Abstract: A data processing system implements receiving a natural language query from a client device, the query including a textual description of one or more actions to be performed using an application on the client device, generating a prompt for a large language model (LLM) based on the natural language query; providing the prompt to the LLM to obtain program code, which when executed, causes the application to perform the one or more actions, the first program code being implemented in a domain specific language (DSL) designed to facilitate program synthesis via the LLM; analyzing a syntax of the first program code to identify syntax errors in the first program code; correcting the syntax errors in the program code to generate corrected program code; and causing the client device to execute the program code to perform the one or more actions in the application on the client device.

Abstract: Examples are disclosed that relate to providing transition-related assistance during a presentation. One example provides a method comprising, during a rehearsal of a presentation, receiving content of the presentation. Based on the content received, a transition within the presentation is determined via a machine learning model. During a performance of the presentation, the transition is automatically enacted.

Abstract: A computing system, including a processor configured to receive a content item. The processor may extract a plurality of content item features from the content item and receive a user request to summarize the content item. The user request may have associated contextual metadata indicating a spatiotemporal context in which the user request is received. Based on the contextual metadata, the processor may determine an estimated distraction level for the user. The processor may select a subset of the plurality of content item features based on the contextual metadata. The processor may generate a content item summary including the subset of the plurality of content item features based at least in part on the estimated distraction level. The processor may convey the content item summary for output on one or more output devices.

Abstract: A computing system, including a processor configured to receive a content item. The processor may extract a plurality of content item features from the content item and receive a user request to summarize the content item. The user request may have associated contextual metadata indicating a spatiotemporal context in which the user request is received. Based on the contextual metadata, the processor may determine an estimated distraction level for the user. The processor may select a subset of the plurality of content item features based on the contextual metadata. The processor may generate a content item summary including the subset of the plurality of content item features based at least in part on the estimated distraction level. The processor may convey the content item summary for output on one or more output devices.

Abstract: In a device including a processor and a memory, the memory includes executable instructions that cause the processor to control the device to perform functions of receiving a user input to initiate a conversation session for generating an outline for a writing; generating a voice output asking a question regarding the writing; receiving a voice input from the user responding to the voice output; identifying, based on the received voice input, content of the voice input responding to the voice output; repeating, until a predetermined condition is met, the steps of generating the voice output, receiving the voice input, and identifying the content of the voice input, wherein the question asked via each voice output is generated in response to the content of the voice input responding to the preceding voice output; and generating, based on the content of the voice inputs, the outline for the writing.

Abstract: Examples are disclosed that relate to providing transition-related assistance during a presentation. One example provides a method comprising, during a rehearsal of a presentation, receiving content of the presentation. Based on the content received, a transition within the presentation is determined via a machine learning model. During a performance of the presentation, the transition is automatically enacted.

Abstract: In a device including a processor and a memory, the memory includes executable instructions that cause the processor to control the device to perform functions of receiving a user input to initiate a conversation session for generating an outline for a writing; generating a voice output asking a question regarding the writing; receiving a voice input from the user responding to the voice output; identifying, based on the received voice input, content of the voice input responding to the voice output; repeating, until a predetermined condition is met, the steps of generating the voice output, receiving the voice input, and identifying the content of the voice input, wherein the question asked via each voice output is generated in response to the content of the voice input responding to the preceding voice output; and generating, based on the content of the voice inputs, the outline for the writing.

Abstract: A system (and corresponding method) that employs wiki-type models to consider authoring rather than composition in an application environment is provided. The innovation enables collaborative information and templates to be used to enhance quality, productivity, etc. within a software application environment. These wiki-type models can provide features, functions and benefits related to, but not limited to, general information, auto-fills, formats, schema, conversions, preferences, etc.

Abstract: A system (and corresponding method) that employs wiki-type models to consider authoring rather than composition in an application environment is provided. The innovation enables collaborative information and templates to be used to enhance quality, productivity, etc. within a software application environment. These wiki-type models can provide features, functions and benefits related to, but not limited to, general information, auto-fills, formats, schema, conversions, preferences, etc.

Abstract: A system (and corresponding method) that employs wiki-type models to consider authoring rather than composition in an application environment is provided. The innovation enables collaborative information and templates to be used to enhance quality, productivity, etc. within a software application environment. These wiki-type models can provide features, functions and benefits related to, but not limited to, general information, auto-fills, formats, schema, conversions, preferences, etc.

Abstract: A method and system for implementing a document processor and re-aggregator is described herein. A document is divided into one or more sections and formatting is removed. A condensed document is generated that includes one or more links to the one or more sections. The condensed document is transmitted to a mobile device to be displayed for a user. The user may choose to download one or more of the sections by selecting one or more of the links. Once downloaded, a section may be modified by the user. The one or more modified sections may be transmitted from the mobile device. The one or more modified sections may then be re-aggregated with the unmodified sections to form a revised document.

