# US 12,216,963 B1 · Computer system-based pausing and resuming of natural language conversations > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,216,963 B1 - Document ID: US12216963B1 - Status: Granted - Kind: B1 - Application number: 18/583,663 - Filed: 2024-02-21 - Granted: 2025-02-04 - Earliest claimed: 2021-12-10 - Assignees: Amazon Technologies, Inc. - Applicants: Amazon Technologies, Inc. - Inventors: Shiveesh Fotedar; Saurabh Rathi; Steven Bishop - Web page: https://patentgrep.com/patent/US12216963B1 ## CPC - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - 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 - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract Techniques for computer system-based conversations are described. In an example, a system receives, from a first device, first data corresponding to a first interaction in a conversation that requests a function. The system causes the first device to output a first response to the first interaction. Prior to an execution of the function, the system determines that the conversation is to be paused and causes the first device to output a first indication that the conversation is paused. Upon determining that the conversation is to be resumed, the system causes a second device to output a second indication that the conversation is resumed. The second device can be the same or different from the first device. The system receives, from the second device, second data corresponding to a second interaction in the conversation and causes the execution of the function based at least in part on the second data. ## Claims ### Claim 1 A system comprising: one or more processors; and one or more memories storing instructions that, upon execution by the one or more processors, configure the system to: receive, from a first device associated with a user profile, first data corresponding to a first natural language input to an artificial intelligence (AI) model; cause a first presentation of second data, the second data associated with the first natural language input and corresponding to a first output of the AI model; store contextual data associated with the user profile and the first output; receive, from the first device or a second device associated with the user profile, third data corresponding to a second natural language input to the AI model; determine a second output of the AI model based at least in part on the contextual data and the third data; and cause a second presentation of fourth data, the fourth data corresponding to the second output. ### Claim 2 (depends on 1) The system of claim 1, wherein the contextual data includes a parameter associated with the first output, and wherein the second output is generated based at least in part on the parameter. ### Claim 3 (depends on 1) The system of claim 1, wherein the first presentation indicates a parameter associated with the first output, wherein the contextual data includes the parameter, and wherein the second output is generated based at least in part on the parameter. ### Claim 4 (depends on 1) The system of claim 1, wherein the first presentation indicates a parameter associated with the first output, wherein the contextual data includes the parameter, and wherein the second presentation indicates the parameter. ### Claim 5 (depends on 1) The system of claim 1, wherein the contextual data indicates an intent associated with the first natural language input, and wherein the second output is generated based at least in part on the intent. ### Claim 6 (depends on 1) The system of claim 1, wherein the contextual data indicates a topic associated with the first output, and wherein the second output is generated based at least in part on the topic. ### Claim 7 (depends on 1) The system of claim 1, wherein the contextual data indicates a function requested by the first natural language input, and wherein the second output is generated based at least in part on the function. ### Claim 8 (depends on 4) The system of claim 4, wherein the contextual data indicates a state of an application configured to execute a function requested by the first natural language input, and wherein the second output is generated based at least in part on the state. ### Claim 9 (depends on 1) The system of claim 1, wherein the fourth data includes at least a portion of the contextual data. ### Claim 10 (depends on 1) The system of claim 1, wherein the contextual data indicates a context of the first natural language input, and wherein the second presentation indicates the context. ### Claim 11 (depends on 1) The system of claim 1, the contextual data includes at least a portion of the first output, and wherein the fourth data includes the portion. ### Claim 12 (depends on 1) The system of claim 1, the contextual data includes at least a portion of the second data, and wherein the fourth data includes the portion. ### Claim 13 A computer-implemented method comprising: receiving, from a first device associated with a user profile, first data corresponding to a first natural language input to an artificial intelligence (AI) model; causing a first presentation of second data, the second data associated with the first natural language input and corresponding to a first output of the AI model; storing contextual data associated with the user profile and the first output; receiving, from the first device or a second device associated with the user profile, third data corresponding to a second natural language input to the AI model; determining a second output of the AI model based at least in part on the contextual data and the third data; and causing a second presentation of fourth data, the fourth data corresponding to the second output. ### Claim 14 (depends on 13) The computer-implemented method of claim 13, further comprising: determining a first association between the first data and the user profile; generating a second association between the contextual data and the user profile based at least in part on the first association; and determining a third association between the third data and the user profile, wherein the second output is determined based at least in part on the second association and the third association. ### Claim 15 (depends on 13) The computer-implemented method of claim 13, further comprising: associating the contextual data and the user profile; receiving, from the first device or the second device, fifth data corresponding to a third natural language input to the AI model; determining that the fifth data is associated with a different user profile; and determining, based at least in part on the fifth data being association with the different user profile, a third output of the AI model independently of the contextual data. ### Claim 16 (depends on 13) The computer-implemented method of claim 13, further comprising: associating the second data with an identifier associated with the first output; associating the contextual data with the identifier; and determining that the third data is associated with the identifier, wherein the second output is determined based at least in part on the third data and the contextual data being associated with the identifier. ### Claim 17 One or more non-transitory computer-readable storage media storing instructions that, upon execution on a system, cause the system to perform operations comprising: receiving, from a first device associated with a user profile, first data corresponding to a first natural language input to an artificial intelligence (AI) model; causing a first presentation of second data, the second data associated with the first natural language input and corresponding to a first output of the AI model; storing contextual data associated with the user profile and the first output; receiving, from the first device or a second device associated with the user profile, third data corresponding to a second natural language input to the AI model; determining a second output of the AI model based at least in part on the contextual data and the third data; and causing a second presentation of fourth data, the fourth data corresponding to the second output. ### Claim 18 (depends on 17) The one or more non-transitory computer-readable storage media of claim 17 storing additional instructions that, upon execution on the system, cause the system to perform additional operations comprising: determining a first association between the first natural language input and the user profile; determining a second association between the user profile a different user profile; and generating a third association between the contextual data and the different user profile. ### Claim 19 (depends on 18) The one or more non-transitory computer-readable storage media of claim 18 storing further instructions that, upon execution on the system, cause the system to perform further operations comprising: determining a fourth association between the second natural language input and the different user profile, wherein the second output is determined based at least in part on the third association and the fourth association. ### Claim 20 (depends on 17) The one or more non-transitory computer-readable storage media of claim 17 storing additional instructions that, upon execution on the system, cause the system to perform additional operations comprising: determining that the first natural language input is associated with an application; and determining a state of the application based at least in part on the contextual data, wherein the second output is determined based at least in part on the state.