Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to incorporating explainability constraints into machine learning model training. A computer-implemented system can comprise a memory that can store computer executable components. The computer-implemented system can further comprise a processor that can execute the computer executable components stored in the memory, wherein the computer executable components can comprise a training component that can train a machine learning model using an objective function that can be modified to incorporate an explainability metric for the machine learning model in addition to a model performance metric of the machine learning model.

Abstract: Provided are techniques for deploying AI models at local sites. A selection of an Artificial Intelligence (AI) model template is received at a local site, where the AI model template is created at a remote site and is packaged in a transportable container. The AI model template in the transportable container is retrieved. A lifecycle of an AI model is orchestrated by: instantiating an AI model from the AI model template, retrieving data from one or more local data sources, training the AI model using the data, deploying the AI model as a service, monitoring the AI model for drift, and, in response to identifying drift, re-training the AI model.

Abstract: Aspects of the present invention disclose a method for calculating a risk resulting from a network of networks that includes unknown relationships in a privacy preserving manner. The method includes one or more processors determining a set of conditions corresponding to a user of a network. The method further includes transmitting a compliance request corresponding to the set of conditions to one or more members of the network utilizing a privacy preserving algorithm. The method further includes determining a respective risk factor of one or more members of the network, wherein the respective risk factor corresponds to a response of each of the one or more members to the compliance request. The method further includes determining an overall risk of the network based at least in part on the risk factors of the one or more members.

Abstract: User authentication based on cognitive profiling. First, usage by a person of one or more computerized devices is automatically and continuously tracked. A cognitive profile of the person is automatically and continuously generated based on the tracked usage. Responsive to a request for authenticating an identity of the person, a cognitive question is automatically generated based on the cognitive profile, and is presented to a user professing to be the person. An answer to the cognitive question is received from the user. Finally, the identity of the person is automatically authenticated when the answer to the cognitive question is determined to be correct.

Abstract: Aspects of the present invention disclose a method for calculating a risk resulting from a network of networks that includes unknown relationships in a privacy preserving manner. The method includes one or more processors determining a set of conditions corresponding to a user of a network. The method further includes transmitting a compliance request corresponding to the set of conditions to one or more members of the network utilizing a privacy preserving algorithm. The method further includes determining a respective risk factor of one or more members of the network, wherein the respective risk factor corresponds to a response of each of the one or more members to the compliance request. The method further includes determining an overall risk of the network based at least in part on the risk factors of the one or more members.

Abstract: A method, apparatus and product for interaction context-based control of output volume level. The method comprising: obtaining a vocal input from a user, wherein the vocal input is part of an interaction between the user and the voice-based interaction agent; determining an interaction context of the interaction between the user and the voice-based interaction agent; determining an output volume level of the voice-based interaction agent based on the interaction context; and providing to the user an output of the voice-based interaction agent, wherein the output comprises a voice-based output having a volume level of the output volume level.

Abstract: In an example computer-implemented method, unstructured interactions between an unstructured conversation bot and a plurality of users are logged. A process flow model is generated based on the logged unstructured interactions. Instructions based on the process flow model are presented to a user in real time via the conversation bot.

Abstract: A system including: A main virtual assistant (VA) that is configured to operate a back-end system according to instructions. An intermediary VA that is configured to: learn, by conversing with the human user and by analyzing responses from the main VA to the human user, to perform a task that is associated with the back-end system; hold a conversation with the main VA, wherein, in the conversation, the instructions are formulated and relayed from the intermediary VA to the main VA based on the learning and on further conversing with the human user, such that the main VA operates the back-end system according to the instructions; and formulate and relay responses to the instructions from the main VA to the human user.

Abstract: User authentication based on cognitive profiling. First, usage by a person of one or more computerized devices is automatically and continuously tracked. A cognitive profile of the person is automatically and continuously generated based on the tracked usage. Responsive to a request for authenticating an identity of the person, a cognitive question is automatically generated based on the cognitive profile, and is presented to a user professing to be the person. An answer to the cognitive question is received from the user. Finally, the identity of the person is automatically authenticated when the answer to the cognitive question is determined to be correct.

Abstract: In an example computer-implemented method, unstructured interactions between an unstructured conversation bot and a plurality of users are logged. A process flow model is generated based on the logged unstructured interactions. Instructions based on the process flow model are presented to a user in real time via the conversation bot.

Abstract: A method comprising: accessing one or more conversational flows of a conversational computer program, wherein the one or more conversational flows each comprises dialogue nodes and fulfillment nodes, and wherein each of the one or more conversational flows is at least one of: (a) a historical conversational flow of a human-computer conversation carried out by the conversational computer program, and (b) a programmed conversational flow, according to which the conversational computer program conducts human-computer conversations; receiving a desirability score of each of at least some of the fulfillment nodes; and based on the one or more conversational flows and the desirability scores, automatically assigning a polarity score to each of at least some of the dialogue nodes.

Abstract: A method, apparatus and product for interaction context-based control of output volume level. The method comprising: obtaining a vocal input from a user, wherein the vocal input is part of an interaction between the user and the voice-based interaction agent; determining an interaction context of the interaction between the user and the voice-based interaction agent; determining an output volume level of the voice-based interaction agent based on the interaction context; and providing to the user an output of the voice-based interaction agent, wherein the output comprises a voice-based output having a volume level of the output volume level.

Abstract: Techniques for sharing content between portals. A producer portal may identify content to be shared with one or more consumer portals. One or more of the shared content objects may then be copied to a consumer portal as remote delta link objects. Changes or modifications to the source object at the producer portal are automatically reflected in the corresponding target remote delta link object on the consumer portal. Any modifications or customizations made to the remote delta link object at the consumer portal override those of the producer's source object. In this manner, changes made to the second object are reflected in the first object while preserving the changes/modifications made to the first object on the first portal.

Abstract: The subject matter disclosed herein provides methods and apparatus, including computer program products, for providing software updates. In one aspect there is provided a method. The method may include copying an application to a shadow system, the application used to upgrade the shadow system rather than a production system; copying data from the production system to the shadow system; selecting whether to lock changes to data in the production system or record changes to the data in the production system; recording one or more changes to data in the production system, the changes recorded in a container, when record changes has been selected; migrating recorded data in the container to the shadow system, so that the shadow system and production system are in a similar data state; and using the shadow system, upgraded with the application and at least one of data copied from the production system and recorded data from the container, for production rather than the production system.

Abstract: The subject matter disclosed herein provides methods and apparatus, including computer program products, for providing software updates. In one aspect there is provided a method. The method may include copying an application to a shadow system, the application used to upgrade the shadow system rather than a production system; copying data from the production system to the shadow system; selecting whether to lock changes to data in the production system or record changes to the data in the production system; recording one or more changes to data in the production system, the changes recorded in a container, when record changes has been selected; migrating recorded data in the container to the shadow system, so that the shadow system and production system are in a similar data state; and using the shadow system, upgraded with the application and at least one of data copied from the production system and recorded data from the container, for production rather than the production system.

Abstract: Techniques for sharing content between portals. A producer portal may identify content to be shared with one or more consumer portals. One or more of the shared content objects may then be copied to a consumer portal as remote delta link objects. Changes or modifications to the source object at the producer portal are automatically reflected in the corresponding target remote delta link object on the consumer portal. Any modifications or customizations made to the remote delta link object at the consumer portal override those of the producer's source object. In this manner, changes made to the second object are reflected in the first object while preserving the changes/modifications made to the first object on the first portal.