# US 12,190,884 B2 · Collaborative artificial intelligence method and system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,190,884 B2 - Document ID: US12190884B2 - Status: Granted - Kind: B2 - Application number: 18/330,775 - Filed: 2023-06-07 - Published: 2023-10-26 - Granted: 2025-01-07 - Earliest claimed: 2019-04-17 - Assignees: Tempus AI, Inc. - Applicants: Tempus AI, Inc. - Inventors: Eric Lefkofsky; Jonathan Ozeran - Web page: https://patentgrep.com/patent/US12190884B2 ## CPC - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G06F 3/0481: based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G06F 16/332: Query formulation - G06F 16/634: {Query by example, e.g. query by humming} - G06N 5/041: {Abduction} - G16H 10/20: for electronic clinical trials or questionnaires - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms - G16H 40/67: for remote operation - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 50/50: for simulation or modelling of medical disorders - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G16H 70/20: relating to practices or guidelines - G16H 70/40: relating to drugs, e.g. their side effects or intended usage - G16H 70/60: relating to pathologies - H04B 1/3827: Portable transceivers - G06N 5/022: Knowledge engineering; Knowledge acquisition - G10L 2015/223: {Execution procedure of a spoken command} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - H04B: TRANSMISSION ## 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. ## Claims ### Claim 1 A method of providing responses to a user based on user queries about a specific subject's molecular report, the method comprising: (i) receiving a query from the user to an input device associated with a collaboration device; (ii) identifying at least one intent associated with the query, including: determining that the query is associated with a specific subject; identifying the specific subject's disease state from a database including information about the specific subject; identifying a state-specific clinical record for the subject corresponding to the specific subject's disease state, the state-specific clinical record having a state-specific clinical record type; determining a pool of disease state related intents associated with the state-specific clinical record type; and selecting an intent from the pool of disease state related intents; (iii) identifying at least one data operation associated with the at least one intent; (iv) associating each of the at least one data operations with a first set of data presented on the molecular report; (v) executing each of the at least one data operations on a second set of data to generate response data; (vi) generating a response associated with the response data; and (vii) providing the response for broadcasting via an output device associated with the collaboration device. ### Claim 2 (depends on 1) The method of claim 1, further comprising: identifying at least one parameter value in the query, wherein at least one of the parameter values includes a subject identity, a subject's disease state, a genetic mutation, or a procedure type. ### Claim 3 (depends on 1) The method of claim 1, further including the step of storing a general knowledge database in a system database that includes non-subject specific data about specific topics, wherein a first data operation of the at least one data operations is associated with a specific subject's molecular report information and a second data operation is associated with the general knowledge database. ### Claim 4 (depends on 3) The method of claim 3, wherein the second data operation associated with the general knowledge database is executed first to generate second data operation results, the second data operation results are used to define the first data operation and the first data operation associated with the specific subject's molecular report information is executed second to generate the response data. ### Claim 5 (depends on 3) The method of claim 3, wherein the first data operation associated with the specific subject's molecular report information is executed first to generate first data operation results, the first data operation results are used to define the second data operation and the second data operation associated with the general knowledge database is executed second to generate the response data. ### Claim 6 (depends on 1) The method of claim 1, wherein the specific subject's disease state is a cancer state, wherein the database including information about the specific subject includes the specific subject's molecular report information, and wherein the pool of disease state related intents is a pool of cancer state related intents. ### Claim 7 (depends on 6) The method of claim 6, further including the step of storing a general knowledge database in a system database that includes non-subject specific data about specific topics, the method further including the steps of, upon determining that the query is not associated with any specific patient, selecting an intent that is associated with the general knowledge database. ### Claim 8 (depends on 1) The method of claim 1, wherein the collaboration device includes at least one visual indicator, the processor linked to the visual indicator and controllable to change at least some aspect of the appearance of the visual indicator to indicate different states of the collaboration device. ### Claim 9 (depends on 1) The method of claim 1, wherein the collaboration device includes a processor, the input device includes a microphone, and the query is an audible query, and wherein the processor is programmed to monitor microphone input to