Agent aptitude prediction
In one or more embodiments, one or more methods, processes, and/or systems may receive data associated with effective completion of tasks by agents and determine a positive correlation within the data between first particular feature values of feature vectors associated with the tasks and second particular feature values of feature vectors associated with the agents. A first agent associated with a feature vector that matches, within a first threshold, the second particular feature values may be selected, and a probability that the first agent will effectively complete a first task based on a feature vector associated with the first task matching, within a second threshold, the first particular feature values may be determined.
1. A system, comprising: one or more processors; a memory that is communicatively coupled to the one or more processors and stores instructions executable by the one or more processors; wherein as the one or more processors execute the instructions, the system:
receives data associated with completion of a plurality of tasks by a plurality of agents;
determines a positive correlation within the data between first particular feature values of a plurality of feature vectors associated with the plurality of tasks and second particular feature values of a plurality of feature vectors associated with the plurality of agents, the first particular feature values characterizing the plurality of tasks and the second particular feature values characterizing the plurality of agents;
determines an aptitude of each agent of the plurality of agents towards one or more tasks of the plurality of tasks that each agent has completed in a manner specified by a work distributor based on the positive correlation between the first particular feature values of a plurality of feature vectors associated with the one or more tasks and the second particular feature values of the feature vector associated with each agent;
determines, using a machine-learning model, a probability that a designated agent will complete a designated task in the manner specified by the work distributor, the probability being determined based on the determined aptitude of the designated agent and a feature vector associated with the designated task matching the first particular feature values associated with the tasks that the designated agent has completed in the manner specified by the work distributor and a feature vector associated with the designated agent matching the second particular feature values; and
provides identification information of the designated agent for display in association with an identification for the designated task and the determined probability that the designated agent will complete the designated task in the manner specified by the work distributor.
2. The system of claim 1 , wherein the system further:
determines a confusion matrix for the designated agent with respect to the designated task that assesses the probability that the designated agent will complete the designated task in the manner specified by the work distributor based on historical completion of other tasks, wherein the other tasks are associated with feature vectors that match the first particular feature values.
3. The system of claim 1 , wherein the plurality of feature vectors associated with the plurality of tasks assess a set of attribute requirements for completing each task of the plurality of tasks.
4. The system of claim 1 , wherein the plurality of feature vectors assess a set of attributes of each agent of the plurality of agents.
5. The system of claim 1 , wherein when the system determines the positive correlation, the system:
assesses a level of effectiveness with which each of the plurality of tasks was completed;
selects a first set of the plurality of tasks that was most effectively completed;
determines similar feature values among agents that completed each task in the first set; and
determines similar feature values among tasks in the first set.
6. The system of claim 1 , wherein when the system determines, using the machine-learning model, the probability that the designated agent will complete the designated task in the manner specified by the work distributor, the system derives a scalar product between the feature vector associated with the designated agent corresponding to the second particular feature values and a feature vector associated with a second agent corresponding to the second particular feature values.
7. The system of claim 1 , wherein the plurality of tasks include requests for a particular type of product.
8. The system of claim 1 , wherein the plurality of tasks include requests to identify a specific type of information within a document or file.
9. The system of claim 1 , wherein the plurality of agents comprises computer modules comprising software instructions for completing a specific task.
10. The system of claim 1 , wherein the system further:
receives a specification of a desired manner of completion of the designated task from the work distributor, wherein the desired manner of completion of the designated task includes prioritization one or more of:
fast return of results from an agent to which the designated task is assigned;
accurate results from the agent to which the designated task is assigned; or
correct output associated with the designated task.
11. A method, comprising:
by one or more processors, receiving data associated with effective completion of a plurality of tasks by a plurality of agents;
by the one or more processors, determining a positive correlation within the data between first particular feature values of a plurality of feature vectors associated with the plurality of tasks and second particular feature values of a plurality of feature vectors associated with the plurality of agents, the first particular feature values characterizing the plurality of tasks and the second particular feature values characterizing the plurality of agents;
by the one or more processors, determining an aptitude of each agent of the plurality of agents towards one or more tasks of the plurality of tasks that each agent has completed in a manner specified by a work distributor based on the positive correlation between the first particular feature values of a plurality of feature vectors associated with the one or more tasks and the second particular feature values of the feature vector associated with each agent;
by the one or more processors, determining, using a machine-learning model, a probability that a designated agent will complete a designated task in the manner specified by the work distributor, the probability being determined based on the determined aptitude of the designated agent and a feature vector associated with the designated task matching the first particular feature values associated with the tasks that the designated agent has completed in the manner specified by the work distributor and a feature vector associated with the designated agent matching the second particular feature values; and
by the one or more processors, providing identification information of the designated agent for display in association with an identification for the designated task and the determined probability that the designated agent will complete the designated task in the manner specified by the work distributor.
12. The method of claim 11 , further comprising:
by the one or more processors, determining a confusion matrix for the designated agent with respect to the designated task that assesses the probability that the designated agent will complete the designated task in the manner specified by the work distributor based on historical completion of other tasks, wherein the other tasks are associated with feature vectors that match the first particular feature values.
13. The method of claim 11 , wherein the plurality of feature vectors associated with the plurality of tasks assess a set of attribute requirements for completing each task of the plurality of tasks.
14. The method of claim 11 , wherein the plurality of feature vectors associated with the plurality of agents assess a set of attributes of each agent of the plurality of agents.
15. The method of claim 11 , wherein the determining the positive correlation includes:
assessing a level of effectiveness with which each of the plurality of tasks was completed;
selecting a first set of the plurality of tasks that was completed;
determining similar feature values among agents that completed each task in the first set; and
determining similar feature values among tasks in the first set.
16. The method of claim 11 , wherein the determining, using the machine-learning model, the probability that the designated agent will complete the designated task in the manner specified by the work distributor includes deriving a scalar product between the feature vector associated with the designated agent corresponding to the second particular feature values and a feature vector associated with a second agent corresponding to the second particular feature values.
17. The method of claim 11 , wherein the plurality of tasks include requests for a particular type of product.
18. The method of claim 11 , wherein the plurality of tasks include requests to identify a specific type of information within a document or file.
19. The method of claim 11 , wherein the plurality of agents comprises computer modules comprising software instructions for completing a specific task.
20. One or more computer-readable non-transitory storage media comprising instructions executable by one or more processors of a system, wherein as the one or more processors execute the instructions, the system:
receives data associated with effective completion of a plurality of tasks by a plurality of agents;
determines a positive correlation within the data between first particular feature values of a plurality of feature vectors associated with the plurality of tasks and second particular feature values of a plurality of feature vectors associated with the plurality of agents, the first particular feature values characterizing the plurality of tasks and the second particular feature values characterizing the plurality of agents;
determines an aptitude of each agent of the plurality of agents towards one or more tasks of the plurality of tasks that each agent has completed in a manner specified by a work distributor based on the positive correlation between the first particular feature values of a plurality of feature vectors associated with the one or more tasks and the second particular feature values of the feature vector associated with each agent;
determines, using a machine-learning model, a probability that a designated agent will complete a designated task in the manner specified by the work distributor, the probability being determined based on the determined aptitude of the designated agent and a feature vector associated with the designated task matching the first particular feature values associated with the tasks that the designated agent has completed in the manner specified by the work distributor and a feature vector associated with the designated agent matching the second particular feature values; and
provides identification information of the designated agent for display in association with an identification for the designated task and the determined probability that the designated agent will complete the designated task in the manner specified by the work distributor.