Abstract: A method for automatically detecting and processing a computer input event comprising one or more intents is provided. The method may include, in response to receiving the computer input event, automatically generating a parse tree comprising nodes including a possible interpretation of the received computer input event and at least one determined intent. The method may further include performing a confidence evaluation for the nodes and receiving one or more first scores from one or more computer agents for a respective node to indicate an ability of a respective computer agent to process the respective node. The method may further include, determining a second score for the respective node by aggregating the one or more first scores from the one or more computer agents for the respective node. The method may further include, based on the determined second score, selecting a node for processing the received computer input event.

Abstract: A computer system includes a display and a processing system. The processing system is configured to receive an input from a user using and to control an aggregated assistant interface displayed on the display. The aggregated assistant interface displays one or more planned operations in response to receiving an initial input from the user and is configured to receive one or more interactive inputs configured to interact with the planned operations.

Abstract: A method, computer program, and computer system are provided for explaining generation of a flow from natural language utterances. Data corresponding to a natural language utterance is received. One or more constraints corresponding to a flow to be generated are determined based on the received natural language utterance. A flow is constructed based on the determined constraints. An explanation associated with the constructed flow is provided, and the explanation identifies parameters corresponding to constructing the flow.

Abstract: A method for automatically detecting and processing a computer input event comprising one or more intents is provided. The method may include, in response to receiving the computer input event, automatically generating a parse tree comprising nodes including a possible interpretation of the received computer input event and at least one determined intent. The method may further include performing a confidence evaluation for the nodes and receiving one or more first scores from one or more computer agents for a respective node to indicate an ability of a respective computer agent to process the respective node. The method may further include, determining a second score for the respective node by aggregating the one or more first scores from the one or more computer agents for the respective node. The method may further include, based on the determined second score, selecting a node for processing the received computer input event.

Abstract: Techniques are provided for reinforcement learning software agents enhanced by external data. A reinforcement learning model supporting the software agent may be trained based on information obtained from one or more knowledge stores, such as online forums. The trained reinforcement learning model may be tested in an environment with limited connectivity to an external environment to meet performance criteria. The reinforcement learning software agent may be deployed with the tested and trained reinforcement learning model within an environment to autonomously perform actions to process requests.

Abstract: A computer system adapts processing of expressions by a command-line interface. An expression provided to the command-line interface is analyzed, wherein the command line interface includes pre-defined expression processing. One or more artificial intelligence agents are selected from a plurality of artificial intelligence agents based on the analysis of the expression. The expression is evaluated by the selected one or more artificial intelligence agents to determine processing modifications for the pre-defined expression processing. The expression is processed in accordance with the determined processing modifications and results are provided to the command-line interface. Embodiments of the present invention further include a method and program product for adapting processing of expressions by a shell in substantially the same manner described above.

Abstract: Embodiments of the present invention provide a computer system a computer program product, and a computer implemented method. Embodiments of the present invention can identify at least one user in a plurality of users using a plurality of indicative markers. Embodiments of the present invention can then dynamically analyze input data stored on a computing device associated with the identified user and generate an automated personalized walkthrough by tailoring a plurality of steps within the input data to the at least one identified user. Certain embodiments of the present invention can then, in response to generating the automated personalized walkthrough, generate an automated personalized tutorial by aggregating the generated walkthrough and the at least one identified user based on a predetermined threshold of assessment.

Abstract: The present disclosure describes systems and methods for a command line interface with artificial intelligence integration. Embodiments of the disclosure provide a command line orchestration component (e.g., including a reinforcement learning model) that provides a generic command line interface environment (e.g., that researchers can interface using a simple sense-act application programming interface (API)). For instance, a command line orchestration component receives commands (e.g., text input) from a user via a command line interface, and the command line orchestration component can identify command line plugins and candidate response from the command line plugins. Further, the command line orchestration component may select a response from the candidate responses based on user preferences, user characteristics, etc., thus providing a generic command line interface environment for various users (e.g., including artificial intelligence developers and researchers).

Abstract: A computer-implemented method of generating explanations for a sequence of actions performed by an aggregated assistant includes receiving a request from a user equipment (UE) to execute a sequence of actions. A decision is rendered on whether to execute the requested sequence of actions. An explanation regarding the rendered decision is provided including a user data upon which the decision is based.

Abstract: Embodiments of the present invention provide a computer system a computer program product, and a computer implemented method. Embodiments of the present invention can identify at least one user in a plurality of users using a plurality of indicative markers. Embodiments of the present invention can then dynamically analyze input data stored on a computing device associated with the identified user and generate an automated personalized walkthrough by tailoring a plurality of steps within the input data to the at least one identified user. Certain embodiments of the present invention can then, in response to generating the automated personalized walkthrough, generate an automated personalized tutorial by aggregating the generated walkthrough and the at least one identified user based on a predetermined threshold of assessment.

Abstract: An optimization method, system, and computer program product for a number of tasks within a business process that can be automated that includes receiving access to an electronic representation of the business process, optimizing the business process to develop an optimized business process, displaying the optimized business process as a storyboard using storyboarding, and receiving an edit of the optimized business process, and automatically making a further edit to the optimized business process.

Abstract: The present disclosure describes systems and methods for a command line interface with artificial intelligence integration. Embodiments of the disclosure provide a command line orchestration component (e.g., including a reinforcement learning model) that provides a generic command line interface environment (e.g., that researchers can interface using a simple sense-act application programming interface (API)). For instance, a command line orchestration component receives commands (e.g., text input) from a user via a command line interface, and the command line orchestration component can identify command line plugins and candidate response from the command line plugins. Further, the command line orchestration component may select a response from the candidate responses based on user preferences, user characteristics, etc., thus providing a generic command line interface environment for various users (e.g., including artificial intelligence developers and researchers).

Abstract: A computer system adapts processing of expressions by a command-line interface. An expression provided to the command-line interface is analyzed, wherein the command line interface includes pre-defined expression processing. One or more artificial intelligence agents are selected from a plurality of artificial intelligence agents based on the analysis of the expression. The expression is evaluated by the selected one or more artificial intelligence agents to determine processing modifications for the pre-defined expression processing. The expression is processed in accordance with the determined processing modifications and results are provided to the command-line interface. Embodiments of the present invention further include a method and program product for adapting processing of expressions by a shell in substantially the same manner described above.

Abstract: Techniques are provided for reinforcement learning software agents enhanced by external data. A reinforcement learning model supporting the software agent may be trained based on information obtained from one or more knowledge stores, such as online forums. The trained reinforcement learning model may be tested in an environment with limited connectivity to an external environment to meet performance criteria. The reinforcement learning software agent may be deployed with the tested and trained reinforcement learning model within an environment to autonomously perform actions to process requests.