# US 11,909,838 B1 · Dynamic user data filtering > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,909,838 B1 - Document ID: US11909838B1 - Status: Granted - Kind: B1 - Application number: 18/072,950 - Filed: 2022-12-01 - Granted: 2024-02-20 - Earliest claimed: 2022-12-01 - Assignees: Accenture Global Solutions Limited - Applicants: Accenture Global Solutions Limited - Inventors: Neelima Ratra; Sameer Siddiqui; Sandnya Dalvie - Web page: https://patentgrep.com/patent/US11909838B1 ## CPC - H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)} - G06F 16/9535: Search customisation based on user profiles and personalisation - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for dynamic user data filtering. In some implementations, a method includes determining one or more values using data representing a sequence of one or more types of interactions between a user and content; using the one or more values to determine whether to include each interaction of the one or more types of interactions in the sequence within a reduced user data set; generating the reduced user data set by removing one or more interactions from the sequence based on determining not to include the one or more interactions using the one or more values; and providing the reduced user data set to a processing server. ## Claims ### Claim 1 A method comprising: obtaining user activity data that represents a sequence of interactions between a user and content, the sequence including different types of interactions; for each interaction action of the sequence, determining a time duration associated with the interaction between the user and the content; for a particular type of interaction, determining a time duration threshold based on the time durations for interactions actions of the particular type of action interactions from the sequence; for each interaction of the particular type, using the time duration threshold to determine whether to exclude the interaction from a reduced user activity data set; generating the reduced user activity data set by selectively removing representations of one or more interactions from the user activity data that have been determined to be excluded from the reduced user activity data set based on the time duration threshold; and providing the reduced user data set to a processing server. ### Claim 2 (depends on 1) The method of claim 1, wherein the obtained user activity represents a subset of all user activity data representing interactions between multiple users and the content. ### Claim 3 (depends on 2) The method of claim 2, comprising: obtaining an output from a model that is trained to detect important actions using one or more values representing time differences. ### Claim 4 (depends on 2) The method of claim 2, wherein the model is specific to a domain associated with the content. ### Claim 5 (depends on 2) The method of claim 2, wherein determining the time duration threshold comprises: wherein the time duration threshold is further determined based on a quantity of interactions of the particular type in the sequence. ### Claim 6 (depends on 1) The method of claim 1, comprising: after generating the reduced user activity data, migrating the user activity data to a data storage device with a reduced energy consumption. ### Claim 7 (depends on 1) The method of claim 1, wherein the particular type of interaction comprises a selection interaction while the content is displayed on an output device of a user terminal. ### Claim 8 (depends on 1) The method of claim 1, comprising: obtaining a recommendation for the user using the reduced user data set. ### Claim 9 A non-transitory computer-readable medium storing one or more instructions executable by a computer system, the instructions, when executed by the computer system, performing operations comprising: obtaining user activity data that represents a sequence of interactions between a user and content, the sequence including different types of interactions; for each interaction action of the sequence, determining a time duration associated with the interaction between the user and the content; for a particular type of interaction, determining a time duration threshold based on the time durations for interactions actions of the particular type of action interactions from the sequence; for each interaction of the particular type, using the time duration threshold to determine whether to exclude the interaction from a reduced user activity data set; generating the reduced user activity data set by selectively removing representations of one or more interactions from the user activity data that have been determined to be excluded from the reduced user activity data set based on the time duration threshold; and providing the reduced user activity data set to a processing server. ### Claim 10 (depends on 9) The medium of claim 9, wherein the obtained user activity represents a subset of all user activity data representing interactions between multiple users and the content. ### Claim 11 (depends on 10) The medium of claim 10, wherein the operations comprise: obtaining an output from a model that is trained to detect important actions using one or more values representing time differences. ### Claim 12 (depends on 9) The medium of claim 9, wherein the model is specific to a domain associated with the content. ### Claim 13 (depends on 9) The medium of claim 9, wherein determining the time duration threshold comprises: wherein the time duration threshold is further determined based on a quantity of interactions of the particular type in the sequence. ### Claim 14 (depends on 9) The medium of claim 9, wherein the operations comprise: after generating the reduced user activity data, migrating the user activity data to a data storage device with a reduced energy consumption. ### Claim 15 (depends on 9) The medium of claim 9, wherein the particular type of interaction comprises a selection interaction while the content is displayed on an output device of a user terminal. ### Claim 16 (depends on 9) The medium of claim 9, wherein the operations comprise: obtaining a recommendation for the user using the reduced user activity data set. ### Claim 17 A system comprising: one or more processors; and machine-readable media interoperably coupled with the one or more processors and storing one or more instructions that, when executed by the one or more processors, perform operations comprising: obtaining user activity data that represents a sequence of interactions between a user and content, the sequence including different types of interactions; for each interaction action of the sequence, determining a time duration associated with the interaction between the user and the content; for a particular type of interaction, determining a time duration threshold based on the time durations for interactions actions of the particular type of action interactions from the sequence; for each interaction of the particular type, using the time duration threshold to determine whether to exclude the interaction from a reduced user activity data set; generating the reduced user activity data set by selectively removing representations of one or more interactions from the user activity data that have been determined to be excluded from the reduced user activity data set based on the time duration threshold; and providing the reduced user activity data set to a processing server. ### Claim 18 (depends on 17) The system of claim 17, wherein the obtained user activity represents a subset of all user activity data representing interactions between multiple users and the content. ### Claim 19 (depends on 18) The system of claim 18, wherein the operations comprise: obtaining an output from a model that is trained to detect important actions using one or more values representing time differences. ### Claim 20 (depends on 17) The system of claim 17, wherein the model is specific to a domain associated with the content.