Google patents assistant that shortens answers for regular users
This patent describes a method for automated assistants to adjust their responses based on how familiar a user is with specific topics. By analyzing past interactions, the system uses a machine learning model to determine if a user is a novice or an expert on a subject. If the user is familiar with the topic, the assistant provides shorter, more efficient answers; if not, it gives more detailed explanations.
In the filing’s own words
Techniques are disclosed that enable dynamically adapting an automated assistant response using a dynamic familiarity measure. Various implementations process received user input to determine at least one intent, and generate a familiarity measure by processing intent specific parameters and intent agnostic parameters using a machine learning model. An automated assistant response is then determined that is based on the intent and that is based on the familiarity measure. The assistant response is responsive to the user input, and is adapted to the familiarity measure. For example, the assistant response can be more abbreviated and/or more resource efficient as the familiarity measure becomes more indicative of familiarity.
What exactly they claim (claim 1)
1. A method implemented by one or more processors, the method comprising: selecting a familiarity training instance, from a set of familiarity training instances, wherein the familiarity training instance includes an input parameters portion and a ground truth familiarity measure for the input parameters portion, wherein the input parameters portion includes one or more measures of user interactions with an automated assistant, including one or more intent specific measures that are based on historical interactions, of a user with the automated assistant, for one or more intents; processing the input parameters portion of the selected familiarity training instance using a machine learning model to generate a predicted familiarity measure for the input parameters portion, wherein the predicted familiarity measure is indicative of familiarity of the user with the one or more intents; comparing the predicted familiarity measure with the ground truth familiarity measure to generate familiarity output; and updating one or more portions of the machine learning model based on the familiarity output.
Facts
- Company
- Google (GOOGLE LLC)
- Official title
- Dynamically adapting assistant responses
- Patent number
- US12749484B2
- Application number
- 18412004
- Filed
- Jan 12, 2024
- Granted
- Sep 29, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G10L 15/22 Physics & computingG10L 13/02 Physics & computingG10L 15/1815 Physics & computingG10L 15/30 Physics & computingG10L 2015/223 Physics & computingG10L 2015/228 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.