# US 12,182,138 B2 · Impression discounting for followfeed > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,182,138 B2 - Document ID: US12182138B2 - Status: Granted - Kind: B2 - Application number: 17/668,153 - Filed: 2022-02-09 - Published: 2023-08-10 - Granted: 2024-12-31 - Earliest claimed: 2022-02-09 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Madhulekha Arunmozhi; Ian Robert Ackerman; Birjodh Singh Tiwana; Sarah Yan Xing - Web page: https://patentgrep.com/patent/US12182138B2 ## CPC - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F 16/24578: {using ranking} - G06F 16/9537: Spatial or temporal dependent retrieval, e.g. spatiotemporal queries - G06F 16/9538: Presentation of query results - G06F 16/958: Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking - G06Q 10/10: Office automation; Time management - G06Q 10/40: Business processes related to social networking or social networking services - G06Q 30/0251: Targeted advertisements - G06Q 30/0282: Rating or review of business operators or products - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - 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 ## Abstract Described herein is a technique for surfacing content for users of a connection network application. The technique involves performing a first query to fetch recently-impressed items viewed by a user of the connection network application and, concurrently with the first query, performing a second query of search nodes to generate a set of search node results. The technique allows for filtering the recently-impressed items from the set of search node results to generate a candidate set and applying a freshness factor to the candidate set. Updates are provided to a user display, based on results of applying the freshness factor to the candidate set. ## Claims ### Claim 1 A system comprising: a non-transitory computer-readable medium having instructions stored thereon, which, when executed by a processor, cause the system to: perform, by a second pass ranker, a first query of a first data store to fetch N most recent impressed items viewed by a user of a connection network application, wherein the first query comprises a batch query having only a single query key comprising a member identifier of the user; concurrently with the first query, perform, by a first pass ranker, a second query of search nodes separate from the first data store to generate a set of top K search node results; subsequent to the first query and the second query, filter, by the first pass ranker, the N most recent impressed items from the set of top K search node results to generate a candidate set that is provided to the second pass ranker; apply, by the second pass ranker, a freshness factor to the candidate set; and provide, by the second pass ranker, updates to display to the user of the connection network application based on results of applying the freshness factor. ### Claim 2 (depends on 1) The system of claim 1, wherein the computer-readable medium is storing additional instructions, which, when executed by the processor, cause the system to apply the freshness factor by: determining an age for each item of the candidate set; and placing each item of the candidate set in an age bucket based on the age for a respective item, the age bucket comprised of items of similar ages. ### Claim 3 (depends on 2) The system of claim 2, wherein the freshness factor is comprised of a boost factor that boosts items generated since a last visit time to the connection network application such that application of the freshness factor provides an indication of increased freshness for the boosted items. ### Claim 4 (depends on 3) The system of claim 3, wherein the freshness factor is further comprised of a half life component and wherein the freshness factor is based on the boost factor, the age bucket of the respective item, and a half life of the respective item. ### Claim 5 (depends on 2) The system of claim 2, wherein the age bucket corresponds to an age displayed to the user upon visiting the connection network application. ### Claim 6 (depends on 5) The system of claim 5, wherein an item of the candidate set that is between 0 and 23 hours old is added to one of 24 hourly age buckets. ### Claim 7 (depends on 5) The system of claim 5, wherein items of the candidate set that are between 7 and 14 days old are added to a same age bucket. ### Claim 8 A method of providing updates to a user of a connection network application, the method comprising: performing, by a second pass ranker, a first query of a first data store to fetch N most recent impressed items viewed by a user of connection network application, wherein the first query comprises a batch query having only a single query key comprising a member identifier of the user; concurrently with the first query, performing, by a first pass ranker, a second query of search nodes separate from the first data store to generate a set of top K search node results; subsequent to the first query and the second query, filtering, by the first pass ranker, the N most recent impressed items from the set of K search node results to generate a candidate set that is provided to the second pass ranker; applying, by the second pass ranker, a freshness factor to the candidate set; and providing, by the second pass ranker, updates to display to the user of the connection network application based on results of applying the freshness factor. ### Claim 9 (depends on 8) The method of claim 8, wherein applying the freshness factor comprises: determining an age for each item of the candidate set; placing each item of the candidate set in an age bucket based on the age for a respective item, the age bucket comprised of items of similar ages; and apply the freshness factor to an SPR ranking score for each item of the candidate set. ### Claim 10 (depends on 9) The method of claim 9, wherein the freshness factor is comprised of a boost factor that boosts items generated since a last visit time to the connection network application such that application of the freshness factor provides an indication of an increased freshness for the boosted items. ### Claim 11 (depends on 10) The method of claim 10, wherein the freshness factor is further comprised of a half life component and wherein the freshness factor is based on the boost factor, the age bucket of the respective item, and a half life. ### Claim 12 (depends on 10) The method of claim 10, wherein the age bucket corresponds to an age displayed to the user upon visiting the connection network application. ### Claim 13 (depends on 12) The method of claim 12, wherein an item of the candidate set that is between 0 and 23 hours old is added to one of 24 hourly age buckets. ### Claim 14 (depends on 12) The method of claim 12, wherein items of the candidate set that are between 7 and 14 days old are added to a same age bucket. ### Claim 15 A system comprising: means for performing, by a second pass ranker, a first query of a first data store to fetch N most recent impressed items viewed by a user of a connection network application, wherein the first query comprises a batch query having only a single query key comprising a member identifier of the user; means for performing, concurrently with the first query and by a first pass ranker, a second query of search nodes separate from the first data store to generate a set of top K search node results; means for filtering, subsequent to the first query and the second query, by the first pass ranker, the N most recent impressed items from the set of K search node results to generate a candidate set that is provided to the second pass ranker; means for applying, by the second pass ranker, a freshness factor to the candidate set; and means for providing, by the second pass ranker, updates to display to the user of the connection network application based on results of application of the freshness factor. ### Claim 16 (depends on 15) The system of claim 15, further comprising: means for determining an age for each item of the candidate set; means for placing each item of the candidate set in an age bucket based on the age for a respective item, the age bucket comprised of items of similar ages; and means for applying a freshness factor to an SPR ranking score for each item of the candidate set. ### Claim 17 (depends on 16) The system of claim 16, wherein the freshness factor is comprised of a boost factor that boosts items generated since a last visit time to the connection network application such that the freshness factor provides an indication of an increased freshness for the boosted items. ### Claim 18 (depends on 17) The system of claim 17, wherein the freshness factor is further comprised of a half life component and wherein the freshness factor is based on the boost factor, the age bucket of the respective item, and a half life indicating a desired steepness of a curve representing freshness factor values for items of the candidate set.