8 results about "Process mining" patented technology

The present disclosure provides a method for optimizing a cross-system permission approval path and related devices, the method comprising: obtaining a historical approval log, and constructing an approval process model based on a process mining algorithm; calculating a comprehensive risk value for a permission application based on a risk assessment algorithm; and generating an approval path based on the approval process model and the comprehensive risk value corresponding to the permission application. The present disclosure constructs a dynamic approval path through process mining technology, and combines a multi-dimensional risk quantification model to achieve dynamic generation of the approval process, thereby significantly improving the efficiency of permission approval.

The present invention relates to a computer-implemented method to generate a process mining repository for analyzing process data, wherein the process data is a multidimensional large-scale dataset which is extracted from at least one external computer system and transformed into a number of data models. The process mining repository represents a process workspace, in which the user may conduct process mining on a valid data model, i.e., explore process data, for instance, using a dynamic question and answer framework.

The application discloses a kind of multi-modal business process chart generation method, system and computer equipment, the method includes: obtaining recording data, screen recording data and event log containing user number and time stamp attribute;Segmented log representing a business step and its start time and end time are obtained by segmenting and merging event log;According to the start time, end time of each business step, extract the recording segment from recording data and generate word cloud, extract screen keyword from screen recording data and generate word cloud, extract operation sequence from the event log of business step, obtain the operation sequence, recording word cloud, screen word cloud representing business semantics;Based on the segmented and merged event log, apply process mining algorithm, and increase corresponding operation sequence, recording word cloud, screen word cloud, obtain multi-modal business process chart.The application can simultaneously process multi-modal data of recording, screen recording and event log, and generate multi-modal business process chart.

The present invention relates to a method to generate an object-centric data model for process mining from any external computer system for any process, wherein the method reduces the cognitive challenge for creating the object-centric data model through queries on raw process data stored in the external computer system.

We provide the system. [Solution] A means of analyzing business procedures by collecting business activity information, pre-processing it, and then applying process mining techniques, Based on the aforementioned analysis results, a means for formulating an artificial intelligence agent implementation plan, In accordance with the aforementioned implementation plan, means for appropriately integrating artificial intelligence agents into business procedures and performing data linkage, A means for monitoring the operational status of the deployed artificial intelligence agent and adjusting or updating the artificial intelligence agent as needed, A means of monitoring the operating status of production equipment, analyzing data in real time, and adjusting optimized business procedures, A means of immediately notifying the business administrator when an anomaly is detected, A system that includes this.

This application discloses a method, system, and storage medium for constructing a multi-view trace graph of an industrial process, belonging to the field of industrial process mining technology. The method includes: acquiring event logs of the industrial process; based on the event logs, mining and generating an initial behavioral relationship graph reflecting the behavioral dependencies between activities, wherein the initial behavioral relationship graph has activities as nodes and behavioral dependencies between activities as edges; extracting multi-view attribute information associated with activities from the event logs, wherein the multi-view attribute information includes at least one or more of resource attributes, scale attributes, product attributes, and personnel attributes; embedding and mapping the multi-view attribute information to generate a multi-view fusion feature vector for each activity node; combining the initial behavioral relationship graph with the multi-view fusion feature vector to construct a multi-view trace graph, which is used to uniformly represent the interaction between the execution structure and multi-view attributes of the industrial process.