Abstract: Embodiments are provided to enable a user to easily and conveniently assign, share, and/or locate characteristic and other information associated with others. In an embodiment, a user can assign, share, and use one or more characterizing tags. A user can use the one or more characterizing tags to characterize a person of interest and/or a relationship or association between the user and the person of interest. A user can also perform searches using one or more characterizing tags to locate others who may be associated with the one or more characterizing tags. Users can also view user profiles including any characterizing tags and/or communicate with others based in part on a characterizing tag. The various embodiments provide a forum for social tagging, allowing a user to apply and use one or more characterizing tags that are associated with a person of interest.

Abstract: The claimed subject matter provides a system and/or a method that facilitates managing data within an environment. An interface component can receive a role-based model reflective of at least one position within an environment, wherein the environment includes two or more entities within an organized hierarchy. The role-based model can include at least one role assigned to an entity in which the assignment is indicative of the position of the entity within the environment. A role component can provide data access to the entity within the environment in accordance with the role assigned to such entity.

Abstract: A method and system for implementing a document processor and re-aggregator is described herein. A document is divided into one or more sections and formatting is removed. A condensed document is generated that includes one or more links to the one or more sections. The condensed document is transmitted to a mobile device to be displayed for a user. The user may choose to download one or more of the sections by selecting one or more of the links. Once downloaded, a section may be modified by the user. The one or more modified sections may be transmitted from the mobile device. The one or more modified sections may then be re-aggregated with the unmodified sections to form a revised document.

Abstract: Embodiments are provided to enable a user to easily and conveniently assign, share, and/or locate characteristic and other information associated with others. In an embodiment, a user can assign, share, and use one or more characterizing tags. A user can use the one or more characterizing tags to characterize a person of interest and/or a relationship or association between the user and the person of interest. A user can also perform searches using one or more characterizing tags to locate others who may be associated with the one or more characterizing tags. Users can also view user profiles including any characterizing tags and/or communicate with others based in part on a characterizing tag. The various embodiments provide a forum for social tagging, allowing a user to apply and use one or more characterizing tags that are associated with a person of interest.

Abstract: A method and system for implementing a document processor and re-aggregator is described herein. A document is divided into one or more sections and formatting is removed. A condensed document is generated that includes one or more links to the one or more sections. The condensed document is transmitted to a mobile device to be displayed for a user. The user may choose to download one or more of the sections by selecting one or more of the links. Once downloaded, a section may be modified by the user. The one or more modified sections may be transmitted from the mobile device. The one or more modified sections may then be re-aggregated with the unmodified sections to form a revised document.

Abstract: Embodiments are provided to enable a user to easily and conveniently assign, share, and/or locate characteristic and other information associated with others. In an embodiment, a user can assign, share, and use one or more characterizing tags. A user can use the one or more characterizing tags to characterize a person of interest and/or a relationship or association between the user and the person of interest. A user can also perform searches using one or more characterizing tags to locate others who may be associated with the one or more characterizing tags. Users can also view user profiles including any characterizing tags and/or communicate with others based in part on a characterizing tag. The various embodiments provide a forum for social tagging, allowing a user to apply and use one or more characterizing tags that are associated with a person of interest.

Abstract: A host securely transmits content to a peripheral thereof. The peripheral has a symmetric key (PK) and a copy of (PK) encrypted according to a public key (PU) of an entity ((PU(PK))). In the method, the host receives (PU(PK)) from the peripheral, and sends (PU(PK)) to the entity. The entity has a private key (PR) corresponding to (PU), applies (PR) to (PU(PK)) to obtain (PK), and sends (PK) back to the host. The host receives (PK) from the entity, encrypts at least a portion of the content according to (PK), and transmits the encrypted content to the peripheral. The peripheral may then decrypt the encrypted content based on (PK). A bind key (BK) encrypted by (PK) ((PK(BK))) may accompany (PU(PK)), where the content is to be encrypted according to (BK). Thus, (PK) is not revealed to the host.

Abstract: A method, system, and apparatus are provided for maintaining user privacy in a knowledge interchange (“KI”) system. A user may provide privacy preferences relating to their participation in the KI system. The user may identify specific keywords, noun phrases, and contacts that should not be transmitted to a server computer. The user may also specify whether each keyword, noun phrase, or contact should be public or private. If a public keyword is identified during a search query as being associated with the user, the user's identity will be made available to a seeker If a private keyword is identified during a search query as being associated with the user, the user's identity will not be made available and a brokered communication process between the seeker and the user will be performed.

Abstract: A method, system, and apparatus are provided for creating a knowledge interchange (“KI”) profile for a user that identifies the interests of the user, the individuals with which the user has communicated, and the topics on which the communication with the user was made. In order to create the KI profile, items of interest are gathered at the client computer by monitoring the interaction between a user and programs executing on the client computer. Once the items of interest have been identified, the KI profile is created by performing a social network analysis, an interest analysis, and a noun phrase analysis. Once the KI profile has been created, it may be uploaded to a server computer where it is aggregated with KI profiles created for other users.