client to a previously assigned VLAN or a VLAN corresponding to an identified home network device, if the wireless client is a roaming client.

Abstract: A novel system and method for enhancing people's personal safety and incident reporting is presented, wherein mobile devices are used to report and/or record both “911” type situations and non-emergency situations. Users of the invention can record, transmit, stream, upload and/or send information from a threatening situation to a dispatcher at an emergency management office or facility and to the user's safety group. The dispatcher can assess the situation and, if the situation warrants action, then the information can be forwarded to the appropriate first responders. The system geo-locates the user and allows integration of camera feeds in the user's vicinity. The inventive system and method enables a user to contact a dispatcher and also to alert the user's safety group. Four pieces of software facilitate video, audio, images and/or text medium of communication between the user-in-distress and the dispatcher, first responders and the user's safety group.

Abstract: A method and system for predictively controlling environmental conditions of multiple occupancy zones in an occupancy space are provided. Occupancy and environmental conditions of each of the occupancy zones are detected and identified. The detected occupancy is stored in an occupancy database. Patterns of occupancy of each of the occupancy zones are determined using the occupancy database. Future occupancy of the occupancy zones is predicted based on the occupancy patterns of the occupancy zones. The environmental conditions of the occupancy zones are controlled based on the detected occupancy and/or the predicted future occupancy. The environmental conditions of the occupancy zones in the occupancy space are thereby predictively controlled by simultaneously incorporating an occupant's desired settings, existing and historical temperature data within the occupancy space, and weather data.

Abstract: The present disclosure discloses a network device and/or method for generating a dynamic walled garden. The disclosed network device a network device receives an Hypertext Transfer Protocol (HTTP) response from a second network device. The HTTP response comprises one or more web resources, which are the only web resources accessible to unauthenticated clients. The network device further extracts the web resources from the HTTP response, and enforces enforcing an access policy based on the extracted web resources.

Abstract: A system and method for generating security alerts for a facility is presented. The system can comprise a server, cameras operable to stream video to the server or other storage location and to a surveillance center of the facility, input devices, a first module operable to assign one or more codes to the facility, associate one or more cameras with each code, and associate response guidelines with each code; and a second module operable to receive one code of the one or more codes from one of the one or more input devices, notify the facility assigned to the one code based on the response guidelines, stream video from the one or more cameras associated with the one code to the surveillance center of the facility, and generate the security alert based on the video stream. In one aspect, a user can send a video feed along with the code.

Abstract: A system and method for real time video streaming from a device through a website to a designated group for security, personal, entertainment or commercial applications and to enable responses from those recipients comprises a server operable to bi-directionally communicate with the device and other devices, which are operable to bi-directionally communicate with the server and a module on the server operable to receive notice of an upstream from the device and authenticate a log-in of the device, e.g., a user, transmit content of the upstream to the website, transmit the notice of the upstream to either Designated Recipient Groups or pre-determined recipients, display the content of the upstream on the website, in response to requests, enable placement of information such as advertising and publicity in the content, and enable responses to the content, such as communicating with the user, posting comments, conducting electronic commerce, making appointments and making reservations.