Abstract: A system, computer program product, and method are presented for leveraging structured data and unstructured data, and, more specifically, to ranking documentation from unstructured data sources through leveraging insights provided by the structured data to facilitate associated business risk inquiries. The method includes identifying, by researching subject business entities, one or more structured data sources that include relevant structured data directed to the subject business entities. The method also include extracting the relevant structured data directed toward the subject business entities and leveraging the relevant structured data to identify unstructured data sources. The method further includes identifying documents from the unstructured data sources that have relevant information, thereby identifying relevant unstructured data, and leveraging the relevant structured data to determine relationships with the relevant unstructured data.

Abstract: Systems, methods, and other embodiments associated with characteristics-based selection of time series forecast algorithms are described. In one embodiment, a method includes analyzing each time series in a training set of time series to yield characteristics vectors for the time series. The method trains an auto-encoder to minimize error: (1) between bottleneck layer and the characteristics vectors, and (2) between input layer and output layer. The method generates new characteristics vectors that fill gaps between neighboring characteristics. The method inputs the new characteristics vectors to the bottleneck layer to generate a testing set of time series. The method tests forecasting algorithms using the testing set to find forecasting error. The method trains a ranking function to assign a rank to each forecasting algorithm based on a provided characteristics vector. And, the method automatically selects one of the forecasting algorithms to monitor an additional time series based on the ranks.

Abstract: A system and method for performing visual odometry is disclosed. In aspects, the system implements methods to generate an image pyramid based on an input image received. A refined pose prior information representing a location and orientation of the autonomous vehicle can be generated based on one or more images of the image pyramid. One or more seed points can be selected from the one or more images of the image pyramid. One or more refined seed representing the one or more seed points with added depth values can be generated. One or more scene points can be generated based on the one or more refined seed points. A point cloud can be generated based on the one or more scene points.

Abstract: Application compliance policies can be dynamically updated. An agent can be deployed on user computing devices to monitor application install events to track how frequently users install applications on the user computing devices and whether applicable application compliance policies dictate that such applications should be removed. A policy management service of a management solution can interface with the agents to gather application metrics and use the application metrics to dynamically update the application compliance policies to prevent future removal of one or more applications that are determined to be commonly installed by the users. These dynamic updates could be made on a per-user basis, a per-group basis, or a global basis.

Abstract: As a media program is aired to listeners, agents executed by a control system monitor actions by the creator or by listeners to ensure that the creator or the listeners comply with relevant policies and that the media program is aired as scheduled. The agents are programmed with sets of rules regarding content, language, advertising or other restrictions, and configured to process signals representative of actions taken by the creator or the listeners to determine whether such actions comply with such rules. The signals may represent spoken words, written messages, or interactions by listeners, among other actions. The agents interpret the signals to identify intended actions of creators or listeners, and to determine whether the intended actions would comply with each of the rules associated with the media program. The agents are also configured to identify and execute alternative actions as necessary.

Abstract: Applications can be automatically grouped in a secure workspace environment. An application organizer service can be deployed on a user computing device to intelligently group applications within secure workspaces based on resource requirements, peripheral usage, threat level and/or data sharing characteristics of the applications. The application organizer service may determine these characteristics in a variety of ways including through the monitoring of the applications as they execute inside the secure workspaces.

Abstract: A summary generation system is disclosed that is configured to generate a summary for content to be summarized by identifying relevant chunks of information from the content to be summarized using a large language model (LLM) and a set of questions. The set of questions enable the system to identify and retrieve relevant chunks of information. Each question undergoes a translation or transformation process to generate multiple question variants for each question. The multiple question variants are used by the system to optimize the search to obtain relevant chunks of information. Then, using the multiple question variants and an LLM, the system extracts information (i.e., answers) from the relevant chunks of information. The summary generation system then collates the answers to create an accurate and comprehensive summary for the content to be summarized.

Abstract: Techniques for time-bound hyperparameter tuning are disclosed. The techniques enable the determination of optimized hyperparameters for a machine learning (ML) model given a specified time bound using a three-stage approach. A series of trials are executed, during each of which the ML model is trained using a distinct set of hyperparameters. In the first stage, a small number of trials are executed to initialize the algorithm. In the second and third stages, a certain number of trials are executed in each stage. The number of trials to run in each stage are determined using one or more computer-implemented techniques. The computer-implemented techniques can also be used to narrow the hyperparameter search space and the feature space. Following the third stage, a set of optimized hyperparameters is adopted based a predefined optimization criterion like minimization of an error function.

Abstract: A summary generation and summary selection system is disclosed that is capable of automatically evaluating multiple summaries generated for content and selecting a single summary that is deemed to be the “best” among the multiple generated summaries. The system includes capabilities to use multiple different selection techniques to select the best summary from multiple generated summaries. A first selection technique involves identifying entities and entity relationships from the content to be summarized and selecting a summary from multiple summaries generated for the content based on the entities and entity relationships identified in the content. A second selection technique involves determining a set of questions that are answered by each summary. The technique then selects a summary based upon the set of questions answered by each summary. The system then outputs the selected summary as the summary for the content.

