# US 2025/0094501 A1 · Content search based on correlating a user propensity with propensity of content providers > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0094501 A1 - Document ID: US20250094501A1 - Status: Published application - Kind: A1 - Application number: 18/468,978 - Filed: 2023-09-18 - Published: 2025-03-20 - Earliest claimed: 2023-09-18 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Charbak Chatterjee; Vijay Kumar Ananthapur Bache; SAON SEN NANDI; NARENDRA KUNTE - Web page: https://patentgrep.com/patent/US20250094501A1 ## CPC - G06F 16/906: Clustering; Classification - G06F 16/953: Querying, e.g. by the use of web search engines - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract According to an embodiment of the present invention, a system for processing a search query comprises one or more memories and at least one processor coupled to the one or more memories. The system clusters content providers based on attributes of the content providers to produce a plurality of clusters each having content providers with aligned attributes. A correlation between a user providing the search query and the clusters is determined based on attributes of the user relative to attributes of the clusters. A cluster from among the plurality of clusters is determined based on the correlation. Content satisfying the search query is retrieved from the content providers of the determined cluster. Embodiments of the present invention further include a method and computer program product for processing a search query in substantially the same manner described above. ## Claims ### Claim 1 A method of processing a search query comprising: clustering, via at least one processor, content providers based on attributes of the content providers to produce a plurality of clusters each having content providers with aligned attributes; determining, via the at least one processor, a correlation strength for each cluster indicating reliability of that cluster based on an amount of change to cluster attributes in response to conditions; determining, via the at least one processor, a correlation between a user providing the search query and the clusters based on the correlation strength and attributes of the user relative to attributes of the clusters; determining, via the at least one processor, a cluster from among the plurality of clusters based on the correlation; and retrieving, via the at least one processor, content satisfying the search query from the content providers of the determined cluster. ### Claim 2 (depends on 1) The method of claim 1, wherein the content includes reviews for a product or service and the content providers include reviewers of the product or service. ### Claim 3 (canceled) ### Claim 4 (depends on 2) The method of claim 2, wherein the attributes of the user include one or more from a group of trust, fairness, self-awareness, motivation, expertise, and an intent with respect to the product or service. ### Claim 5 (depends on 2) The method of claim 2, further comprising: generating, via the at least one processor, one or more review questions for the reviewers of the determined cluster based on a change in correlation between the user and the determined cluster. ### Claim 6 (depends on 1) The method of claim 1, further comprising: re-clustering, via the at least one processor, the content providers in response to reliability of the determined cluster and correlation with the user failing to satisfy corresponding thresholds. ### Claim 7 (depends on 1) The method of claim 1, further comprising: adding, via the at least one processor, the user to a cluster of content providers based on a correlation of the attributes of the user to the attributes of the cluster of content providers. ### Claim 8 A system for processing a search query comprising: one or more memories; and at least one processor coupled to the one or more memories and configured to: cluster content providers based on attributes of the content providers to produce a plurality of clusters each having content providers with aligned attributes; determine a correlation strength for each cluster indicating reliability of that cluster based on an amount of change to cluster attributes in response to conditions; determine a correlation between a user providing the search query and the clusters based on the correlation strength and attributes of the user relative to attributes of the clusters; determine a cluster from among the plurality of clusters based on the correlation; and retrieve content satisfying the search query from the content providers of the determined cluster. ### Claim 9 (depends on 8) The system of claim 8, wherein the content includes reviews for a product or service and the content providers include reviewers of the product or service, and the attributes of the user include one or more from a group of trust, fairness, self-awareness, motivation, expertise, and an intent with respect to the product or service. ### Claim 10 (canceled) ### Claim 11 (depends on 9) The system of claim 9, wherein the at least one processor is further configured to: generate one or more review questions for the reviewers of the determined cluster based on a change in correlation between the user and the determined cluster. ### Claim 12 (depends on 8) The system of claim 8, wherein the at least one processor is further configured to: re-cluster the content providers in response to reliability of the determined cluster and correlation with the user failing to satisfy corresponding thresholds. ### Claim 13 (depends on 8) The system of claim 8, wherein the at least one processor is further configured to: add the user to a cluster of content providers based on a correlation of the attributes of the user to the attributes of the cluster of content providers. ### Claim 14 A computer program product for processing a search query, the computer program product comprising one or more computer readable storage media having program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by at least one processor to cause the at least one processor to: cluster content providers based on attributes of the content providers to produce a plurality of clusters each having content providers with aligned attributes; determine a correlation strength for each cluster indicating reliability of that cluster based on an amount of change to cluster attributes in response to conditions; determine a correlation between a user providing the search query and the clusters based on the correlation strength and attributes of the user relative to attributes of the clusters; determine a cluster from among the plurality of clusters based on the correlation; and retrieve content satisfying the search query from the content providers of the determined cluster. ### Claim 15 (depends on 14) The computer program product of claim 14, wherein the content includes reviews for a product or service and the content providers include reviewers of the product or service. ### Claim 16 (canceled) ### Claim 17 (depends on 15) The computer program product of claim 15, wherein the attributes of the user include one or more from a group of trust, fairness, self-awareness, motivation, expertise, and an intent with respect to the product or service. ### Claim 18 (depends on 15) The computer program product of claim 15, wherein the program instructions further cause the at least one processor to: generate one or more review questions for the reviewers of the determined cluster based on a change in correlation between the user and the determined cluster. ### Claim 19 (depends on 14) The computer program product of claim 14, wherein the program instructions further cause the at least one processor to: re-cluster the content providers in response to reliability of the determined cluster and correlation with the user failing to satisfy corresponding thresholds. ### Claim 20 (depends on 14) The computer program product of claim 14, wherein the program instructions further cause the at least one processor to: add the user to a cluster of content providers based on a correlation of the attributes of the user to the attributes of the cluster of content providers.