Back to results
US 12,754,937 B2Granted
Automated user interface feedback based generative AI systems
AssigneeQUALCOMM Incorporated
InventorsVikram Gupta, Wesley James Holland, Ziad Asghar, Vinesh Sukumar, Roland Memisevic
Life of this patent
Estimating the term…
Abstract
Various embodiments include systems and methods for improving the user experience with LXMs. A computing device may be configured to receive a user prompt, observe user responses to an output received from a LXM in response to a prompt that is at least partially based on the user's prompt, and take an action to improve the user's experience with the LXM based on the observed user response.
Claims30
A computing device, comprising:
- a processing system configured to:
- receive a user prompt;
- select a large generative artificial intelligence model (LXM) from a plurality of LXMs based on user context information associated with a user providing the user prompt;
- generate a prompt based on the user prompt;
- observe user responses of a user to an output received from the LXM in response to the prompt;
- categorize the user responses based on detected visual cues of the user, wherein the visual cues include at least one of facial expressions of the user or gaze direction of the user;
- identify, based on the categorization, one or more portions of the output that elicited the categorized user responses;
- inquire the LXM about prompt parameters or content characteristics of the prompt that caused the identified one or more portions of the output to elicit the categorized user responses;
- and
- update a selected user profile based on information on prompt parameters received from the LXM to include or increase prompt parameters that elicited the user responses.
7 more elements
A method performed by a computing device comprising:
- receiving a user prompt;
- selecting a large generative artificial intelligence model (LXM) from a plurality of LXMs based on user context information associated with a user providing the user prompt;
- generating a prompt based on the user prompt;
- observing user responses of a user to an output received from the LXM in response to the prompt;
- categorizing the user responses based on detected visual cues of the user, wherein the visual cues include at least one of facial expressions of the user or gaze direction of the user;
- identifying, based on the categorization, one or more portions of the output that elicited the categorized user responses;
- inquiring the LXM about prompt parameters or content characteristics of the prompt that caused the identified one or more portions of the output to elicit the categorized user responses;
- and
- updating a selected user profile based on information on prompt parameters received from the LXM to include or increase prompt parameters that elicited the user responses.
6 more elements
A computing device, comprising:
- means for receiving a user prompt;
- means for selecting a large generative artificial intelligence model (LXM) from a plurality of LXMs based on user context information associated with a user providing the user prompt;
- means for generating a prompt based on the user prompt;
- means for observing user responses of a user to an output received from in response to the prompt;
- means for categorizing the user responses based on detected visual cues of the user, wherein the visual cues include at least one of facial expressions of the user or gaze direction of the user;
- means for identifying, based on the categorization, one or more portions of the output that elicited the categorized user responses;
- means for inquiring the LXM about prompt parameters or content characteristics that caused the identified one or more portions of the output to elicit the categorized user responses;
- and
- means for updating a selected user profile based on information on prompt parameters received from the LXM to include or increase prompt parameters that elicited the user responses.
6 more elements
A non-transitory processor readable media having stored thereon processor-executable instructions configured to cause a processing system of a computing device to perform operations comprising:
- receiving a user prompt;
- selecting a large generative artificial intelligence model (LXM) from a plurality of LXMs based on user context information associated with a user providing the user prompt;
- generating a prompt based on the user prompt;
- observing user responses of a user to an output received from the LXM in response to the prompt;
- categorizing the user responses based on detected visual cues of the user, wherein the visual cues include at least one of facial expressions of the user or gaze direction of the user;
- identifying, based on the categorization, one or more portions of the output that elicited the categorized user responses;
- inquiring the LXM about prompt parameters or content characteristics of the prompt that caused the identified one or more portions of the output to elicit the categorized user responses;
- and
- updating a selected user profile based on information on prompt parameters received from the LXM to include or increase prompt parameters that elicited the user responses.
6 more elements
Dependencies are inferred from the claim text.