According to GlobalData’s company profile on Automatic Data Processing, Digital lending was a key innovation area identified from patents. Automatic Data Processing's grant share as of September 2023 was 59%. Grant share is based on the ratio of number of grants to total number of patents.

Managing time record events based on geolocation and machine learning

A recently filed patent (Publication Number: US20230316234A1) describes a system and method for predicting events based on time record events and geolocations using machine learning models. The system includes one or more processors coupled with memory to perform various tasks.

The system utilizes a first machine learning model trained using time record events corresponding to geolocations to predict events based on a sequence of these time record events. It determines the probability for the timing of each event based on the sequence of time record events and identifies a geolocation associated with a profile using a client device. The system then selects an event based on the geolocation and timing using the first machine learning model and displays it on the client device associated with the profile. Feedback regarding the event is received from the client device, and the first machine learning model is retrained based on the time record events and feedback using a second machine learning model.

The geolocations corresponding to the time record events can include clock-in or clock-out locations of multiple profiles associated with different client devices. The first machine learning model used in the system can be multimodal multi-task learning, and it can be trained for each profile associated with client devices. The system can also determine the probability for the timing of events based on the sequence of time record events and the profile.

The feedback received from the client device can include changes in geolocation or timing. Based on this feedback, the system can establish the event as a first event and select a second event from the predicted events using the second machine learning model, considering the geolocation, timing, and the first event.

In addition to the system, the patent also describes a method for predicting events using the same machine learning models and a non-transitory computer-readable medium containing instructions to perform the tasks described above.

Overall, this patent presents a system and method for predicting events based on time record events and geolocations using machine learning models. The system aims to improve event prediction accuracy and provide personalized event recommendations based on user feedback.

To know more about GlobalData’s detailed insights on Automatic Data Processing, buy the report here.

Data Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

Be better informed