# US 2018/0322155 A1 · Search system for temporally relevant social data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0322155 A1 - Document ID: US20180322155A1 - Status: Published application - Kind: A1 - Application number: 15/588,217 - Filed: 2017-05-05 - Published: 2018-11-08 - Earliest claimed: 2017-05-05 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Omar Rogelio Alonso; Serge-Eric Tremblay; Vasileios Kandylas - Web page: https://patentgrep.com/patent/US20180322155A1 ## CPC - G06F 16/9536: Search customisation based on social or collaborative filtering - G06F 16/23: Updating - G06F 16/24578: {using ranking} - G06F 16/248: Presentation of query results - G06F 16/26: Visual data mining; Browsing structured data - G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)} - G06F 16/9535: Search customisation based on user profiles and personalisation - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G06N 5/022: Knowledge engineering; Knowledge acquisition - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Surfacing relevant socially trending informational items in response to an exploratory query is provided. A temporally relevant social data search system includes an intelligent assistant, a knowledgebase generation system, and a temporal graph knowledgebase. The knowledgebase generation system builds the temporal graph knowledgebase from entities and relationships detected in social data mined from a plurality of social networking data sources. Responsive to receiving an exploratory query associated with one or more entities, the intelligent assistant queries the temporal graph knowledgebase for information items related to the one or more entities, selects a relevant information item to include in a response, and provides the response to the user. ## Claims ### Claim 1 A method for providing a relevant informational item to a user, comprising: mining a plurality of social networking data sources for collecting social data items; parsing the collected social data items for detecting entities; generating a graph knowledgebase storing a first node representing a first entity, wherein the first entity is a social data item from the collected social data items, a second node representing a second entity, wherein the second entity is associated with the social data item, and an edge representing a relationship connecting the first node and the second node; responsive to receiving an exploratory query by the user for information associated with the second entity, querying the graph knowledgebase for identifying social data items related to the second entity; selecting a social data item related to the second entity based on a relatedness score, the relatedness score based at least in part on an amount of and recency of social activity associated with the first entity and the second entity; generating a response to the user including the information parsed from the selected social data item; and delivering the response to the user via a communication channel. ### Claim 2 (depends on 1) The method of claim 1, wherein selecting the social data item further comprises: determining whether the social data item includes information relevant to the user based on personalization information; when the social data item includes information relevant to the user based on personalization information, incrementing the relatedness score; and when the social data item does not include information relevant to the user based on personalization information, decrementing the relatedness score. ### Claim 3 (depends on 2) The method of claim 2, wherein determining whether the social data item includes information relevant to the user comprises determining whether the social data item includes information relevant to the user based on personalization information explicitly defined by the user in a user profile. ### Claim 4 (depends on 2) The method of claim 2, wherein determining whether the social data item includes information relevant to the user comprises determining whether the social data item includes information relevant to the user based on personalization information implicitly defined based on user interaction data. ### Claim 5 (depends on 1) The method of claim 1, wherein generating the graph knowledgebase comprises storing the second node representing the second entity, wherein the second entity is an entity mentioned in the social data item represented by the first node. ### Claim 6 (depends on 1) The method of claim 1, wherein generating the graph knowledgebase comprises storing the second node representing the second entity, wherein the second entity is an author of the social data item represented by the first node. ### Claim 7 (depends on 1) The method of claim 1, wherein calculating the relatedness score comprises calculating the relatedness score based on a number of: shares; likes, posts, or re-posts. ### Claim 8 (depends on 1) The method of claim 1, wherein querying the graph knowledgebase comprises: extracting a portion of the graph knowledgebase including the second entity; and traversing the extracted portion of the graph knowledgebase for discovering other entities, relationships, and associated relatedness scores. ### Claim 9 (depends on 1) The method of claim 1, further comprising: continually mining the plurality of social networking data sources for collecting social data items; parsing the collected social data items for detecting entities; and updating the graph knowledgebase with the detected entities and relationships connecting the entities. ### Claim 10 (depends on 1) The method of claim 1, further comprising: responsive to a follow-up exploratory query by the user for information associated with the second entity and a third entity, querying the graph knowledgebase for identifying other entities related to the second entity and the third entity; selecting a social data item related to the second entity and the third entity based on a relatedness score; generating a response to the user including the information parsed from the selected social data item; and delivering the