Automatic process discovery from textual process documentations is highly desirable to reduce time and cost of Business Process Management (BPM) implementation in organizations. However, existing automatic process discovery approaches mainly focus on identifying activities out of the documentations. Deriving the structural relationships between activities, which is important in the whole process discovery scope, is still a challenge. In fact, a business process has latent semantic hierarchical structure which defines different levels of detail to reflect the complex business logic. Recent findings in neural machine learning area show that the meaningful linguistic structure can be induced by joint language modeling and structure learning. Inspired by these findings, we propose to retrieve the latent hierarchical structure present in the textual business process documents by building a neural network that leverages a novel recurrent architecture, Ordered Neurons LSTM (ON-LSTM), with process-level language model objective. We tested the proposed approach on data set of Process Description Documents (PDD) from our practical Robotic Process Automation (RPA) projects. Preliminary experiments showed promising results.

No abstract

Dialog Router is a general paradigm for human-bot symbiosis dialog systems to provide friendly customer care service. It is equipped with a multi-task learning model to automatically capture the underlying correlation between multiple related tasks, i.e. dialog classification and regression, and greatly reduce human labor work for system customization, which improves the accuracy of dialog transition. In addition, for learning the multi-task model, the training data and labels are easy to collect from human-to-human historical dialog logs, and the Dialog Router can be easily integrated into the majority of existing dialog systems by calling general APIs. We conduct experiments on real-world datasets for dialog classification and regression. The results show that our model achieves improvements on both tasks, which benefits the dialog transition application. The demo illustrates our method’s effectiveness in a real customer care service.

The paper proposes a method to simulate the mechanical behavior of compact rock considering hydromechanics by combining physical experiments and numerical analysis. The effectiveness of the constructed method is validated by the comparison between the numerical and physical results of triaxial shear experiments on sandstone in seepage conditions. Based on the validated method, the stability of underground water-sealed oil and gas storage caverns in surrounding compact sandstone during excavation is analyzed. The main findings are as follows: The intrinsic permeability of compact sandstone has a power function relationship with the porosity; the combination of the porous media elastic model and the modified Drucker–Prager plasticity model can preciously represent the mechanical properties of compact sandstone; the proposed method can accurately replicate the hydromechanical response of compact sandstone in seepage conditions; the effects of hydromechanical effects have significant impacts on the stability of surround compact sandstone during the excavation of underground water sealed oil and gas storage caverns, which causes the obvious increase in stress, deformation and plastic deformation zones of the surrounding compact sandstone and remarkable decrease in the stability safety factor.

No abstract