Abstract: A computer-implemented process for updating an electronic document includes the following operations. Using a preprocessor, preprocessing is performed on the electronic document to generate a computer data structure. The computer data structure is evaluated using a word sense disambiguation (WSD) engine and a deep neural network to determine a context of a sentence within the electronic document. Based upon the context, a determination is made that a word within the sentence is a word of interest. The sentence is rewritten using a mitigation engine and a large language model to generate a revised sentence that does not include the word of interest. A determination is made that the revised sentence does not include any other word of interest; and the electronic document is updated to include the revised sentence.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to automatic sentence condition matching using natural language processing (NLP). The computer-implemented system can comprise a memory that can store computer-executable components and a processor that can execute the computer-executable components, wherein the computer-executable components can comprise an extraction module that can use a probabilistic relevance weighting model to retrieve a first sentence from a document by computing a normalized relevance score of the first sentence based on a relevance weighting score of a second sentence from a dictionary of query sentences. The computer-executable components can further comprise a resolution module that can use a set of NLP rules and a linguistic dictionary to automatically identify whether the first sentence and the second sentence have a same meaning based on the normalized relevance score being above a defined threshold.

Abstract: An embodiment senses an object from an object screening system, and responsive to the sensed object, generates a context information based on the sensed object. The embodiment generates a cultural classification by a Culturally Aware Objects Model based in part on the context information wherein the Culturally Aware Objects Model is trained on a cultural factor of an object. The embodiment generates a moderated context information by a Sensitive Information Moderation Model based in part on the cultural classification and the context information wherein the Sensitive Information Moderation Model is trained on a privacy parameter. The embodiment also computes a recommendation by a Recommendation Component based in part on the moderated context information wherein the object screening system is updated with the recommendation.

Abstract: Pairing a user response and associated context with a neural network associated with a virtual assistant computer during a dynamic text conversation with an end user. The virtual assistant computer receives a detected user generated text input; determines context of the detected user generated text input; compares the context of the detected user generated text input by comparing a confidence score representing context of the user generated input to a classification associated with each of a plurality of existing nodes of a neural network. For confidence scores below a threshold relative to the classification associated with each of the existing nodes of the neural network, the virtual assistant computer creates a new node within the neural network and assigns the context of the user generated text to the new node.

Abstract: A computer-implemented method, system and computer program product for initiating a conversation by a virtual agent. The boundary of a widget of a webpage the user is utilizing is determined. The user's interactions or lack of interactions with the widget within the determined boundary of the widget of the webpage is then determined, such as based on tracking the eye gaze or focus of the user. If it is determined that the user is experiencing difficulty in utilizing the widget, then the content associated with the widget is extracted. The extracted widget content is then mapped to the virtual agent content. The virtual agent is instructed to initiate a conversation based on the extracted widget content. In this manner, the virtual agent will now be able to dynamically initiate a conversation with the user to assist the user in addressing a problem the user is currently experiencing with the widget.

Abstract: According to a computer-implemented method, a chat data set is received, which chat data set includes information indicative of a plurality of natural language chat transcripts of chats that occurred between a virtual agent and a human. Machine logic analyzes the chat data set to identify an error that occurred in the operation of the virtual agent. The machine logic updates a chat model based on the chat data set.

Abstract: According to a computer-implemented method, a virtual agent log data set is received which log data set includes information indicative of operation of a virtual agent. Machine logic analyzes the virtual agent log data set to identify an error that occurred in the operation of the virtual agent. The machine logic also determines an error correction for correcting conditions in the virtual agent that resulted in the error. The error correction is sent to the virtual agent.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining chat session data of a chat session having a first participant provided by a patron user and a second participant provided by an enterprise user; detecting, subsequent to a connectivity failure, that a network connection supporting the chat session has been restored; presenting in response to the detecting a prompt to the first participant, the prompt being in dependence on the chat session data; deciding an authentication action in dependence on a received response of the first participant in response to the presented prompt; and performing the authentication action in accordance with the deciding.

Abstract: Cognitive software and/or machine learning software are monitored in a cognitive computing environment. Open interface management of virtual agent nodes is performed in the cognitive computing environment.

Abstract: An expert system incorporates multiple virtual-agent experts, each trained in a particular field or domain. When a user enters a block of input, an interactive front-end infers the semantic meaning of the input and creates a chat-table record that stores the inferred meaning and other characteristics of the input. A distributed virtual-assistant manager (DVAM) module uses that record to identify the domain of the input and, after retrieving cross-reference information stored in a virtual-assistant intent (VAI) table, selects a virtual-agent expert trained in the identified domain. If necessary, the DVAM directs the front-end to seamlessly switch the user to the newly selected expert. As the session continues, the system continues to dynamically switch the user to different experts as the session traverses different domains. The system may also consider the domain history of the entire session when selecting a domain.

