# US 12,112,746 B2 · Method and device for processing voice interaction, electronic device and storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,112,746 B2 - Document ID: US12112746B2 - Status: Granted - Kind: B2 - Application number: 17/476,333 - Filed: 2021-09-15 - Published: 2022-01-06 - Granted: 2024-10-08 - Earliest claimed: 2020-11-10 - Assignees: Beijing Baidu Netcom Science Technology Co., Ltd. - Applicants: Beijing Baidu Netcom Science Technology Co., Ltd. - Inventors: Jinfeng Bai; Zhijian Wang; Cong Gao - Web page: https://patentgrep.com/patent/US12112746B2 ## CPC - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G10L 15/04: Segmentation; Word boundary detection - G10L 2015/088: {Word spotting} - 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 ## Abstract The present disclosure provides a method and a device for processing voice interaction, an electronic device and a storage medium. The method includes: determining a first integrity of a voice instruction from a user by using a pre-trained integrity detection model in response to detecting that the voice instruction from the user is not a high-frequency instruction; determining a waiting duration for the voice instruction based on the first integrity and a preset integrity threshold, wherein the waiting duration for the voice instruction indicates a length of period between a time when a voice interaction device determines that receiving the voice instruction is completed and a time when the voice interaction device performs an operation in response to the voice instruction of the user; and controlling the voice interaction device to respond to the voice instruction of the user based on the waiting duration. ## Claims ### Claim 1 A method for processing voice interaction, comprising: determining a first integrity of a voice instruction from a user by using a pre-trained integrity detection model in response to detecting that the voice instruction from the user is not a high-frequency instruction; determining a waiting duration for the voice instruction based on the first integrity and a preset integrity threshold, wherein the waiting duration for the voice instruction indicates a length of period between a time when a voice interaction device determines that receiving the voice instruction is completed and a time when the voice interaction device performs an operation in response to the voice instruction of the user; and controlling the voice interaction device to respond to the voice instruction of the user based on the waiting duration; wherein the method further comprises: prior to responding to the voice instruction based on the waiting duration for the voice instruction, receiving a supplementary voice instruction from the user within the waiting duration for the voice instruction; determining a second integrity of a combined instruction composed of the voice instruction of the user and the supplementary voice instruction of the user by using the integrity detection model in response to detecting that the supplementary voice instruction is not a high-frequency instruction; and determining a waiting duration for the combined instruction based on the second integrity and the preset integrity threshold in response to determining that the second integrity is greater than the first integrity, wherein the waiting duration for the combined instruction indicates a length of period between a time when the voice interaction device determines that receiving the supplementary voice instruction is completed and a time when the voice interaction device performs an operation in response to the combined instruction. ### Claim 2 (depends on 1) The method according to claim 1, wherein the determining a waiting duration for the voice instruction based on the first integrity and a preset integrity threshold comprises: determining that the waiting duration for the voice instruction is a first waiting duration, in response to the first integrity being greater than or equal to the preset integrity threshold. ### Claim 3 (depends on 2) The method according to claim 2, wherein the determining a waiting duration for the voice instruction based on the first integrity and a preset integrity threshold further comprises: determining that the waiting duration for the voice instruction is a second waiting duration, in response to the first integrity being less than the preset integrity threshold, wherein the second waiting duration is greater than the first waiting duration. ### Claim 4 (depends on 1) The method according to claim 1, wherein the determining a waiting duration for the combined instruction comprises: deleting the waiting duration for the voice instruction; and determining a waiting duration for the combined instruction based on the second integrity and the preset integrity threshold. ### Claim 5 (depends on 4) The method according to claim 4, wherein the determining a waiting duration for the combined instruction further comprises: determining that the waiting duration for the combined instruction is a first waiting duration in response to the second integrity being greater than or equal to the preset integrity threshold; or determining that the waiting duration for the combined instruction is a second waiting duration in response to the second integrity being less than the preset integrity threshold, wherein the second waiting duration is greater than the first waiting duration. ### Claim 6 (depends on 1) The method according to claim 1, further comprises: determining that the waiting duration for the voice instruction or a waiting duration for the supplementary voice instruction is a third waiting duration, in response to detecting that the voice instruction is a high-frequency instruction, and wherein the third waiting duration is less than the first waiting duration; and responding to the voice instruction from the user or the supplementary voice instruction from the user according to the third waiting duration. ### Claim 7 A method for processing voice interaction, comprising: receiving a voice instruction from a user; uploading the voice instruction of the user to a cloud server; receiving a control command generated by the cloud server for the voice instruction from the user, wherein the control command comprises a waiting duration determined by the cloud server, and the waiting duration indicates a length of period between a time when a voice interaction device determines that receiving the voice instruction is completed and a time when the voice interaction device performs an operation in response to the voice instruction from the user; and responding to the voice instruction according to the waiting duration in the control command; wherein the waiting duration is determined by: determining a first integrity of a voice instruction from a user by using a pre-trained integrity detection model in response to detecting that the