response to the user via a communication channel. ### Claim 11 A system for providing a relevant informational item to a user, comprising: a processing unit; and a memory, including computer readable instructions, which when executed by the processing unit is operable to provide a temporally relevant social data search system operative to: mine a plurality of social networking data sources for collecting social data items; parse the collected social data items for detecting entities; generate a graph knowledgebase storing a first node representing a first entity, wherein the first entity is a social data item from the collected social data items, a second node representing a second entity, wherein the second entity is associated with the social data item, and an edge representing a relationship connecting the first node and the second node; calculate a relatedness score between the first entity and the second entity based at least in part on an amount of and recency of social activity associated with the first entity and the second entity; responsive to receiving an exploratory query by the user for information associated with the second entity, query the graph knowledgebase for identifying social data items related to the second entity; increase the relatedness score of identified social data items related to the second entity that include information relevant to the user based on personalization information; select a social data item related to the second entity based on the relatedness score; generate a response to the user including the information parsed from the selected social data item; and deliver the response to the user via a communication channel. ### Claim 12 (depends on 11) The system of claim 11, wherein: the personalization information is explicitly defined by the user in a user profile; or the personalization information is implicitly defined based on user interaction data. ### Claim 13 (depends on 11) The system of claim 11, wherein in calculating the relatedness score, the temporally relevant social data search system is operative to calculate the relatedness score based on a number of: shares; likes, posts, or re-posts. ### Claim 14 (depends on 11) The system of claim 11, wherein in querying the graph knowledgebase, the temporally relevant social data search system is operative to: extract a portion of the graph knowledgebase including the second entity; and traverse the extracted portion of the graph knowledgebase for discovering other entities, relationships, and associated relatedness scores. ### Claim 15 (depends on 11) The system of claim 11, wherein the temporally relevant social data search system is further operative to continually mine the plurality of social networking data sources for collecting social data items; parse the collected social data items for detecting entities; and update the graph knowledgebase with the detected entities and relationships connecting the entities. ### Claim 16 (depends on 11) The system of claim 11, wherein the temporally relevant social data search system is further operative to: responsive to a follow-up exploratory query by the user for information associated with the second entity and a third entity, query the graph knowledgebase for identifying other entities related to the second entity and the third entity; select a social data item related to the second entity and the third entity based on a relatedness score; generate a response to the user including the information parsed from the selected social data item; and deliver the response to the user via a communication channel. ### Claim 17 A computer readable storage device including computer readable instructions, which when executed by a processing unit is operable to: mine a plurality of social networking data sources for collecting social data items; parse the collected social data items for detecting entities; generate a graph knowledgebase storing a first node representing a first entity, wherein the first entity is a social data item from the collected social data items, a second node representing a second entity, wherein the second entity is associated with the social data item, and an edge representing a relationship connecting the first node and the second node; calculate a relatedness score between the first entity and the second entity based at least in part on an amount of and recency of social activity associated with the first entity and the second entity; responsive to receiving an exploratory query by the user for information associated with the second entity, query the graph knowledgebase for identifying social data items related to the second entity; increase a relatedness score of identified social data items related to the second entity that include information relevant to the user based on personalization information; select a social data item related to the second entity based on the relatedness score; generate a response to the user including the information parsed from the selected social data item; and deliver the response to the user via a communication channel. ### Claim 18 (depends on 17) The computer readable storage device of claim 17, wherein: the personalization information is explicitly defined by the user in a user profile; or the personalization information is implicitly defined based on user interaction data. ### Claim 19 (depends on 17) The computer readable storage device of claim 17, wherein the device is further operative to: continually mine the plurality of social networking data sources for collecting social data items; parse the collected social data items for detecting entities; and update the graph knowledgebase with the detected entities and relationships connecting the entities. ### Claim 20 (depends on 17) The computer readable storage device of claim 17, wherein in querying the graph knowledgebase, the device is operative to: extract a portion of the graph knowledgebase including the second entity; and traverse the extracted portion of the graph knowledgebase for discovering other entities, relationships, and associated relatedness scores.