Abstract: A system and method for aiding a user in troubleshooting a problem includes extracting one or more entities and actions from a problem statement received from a user computing device, wherein, in response to the extracting: mapping, the one or more entities and actions to one or more images related to the one or more entities and actions, and ordering, the one or more entities and actions into a user action sequence, creating a pictorial sequence of user-taken actions to correct the problem, comparing the pictorial sequence of user-taken actions to correct the problem with a correct pictorial sequence to correct the problem, to identify a correct action that the user failed to perform, and isolating a portion of the correct pictorial sequence that corresponds to the correct action that the user failed to perform, for displaying to the user on the user computing system.

Abstract: Pairing a user response and associated context with a neural network associated with a virtual assistant computer during a dynamic text conversation with an end user. The virtual assistant computer receives a detected user generated text input; determines context of the detected user generated text input; compares the context of the detected user generated text input by comparing a confidence score representing context of the user generated input to a classification associated with each of a plurality of existing nodes of a neural network. For confidence scores below a threshold relative to the classification associated with each of the existing nodes of the neural network, the virtual assistant computer creates a new node within the neural network and assigns the context of the user generated text to the new node.

Abstract: A system and method compare performance of virtual assistants. A user selects metrics for evaluating two or more virtual assistants, and these metrics may be weighted by the user. One or more chat sessions from each virtual assistant are then analyzed using the weighted metrics to generate a score for each chat session. The scores of chat sessions of different virtual assistants are then compared according to the selected weighted metrics, and a recommendation of a virtual assistant may be made based on the score comparison. The evaluation of multiple virtual assistants allows comparing these virtual assistants to determine which provides the better customer service according to the selected weighted metrics.

Abstract: A computer-implemented method, system and computer program product for initiating a conversation by a virtual agent. The boundary of a widget of a webpage the user is utilizing is determined. The user's interactions or lack of interactions with the widget within the determined boundary of the widget of the webpage is then determined, such as based on tracking the eye gaze or focus of the user. If it is determined that the user is experiencing difficulty in utilizing the widget, then the content associated with the widget is extracted. The extracted widget content is then mapped to the virtual agent content. The virtual agent is instructed to initiate a conversation based on the extracted widget content. In this manner, the virtual agent will now be able to dynamically initiate a conversation with the user to assist the user in addressing a problem the user is currently experiencing with the widget.

Abstract: According to a computer-implemented method, a chat data set is received, which chat data set includes information indicative of a plurality of natural language chat transcripts of chats that occurred between a virtual agent and a human. Machine logic analyzes the chat data set to identify an error that occurred in the operation of the virtual agent. The machine logic updates a chat model based on the chat data set.

Abstract: According to a computer-implemented method, a virtual agent log data set is received which log data set includes information indicative of operation of a virtual agent. Machine logic analyzes the virtual agent log data set to identify an error that occurred in the operation of the virtual agent. The machine logic also determines an error correction for correcting conditions in the virtual agent that resulted in the error. The error correction is sent to the virtual agent.

Abstract: Disclosed embodiments provide techniques for restoring an interrupted automated assistance session. Session contexts including pertinent metadata are periodically saved for each session, including a session reentry point. When a user calls an automated response system, metadata is collected from the user and compared with metadata from saved session contexts. If the user is determined to be associated with a saved session context, the user is connected to a conversation starting at the session reentry point, thereby eliminating the need to repeat the entirety of previously provided information.

Abstract: Cognitive software and/or machine learning software are monitored in a cognitive computing environment. Open interface management of virtual agent nodes is performed in the cognitive computing environment.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining chat session data of a chat session having a first participant provided by a patron user and a second participant provided by an enterprise user; detecting, subsequent to a connectivity failure, that a network connection supporting the chat session has been restored; presenting in response to the detecting a prompt to the first participant, the prompt being in dependence on the chat session data; deciding an authentication action in dependence on a received response of the first participant in response to the presented prompt; and performing the authentication action in accordance with the deciding.

Abstract: Disclosed embodiments provide techniques for restoring an interrupted automated assistance session. Session contexts including pertinent metadata are periodically saved for each session, including a session reentry point. When a user calls an automated response system, metadata is collected from the user and compared with metadata from saved session contexts. If the user is determined to be associated with a saved session context, the user is connected to a conversation starting at the session reentry point, thereby eliminating the need to repeat the entirety of previously provided information.