20240020484. Chatbot Disambiguation simplified abstract (ADP, INC.)

Chatbot Disambiguation

Organization Name

ADP, INC.

Inventor(s)

Henry C. Will, Iv of Dover NJ (US)

Stefan George Wilk of Martinsburg WV (US)

Chatbot Disambiguation - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240020484 titled 'Chatbot Disambiguation

Simplified Explanation

The abstract describes a method for disambiguating user utterances. It involves determining the user's intent by comparing confidence scores of possible user intents. If the confidence score is below a certain threshold, the user intent is considered ambiguous. The method also includes extracting human interpretable labels corresponding to the user intents and sending them to the user's device.

• The method disambiguates user utterances by comparing confidence scores of possible user intents.
• If a user intent has a confidence score below a certain threshold, it is considered ambiguous.
• Human interpretable labels corresponding to the user intents are extracted.
• The extracted labels are assembled into a set of user intent options.
• The set of user intent options is sent to the user's device.

Potential applications of this technology:

• Voice assistants: This method can be used in voice assistants to accurately understand user commands and provide appropriate responses.
• Chatbots: Chatbots can utilize this method to better understand user messages and provide relevant information or assistance.
• Customer service: This technology can be applied in customer service systems to improve the accuracy of understanding customer queries and provide appropriate solutions.

Problems solved by this technology:

• Ambiguity in user utterances: This method helps in resolving ambiguity in user utterances by determining the most likely user intent.
• Misinterpretation of user commands: By disambiguating user utterances, this technology reduces the chances of misinterpreting user commands and provides more accurate responses.

Benefits of this technology:

• Improved user experience: By accurately understanding user intents, this technology enhances the user experience by providing relevant and precise responses.
• Increased efficiency: Disambiguating user utterances reduces the need for clarification or repetition, leading to more efficient interactions between users and systems.
• Enhanced accuracy: By considering confidence scores and extracting human interpretable labels, this method improves the accuracy of understanding user intents.

Original Abstract Submitted

disambiguating user utterances is provided. disambiguation of an utterance of a user is performed using up to a defined number of user intents in a set of possible user intents having highest confidence scores between a first confidence score threshold level and a second confidence score threshold level in response to determining that each user intent in the set of possible user intents does have a corresponding confidence score less than the second confidence score threshold level. each of the up to the defined number of user intents is located in a user intent mapping table. a human interpretable label corresponding to each of the up to the defined number of user intents located in the user intent mapping table is extracted. extracted human interpretable labels are assembled into a set of user intent options. the set of user intent options is sent to a client device of the user.