identify a “wake up” phrase, the processor monitoring for the audible query after the wake up phrase is detected. ### Claim 10 (depends on 1) The method of claim 1, wherein a series of queries are received, the at least one of the identified data operations including identifying a subset of data that is usable with subsequent queries to identify intents associated with the subsequent queries. ### Claim 11 (depends on 1) The method of claim 1, further including the steps of, based on at least one received query and related data in a system database, identifying at least one activity that a collaboration device user may want to perform and initiating the at least one activity. ### Claim 12 (depends on 11) The method of claim 11, wherein the step of initiating the at least one activity includes generating a second response and providing the second response to the user seeking verification that the at least one activity should be performed and monitoring for an affirmative response and, upon receiving an affirmative response, initiating the at least one activity. ### Claim 13 (depends on 11) The method of claim 11, wherein the at least one activity includes periodically capturing health information from electronic health records included in the system database. ### Claim 14 (depends on 11) The method of claim 11, wherein the at least one activity includes checking status of an existing clinical or lab order, or ordering a new clinical or lab order. ### Claim 15 (depends on 11) The method of claim 11, wherein the step of initiating the at least one activity includes automatically initiating the at least one activity without any initiating input from the user. ### Claim 16 (depends on 1) The method of claim 1, further including storing and maintaining a general cancer knowledge database, updating the specific subject's molecular report, automatically identifying at least one intent and associated data operation related to the general cancer knowledge database based on the specific subject's molecular report, executing the associated data operation on the general cancer knowledge database to generate a new set of response data not previously generated, and upon generating the new set of response data, using the new set of response data to generate another response and providing the another response. ### Claim 17 (depends on 1) The method of claim 1, further comprising: identifying an additional data operation associated with the at least one intent and executing the additional data operation on a specific subject's health record maintained in an electronic health records system to generate additional response data. ### Claim 18 (depends on 17) The method of claim 17, wherein the step of using the response data to generate a response includes using the response data and the additional response data to generate the response. ### Claim 19 A system for providing responses to a user based on user queries about a specific subject's molecular report, the system comprising: a computer including a processing device, the processing device configured to: (i) receive a query from the user to an input device associated with a collaboration device; (ii) identify at least one intent associated with the query, including: determining that the query is associated with a specific subject; identifying the specific subject's disease state from a database including information about the specific subject; identifying a state-specific clinical record for the subject corresponding to the specific subject's disease state, the state-specific clinical record having a state-specific clinical record type; determining a pool of disease state related intents associated with the state-specific clinical record type; and selecting an intent from the pool of disease state related intents; (iii) identify at least one data operation associated with the at least one intent; (iv) associate each of the at least one data operations with a first set of data presented on the molecular report; (v) execute each of the at least one data operations on a second set of to generate response data; (vi) generate a response associated with the response data; and (vii) provide the response for broadcasting via an output device associated with the collaboration device. ### Claim 20 A non-transitory computer readable medium for providing responses to a user based on user queries about a specific subject's molecular report, comprising instructions for causing a computer to: (i) receive a query from the user to an input device associated with a collaboration device; (ii) identify at least one intent associated with the query, including: determining that the query is associated with a specific subject; identifying the specific subject's disease state from a database including information about the specific subject; identifying a state-specific clinical record for the subject corresponding to the specific subject's disease state, the state-specific clinical record having a state-specific clinical record type; determining a pool of disease state related intents associated with the state-specific clinical record type; and selecting an intent from the pool of disease state related intents; (iii) identify at least one data operation associated with the at least one intent; (iv) associate each of the at least one data operations with a first set of data presented on the molecular report; (v) execute each of the at least one data operations on a second set of data to generate response data; (vi) generate a response associated with the response data; and (vii) provide the response for broadcasting via an output device associated with the collaboration device.