Abstract: Systems and methods are provided for utilizing cursor prompt interfaces to facilitate multiple functionalities and techniques for interacting with content selected by corresponding cursor prompts. Selection of displayed content causes the cursor prompt interfaces to be generated and displayed with interactive components for generating new content corresponding to the selected content and that is based on a context of the application instance and/or a user context. In some instances, the cursor prompt interfaces also interact with remote machine-learning models to obtain the new content.

Abstract: Systems and methods are provided for facilitating the discovery and presentations of skills and data processed by the skills within blocks of a canvas displayed to a user within a user interface. The systems selectively process structured and unstructured data based on user context for facilitating presentation of contextually relevant data to a user.

Abstract: Systems and methods are provided for facilitating the discovery and presentations of skills and data processed by the skills within blocks of a canvas displayed to a user within a user interface. The systems also identify schemas and data output formats of the relevant skills, and a desired presentation schema based on the user contexts and the application contexts. The systems further identify modules for normalizing the schemas of the relevant skills to the desired presentation schema, and uses the identified modules to normalize data obtained from the relevant skills into the desired presentation schema for presentation within the blocks of the canvas.

Abstract: Systems and methods are provided for managing the utilization and switching of modes for a multi-modal cursor. A user interface with selectable content is displayed, along with a cursor prompt for a multi-modal cursor. A traditional cursor mode icon and an artificial intelligence (AI) cursor mode icon are also displayed with user interface. The systems determine which mode of the multi-modal cursor to activate and utilize based on user input selecting either the traditional cursor mode icon or the AI cursor mode icon. User selection of the traditional cursor mode icon activates the first cursor mode and user selection of the AI cursor mode icon activates the second cursor mode.

Abstract: Systems and methods are provided for facilitating the discovery and presentations of skills and data within blocks of a canvas displayed to a user within a user interface. The data is presented to provide personalized and contextually relevant experiences as the user interacts with the data and interfaces.

Abstract: Examples described herein generate training data for machine learning (ML) for natural language (NL) processing (such as semantic parsing for translating NL). A formula tree is generated based on sampling both a formula grammar and NL templates. Using the formula tree, an ML training data instance pair is generated comprising a formula example and an NL example. A context example may also be used during instantiation of the formula tree. An ML model is trained with training data including the ML training data instance pair, and ML output is generated from NL input. The ML output includes, for example, a machine-interpretable formula, a database querying language command, or a general programming language instruction. Some examples support context-free grammar, probabilistic context-free grammar, and/or non-context-free production rules.

Abstract: The disclosure herein describes generating an application from input content. Input content of a content type is obtained, such as an image file, digital document file, or the like. A content data extractor is selected from a set of content data extractors based on the content type. A set of content entities is extracted from the obtained input content using the selected content data extractor, such as text labels, text boxes, buttons, or the like. The set of content entities are normalized according to a standard interface schema and an application template is generated using the normalized set of content entities, whereby an application can be developed using the generated application template. The disclosure enables application interfaces to be designed using a variety of methods and for those different types of designs to be efficiently converted to a functional application.

Abstract: The disclosure herein describes generating an application from input content. Input content of a content type is obtained, such as an image file, digital document file, or the like. A content data extractor is selected from a set of content data extractors based on the content type. A set of content entities is extracted from the obtained input content using the selected content data extractor, such as text labels, text boxes, buttons, or the like. The set of content entities are normalized according to a standard interface schema and an application template is generated using the normalized set of content entities, whereby an application can be developed using the generated application template. The disclosure enables application interfaces to be designed using a variety of methods and for those different types of designs to be efficiently converted to a functional application.

Abstract: Examples described herein generate training data for machine learning (ML) for natural language (NL) processing (such as semantic parsing for translating NL). A formula tree is generated based on sampling both a formula grammar and NL templates. Using the formula tree, an ML training data instance pair is generated comprising a formula example and an NL example. A context example may also be used during instantiation of the formula tree. An ML model is trained with training data including the ML training data instance pair, and ML output is generated from NL input. The ML output includes, for example, a machine-interpretable formula, a database querying language command, or a general programming language instruction. Some examples support context-free grammar, probabilistic context-free grammar, and/or non-context-free production rules.

Abstract: The disclosure herein describes generating an application from input content. Input content of a content type is obtained, such as an image file, digital document file, or the like. A content data extractor is selected from a set of content data extractors based on the content type. A set of content entities is extracted from the obtained input content using the selected content data extractor, such as text labels, text boxes, buttons, or the like. The set of content entities are normalized according to a standard interface schema and an application template is generated using the normalized set of content entities, whereby an application can be developed using the generated application template. The disclosure enables application interfaces to be designed using a variety of methods and for those different types of designs to be efficiently converted to a functional application.

Abstract: Methods, systems, and computer program products are provided for dynamic and adaptive user-interface component selection for rendering in distributed applications. An adaptive user-interface component selection system is enabled to select user-interface components for rendering and display on a client device running an instance of a client application. User-interface components are selected based on a set of applicable component rules. Applicable component rules are determined based on client feedback information that includes information regarding the client including: network bandwidth, geolocation, user role, user context and required application features. Selected user-interface components are transformed into renderable code either locally to the system or remotely at the client device, and rendered and displayed on the client device.

Abstract: Methods, systems, and computer program products are provided for dynamic and adaptive user-interface component selection for rendering in distributed applications. An adaptive user-interface component selection system is enabled to select user-interface components for rendering and display on a client device running an instance of a client application. User-interface components are selected based on a set of applicable component rules. Applicable component rules are determined based on client feedback information that includes information regarding the client including: network bandwidth, geolocation, user role, user context and required application features. Selected user-interface components are transformed into renderable code either locally to the system or remotely at the client device, and rendered and displayed on the client device.

Abstract: Methods for resolving anomalies for network applications using code injection are performed by network services systems. Notifications for electronic communications incoming to executing applications are received and monitored on the network services system. The notifications are analyzed to identify anomalies in the electronic communications for executing applications. Application contexts associated with executing applications are determined, and code solutions are selected from a set of code solutions to correspondingly apply against the anomalies. Code solutions include code blocks, scripts, or code assemblies to resolve specific anomalies for executing applications. Code solutions are selected based on the application contexts and the one or more anomalies. Selected code solutions are injected into the first executing application to resolve or mitigate the anomalies.