Abstract: Techniques for multi-output model forecasting are provided herein. An example method can include a computing system receiving a request to forecast a value for a variable at a future time point based upon a time series, the time series comprising a sequence of data points, each data point in the sequence of data points identifying a time point and at least one value associated with the time point. The computing system can predict, using a first trained machine learning model and based upon the times series, a plurality of forecast values for the future time point, the plurality of forecast values including: a first forecast value forecasted for the variable at the future time point; and a set of one or more forecast attribute values for one or more attributes of the time series, each of the set of one or more forecast attribute values predicted for the future time point.

Abstract: State can be maintained between web applications such as a lightweight and a classic version of a web application. A lightweight viewer of a web application providing a visualization dashboard is run in a web browser. User inputs that modify the visualization dashboard are obtained. Then user input for navigation to a classic viewer of the web application is obtained. The classic viewer is navigated to in the web browser. Then the visualization dashboard of the classic viewer is modified to the modified state from the lightweight viewer without user input to the classic viewer.

Abstract: A system for two-way projection of information and contactless communication of a data item includes a memory and a processor coupled to the memory. The processor initiates a virtual session for an interaction between an entity owner and a user relating to a set of objects and generates a non-fungible token for the virtual session. The processor tracks current information associated with the set of objects and simultaneously project the current information to a first virtual device of the entity owner and a second virtual device of the user. The processor receives, via the second virtual device of the user, a selection of one or more objects and a data item with respect to the selected objects. The processor communicates the data item and the generated non-fungible token for fulfillment of the selected objects to the user. The data item is communicated without requiring explicit contact by the user.

Abstract: In some aspects, the disclosure is directed to methods and systems for detection and classification of stamps in documents. The system can receive image data and textual data of a document. The system can pre-process and filter that data, and covert the textual data to a term frequency inverse document frequency (TF-IDF) vector. The system can detect the presence of a stamp on the document. The system can extract a subset of the image data including the stamp. The system can extract text from the subset of the image data. The system can classify the stamp using the extracted text, the image data, and the TF-IDF vector. The system can store the classification in a database.

Abstract: Embodiments provide systems and methods to load balance using tenant affinities. A method includes configuring a load balancer with a set of tenant affinities, the set of tenant affinities including a tenant affinity for each of a plurality of tenants with respect to each of a plurality of computing nodes that provide services to users in a multitenant environment. Load balancing may include receiving a user request, associated with a tenant, for a service provided by the computing nodes, determining a highest tenant affinity computing node for the tenant using the set of tenant affinities and directing the user request to the highest tenant affinity computing node for the tenant.

Abstract: A computer-implemented system, method and/or computer program product to monitor changes in business risk of a targeted entity includes retrieving one or more industry classifications for one or more core businesses of the targeted entity; receiving news feeds related to the one or more industry classifications; detecting and extracting negative news related to the core businesses of the targeted entity from the news feeds; calculating an industry confidence score based upon the negative news; determining if the industry confidence score is greater than an industry confidence threshold; calculating, in response to the industry confidence score being larger than the industry confidence threshold, an entity confidence score for the targeted entity based upon negative news; and generating, in response to the entity confidence score being larger than an entity confidence threshold, an alert report for the targeted entity.

Abstract: An embodiment may involve storage containing incident logs and mappings between incident logs and vector representations generated by a machine learning (ML) model.

Abstract: In implementations of systems for stylizing digital content, a computing device receives digital content having a plurality of content entities. Classified content entities are generated by classifying the plurality of content entities using one or more machine-learning models. A determination is then made regarding correspondence of the classified content entities with visual styles of a digital template. Based on the determined correspondence, the plurality of content entities of the digital content are displayed as having the visual styles, respectively, of the digital template.

Abstract: Some embodiments of the invention provide a method of sending data messages from an edge router at a first location of an enterprise network to a SaaS (software as a service) application server provided by a third-party at a second location. The method receives, from a DNS (domain name system) first server, a resolution for a particular destination network address for the SaaS application server at the second location. From a second server, the method obtains an identifier for a first cloud gateway from multiple cloud gateways at multiple locations through which the particular destination address for the SaaS application server can be reached, the first cloud gateway farther from the first location than a second cloud gateway in the multiple cloud gateways but closer to the second location than the second cloud gateway. The method uses an optimized SD-WAN connection to the first cloud gateway to forward data messages for the first cloud gateway to the SaaS application at the second location.

Abstract: Described herein are embodiments for assisting in creating a listing for a For Sale Object (FSO). An item name suggestion module receives seller input and provides suggested entries for the listing to help the seller describe the FSO more accurately and consistently. A hierarchical database provides a structure for ordering suggested entries, with the structure ordered based on scores. The scores are based on rules that relate item characteristics and take into account rankings of those item characteristics with respect to one another. Metadata tags that are used by the online merchandise platforms can be identified and included in the listing, even if a seller is not familiar with the metadata tags. The hierarchical database also connects or associates item characteristics in groups that describe specific FSO. The connections can help to optimize search results as the listing is completed by the seller.

Abstract: Embodiments are described for a user device comprising a transceiver configured to communicate with a server and a processor communicatively coupled to the transceiver. The processor is configured to receive a uniform resource locator (URL) from the server and determine that the URL is a universal link. The processor is further configured to authenticate the universal link and parse the universal link to obtain a domain link. The processor is further configured to connect to the domain link.