# US 12,118,985 B2 · Electronic device and method for providing on-device artificial intelligence service > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,985 B2 - Document ID: US12118985B2 - Status: Granted - Kind: B2 - Application number: 17/833,179 - Filed: 2022-06-06 - Published: 2022-09-22 - Granted: 2024-10-15 - Earliest claimed: 2021-02-19 - Assignees: Samsung Electronics Co., Ltd. - Applicants: Samsung Electronics Co., Ltd. - Inventors: Sangmin Park; Gajin Song - Web page: https://patentgrep.com/patent/US12118985B2 ## CPC - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G10L 15/083: {Recognition networks (G10L15/142, G10L15/16 take precedence)} - G06F 3/041: Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means - G06F 16/907: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually - G06F 16/955: using information identifiers, e.g. uniform resource locators [URL] - G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) - G06N 3/08: Learning methods - G06N 20/00: Machine learning - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G10L 2015/223: {Execution procedure of a spoken command} - 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 - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract An electronic device and method for providing an on-device AI service are provided herein. The electronic device includes an input module configured to receive a command or data; a display module; a memory storing a first application; and a processor configured to receive, from the input module or the display module, a user request, while the first application is executed, determine content data associated with the user request, generate request information corresponding to the user request based on the content data, determine a second application to process the user request, and transmit the request information to the second application. ## Claims ### Claim 1 An electronic device, comprising: an input module configured to receive a command or data; a display module; a memory storing a first application; and a processor configured to: receive, from the input module or the display module, a user request, while the first application is executed, determine content data associated with the user request, generate request information corresponding to the user request based on the content data, determine a second application to process the user request, and transmit the request information to the second application, wherein the request information includes intent information about an action to be performed in the second application. ### Claim 2 (depends on 1) The electronic device of claim 1, wherein the processor is further configured to: when the user request is received through a microphone of the input module, extract text corresponding to the user request through speech recognition for the received user request, and determine the content data based on the extracted text. ### Claim 3 (depends on 1) The electronic device of claim 1, wherein the processor is further configured to: when the user request is received through a touch panel of the display module, determine text corresponding to the user request, and determine the content data based on the text. ### Claim 4 (depends on 1) The electronic device of claim 1, wherein at least one of the first application and the second application operates offline. ### Claim 5 (depends on 1) The electronic device of claim 1, wherein the processor is further configured to: extract text corresponding to the user request, and determine the content data based on text related to the content data in the extracted text. ### Claim 6 (depends on 5) The electronic device of claim 5, wherein the request information includes content information about the content data, and wherein the content information includes at least one of detail information of the content data, identification information of the content data, property information of the content data, or common information of multiple content data. ### Claim 7 (depends on 6) The electronic device of claim 6, wherein the processor is further configured to, in the first application, determine the content information based on a preset option according to the user request. ### Claim 8 (depends on 6) The electronic device of claim 6, wherein the processor is further configured to process the content information, using an artificial intelligence model trained to generate a sentence based on an input keyword. ### Claim 9 (depends on 1) The electronic device of claim 1, wherein the processor is further configured to determine the intent information from text corresponding to a user utterance, using an artificial intelligence model. ### Claim 10 (depends on 1) The electronic device of claim 1, wherein the memory stores the text corresponding to the user request and the content data and the request information for the user request mapped to the text corresponding to the user request, and wherein the processor is further configured to: determine the content data by comparing a new user request with a pre-stored user request, and generate the request information. ### Claim 11 An electronic device, comprising: an input module configured to receive a command or data; a display module; a memory storing a first application; and a processor configured to: receive, from the input module or the display module, a user request, while the first application is executed, analyze the user request using an artificial intelligence (AI) model trained to perform natural language processing, determine a second application to process the user request based analyzing the user request, and process the user request through the second application, wherein the processor is further configured to determine the second application based on intent information generated using an AI model trained to determine intent information from text corresponding to the user request, and wherein the intent information includes information about an action to be performed in the second application. ### Claim 12 (depends on 11) The electronic device of claim 11, wherein the processor is further configured to: when the user request is received through a microphone of the input module, extract the text corresponding to the user request through speech recognition for the received user request, and analyze the user request based on the extracted text. ### Claim 13 (depends on 11) The electronic device of claim 11, wherein the processor is further configured to: when the user request is received through a touch panel of the display module, determine the text corresponding to the user request, and analyze the user request based on the determined text. ### Claim 14 A method of providing an on-device artificial intelligence service, the method comprising: receiving a user request while a first application is executed; determining content data associated with the user request; generating request information corresponding to the user request based on the content data; determining a second application to process the user request; and transmitting the content data and the request information to the second application, wherein the request information includes intent information about an action to be performed in the second application.