Computing devices with improved interactive animated conversational interface systems
Inventors
Dohrmann, Anthony • Chasko, Bryan J. • Blake, Samuel
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12265900-B2
Publication Date
2025-04-01
Expiration Date
Abstract
A conversational interface system including an interactive virtual avatar and method for completing and updating fillable forms and database entries. The conversational interface provides a user with the option of inputting data in either text or voice form, and logs user response data and populates fields within form documents. As the user progresses through the system, instructions and guidance are consistently provided via the interactive avatar presented within the system web browser. Without exiting the system, the conversational interface validates user input data types and data while updating entries within cloud-based databases.
Core Innovation
The invention relates to a computing device that dynamically displays, within a web browser, a specific, structured interactive animated conversational graphical interface paired with prescribed functionality directly related to the interface structure. The structured interface requests response data from a human user, receives the response data, and guides the human user through a conversational interaction through a three-dimensional electronic image of a human health caregiver displayed within the web browser.
The computing device encrypts the response data prior to transmission to cloud-based storage and transmits the response data to cloud-based storage for validation, retention, and processing performed by a cloud-based application communicatively coupled to the cloud-based storage. The response data is converted into an audio file using a cloud-based text-to-speech application capable of being integrated into a web browser-based avatar, and output data read in Speech Synthesis Markup Language is used to produce the responsive audio file.
The Speech Synthesis Markup Language is further used to control at least one aspect of the responsive audio file as delivered by the web browser-based avatar. The three-dimensional electronic image of the human health caregiver provides step-by-step verbal health care instructions to the human user and provides a survey comprising questions directed to eliciting information regarding assessing falls risk, and receives answers indicative of a risk of falling of the human user.
Claims Coverage
The independent claim (clm-00001) covers a computing device that combines a web-browser conversational graphical interface with cloud-based encryption, validation, retention, and processing, and Speech Synthesis Markup Language-controlled audio output from a three-dimensional electronic health caregiver avatar. The independent claim includes four core inventive features: structured web-browser conversational interface behavior, cloud-based encryption and processing, SSML-controlled responsive audio generation, and a caregiver avatar that delivers step-by-step health care instructions and a falls-risk survey workflow.
Structured interactive animated conversational graphical interface in a web browser
A display screen configured to dynamically display within a web browser a specific, structured interactive animated conversational graphical interface that requests response data from a human user, receives the response data, and provides a three-dimensional electronic image of a human health caregiver for the human user.
Cloud encryption, transmission, and cloud validation, retention, and processing
Encrypt the response data prior to transmission to a cloud-based storage; transmit the response data to a cloud-based storage for validation, retention, and processing performed by a cloud-based application communicatively coupled to the cloud-based storage.
Cloud text-to-speech audio file generation with SSML-controlled responsive audio
Convert the response data into an audio file using a cloud-based text-to-speech application integrated into a web browser-based avatar; produce a responsive audio file by applying a conversational decision tree to the response data, reading output data from the cloud-based application in Speech Synthesis Markup Language to produce the responsive audio file, and using the Speech Synthesis Markup Language to control at least one aspect of the responsive audio file as delivered by the web browser-based avatar.
Falls risk survey and caregiver-provided step-by-step verbal health care instructions
The three-dimensional electronic image of the human health caregiver provides step-by-step verbal health care instructions to the human user; provides a survey comprising questions directed to eliciting information regarding assessing falls risk; and receives elicited information comprising answers indicative of a risk of falling of the human user.
Overall, claim coverage centers on a web-browser conversational interface that collects response data from a human user, encrypts and transmits the response data to cloud storage for validation, retention, and processing, and generates SSML-controlled responsive audio via cloud text-to-speech and a conversational decision tree. The three-dimensional electronic caregiver avatar provides step-by-step verbal health care instructions and administers a falls-risk survey whose answers are indicative of a risk of falling.
Stated Advantages
Provides step-by-step verbal health care instructions to the human user.
Elicits information through a survey directed to assessing falls risk.
Produces responsive audio controlled using Speech Synthesis Markup Language as delivered by the web browser-based avatar.
Validates, retains, and processes response data using a cloud-based application communicatively coupled to cloud-based storage.
Encrypts response data prior to transmission to cloud-based storage.
Documented Applications
A survey interaction directed to eliciting information for assessing falls risk, where answers are indicative of a risk of falling of the human user.
Interested in licensing this patent?