# US 12,602,926 B2 · Attention monitoring in a video conferencing session > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,602,926 B2 - Document ID: US12602926B2 - Status: Granted - Kind: B2 - Application number: 18/065,074 - Filed: 2022-12-13 - Published: 2024-06-13 - Granted: 2026-04-14 - Earliest claimed: 2022-12-13 - Assignees: Capital One Services, LLC - Applicants: Capital One Services, LLC - Inventors: Vamsi Kavuri; Jignesh Rangwala; Lee Adcock; Mehulkumar Jayantilal Garnara - Web page: https://patentgrep.com/patent/US12602926B2 ## CPC - G06V 20/40: in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44) - G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88) - G06V 40/18: Eye characteristics, e.g. of the iris - G08B 3/1008: {Personal calling arrangements or devices, i.e. paging systems (selective calling systems and call receivers H04W84/00, H04W68/00)} - H04L 65/403: Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract In some implementations, a system may receive user data from a plurality of user devices corresponding to a plurality of users participating in a video conferencing session. The system may provide, based on the user data and as input to a machine learning model, user attention data associated with attentions of the plurality of users with respect to the video conferencing session. The machine learning model may be trained based on historical user attention data associated with a plurality of historical video conferencing sessions. The system may receive, as output from the machine learning model, an indication that one or more non-attentive users, of the plurality of users, are not attentive to the video conferencing session. The system may perform, based on the indication, one or more actions to gain attention from the one or more non-attentive users. ## Claims ### Claim 1 A method of monitoring attention in a video conferencing session, comprising: receiving, by a system having one or more processors and from a plurality of user devices, user data corresponding to a plurality of users attending the video conferencing session; determining, by the system and based on processing the user data with a machine learning model, a plurality of attention scores corresponding to the plurality of users, wherein the machine learning model is trained based on historical user attention data associated with a plurality of historical video conferencing sessions, and wherein an attention score, of the plurality of attention scores, represents a level of attention of a corresponding user of the plurality of users; identifying, by the system and based on the plurality of attention scores, one or more non-attentive users of the plurality of users, wherein one or more attention scores, of the plurality of attention scores, corresponding to the one or more non-attentive users satisfy an attention score threshold; determining, by the system, whether a number of the one or more non-attentive users satisfies a threshold value; and transmitting, by the system, to one or more user devices of the plurality of user devices associated with the identified one or more non-attentive users, and based on determining whether the number of the one or more non-attentive users satisfies a threshold value, a notification to gain the attention of the one or more non-attentive users. ### Claim 2 (depends on 1) The method of claim 1, wherein the video conferencing session is associated with a video conferencing type, and wherein the attention score threshold is based, at least in part, on the video conferencing type. ### Claim 3 (depends on 1) The method of claim 1, wherein the video conferencing session is associated with a video conferencing type, and wherein the attention score threshold is based, at least in part, on a number of users of the plurality of users. ### Claim 4 (depends on 1) The method of claim 1, wherein the video conferencing session is associated with a subject matter category, and wherein the attention score threshold is based, at least in part, on the subject matter category. ### Claim 5 (depends on 1) The method of claim 1, wherein the user data for a particular user, of the plurality of users, includes a video feed from a corresponding user device of the plurality of user devices, and wherein the method further comprises: determining, from the video feed, a participation viewing direction of the particular user, wherein a corresponding attention score, of the plurality of attention scores, corresponding to the particular user is based on one or more deviations of eyes of the particular user from the participation viewing direction for at least a deviation time threshold. ### Claim 6 (depends on 1) The method of claim 1, wherein the user data for a particular user, of the plurality of users, includes user participation data indicating participation of the particular user in the video conferencing session, wherein the user participation data includes one or more user inputs by the particular user, and wherein a corresponding attention score, of the plurality of attention scores, corresponding to the particular user is based on the one or more user inputs. ### Claim 7 (depends on 1) The method of claim 1, wherein the user data for a particular user, of the plurality of users, includes user activity data indicating user activity with one or more applications operating on a corresponding user device, of the plurality of user devices, and wherein a corresponding attention score, of the plurality of attention scores, corresponding to the particular user is based on the user activity data. ### Claim 8 A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising: one or more instructions that, when executed by one or more processors of a device, cause the device to: receive, from a plurality of user devices, user data corresponding to a plurality of users attending a video conferencing session; determine, based on processing the user data with a machine learning model, a plurality of attention scores corresponding to the plurality of users, wherein the machine learning model is trained based on historical user attention data associated with a plurality of historical video conferencing sessions, and wherein an attention score, of the plurality of attention scores, represents a level of attention of a corresponding user of the plurality of users; identify, based on the plurality of attention scores, one or more non-attentive users of the plurality of users, wherein a corresponding attention score of a non-attentive user, of the one or more non-attentive