Abstract: A text-based real-time communication interface, such as a chatbot, is presented to a user for the exchange of customer support information. A user's freeform text input is analyzed using machine learning algorithms to derive the meaning of the input text as well as to determine the user sentiment expressed therein. These determinations may be further supported by signals extracted from session-based activity, which signals can be used to infer the intended workflow of the user and whether or not that workflow was achieved. The expressed user sentiment is considered along with other historical or session-based user data to generate tailored questions and responses to be delivered in real-time to the user. The responses are displayed to the user along with information that routes the user to a workflow resolution.

Abstract: A preliminary software feature is applied in a testing rollout to a discrete subset of customers. Survey data may be collected from those customers through a variety of sources, such as chatbot text, session workflow, historical user data, social media data, email survey data, user profile data, messaging threads, and the like. This survey data is analyzed using machine learning algorithms to derive the meaning of input text as well as to determine the user sentiment expressed therein. The outputs of this analysis are normalized across sources and aggregated at a feature-level to generate overall metrics of customer satisfaction with the feature. A holistic analysis is performed on this customer sentiment data to obtain an aggregate or combined user satisfaction score. This score is applied against a set of guardrails to determine whether to ship the feature to a broader customer base.

Abstract: A text-based real-time communication interface, such as a chatbot, is presented to a user for the exchange of customer support information. A user's freeform text input is analyzed using machine learning algorithms to derive the meaning of the input text as well as to determine the user sentiment expressed therein. These determinations may be further supported by signals extracted from session-based activity, which signals can be used to infer the intended workflow of the user and whether or not that workflow was achieved. The expressed user sentiment is considered along with other historical or session-based user data to generate tailored questions and responses to be delivered in real-time to the user. The responses are displayed to the user along with information that routes the user to a workflow resolution.