# US 2021/0240432 A1 · Intelligent Audio Playback Resumption > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0240432 A1 - Document ID: US20210240432A1 - Status: Published application - Kind: A1 - Application number: 16/782,964 - Filed: 2020-02-05 - Published: 2021-08-05 - Earliest claimed: 2020-02-05 - Assignees: Sap SE - Applicants: Sap SE - Inventors: Jan Lukas Max Aljoscha Melzer - Web page: https://patentgrep.com/patent/US20210240432A1 ## CPC - G06F 3/165: {Management of the audio stream, e.g. setting of volume, audio stream path} - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G06N 20/00: Machine learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract The present disclosure pertains to audio playback resumption and adjustment of audio resumption settings based on feedback. A first date timestamp and a playback timestamp of audio content may be stored when pausing audio content. Then when resuming the audio content, a time interval between the first date timestamp and a current date timestamp may be determined. A resumption timestamp in the audio content may be determined based on the time interval being within a certain time range. After resuming playback, a feedback input may be determined. The feedback may be used in adjusting the resumption settings. The adjusted resumption settings may be used in subsequent resumption of the same or different content. ## Claims ### Claim 1 A computer-implemented method, comprising: storing a first date timestamp and a playback timestamp of audio content in response to a pause input; determining a time interval between the first date timestamp and a second date timestamp in response to a play input; determining a resumption timestamp based on the time interval being within a time range; determining a feedback input after resuming playback of the audio content at the resumption timestamp, the feedback input including a fast-forward input or a rewind input; and adjusting the time range to an adjusted time range based on the feedback input and the time interval, the adjusting of the time range including increasing a minimum time of the time range based on the fast-forward input or decreasing a maximum time of the time range based on the rewind input, the adjusted time range usable in subsequent resumption of content. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising: storing resumption settings including a plurality of time ranges, each time range of the plurality of time ranges corresponding to a different context loss amount; and adjusting the resumption settings using a reinforcement learning algorithm based on the feedback input. ### Claim 3 (canceled) ### Claim 4 (canceled) ### Claim 5 (depends on 1) The computer-implemented method of claim 1, further comprising: requesting user feedback based on the resumption timestamp at a predetermined time after the resuming of the playback of the audio content, wherein the feedback input includes the user feedback. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, further comprising: determining an audio pause length corresponding to a context loss amount based on the time interval being within the time range; determining a pause of at least the audio pause length in the audio content based on an amplitude of an audio signal of the audio content; determining a segment of the audio content separated by the pause, the determining of the resumption timestamp being based on a start timestamp of the segment. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein the audio content is an audiobook, wherein the time range includes one day to thirty days, wherein the playback timestamp is within a chapter of the audiobook, and wherein the resumption timestamp is at a start of the chapter. ### Claim 8 A non-transitory machine-readable medium storing a program executable by at least one processing unit of a device, the program comprising sets of instructions for: storing a first date timestamp and a playback timestamp of audio content in response to a pause input; determining a time interval between the first date timestamp and a second date timestamp in response to a play input; determining a resumption timestamp based on the time interval being within a time range; determining a feedback input after resuming playback of the audio content at the resumption timestamp, the feedback input including a fast-forward input or a rewind input; and adjusting the time range to an adjusted time range based on the feedback input and the time interval, the adjusting of the time range including increasing a minimum time of the time range based on the fast-forward input or decreasing a maximum time of the time range based on the rewind input, the adjusted time range usable in subsequent resumption of content. ### Claim 9 (depends on 8) The non-transitory machine-readable medium of claim 8, wherein the program further comprises sets of instructions for: storing resumption settings including a plurality of time ranges, each time range of the plurality of time ranges corresponding to a different context loss amount; and adjusting the resumption settings using a reinforcement learning algorithm based on the feedback input. ### Claim 10 (canceled) ### Claim 11 (canceled) ### Claim 12 (depends on 8) The non-transitory machine-readable medium of claim 8, wherein the program further comprises sets of instructions for: requesting user feedback based on the resumption timestamp at a predetermined time after the resuming of the playback of the audio content, wherein the feedback input includes the user feedback. ### Claim 13 (depends on 8) The non-transitory machine-readable medium of claim 8, wherein the program further comprises sets of instructions for: determining an audio pause length corresponding to a context loss amount based on the time interval being within the time range; determining a pause of at least the audio pause length in the audio content based on an amplitude of an audio signal of the audio content; determining a segment of the audio content separated by the pause, the determining of the resumption timestamp being based on a start timestamp of the segment. ### Claim 14 (depends on 8) The non-transitory machine-readable medium of claim 8, wherein the audio content is an audiobook, wherein the time range includes one day to thirty days, wherein the playback timestamp is within a chapter of the audiobook, and wherein the resumption timestamp is at a start of the chapter. ### Claim 15 A computer system, comprising: one or more processors; memory; and computer program code comprising instructions, executable on the one or more processors, the computer program code configured to: store a first date timestamp and a playback timestamp of audio content in response to a pause input; determine a time interval between the first date timestamp and a second date timestamp in response to a play input; determine a resumption timestamp based on the time interval being within a time range; determine a feedback input after resuming playback of the audio content at the resumption timestamp, the feedback input including a fast-forward input or a rewind input; and adjust the time range to an adjusted time range based on the feedback input and the time interval, the adjusting of the time range including increasing a minimum time of the time range based on the fast-forward input or decreasing a maximum time of the time range based on the rewind input, the adjusted time range usable in subsequent resumption of content. ### Claim 16 (depends on 15) The computer system of claim 15, wherein the computer program code is further configured to: store resumption settings including a plurality of time ranges, each time range of the plurality of time ranges corresponding to a different context loss amount; and adjust the resumption settings using a reinforcement learning algorithm based on the feedback input. ### Claim 17 (canceled) ### Claim 18 (depends on 15) The computer system of claim 15, wherein the computer program code is further configured to: request user feedback based on the resumption timestamp at a predetermined time after the resuming of the playback of the audio content, wherein the feedback input includes the user feedback. ### Claim 19 (depends on 15) The computer system of claim 15, wherein the computer program code is further configured to: determine an audio pause length corresponding to a context loss amount based on the time interval being within the time range; determine a pause of at least the audio pause length in the audio content based on an amplitude of an audio signal of the audio content; determine a segment of the audio content separated by the pause, the determining of the resumption timestamp being based on a start timestamp of the segment. ### Claim 20 (depends on 15) The computer system of claim 15, wherein the audio content is an audiobook, wherein the time range includes one day to thirty days, wherein the playback timestamp is within a chapter of the audiobook, and wherein the resumption timestamp is at a start of the chapter.