Unlock instant, AI-driven research and patent intelligence for your innovation.

A data-driven method for online prediction of activity time series based on artificial intelligence

An artificial intelligence, data-driven technology, applied in data processing applications, electrical digital data processing, digital data information retrieval, etc., can solve problems such as few and inconsistencies

Active Publication Date: 2022-03-08
探循智能科技(杭州)有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In summary, there are not many researches on the online prediction of activity time series. Most of the existing research is based on iterative prediction of the next activity to achieve sequence prediction, and the deviation of the intermediate prediction will cause the entire sequence to be inconsistent with the real sequence.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A data-driven method for online prediction of activity time series based on artificial intelligence
  • A data-driven method for online prediction of activity time series based on artificial intelligence
  • A data-driven method for online prediction of activity time series based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0084] The steps in this embodiment are the same as those described above in the specific implementation mode, and will not be repeated here. Part of the implementation process and results are shown below:

[0085] The original log files used in this embodiment are logs generated from four real business processes obtained from the 4TU research data center: Helpdesk, Sepsis, BPIC2013Incidents, BPIC2012W, BPIC2012O and BPIC2012W without duplication. Among them, the Helpdesk log involves the ticket management process of the help desk of an Italian software company. There are 4,580 instance data in total, including 21,349 events and 14 activities. The longest instance event number is 15, and the shortest instance event number is 1 instance. The Sepsis log records the events of sepsis cases through the hospital's ERP system, the log has about 1000 instances, the number of events is about 15000, and the number of activities is 16. The BPIC2013 dataset is an event log from Volvo IT ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an online prediction method of activity time series based on artificial intelligence driven by data. Based on the event log data, the method first uses the trajectory replay technology to simulate the execution of the trajectory in the real context, that is, to obtain the behavioral context information; after that, the long short-term memory neural network is used to predict the future execution of the online instance, that is, the data context information; Finally, the method fuses the above two kinds of contextual information to realize the temporal prediction of future activities of online process instances. This method has high prediction accuracy and can provide decision support for business process management, especially process exception management.

Description

technical field [0001] The invention relates to the field of business process monitoring, in particular to an artificial intelligence-based online activity timing prediction method driven by data. Background technique [0002] A business process is a series of activities completed by different people to achieve a specific value goal. As an application of data mining in business process management, business process mining aims to discover, model, monitor and improve business processes by analyzing event logs of business processes. In recent years, the focus of business process mining is no longer limited to providing offline analysis of event logs, but to provide online support for business process optimization, that is, to achieve predictive business process monitoring (Predictive Process Monitoring, PPM). [0003] Accurately predicting the timing of the remaining activities of an executing process instance is the most intuitive problem in PPM research, which is conducive t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/06G06F16/2458
CPCG06Q10/0633G06F16/2465
Inventor 孙笑笑叶春毅应钰柯俞东进
Owner 探循智能科技(杭州)有限公司