| CPC G06Q 10/063116 (2013.01) [G06Q 10/063112 (2013.01)] | 15 Claims |
|
1. A system for scheduling and managing human resources, comprising:
a processor;
a memory coupled to the processor, the memory storing instructions executable by the processor to implement a human resource management module, the human resource management module comprising:
a registration and tracking block, wherein the registration and tracking block tracks a first shift for at least one first empty spot associated with the human resources in an organization and triggers an action when the at least one first empty spot is detected, wherein the action is defined as a triggered action, wherein the human resources comprise at least one of an employee, a contractor and a volunteer, wherein the triggered action includes:
compile a list of human resources based on at least one factor, wherein the at least one factor comprises admin-identified criteria and preferences; and
transmit, via a network interface coupled to the processor, a notification to a mobile device associated with each of the human resources on the list, the notification prompting the human resources to confirm attendance for the first shift through a user interface of the mobile device, and receive, via the network interface, confirmation data from the mobile device to update the schedule block in real-time, wherein the action is triggered when the at least one first empty spot is detected, it is determined, based on at least one parameter, that not enough human resources will sign up for the at least one first empty spot, or that an admin has not filled the at least one first empty spot;
upon determining that the registration and tracking block identifies a difficulty in scheduling the at least one first empty spot on a regular basis, the registration and tracking block provides recommendations to the admin to hire additional human resources;
a schedule block configured to facilitate self-scheduling allowing the human resources to craft their own schedule one shift at a time, the schedule block configured to display one or more filtered shifts to the human resources based on selectivity, wherein the selectivity is modifiable based on situation, wherein the schedule block determines that the selectivity is undesirable, and the schedule block opens shift availability to every human resource who meets a minimum criterion as defined and specified by the admin;
a rating block configured to determine rating of each human resource by the admin based on one or more data points;
an intelligence block configured to predict one or more instances, wherein the one or more instances include client event density and roster utilization, wherein the intelligence block uses admin feedback and evaluation to train an artificial intelligence system, and wherein the intelligence block determines, in conjunction with an artificial intelligence system, optimizes the scheduling process by:
determining a likelihood of the human resource's specific performance occurring during a future event based on historical analytics data; and
dynamically adjusting the selectivity of the schedule block to prioritize human resources with a predicted performance likelihood above a threshold, thereby reducing scheduling conflicts and improving roster utilization efficiency;
the intelligence block configured to alert the admin by calling attention to the at least one first empty spot that is important to fill with the human resources; and
the intelligence block tracks at least one of: a worker's no-show tendencies for the first shift when an organization carpool is unavailable, if a worker has no showed lately, admin sentiment, and performance issues desired by an organization using the artificial intelligence;
wherein the human resource management module is configured for predictive analysis, using the intelligence block and the artificial intelligence system executed on the processor by: processing: a plurality of datasets and a historical analytics dataset stored in the memory, wherein the plurality of datasets includes a rating dataset, a qualitative dataset, and an engagement dataset;
creating a score for each criterion by applying a machine-learning model to combine performance data of the human resources, wherein the machine-learning model is trained to weigh the datasets based on admin feedback; and
projecting the score using a time-series analysis algorithm to identify recent trends in the human resource's behavior, thereby enabling the schedule block to dynamically adjust shift assignments to minimize no-show risks and optimize the organization's current open spots.
|