# US 2025/0095645 A1 · Method and apparatus for inferring user intention in vehicle voice recognition system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0095645 A1 - Document ID: US20250095645A1 - Status: Published application - Kind: A1 - Application number: 18/424,070 - Filed: 2024-01-26 - Published: 2025-03-20 - Earliest claimed: 2023-09-19 - Assignees: Hyundai Motor Company; Kia Corporation - Applicants: Hyundai Motor Company; Kia Corporation - Inventors: Yoon Jung Lee - Web page: https://patentgrep.com/patent/US20250095645A1 ## CPC - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G10L 15/1822: {Parsing for meaning understanding} - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - 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) ## Abstract An embodiment computer-implemented method for predicting an intention of a user includes receiving from a vehicle first utterance data obtained by converting a voice command of the user into text, performing natural language understanding to attempt to decide the intention of the user from the first utterance data, predicting the intention of the user using stored pattern data in response to failing to decide the intention of the user, wherein the stored pattern data includes a plurality of patterns and confidence generated based on second utterance data received from each of a plurality of vehicles that are unable to decide the intention of the user and subsequent action data, generating a prompt suggesting an operation based on the predicted intention, and transmitting the prompt to the vehicle. ## Claims ### Claim 1 A computer-implemented method for predicting an intention of a user, the method comprising: receiving from a vehicle first utterance data obtained by converting a voice command of the user into text; performing natural language understanding to attempt to decide the intention of the user from the first utterance data; predicting the intention of the user using stored pattern data in response to failing to decide the intention of the user, wherein the stored pattern data comprises a plurality of patterns and confidence generated based on second utterance data received from each of a plurality of vehicles that are unable to decide the intention of the user and subsequent action data; generating a prompt suggesting an operation based on the predicted intention; and transmitting the prompt to the vehicle. ### Claim 2 (depends on 1) The method of claim 1, wherein performing the natural language understanding comprises attempting to decide the intention corresponding to the first utterance data with reference to a database including one or more mappings between utterance data and intentions. ### Claim 3 (depends on 1) The method of claim 1, wherein the action data comprises an action of the user to operate a vehicle function received within a certain period of time after the second utterance data is received. ### Claim 4 (depends on 1) The method of claim 1, wherein the action data comprises third utterance data obtained by converting, into text, a voice command of the user received within a certain period of time after the second utterance data is received, wherein the third utterance data comprises utterance data capable of being used to decide the intention of the user by performing the natural language understanding. ### Claim 5 (depends on 1) The method of claim 1, wherein predicting the intention of the user comprises: extracting a pattern that comprises the first utterance data and has a confidence equal to or greater than a first threshold from the pattern data; and predicting the intention of the user based on the action data of the extracted pattern. ### Claim 6 (depends on 1) The method of claim 1, further comprising: receiving a confirmation response of the user to the prompt from the vehicle; calculating accuracy of intention prediction of the user based on the received confirmation response; and correcting a confidence of a pattern that is a basis for predicting the intention of the user using the calculated accuracy. ### Claim 7 A system comprising one or more processors and a memory operatively coupled to the one or more processors, the memory storing commands that, in response to execution of the commands by the one or more processors, cause the one or more processors to perform operations, wherein the operations comprise: receiving from a vehicle first utterance data obtained by converting a voice command of a user into text; performing natural language understanding to attempt to decide an intention of the user from the first utterance data; predicting the intention of the user using stored pattern data in response to failing to decide the intention of the user, wherein the stored pattern data comprises a plurality of patterns and confidence generated based on second utterance data received from each of a plurality of vehicles that are unable to decide the intention of the user and subsequent action data; generating a prompt suggesting an operation based on the predicted intention; and transmitting the prompt to the vehicle. ### Claim 8 (depends on 7) The system of claim 7, wherein performing the natural language understanding comprises attempting to decide the intention corresponding to the first utterance data with reference to a database including one or more mappings between utterance data and intentions. ### Claim 9 (depends on 7) The system of claim 7, wherein the action data comprises an action of the user to operate a vehicle function received within a certain period of time after the second utterance data is received. ### Claim 10 (depends on 7) The system of claim 7, wherein the action data comprises third utterance data obtained by converting into text a voice command of the user received within a certain period of time after the second utterance data is received, wherein the third utterance data comprises utterance data capable of being used to decide the intention of the user by performing the natural language understanding. ### Claim 11 (depends on 7) The system of claim 7, wherein predicting the intention of the user comprises: extracting a pattern that comprises the first utterance data and has a confidence equal to or greater than a first threshold from the pattern data; and predicting the intention of the user based on the action data of the extracted pattern. ### Claim 12 (depends on 7) The system of claim 7, wherein the operations further comprise: receiving a confirmation response of the user to the prompt from the vehicle; calculating accuracy of intention prediction of the user based on the received confirmation response; and correcting a confidence of the pattern that is a basis for predicting the intention of the user using the calculated accuracy. ### Claim 13 A vehicle voice recognition system, the system comprising: a vehicle comprising: a voice recognition input/output device configured to receive a voice command uttered by a user in the vehicle; and a head unit comprising a vehicle usage data collection unit and a voice recognition module, wherein the voice recognition module is configured to convert the voice command into text to create first utterance data; a vehicle usage data server configured to store vehicle usage data from a plurality of vehicles including the vehicle; and a voice recognition server configured to receive the utterance data and the vehicle usage data, wherein the voice recognition server comprises: one or more processors; and a storage device storing a program to be executed by the one or more processors, the program including instructions for: performing natural language understanding to attempt to determine an intention of the user from the first utterance data; in response to failing to determine the intention of the user from the first utterance data, predicting the intention of the user using stored pattern data, wherein the stored pattern data comprises a plurality of patterns and confidence generated based on second utterance data received from each of a plurality of vehicles including the vehicle and subsequent action data; generating a prompt suggesting an operation based on the predicted intention; and transmitting the prompt to the vehicle. ### Claim 14 (depends on 13) The system of claim 13, wherein performing the natural language understanding comprises attempting to determine the intention corresponding to the first utterance data with reference to a database including one or more mappings between utterance data and intentions. ### Claim 15 (depends on 13) The system of claim 13, wherein the action data comprises an action of the user to operate a vehicle function received within a certain period of time after the second utterance data is received. ### Claim 16 (depends on 13) The system of claim 13, wherein the action data comprises third utterance data obtained by converting into text a voice command of the user received within a certain period of time after the second utterance data is received, wherein the third utterance data comprises utterance data capable of being used to decide the intention of the user by performing the natural language understanding. ### Claim 17 (depends on 13) The system of claim 13, wherein predicting the intention of the user comprises: extracting a pattern that comprises the first utterance data and has a confidence equal to or greater than a first threshold from the pattern data; and predicting the intention of the user based on the action data of the extracted pattern. ### Claim 18 (depends on 13) The system of claim 13, wherein the program further includes instructions for: receiving a confirmation response of the user to the prompt from the vehicle; calculating accuracy of intention prediction of the user based on the received confirmation response; and correcting a confidence of the pattern that is a basis for predicting the intention of the user using the calculated accuracy.