# US 12,769,780 B2 · Machine learning-based management of feedback data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,769,780 B2 - Document ID: US12769780B2 - Status: Granted - Kind: B2 - Application number: 18/618,448 - Filed: 2024-03-27 - Published: 2025-10-02 - Granted: 2026-10-20 - Earliest claimed: 2024-03-27 - Assignees: Dell Products L.P. - Applicants: Dell Products L.P. - Inventors: Anil Kumar Kolugur; Biraj Silwal; Songlin Hou; Neel Pravin Chaudhari; David C. Sydow - Web page: https://patentgrep.com/patent/US12769780B2 ## CPC - G06F 16/383: using metadata automatically derived from the content - G06F 16/3329: Natural language query formulation - G06F 16/3347: {using vector based model} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract An apparatus includes at least one processing device including a processor coupled to a memory, wherein the at least one processing device is configured to modify first data obtained from one or more sources, wherein the modifying includes adding user context data to the first data to generate second data, the second data representing the first data supplemented with a per-user context and, in response to receipt of a query, generate a response to the query using at least one generative language model supplemented by a retrieval augmented generation process based on at least a portion of the second data. ## Claims ### Claim 1 An apparatus comprising: at least one processing device comprising a processor coupled to a memory, the at least one processing device being configured to: modify first data obtained from one or more sources, wherein the modifying comprises adding user context data to the first data to generate second data, the second data representing the first data supplemented with a per-user context, wherein the user context data further comprises one or more identifiers of one or more users; generate one or more virtual user feedback profiles based on at least a portion of the second data, wherein the one or more virtual user feedback profiles simulate one or more virtual users of at least one item used by the one or more users; and in response to receipt of a query, generate a response to the query using at least one generative language model supplemented by a retrieval augmented generation process based on at least a portion of the one or more virtual user feedback profiles. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein the modifying further comprises generating a mapping between the first data and the second data, wherein the mapping comprises links between the first data and the second data. ### Claim 3 (depends on 1) The apparatus of claim 1, wherein the user context data further comprises one or more parameters attributable to one or more users such that the first data is supplemented based on the one or more parameters to form the per-user context in the second data. ### Claim 4 (depends on 3) The apparatus of claim 3, wherein the one or more parameters attributable to the one or more users comprise a user familiarity with one or more subjects associated with the first data. ### Claim 5 (depends on 1) The apparatus of claim 1, wherein the at least one generative language model comprises a large language model. ### Claim 6 (depends on 5) The apparatus of claim 5, wherein the generating of the response to the query further comprises translating the query into a prompt for the large language model. ### Claim 7 (depends on 1) The apparatus of claim 1, wherein the first data is obtained from the one or more sources using a data scraping process. ### Claim 8 (depends on 1) The apparatus of claim 1, wherein the one or more sources of the first data comprise one or more of external data and internal data with respect to a given entity associated with managing the processing device. ### Claim 9 A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device to: modify first data obtained from one or more sources, wherein the modifying comprises adding user context data to the first data to generate second data, the second data representing the first data supplemented with a per-user context, wherein the user context data further comprises one or more identifiers of one or more users; generate one or more virtual user feedback profiles based on at least a portion of the second data, wherein the one or more virtual user feedback profiles simulate one or more virtual users of at least one item used by the one or more users; and in response to receipt of a query, generate a response to the query using at least one generative language model supplemented by a retrieval augmented generation process based on at least a portion of the one or more virtual user feedback profiles. ### Claim 10 (depends on 9) The computer program product of claim 9, wherein the modifying further comprises generating a mapping between the first data and the second data, wherein the mapping comprises links between the first data and the second data. ### Claim 11 (depends on 9) The computer program product of claim 9, wherein the user context data further comprises one or more parameters attributable to one or more users such that the first data is supplemented based on the one or more parameters to form the per-user context in the second data. ### Claim 12 (depends on 11) The computer program product of claim 11, wherein the one or more parameters attributable to one or more users comprise a user familiarity with one or more subjects associated with the first data. ### Claim 13 (depends on 9) The computer program product of claim 9, wherein the at least one generative language model comprises a large language model. ### Claim 14 (depends on 13) The computer program product of claim 13, wherein the generating of the response to the query further comprises translating the query into a prompt for the large language model. ### Claim 15 (depends on 9) The computer program product of claim 9, wherein the first data is obtained from the one or more sources using a data scraping process, and wherein the one or more sources of the first data comprise one or more of external data and internal data with respect to a given entity associated with managing the processing device. ### Claim 16 A method comprising: modifying first data obtained from one or more sources, wherein the modifying comprises adding user context data to the first data to generate second data, the second data representing the first data supplemented with a per-user context, wherein the user context data further comprises one or more identifiers of one or more users; generating one or more virtual user feedback profiles based on at least a portion of the second data, wherein the one or more virtual user feedback profiles simulate one or more virtual users of at least one item used by the one or more users; and in response to receipt of a query, generating a response to the query using at least one generative language model supplemented by a retrieval augmented generation process based on at least a portion of the one or more virtual user feedback profiles; wherein the method is performed by at least one processing device comprising a processor coupled to a memory. ### Claim 17 (depends on 16) The method of claim 16, wherein the modifying further comprises generating a mapping between the first data and the second data, wherein the mapping comprises links between the first data and the second data. ### Claim 18 (depends on 16) The method of claim 16, wherein the user context data further comprises one or more parameters attributable to one or more users such that the first data is supplemented based on the one or more parameters to form the per-user context in the second data. ### Claim 19 (depends on 18) The method of claim 18, wherein the one or more parameters attributable to the one or more users comprise a user familiarity with one or more subjects associated with the first data. ### Claim 20 (depends on 16) The method of claim 16, wherein the at least one generative language model comprises a large language model.