# US 11,113,719 B2 · Content demotion > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,113,719 B2 - Document ID: US11113719B2 - Status: Granted - Kind: B2 - Application number: 16/133,671 - Filed: 2018-09-17 - Published: 2020-03-19 - Granted: 2021-09-07 - Earliest claimed: 2018-09-17 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Komminist Weldemariam; Sushain Pandit; Clifford A. Pickover - Web page: https://patentgrep.com/patent/US11113719B2 ## CPC - G06Q 30/0244: {Optimization} - G06N 3/0499: Feedforward networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06N 3/091: Active learning - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract An apparatus, for example a primary device, implements a method that includes receiving promoted content for display at the primary device; predicting a user's behavior with respect to the promoted content by estimating the user's context and preferences, using a neural network; and in response to the prediction of the user's behavior, automatically demoting the promoted content. ## Claims ### Claim 1 A computer-implemented method comprising: receiving promoted content for display at a primary device that is a node of a cloud network and a user device; detecting and profiling a user's cognitive state by monitoring the user's interactions with the primary device using at least one of: eye tracking sensors, motion tracking sensors, audio/speech sensors, and a camera and monitoring the user's interactions with one or more applications using at least one of: typing characteristics, mouse movement, analysis of typed content, and an application profile; predicting the user's behavior with respect to the promoted content by inferring the user's context and preferences from the detected profile of the user's cognitive state, using a neural network; prompting the user for feedback via the primary device; retraining the neural network using the feedback; and in response to the prediction of the user's behavior that the user may attempt to purchase promoted content, automatically demoting the promoted content, wherein demoting the promoted content includes blocking transfer of the promoted content that is displayed at the primary device from the primary device to one or more secondary devices via a peer-to-peer network that is established between the primary device and the one or more secondary devices. ### Claim 2 (depends on 1) The method of claim 1, wherein predicting the user's behavior includes detecting and profiling a primary user on the primary device and detecting and profiling secondary users on secondary devices. ### Claim 3 (depends on 1) The method of claim 1, wherein demoting the promoted content includes at least one of temporarily or permanently removing, hiding, deleting, changing, replacing or morphing video, audio, text, or image components of the promoted content. ### Claim 4 (depends on 1) The method of claim 1, wherein inferring the user's context includes inferring the user's context from social media posts made by the user or by members of the user's social graph within a predetermined number of days preceding the present day. ### Claim 5 (depends on 4) The method of claim 4, wherein inferring the user's cognitive state includes obtaining user feedback on promoted content, and re-training a neural network model of the user's cognitive state in response to the user feedback. ### Claim 6 (depends on 1) The method of claim 1, wherein demoting the promoted content includes estimating content demotion factors that include a temporal aspect of the content to be demoted and a risk associated with a relationship of the user to the promoted content. ### Claim 7 (depends on 1) The method of claim 1, wherein demoting the promoted content includes estimating a confidence level C that the promoted content will be objectionable to the user, then obscuring the promoted content to a degree that is a function of the confidence level C. ### Claim 8 (depends on 1) The method of claim 1, wherein demoting the promoted content includes demoting the promoted content at the primary device. ### Claim 9 A non-transitory computer readable medium embodying computer executable instructions which when executed by a computer cause the computer to facilitate the method of: receiving promoted content for display at a primary device that is a user device: detecting and profiling a user's cognitive state by monitoring the user's interactions with the primary device using at least one of: eye tracking sensors, motion tracking sensors, audio/speech sensors, and a camera and monitoring the users interactions with one or more applications using at least one of: typing characteristics, mouse movement, analysis of typed content, and an application profile; predicting the user's behavior with respect to the promoted content by inferring the user's context and preferences from the detected profile of the user's cognitive state, using a neural network; prompting the user for feedback via the primary device: retraining the neural network using the feedback; and in response to the prediction of the user's behavior that the user may attempt to purchase promoted content, automatically demoting the promoted content, wherein demoting the promoted content includes blocking transfer of the promoted content that is displayed at the primary device from the primary device to one or more secondary devices via a peer-to-peer network that is established by the primary device with the one or more secondary devices. ### Claim 10 (depends on 9) The computer readable medium of claim 9, wherein predicting the user's behavior includes detecting and profiling a primary user on the primary device and detecting and profiling secondary users on secondary devices. ### Claim 11 (depends on 9) The computer readable medium of claim 9, wherein inferring the user's context includes inferring the user's context from social media posts made by the user or by members of the user's social graph within a predetermined number of days preceding the present day. ### Claim 12 (depends on 11) The computer readable medium of claim 11, wherein inferring the user's cognitive state includes obtaining user feedback on promoted content, and re-training a neural network model of the user's cognitive state in response to the user feedback. ### Claim 13 An apparatus comprising: a memory embodying computer executable instructions; and at least one processor, coupled to the memory, and operative by the computer executable instructions to facilitate a method of: receiving promoted content for display at a primary device that is a user device: detecting and profiling a user's cognitive state by monitoring the user's interactions with the primary device using at least one of: eye tracking sensors, motion tracking sensors, audio/speech sensors, and a camera and monitoring the user's interactions with one or more applications using at least one of: typing characteristics, mouse movement, analysis of typed content, and an application profile; predicting the user's behavior with respect to the promoted content by inferring the user's context and preferences from the detected profile of the user's cognitive state, using a neural network; prompting the user for feedback via the primary device: retraining the neural network using the feedback; and in response to the prediction of the user's behavior that the user may attempt to purchase promoted content, automatically demoting the promoted content, wherein demoting the promoted content includes blocking transfer of the promoted content that is displayed at the primary device from the primary device to one or more secondary devices via a peer-to-peer network that is established by the primary device with the one or more secondary devices. ### Claim 14 (depends on 13) The apparatus of claim 13, wherein predicting the user's behavior includes detecting and profiling a primary user on the primary device and detecting and profiling secondary users on secondary devices.