# US 11,443,256 B2 · Real-time matching and smart recommendations for tasks and experts > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,256 B2 - Document ID: US11443256B2 - Status: Granted - Kind: B2 - Application number: 16/451,959 - Filed: 2019-06-25 - Published: 2020-12-31 - Granted: 2022-09-13 - Earliest claimed: 2019-06-25 - Assignees: Sap SE - Applicants: Sap SE - Inventors: Oren Haze - Web page: https://patentgrep.com/patent/US11443256B2 ## CPC - G06Q 10/063112: {Skill-based matching of a person or a group to a task} - G06N 5/04: Inference or reasoning models - G06N 20/00: Machine learning - G06Q 50/2057: {Career enhancement or continuing education service} - G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks - 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 - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract User information for a particular user is accessed. Expert information for experts and training that is available in an organization of the particular user is accessed. One or more pattern matches between the user information and the expert information are determined. One or more expert recommendations are generated based on the one or more pattern matches and provided. ## Claims ### Claim 1 A computer-implemented method, comprising: accessing, by one or more processors, user information for a particular user; accessing, by the one or more processors, expert information for experts and training that is available in an organization of the particular user; determining, by the one or more processors, by using a plurality of pattern recognition algorithms, a plurality of pattern matches defining matches between the user information and a predefined pattern relating to the expert information, wherein each pattern match is weighed using an adjustable weight corresponding to a type of pattern recognition algorithm from the plurality of pattern recognition algorithms; generating, by the one or more processors, by using a machine learning engine, one or more expert recommendations based on the plurality of pattern matches and past user feedback; providing, by the one or more processors, in real time, the one or more expert recommendations corresponding to the training that is available in the organization; receiving, by the one or more processors, user feedback associated with the one or more expert recommendations corresponding to the training that is available in the organization; and updating, by the one or more processors, the machine learning engine based on the user feedback to tailor future expert recommendations. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the user information comprises context information, organizational data for the particular user, demographic data, expert or training usage information, a user role for the particular user, project participation data, user profile information, user activity data, user preferences, a current location of the particular user, or a current time at which a recommendation can be presented to the particular user. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the expert information comprises one or more of an expert category, expert description, expert prerequisite information, expert functionality, expert availability, expert cost, expert preferences, an expert profile, and an expert location. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein at least one pattern match is a match between the user information and a predefined pattern relating to expert data. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein at least one pattern match is a match between the expert information and a predefined pattern relating to the user information. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the one or more expert recommendations are generated in response to a trigger. ### Claim 7 (depends on 6) The computer-implemented method of claim 6, wherein the trigger comprises one of a change in the user information, a change in the expert information, a change in training information, or a start of a periodic interval at which to automatically process the user information, the expert information, and the training information. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, further comprising: storing the plurality of pattern matches. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, further comprising: receiving feedback related to one or more provided expert recommendations; and adjusting a pattern recognition engine to improve generation of future expert recommendations. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein determining the plurality of pattern matches comprises determining an expert to which the particular user has access. ### Claim 11 (depends on 1) The computer-implemented method of claim 1, wherein determining the plurality of pattern matches comprises determining an expert that matches historical expert usage for the particular user. ### Claim 12 (depends on 1) The computer-implemented method of claim 1, wherein determining the plurality of pattern matches comprises determining an expert that matches a requirement of the particular user. ### Claim 13 (depends on 1) The computer-implemented method of claim 1, wherein determining the plurality of pattern matches comprises: determining an expert that matches some of the user information but lacks knowledge or training to perform a specific task for the particular user and is trainable to obtain the knowledge or the training. ### Claim 14 (depends on 1) The computer-implemented method of claim 1, further comprising: assessing a payment for the one or more expert recommendations if a particular expert recommendation of the one or more expert recommendations is followed by the organization. ### Claim 15 A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising: accessing user information for a particular user; accessing expert information for experts and training that is available in an organization of the particular user; determining, by using a plurality of pattern recognition algorithms, a plurality of pattern matches defining matches between the user information and a predefined pattern relating to the expert information, wherein each pattern match is weighed using an adjustable weight corresponding to a type of pattern recognition algorithm from the plurality of pattern recognition algorithms; generating, by using a machine learning engine, one or more expert recommendations based on the plurality of pattern matches and past user feedback; providing, in real time, the one or more expert recommendations corresponding to the training that is available in the organization; receiving user feedback associated with the one or more expert recommendations corresponding to the training that is available in the organization; and updating the machine learning engine based on the user feedback to tailor future expert recommendations. ### Claim 16 (depends on 15) The non-transitory, computer-readable medium of claim 15, wherein the user information comprises context information, organizational data for the particular user, demographic data, expert or training usage information, a user role for the particular user, project participation data, user profile information, user activity data, user preferences, a current location of the particular user, or a current time at which a recommendation can be presented to the particular user. ### Claim 17 (depends on 15) The non-transitory, computer-readable medium of claim 15, wherein the expert information comprises one or more of an expert category, expert description, expert prerequisite information, expert functionality, expert availability, expert cost, expert preferences, an expert profile, and an expert location. ### Claim 18 A computer-implemented system, comprising: one or more computers; and one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising: accessing user information for a particular user; accessing expert information for experts and training that is available in an organization of the particular user; determining, by using a plurality of pattern recognition algorithms, a plurality of pattern matches defining matches between the user information and a predefined pattern relating to the expert information, wherein each pattern match is weighed using an adjustable weight corresponding to a type of pattern recognition algorithm from the plurality of pattern recognition algorithms; generating, by using a machine learning engine, one or more expert recommendations based on the plurality of pattern matches and past user feedback; providing, in real time, the one or more expert recommendations corresponding to the training that is available in the organization; receiving user feedback associated with the one or more expert recommendations corresponding to the training that is available in the organization; and updating the machine learning engine based on the user feedback to tailor future expert recommendations. ### Claim 19 (depends on 18) The computer-implemented system of claim 18, wherein the user information comprises context information, organizational data for the particular user, demographic data, expert or training usage information, a user role for the particular user, project participation data, user profile information, user activity data, user preferences, a current location of the particular user, or a current time at which a recommendation can be presented to the particular user. ### Claim 20 (depends on 18) The computer-implemented system of claim 18, wherein the expert information comprises one or more of an expert category, expert description, expert prerequisite information, expert functionality, expert availability, expert cost, expert preferences, an expert profile, and an expert location.