# US 10,482,903 B2 · Method, device and apparatus for selectively interacting with multi-devices, and computer-readable medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,482,903 B2 - Document ID: US10482903B2 - Status: Granted - Kind: B2 - Application number: 15/854,430 - Filed: 2017-12-26 - Published: 2019-05-16 - Granted: 2019-11-19 - Earliest claimed: 2017-11-16 - Assignees: Baidu Online Network Technology (Beijing) Co., Ltd. - Applicants: Baidu Online Network Technology (Beijing) Co., Ltd. - Inventors: Sha Tao; Yonghui Zuo; Peng Wang; Guoguo Chen; Ji Zhou; Kaihua Zhu - Web page: https://patentgrep.com/patent/US10482903B2 ## CPC - G10L 25/78: Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10) - G06F 1/3206: Monitoring of events, devices or parameters that trigger a change in power modality - G10L 15/08: Speech classification or search - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G10L 25/21: the extracted parameters being power information - 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 - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A method for selectively interacting with multi-devices is provided. The method includes the following steps: receiving identical voice information transmitted by a plurality of terminal devices respectively; performing voice recognition on the received voice information; calculating energy of a wake-up word in respective voice information; and comparing the energy of one wake-up word with another, and transmitting feedback information to the terminal devices according to an energy comparison result and a voice recognition result. By calculating the energy of the wake-up word in respective voice information transmitted by respective devices, the distances between respective device and a user can be distinguished. A unique response can be ensured by determining that the device closest to the user responds to the user's request, thus ensuring the user experience. ## Claims ### Claim 1 A method for selectively interacting with multi-devices, comprising: receiving voice information from a plurality of terminal devices, wherein the voice information from the plurality of terminal devices comprises an identical wake-up word; performing voice recognition on the received voice information; calculating an energy value of the wake-up word in the voice information from the plurality of terminal devices; and comparing the energy values of the wake-up word, and transmitting feedback information to the terminal devices according to an energy comparison result and a voice recognition result, wherein before the receiving voice information from a plurality of terminal devices, the method further comprises: calibrating recording performances of the plurality of terminal devices, wherein the calibrating comprises: transmitting a play request for a standard speech to the plurality of terminal devices, wherein the standard speech is played and recorded by the plurality of terminal devices; and receiving recordings uploaded by the plurality of terminal devices, acquiring the recording performances of the respective terminal devices based on the received recordings, and setting recording performance coefficients for the respective terminal devices. ### Claim 2 (depends on 1) The method for selectively interacting with multi-devices according to claim 1, wherein the receiving voice information from a plurality of terminal devices further comprises: extracting the wake-up word carried in the voice information. ### Claim 3 (depends on 1) The method for selectively interacting with multi-devices according to claim 1, wherein the calculating an energy value of the wake-up word in the voice information comprises: calculating the energy value according to a sound volume of the wake-up word. ### Claim 4 (depends on 1) The method for selectively interacting with multi-devices according to claim 1, wherein the transmitting feedback information to the terminal devices according to an energy comparison result and a voice recognition result comprises: transmitting response information of the voice information to the terminal device with the highest energy value. ### Claim 5 (depends on 1) The method for selectively interacting with multi-devices according to claim 1, before the receiving voice information from a plurality of terminal devices, further comprising: adding or deleting a terminal device. ### Claim 6 A device for selectively interacting with multi-devices, comprising: one or more processors; and a storage device configured for storing one or more programs, wherein the one or more programs are executed by the one or more processors to enable the one or more processors to: receive voice information from a plurality of terminal devices, wherein the voice information from the plurality of terminal devices comprises an identical wake-up word; perform voice recognition on the received voice information; calculate an energy value of the wake-up word in the voice information from the plurality of terminal devices; compare the energy values of the wake-up word, and transmit feedback information to the terminal devices according to an energy comparison result and a voice recognition result, and calibrate recording performances of the plurality of terminal devices by: transmitting a play request for a standard speech to the plurality of terminal devices, wherein the standard speech is played and recorded by the plurality of terminal devices; and receiving recordings uploaded by the plurality of terminal devices, acquire the recording performances of the respective terminal devices, and set recording performance coefficients for the respective terminal devices. ### Claim 7 (depends on 6) The device for selectively interacting with multi-devices according to claim 6, wherein the one or more programs are executed by the one or more processors to enable the one or more processors to extract the wake-up word carried in the voice information. ### Claim 8 (depends on 6) The device for selectively interacting with multi-devices according to claim 6, wherein the one or more programs are executed by the one or more processors to enable the one or more processors to calculate the energy value according to a sound volume of the wake-up word. ### Claim 9 (depends on 6) The device for selectively interacting with multi-devices according to claim 6, wherein the one or more programs are executed by the one or more processors to enable the one or more processors to compare the energy values of the wake-up word, transmit response information of the voice information to the terminal device with the highest energy value. ### Claim 10 (depends on 6) The device for selectively interacting with multi-devices according to claim 6, wherein the one or more programs are executed by the one or more processors to enable the one or more processors to add or delete a terminal device. ### Claim 11 (depends on 1) A non-transitory computer-readable medium in which computer programs are stored, wherein the method for selectively interacting with multi-devices of claim 1 is implemented when the programs are executed by a processor.