users, indicates that the user data satisfies one or more conditions associated with a lack of attentiveness; determine whether a number of the one or more non-attentive users satisfies a threshold value; and perform one or more actions to gain attention from the one or more non-attentive users, wherein the one or more actions include: transmitting, to one or more user devices of the plurality of user devices associated with the identified one or more non-attentive users, and based on determining whether the number of the one or more non-attentive users satisfies a threshold value, a notification to gain the attention from the one or more non-attentive users. ### Claim 9 (depends on 8) The non-transitory computer-readable medium of claim 8, wherein the user data for a particular user, of the plurality of users, includes a video feed from a corresponding user device of the plurality of user devices, and wherein the one or more instructions, when executed by the one or more processors, further cause the device to: track, from the video feed, movement of eyes of the particular user; and determine a participation viewing direction of the particular user, wherein one condition, of the one or more conditions, is that the eyes of the particular user deviate from the participation viewing direction for at least a deviation time threshold. ### Claim 10 (depends on 8) The non-transitory computer-readable medium of claim 8, wherein the user data for a particular user, of the plurality of users, includes user participation data indicating participation of the particular user in the video conferencing session, wherein the user participation data includes one or more user inputs by the particular user, and wherein one condition, of the one or more conditions, is that a number of user inputs by the particular user is below an input threshold within a time threshold. ### Claim 11 (depends on 8) The non-transitory computer-readable medium of claim 8, wherein the user data for a particular user, of the plurality of users, includes user activity data indicating user activity with one or more applications operating on a corresponding user device of the plurality of user devices, and wherein one condition, of the one or more conditions, is that user activity with the one or more applications exceeds a time threshold. ### Claim 12 (depends on 8) The non-transitory computer-readable medium of claim 8, wherein the one or more instructions, that cause the device to perform the one or more actions, cause the device to: perform the one or more actions when a number of non-attentive users satisfies a number threshold. ### Claim 13 A system, comprising: one or more memories; and one or more processors, communicatively coupled to the one or more memories, configured to: receive, from a plurality of user devices, user data corresponding to a plurality of users attending a video conferencing session; determine, based on processing the user data with a machine learning model, a plurality of attention scores corresponding to the plurality of users, wherein the machine learning model is trained based on historical user attention data associated with a plurality of historical video conferencing sessions, and wherein an attention score, of the plurality of attention scores, represents a level of attention of a corresponding user of the plurality of users; identify, based on the plurality of attention scores, one or more non-attentive users of the plurality of users, wherein one or more attention scores, of the plurality of attention scores, corresponding to the one or more non-attentive users satisfy an attention score threshold; determine whether a number of the one or more non-attentive users satisfies a threshold value; and transmit, to one or more user devices of the plurality of user devices associated with the identified one or more non-attentive users, and based on determining whether the number of the one or more non-attentive users satisfies a threshold value, a notification to gain the attention of the one or more non-attentive users. ### Claim 14 (depends on 13) The system of claim 13, wherein the video conferencing session is associated with a video conferencing type, and wherein the attention score threshold is based, at least in part, on the video conferencing type. ### Claim 15 (depends on 13) The system of claim 13, wherein the video conferencing session is associated with a video conferencing type, and wherein the attention score threshold is based, at least in part, on a number of users of the plurality of users. ### Claim 16 (depends on 13) The system of claim 13, wherein the video conferencing session is associated with a subject matter category, and wherein the attention score threshold is based, at least in part, on the subject matter category. ### Claim 17 (depends on 13) The system of claim 13, wherein the user data for a particular user, of the plurality of users, includes a video feed from a corresponding user device of the plurality of user devices, and wherein the one or more processors are further configured to: determine, from the video feed, a participation viewing direction of the particular user, wherein a corresponding attention score, of the plurality of attention scores, corresponding to the particular user is based on one or more deviations of eyes of the particular user from the participation viewing direction for at least a deviation time threshold. ### Claim 18 (depends on 13) The system of claim 13, wherein the user data for a particular user, of the plurality of users, includes user participation data indicating participation of the particular user in the video conferencing session, wherein the user participation data includes one or more user inputs by the particular user, and wherein a corresponding attention score, of the plurality of attention scores, corresponding to the particular user is based on the one or more user inputs. ### Claim 19 (depends on 13) The system of claim 13, wherein the user data for a particular user, of the plurality of users, includes user activity data indicating user activity with one or more applications operating on a corresponding user device, of the plurality of user devices, and wherein a corresponding attention score, of the plurality of attention scores, corresponding to the particular user is based on the user activity data. ### Claim 20 (depends on 13) The system of claim 13, wherein the one or more processors are further configured to: transmit the notification based on a number of non-attentive users satisfying a threshold value.