# US 10,318,900 B2 · Job profile generation based on intranet usage > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,318,900 B2 - Document ID: US10318900B2 - Status: Granted - Kind: B2 - Application number: 15/232,911 - Filed: 2016-08-10 - Published: 2018-02-15 - Granted: 2019-06-11 - Earliest claimed: 2016-08-10 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Brian T. Carter; Patrick J. Cronin; Paul C. J. Dunning; Shane Quigley - Web page: https://patentgrep.com/patent/US10318900B2 ## CPC - G06Q 10/063112: {Skill-based matching of a person or a group to a task} - G06Q 10/1053: Employment or hiring - 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 A method, computer program product, and system for job profile generation, the method, computer program product, and system include receiving employee intranet usage data, storing the received employee intranet usage data in a database, identifying a portion of the stored employee intranet usage data associated with the former employee, transmitting the portion to a recommender system, where the recommender system identifies one or more required job skills of the former employee, based on the transmitted portion, and generating a job profile based on the one or more identified required job skills. ## Claims ### Claim 1 A method for job profile generation on a computer, the method comprising: receiving employee intranet usage data related to each employee of a company, wherein the intranet usage data is at least one member selected from a group consisting of websites visited, an associated link for each website, commands executed, text entered, searches executed, version control systems, and internal social networks; storing the received employee intranet usage data in a database; identifying a portion of the stored employee intranet usage data related to each employee of the company which is associated with a first employee; transmitting the identified portion to a recommender system, wherein the recommender system identifies one or more required job skills of the first employee, based on the transmitted portion, wherein training of the recommender system comprises training with sample lists of associated tags and keywords from the employee intranet usage data, generating a group of sample lists and identifying a best list of the group of sample lists based on a fitness function associated with each sample list of the group of sample lists; and generating a job profile based on the one or more identified required job skills of the first employee. ### Claim 2 (depends on 1) The method according to claim 1, wherein the stored employee intranet usage data is at least one member selected from a group consisting of a date performed, an event description, and an intranet link associated with an event. ### Claim 3 (depends on 2) The method according to claim 2, wherein a tag is assigned to the event description from the event of the stored employee intranet usage data. ### Claim 4 (depends on 1) The method according to claim 1, wherein identifying the portion of the stored employee intranet usage data further comprises: removing extraneous information common to a plurality of employees. ### Claim 5 (depends on 3) The method according to claim 3, wherein the one or more required skills are identified by ranking a random list of one or more associated tags, and wherein a best list is identified from the random list, and wherein the best list has a highest probability of matching a required job skill of the former employee. ### Claim 6 (depends on 1) The method according to claim 1, wherein generating the job profile further comprises: formatting the one or more identified required job skills into a recruitment template. ### Claim 7 (depends on 1) The method according to claim 1, further compromising: posting the generated job profile on a recruitment web site. ### Claim 8 A method for job profile generation on a computer, the method comprising: receiving employee intranet usage data related to each employee of a company, wherein the intranet usage data is at least one member selected from a date performed, an event description, and an intranet link associated with an event; storing the received employee intranet usage data in a database; identifying a portion of the stored employee intranet usage data related to each employee of the company which is associated with a first employee; utilizing machine learning to provide associated tags for each event description and each intranet link in the portion of the stored employee intranet usage data; providing associated keywords for each event description, each intranet link and each associated tag in the portion of the stored employee intranet usage data; transmitting the portion of the stored employee intranet usage data, the associated tags and the associated keywords, to a recommender system, wherein the recommender system identifies one or more required job skills of the first employee, based on the transmitted portion, wherein training of the recommender system comprises training with sample lists of associated tags and keywords from the employee intranet usage data, generating a group of sample lists and identifying a best list of the group of sample lists based on a fitness function associated with each sample list of the group of sample lists; and generating a job profile based on the one or more identified required job skills of the first employee. ### Claim 9 (depends on 8) The method according to claim 8, wherein the stored employee intranet usage data is at least one member selected from a group consisting of a date performed, an event description, and an intranet link associated with an event, wherein a tag is assigned to the event description from the event of the stored employee intranet usage data, and wherein the one or more required skills are identified by ranking a random list of one or more associated tags, and wherein a best list is identified from the random list, and wherein the best list has a highest probability of matching a required job skill of the former employee. ### Claim 10 (depends on 8) The method according to claim 8, wherein identifying the portion of the stored employee intranet usage data further comprises: removing extraneous information common to a plurality of employees. ### Claim 11 (depends on 8) The method according to claim 8, wherein generating the job profile further comprises: formatting the one or more identified required job skills into a recruitment template. ### Claim 12 (depends on 8) The method according to claim 8, further compromising: posting the generated job profile on a recruitment web site. ### Claim 13 (depends on 8) The method according to claim 8, wherein providing associated keywords for each event description comprises: aggregating all adjectives and nouns together in the event description. ### Claim 14 A method for job profile generation on a computer, the method comprising: receiving employee intranet usage data related to each employee of a company, wherein the intranet usage data is at least one member selected from a date performed, an event description, and an intranet link associated with an event; storing the received employee intranet usage data in a database; identifying a portion of the stored employee intranet usage data related to each employee of the company which is associated with a first employee; utilizing machine learning to provide associated tags for each event description and each intranet link in the portion of the stored employee intranet usage data; providing associated keywords for each event description, each intranet link and each associated tag in the portion of the stored employee intranet usage data; transmitting the portion of the stored employee intranet usage data, the associated tags and the associated keywords, to a recommender system, wherein the recommender system identifies one or more required job skills of the first employee, based on the transmitted portion; and generating a job profile based on the one or more identified required job skills of the first employee. ### Claim 15 (depends on 14) The method according to claim 14, wherein the stored employee intranet usage data is at least one member selected from a group consisting of a date performed, an event description, and an intranet link associated with an event. ### Claim 16 (depends on 14) The method according to claim 14, wherein the stored employee intranet usage data is at least one member selected from a group consisting of a date performed, an event description, and an intranet link associated with an event, wherein a tag is assigned to the event description from the event of the stored employee intranet usage data, and wherein the one or more required skills are identified by ranking a random list of one or more associated tags, and wherein a best list is identified from the random list, and wherein the best list has a highest probability of matching a required job skill of the former employee. ### Claim 17 (depends on 14) The method according to claim 14, wherein identifying the portion of the stored employee intranet usage data further comprises: removing extraneous information common to a plurality of employees. ### Claim 18 (depends on 14) The method according to claim 14, wherein generating the job profile further comprises: formatting the one or more identified required job skills into a recruitment template. ### Claim 19 (depends on 14) The method according to claim 14, further compromising: posting the generated job profile on a recruitment web site. ### Claim 20 (depends on 14) The method according to claim 14, wherein providing associated keywords for each event description comprises: aggregating all adjectives and nouns together in the event description.