Chat Task Allocation via Vector Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In group chat channels, users face inefficiencies in finding and assigning tasks to suitable individuals due to the need for manual identification based on multiple factors like skills, engagement ability, and availability, which can be time-consuming and sub-optimal.
Innovation Solution
A computer-implemented method that uses action to vector modeling to assign tasks by parsing chat text into keywords, determining desired actions, and calculating coefficients for users' abilities and availability, selecting the most suitable user based on a set of vectors including skills, engagement, location, and device, and automatically requesting them to perform the task.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual identification of suitable users is performed in chat channels, then task assignment can be made, but it consumes excessive time and may result in sub-optimal assignments
Solution Approach 1:
The patent introduces an automated intermediary system that acts as a mediator between task requesters and suitable users. This system monitors chat channels, parses messages to identify tasks, evaluates user engagement and availability, and automatically assigns tasks. The intermediary eliminates the time-consuming manual search process while ensuring optimal task allocation based on multiple user parameters.
Solution Approach 2:
The patent replaces the manual mechanical process of user identification and task assignment with an automated computational system. The system uses text parsing, vector modeling, and coefficient calculation to automatically identify suitable users and assign tasks, substituting human manual evaluation with algorithmic processing that is both faster and more accurate.
2Reliability
If multiple parameters are considered for user selection, then assignment quality improves, but system complexity increases
Solution Approach 1:
The patent segments the complex evaluation process into distinct components: text parsing to identify tasks, vector modeling to represent user parameters, coefficient calculation to quantify engagement and availability, and ranking to select the best match. This segmentation allows the system to handle multiple parameters systematically without becoming unmanageably complex.
Solution Approach 2:
The patent transforms multiple qualitative user parameters (skills, engagement, availability) into quantitative coefficients through vector modeling. By converting diverse parameters into a standardized numerical format, the system can efficiently compare and evaluate users across multiple dimensions without the complexity of handling heterogeneous data types.
Data Source
AI summary
The illustrative embodiments provide for a computer-implemented method of allocating, in real time, actions to individuals based on text monitored in chat channels executing on different computers in a computer network. A desired action mentioned in the chat session is detected. Action to vector modeling is then performed by assigning a corresponding coefficient for the action to ones of a plurality of different vectors for ones of a plurality of different users. A corresponding set of coefficients is combined for all users. A highest coefficient is selected, corresponding to a second user from among the ones of the plurality of different users. A message is sent to the second user requesting the second user to perform the action.