Targeted prioritization within a network based on user-defined factors and success rates

Patent metadata

Field	Value
Publication number	US-11783243-B2
Application number	US-201715709495-A
Country	US
Kind code	B2
Filing date	Sep 20, 2017
Priority date	Sep 20, 2017
Publication date	Oct 10, 2023
Grant date	Oct 10, 2023

Abstract

Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: establishing a relationship graph for a certain user, the relationship graph having a primary node that specifies the certain user and a plurality of lower order nodes, wherein the primary node and at least one lower order node of the plurality of lower order nodes is connected to at least one other node by an edge so that there are defined a plurality of edges; generating a prioritized list of individuals to provide assistance to the certain user in respect to the certain task based on populated edge weight scores for edges of the relationship graph; and providing one or more output based on the prioritized list.

First claim

What is claimed is:

1. A method comprising:
initiating a request to provide assistance to a certain user, wherein the method includes in response to the initiating subjecting text based data to natural language processing to extract a topic classifier that specifies a certain task topic for a certain task to be performed for the certain user;
in response to the initiating, examining social media data to identify socially connected individuals who are socially connected to the certain user;
establishing, based on identified socially connected individuals who are socially connected to the certain as identified by the examining, a relationship graph for the certain user, the relationship graph having a primary node that specifies the certain user and a plurality of lower order nodes specifying individuals of the identified socially connected individuals of the certain user as identified by the examining, wherein the primary node and at least one lower order node of the plurality of lower order nodes is connected to at least one other node by an edge so that there are defined a plurality of edges, wherein one or more lower order node of the plurality of lower order nodes specifies an individual socially connected to the certain user;
wherein the establishing includes populating for edges of the plurality of edges an edge weight score indicating an ability of an individual specified in a lower order node to provide assistance to the certain user in respect to the certain task, wherein the populating includes using historical task data of at least one connected individual of the identified socially connected individuals stored in a data repository, the historical task data specifying an attribute of performance by the at least one connected individual with respect to an historical task having the topic classifier that specifies the certain task topic;
generating a prioritized list of individuals to provide assistance to the certain user in respect to the certain task based on the populated edge weight scores for the edges of the relationship graph having the primary node that specifies the certain user, which edges indicate an ability of an individual specified in a lower order node to provide assistance to the certain user in respect to the certain task; and
providing one or more output based on the prioritized list, wherein the method includes monitoring performance, using one or more sensor, of the certain task by a selected individual selected from the prioritized list of individuals to provide assistance to the certain user, wherein the method includes, in response to the monitoring, storing result data in the data repository specifying a result of the selected individual performing the certain task, wherein the method includes updating the relationship graph using the result data to provide an updated relationship graph, and generating, using the updated relationship graph, a second prioritized list of individuals to provide assistance to the certain user in respect to a subsequent task.

2. The method of claim 1 , wherein the method includes providing a user interface that allows the user to define factors for use in performing the populating for edges of the plurality of edges an edge weight score.

3. The method of claim 1 , wherein the one or more output is a communication to initiate a machine process, the machine process including examining data provided by one or more sensor to monitor performance of the certain task.

4. The method of claim 1 , wherein the populating includes examining historical task information respecting one or more previously performed task, wherein the populating for edges of the plurality of edges an edge weight score includes applying a set of weighted factors, wherein one of the factors is a success factor, and wherein the examining historical task information respecting one or more previously performed task includes for determination of the success factor examining past success data for an individual in the performance of a prior task in common with the certain task.

5. The method of claim 1 , wherein the populating includes examining historical task information respecting one or more previously performed task, wherein the populating for edges of the plurality of edges an edge weight score includes applying a set of weighted factors, wherein the set of weighted factors includes a relationship factor that specifies a relationship of the certain user and individual socially connected to the certain user, an equipment factor based on equipment in possession by the individual socially connected to the certain user, an education factor level of the individual socially connected to the certain user, a location factor based on a location of the individual socially connected to the certain user, a calendar factor that specifies calendar availability of the individual socially connected to the certain user, and a success factor based on success information of the individual socially connected to the certain user in the performance of one or more prior tasks.

6. The method of claim 1 , wherein the populating includes examining historical task information respecting one or more previously performed task, wherein the populating for edges of the plurality of edges an edge weight score includes identifying a task associated to the certain task, and wherein the examining historical task information respecting one or more previously performed task includes for performing the identifying examining success profiles for a set of individuals in respect to a plurality of prior performed tasks to determine a task having a success profile matching a success profile for the certain task.

7. The method of claim 1 , wherein the populating includes examining historical task information respecting one or more previously performed task, wherein the populating for edges of the plurality of edges an edge weight score includes applying a set of one or more factor, and wherein the examining historical task information respecting one or more previously performed task includes for performing the applying identifying a successfully performed one or more task in common with the certain task and performing the applying based on at least one factor resulting in selection of one or more task assisting individual in the successfully performed one or more task.

8. The method of claim 1 , wherein the populating includes establishing a relationship graph for each of first through Nth users, the first through Nth users being other than the certain user, wherein the relationship graph for each of the first through Nth users includes a primary node that connects to a set of secondary nodes by a set of edges, the primary node specifying a user of the first through Nth user and the set of secondary nodes specifying a set of individuals socially connected to the user specified by the primary node, the set of edges indicating an ability of respective individuals of the set of individuals to provide assistance to the user specified by the primary node in respect to the certain task, aggregating relationship graphs for each of the first through Nth users to provide an aggregated relationship graph; and processing edge weights of the aggregated relationship graph for determining an edge weight of the edge weight scores.

9. The method of claim 1 , wherein the method includes activating a natural language processing (NLP) process for examining newsfeed data and based on examining automatically performing the establishing, the generating and the providing.

10. The method of claim 1 , wherein the method includes evaluating calendar information of the certain user using natural language processing (NLP) processing to determine a topic of a task of the calendar of

Assignees

• IBM

Inventors

• Lu Cindy Han
• Mandhan Ishita
• Tran Thai Quoc
• Van Eck Paul

Classifications

• G06Q10/063112 Primary

  Skill-based matching of a person or a group to a task · CPC title

• G06F21/6218

  to a system of files or objects, e.g. local or distributed file system or database · CPC title

• G06F16/24578

  using ranking · CPC title

• G06F2221/2111

  Location-sensitive, e.g. geographical location, GPS · CPC title

• G06Q10/06

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title