voice instruction from the user is not a high-frequency instruction; determining a waiting duration for the voice instruction based on the first integrity and a preset integrity threshold, wherein the waiting duration for the voice instruction indicates a length of period between a time when a voice interaction device determines that receiving the voice instruction is completed and a time when the voice interaction device performs an operation in response to the voice instruction of the user; wherein the method further comprises: prior to responding to the voice instruction based on the waiting duration for the voice instruction, receiving a supplementary voice instruction from the user within the waiting duration for the voice instruction; determining a second integrity of a combined instruction composed of the voice instruction of the user and the supplementary voice instruction of the user by using the integrity detection model in response to detecting that the supplementary voice instruction is not a high-frequency instruction; and determining a waiting duration for the combined instruction based on the second integrity and the preset integrity threshold in response to determining that the second integrity is greater than the first integrity, wherein the waiting duration for the combined instruction indicates a length of period between a time when the voice interaction device determines that receiving the supplementary voice instruction is completed and a time when the voice interaction device performs an operation in response to the combined instruction. ### Claim 8 An electronic device, comprising: at least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, cause the at least one processor to perform operations of: determining a first integrity of a voice instruction from a user by using a pre-trained integrity detection model in response to detecting that the voice instruction from the user is not a high-frequency instruction; determining a waiting duration for the voice instruction based on the first integrity and a preset integrity threshold, wherein the waiting duration for the voice instruction indicates a length of period between a time when a voice interaction device determines that receiving the voice instruction is completed and a time when the voice interaction device performs an operation in response to the voice instruction of the user; and controlling the voice interaction device to respond to the voice instruction of the user based on the waiting duration; wherein the instructions, when executed by the at least one processor, cause the at least one processor further to perform operations of, prior to responding to the voice instruction based on the waiting duration for the voice instruction: receiving a supplementary voice instruction from the user within the waiting duration for the voice instruction; determining a second integrity of a combined instruction composed of the voice instruction of the user and the supplementary voice instruction of the user by using the integrity detection model in response to detecting that the supplementary voice instruction is not a high-frequency instruction; and determining a waiting duration for the combined instruction based on the second integrity and the preset integrity threshold in response to determining that the second integrity is greater than the first integrity, wherein the waiting duration for the combined instruction indicates a length of period between a time when the voice interaction device determines that receiving the supplementary voice instruction is completed and a time when the voice interaction device performs an operation in response to the combined instruction. ### Claim 9 (depends on 8) The device according to claim 8, wherein the instructions, when executed by the at least one processor, cause the at least one processor further to perform operations of determining that the waiting duration for the voice instruction is a first waiting duration, in response to the first integrity being greater than or equal to the preset integrity threshold. ### Claim 10 (depends on 8) The device according to claim 8, wherein the instructions, when executed by the at least one processor, cause the at least one processor further to perform operations of: determining that the waiting duration for the voice instruction is a second waiting duration, in response to the first integrity being less than the preset integrity threshold, wherein the second waiting duration is greater than the first waiting duration. ### Claim 11 (depends on 8) The device according to claim 8, wherein the instructions, when executed by the at least one processor, cause the at least one processor further to perform operations of: deleting the waiting duration for the voice instruction; and determining a waiting duration for the combined instruction based on the second integrity and the preset integrity threshold. ### Claim 12 (depends on 8) The device according to claim 8, wherein the instructions, when executed by the at least one processor, cause the at least one processor further to perform operations of: determining that the waiting duration for the combined instruction is a first waiting duration in response to the second integrity being greater than or equal to the preset integrity threshold; or determining that the waiting duration for the combined instruction is a second waiting duration in response to the second integrity being less than the preset integrity threshold, wherein the second waiting duration is greater than the first waiting duration. ### Claim 13 (depends on 8) The device according to claim 8, wherein the instructions, when executed by the at least one processor, cause the at least one processor further to perform operations of determining that the waiting duration for the voice instruction or a waiting duration for the supplementary voice instruction is a third waiting duration, in response to detecting that the voice instruction is a high-frequency instruction, and wherein the third waiting duration is less than the first waiting duration; and responding to the voice instruction from the user or the supplementary voice instruction from the user according to the third waiting duration. ### Claim 14 (depends on 7) An electronic device, comprising: at least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, cause the at least one processor to perform the method according to claim 7. ### Claim 15 (depends on 1) A non-transitory computer-readable storage medium having computer instructions stored thereon, wherein the computer instructions, when executed, cause a computer to perform the method according to claim 1. ### Claim 16 (depends on 7) A non-transitory computer-readable storage medium having computer instructions stored thereon, wherein the computer instructions, when executed, cause a computer to perform the method according to claim 7.