Browse Prior Art Database

Task Based Struggle Detection and Team Based Correction Management Disclosure Number: IPCOM000254583D
Publication Date: 2018-Jul-12
Document File: 6 page(s) / 196K

Publishing Venue

The Prior Art Database

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 36% of the total text.


Task Based Struggle Detection and Team Based Correction Management When performing any activity, people may experience difficulty while executing one or more steps. The difficulty may arise due to lack of information, poor connectivity, inefficient or nonworking mode of communication, low skill levels, emotional state, etc. At the same time, contextual analysis of spoken and written content can be analyzed to identify the difficulties in various stages. In a given project, for example, group members might have varying strengths and weaknesses for different aspects of the job. Not everyone is good at every activity of the work to be executed; people perform at different effectiveness levels in each of the associated activities. Based on the task, some people will struggle to perform. For example, an employee may not be good at oral presentations. A cognitive system can identify struggling patterns by recognizing user behavior to identify indicators such as stammering, referring multiple reference links, lags in response time and/or asking another person etc. The core novel idea is a for a system that interacts with a user that is working on a task that involves a series of activities. The system uses a Task Tracking Portal software to identify the activities with which the user struggles. It dynamically tracks the user’s performance (e.g., cadence and rhythm of actions). If the system detects that the user is having difficulty, then it automatically and in real time (i.e., live) provides feedback to the user and offers assistance in the form of alternate methods of performance. The system analyzes the historical behavior pattern(s) of the user(s) in scope while performing different activities, and then accordingly, using machine learning methods, becomes able to identify what type of activity is difficult for a user. When any work is assigned to a user or user wants to perform any work, the intelligent system identifies the activities with which the user might have any problem. Using machine learning, the system identifies alternative methods for completing different types of activities with which the user struggles. It might suggest that the user ask another person for assistance, refer to a resource, etc. Novel components and features include:

 Temporal based (time) delayed interaction(s) with a user based on a certain amount of task or application interaction within the task tracking portal

 Method to evaluate all the tasks that the user works through a common portal approach, and then suggest and confirm multiple types of user interaction changes based on defined time-based temporal triggers as detected through a user's struggle


 User-configured variable timing controls and triggers  Machine learning for historical user-based utilization patterns of data within time-

based user interface(s) pertaining to task related items The system references seven learning styles:

 Visual: preference for pictures, images, diagrams, colors...