# US 10,122,854 B2 · Interactive voice response (IVR) using voice input for tactile input based on context > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,122,854 B2 - Document ID: US10122854B2 - Status: Granted - Kind: B2 - Application number: 15/453,012 - Filed: 2017-03-08 - Published: 2018-08-23 - Granted: 2018-11-06 - Earliest claimed: 2017-03-08 - Assignees: Motorola Mobility LLC - Applicants: Motorola Mobility LLC - Inventors: Himanshu Chug; Amit Kumar Agrawal - Web page: https://patentgrep.com/patent/US10122854B2 ## CPC - H04M 3/4936: {Speech interaction details (speech recognition per se G10L15/00)} - H04M 1/72454: according to context-related or environment-related conditions - H04M 1/72457: according to geographic location - H04M 7/1295: {Details of dual tone multiple frequency signalling} - H04M 2201/60: Medium conversion - H04M 2203/353: where the information comprises non-audio but is provided over voice channels - H04M 2250/74: with voice recognition means - H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08) ## Abstract When the context of a user indicates that tactile input to a mobile device on an interactive voice response (IVR) call is not feasible or desirable and the IVR downlink audio does not provide for a voice response option, the user nonetheless is prompted to respond by voice. The user's response is used to programmatically select the correct key by, e.g., sending the DTMF tone corresponding to the user's response on the uplink back to the IVR system. ## Claims ### Claim 1 A device, comprising: at least one processor; and storage accessible to the at least one processor, the storage comprising instructions executable by the processor to: identify that a context of the device indicates touchless interactive voice response (IVR) based at least in part on a signal from at least one location sensor, and identifying that communication is activated with at least one wireless headset; identify that an interactive voice response (IVR) prompt on a communication downlink indicates to select an option by using tactile input; receive voice input from a microphone; responsive to the context indicating touchless IVR, transmit at least one dual tone multi frequency (DTMF) tone on a communication uplink associated with the communication downlink based on the voice input from the microphone. ### Claim 2 (depends on 1) The device of claim 1, wherein the instructions are executable to: responsive to identifying that the IVR prompt indicates to a user to select an option by using tactile input, play on at least one speaker an audio prompt to speak a response to the IVR audio. ### Claim 3 (depends on 1) The device of claim 1, wherein the instructions are executable to: identify that the IVR prompt on the communication downlink indicates to a user to select an option by using tactile input at least in part by converting the IVR audio to text and identifying whether the text satisfies a match condition with at least one text in a database. ### Claim 4 (depends on 1) The device of claim 1, wherein the instructions are executable to: identify that the IVR prompt on the communication downlink indicates to a user to select an option by using tactile input at least in part by converting IVR graphic information to text and identifying whether the text satisfies a match condition with at least one text in a database. ### Claim 5 (depends on 1) The device of claim 1, wherein the instructions are executable to: dynamically load a grammar data structure to process the voice input from the microphone. ### Claim 6 A method comprising: determining, at an electronic device, a context for an interactive voice response (IVR) system generating an audible menu; determining, at the electronic device, at least a portion of the IVR system necessitates tactile input; dynamically loading a grammar set to process a voice-based response corresponding to a tactile input; receiving and processing, at the electronic device, the audio input; and performing a function at the electronic device based on the processed audio input, wherein the dynamically loading a grammar set comprises: detecting a first numeral in the audible menu; correlating the first numeral with at least a first word following the first numeral in the menu, a first dual tone multi frequency (DTMF) data being correlated with both the first numeral and first word; detecting a second numeral in the audible menu; correlating the second numeral with at least a second word following the second numeral in the menu, a second DTMF data being correlated with both the second numeral and second word; wherein the audio input of the first word causes the first DTMF data to be sent and audio input of the first numeral causes the first DTMF data to be sent, and the audio input of the second word causes the second DTMF data to be sent and audio input of the second numeral causes the second DTMF data to be sent. ### Claim 7 (depends on 6) The method of claim 6, wherein determining at least a portion of the interactive voice response system necessitates tactile input comprises determining for the at least a portion of the interactive voice response system that a capability of voice input is not available. ### Claim 8 (depends on 6) The method of claim 6, wherein determining an IVR assistance context comprises determining that a device is in a driving state. ### Claim 9 (depends on 8) The method of claim 8, wherein detecting driving state is based at least in part on a location sensor indicating device movement above a threshold. ### Claim 10 (depends on 6) The method of claim 6, wherein determining an IVR assistance context comprises determining that a device is in walking or jogging state with an active wired and/or wireless headset connection. ### Claim 11 (depends on 10) The method of claim 10, wherein detecting walking or jogging state with an active wired and/or wireless headset connection comprises determining sensor based in-pocket or in-bag detection. ### Claim 12 (depends on 6) The method of claim 6, wherein determining an IVR assistance context comprises determining that a device is configured in a meaningful location state. ### Claim 13 (depends on 12) The method of claim 12, wherein meaningful location detection further comprises determining locations on which the device has been configured to work on hands-free voice-driven mode of interaction. ### Claim 14 (depends on 6) The method of claim 6, determining at least a portion of IVR call necessitates tactile input comprises executing speech processing on downlink channel audio and parsing the speech to text output to determine required actions to proceed with the IVR call corresponds to user providing tactile inputs. ### Claim 15 (depends on 6) The method of claim 6, wherein dynamically loading a grammar set to spot voice based response corresponding to tactile inputs comprises creating a grammar set on the fly corresponding to the options and variants associated with specific tactile input. ### Claim 16 An apparatus, comprising: at least a first processor; at least one network adapter; and storage with instructions executable by the first processor for: identifying that a context of the apparatus indicates touchless interactive voice response (IVR) based on a signal from location sensor and identifying that communication is activated between the apparatus and wireless headset; responsive to the context indicating touchless interactive voice response (IVR), identifying whether an IVR prompt indicates to select an option by using tactile input; correlating an audio response to the IVR prompt to a dual tone multi frequency (DTMF) tone; and sending the DTMF tone on an uplink back to an IVR system. ### Claim 17 (depends on 16) The apparatus of claim 16, wherein the instructions are executable for: identifying that IVR call on an IVR downlink does not provide for a voice response option; receiving voice input from a microphone; and based on the voice input from the microphone, transmitting the DTMF tone. ### Claim 18 (depends on 16) The apparatus of claim 16, wherein the instructions are executable for: identifying that the IVR prompt on the communication downlink prompts a user to select an option by using tactile input at least in part by converting an IVR audio or video to text and identifying whether the text satisfies a match condition with at least one text in a database. ### Claim 19 (depends on 16) The apparatus of claim 16, wherein the instructions are executable for: dynamically generating a grammar data structure based on recognized terms in the IVR audio on the communication downlink to process the voice input from the microphone. ### Claim 20 (depends on 1) The device of claim 1, wherein the instructions are executable for identifying that the context indicates touchless IVR by identifying that communication is activated between the apparatus device and the wireless headset.