Abstract: A processor-implemented method for monitoring and improving conversational alignment to develop an alliance between an artificial intelligence (AI) chatbot and a user is provided. The method includes extracting sentiment or contextual features such as emotions, domains and medicalized terms from a response from the user and generating empathetic open-ended or closed-ended prompts based on them. Various AI models are used to determine if a conversation between the user and the AI chatbot has conversational alignment and a conversational alignment score is maintained which is updated after every message exchange. Recovery prompts are generated whenever a misalignment is detected in an attempt to bring the user back to the conversation. Appropriate prompts make the user feel heard and understood and enhance their trust in the AI chatbot. Once the conversational alignment score exceeds a threshold, alliance is assumed to be established and the user is offered an intervention.

Abstract: A processor-implemented method for automatically determining a mismatch between a sentiment and a polarity of a life situation using an Artificial Intelligence (AI) model during a conversation with an AI chatbot is provided. The method includes (i) determining at least one sentiment of the user using a sentiment detecting AI model, (ii) predicting life situation from the conversation between the AI chatbot and the user using an intent recognition AI model, (ii) determining, a gravity and a polarity of the life situation using a life events scale, (iii) comparing the at least one sentiment of the user to the polarity of the life situation when the life situation is determined to the high gravity, and (iv) automatically determining the mismatch between the at least one sentiment of the user and the polarity of the at least one life situation of the high gravity situation.

Abstract: A processor-implemented method for automatically determining a mismatch between a sentiment and a polarity of a life situation using an Artificial Intelligence (AI) model during a conversation with an AI chatbot is provided. The method includes (i) determining at least one sentiment of the user using a sentiment detecting AI model, (ii) predicting life situation from the conversation between the AI chatbot and the user using an intent recognition AI model, (ii) determining, a gravity and a polarity of the life situation using a life events scale, (iii) comparing the at least one sentiment of the user to the polarity of the life situation when the life situation is determined to the high gravity, and (iv) automatically determining the mismatch between the at least one sentiment of the user and the polarity of the at least one life situation of the high gravity situation.

Abstract: One embodiment provides a method for ensuring device security via swipe pattern recognition, the method comprising: utilizing at least one processor to execute computer code that performs the steps of: receiving, using a touch device, at least one swipe input of a user; determining, using the at least one processor, if the at least one swipe input matches a known swipe pattern of the user, the match requiring exceeding a match confidence level; and responsive to said determining, executing an action associated with the touch device. Other aspects are described and claimed.

Abstract: One embodiment provides a method for ensuring device security via swipe pattern recognition, the method comprising: utilizing at least one processor to execute computer code that performs the steps of: receiving, using a touch device, at least one swipe input of a user; determining, using the at least one processor, if the at least one swipe input matches a known swipe pattern of the user, the match requiring exceeding a match confidence level; and responsive to said determining, executing an action associated with the touch device. Other aspects are described and claimed.