Collaborative artificial intelligence method and system
Inventors
Lefkofsky, Eric • Ozeran, Jonathan
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12062372-B2
Publication Date
2024-08-13
Expiration Date
Abstract
A method and system of audibly broadcasting responses to a user based on user queries about a specific patient report, the method comprising receiving an audible query from the user to a microphone coupled to a collaboration device, identifying at least one intent associated with the audible query, identifying at least one data operation associated with the at least one intent, associating each of the at least one data operations with a first set of data presented on the report, executing each of the at least one data operations on a second set of data to generate response data, generating an audible response file associated with the response data and providing the audible response file for broadcasting via a speaker coupled to the collaboration device.
Core Innovation
The invention provides responses to user queries using a collaboration device, where a query is answerable in part by reference to a specific subject's treatment. A machine learning module identifies at least one weightable intent associated with the query by recognizing the query as sufficiently corresponding to an intent phrase provided to or generated by the machine learning module, and disease state-related intents are weighted more heavily than other possible intents.
The invention extracts at least one qualifying entity and identifies at least one parameter value associated with the qualifying entity in the query. It also identifies at least one data operation associated with the at least one weightable intent and executes at least one data operation on a set of data for a plurality of subjects to generate response data.
The response associated with the response data is generated and provided for broadcasting via an output device associated with the collaboration device. The described data architecture includes a molecular report dataset linked with a non-patient-specific knowledge database (KDB) organized into sub-databases, with cross-operation dependencies between report-derived results and KDB queries.
Claims Coverage
The independent claim set comprises three independent claim types: a method, a system, and a non-transitory computer-readable medium. The claims share three inventive features.
Disease state intent weighting in intent recognition
Identifying at least one weightable intent associated with the query, including recognizing the query as sufficiently corresponding to an intent phrase provided to or generated by the machine learning module and weighting disease state-related intents more heavily than other possible intents.
Qualifying entity parameter extraction
Identifying at least one parameter value associated with the qualifying entity in the query corresponding to the at least one qualifying entity.
Qualifying entity to data operation mapping and execution over plurality of subjects
Identifying at least one data operation associated with the at least one weightable intent, executing at least one of the data operations on a set of data for a plurality of subjects to generate response data, generating a response associated with the response data, and providing the response for broadcasting via an output device associated with the collaboration device.
Across the independent claims, the coverage centers on a collaboration-based flow that uses a machine learning module to identify and weight disease state-related intents, extract parameter values for qualifying entities, select and execute associated data operations over data for multiple subjects to generate response data, and then generate and broadcast the response via the collaboration-associated output device.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?