Accenture Global Solutions Limited

Yikai Wu

Fang Hou

Xiaopei Cheng

Hui Shen

Guo Ma

Bin Xie

Kexin Ren

Guanyi Sun

Xinyong Min

Sifei Ding

An iterative classifier for unsegmented electronic documents is based on machine learning algorithms. The textual strings in the electronic document are segmented using a composite dictionary that combines a conventional dictionary and an adaptive dictionary developed based on the context and nature of the electronic document. The classifier is built using a corpus of training and testing samples automatically extracted from the electronic document by detecting signatures for a set of pre-established classes for the textual strings. The classifier is further iteratively improved by automatically expanding the corpus of training and testing samples in real-time when textual strings in new electronic documents are processed and classified.

Automatic extraction of a training corpus for a data classifier based on machine learning algorithms

This disclosure relates to industrial data services, data modeling and applications for controlling an industrial operation. In one implementation, a platform is disclosed for allocating a data modeling request to a collaborative group of experts based on a two-dimensional data modeling flow data structure and a multilayer resource allocation graph to obtain a data model for controlling the industrial operation. The two-dimensional data modeling flow data structure and the multilayer resource allocation graph are established from an industrial graph knowledgebase using various data analytics and machine learning techniques.

Industrial data service, data modeling, and data application platform

A customized industrial graph knowledge base for an industrial operation includes a graph database storing nodes of multiple dimensions predefined according to the nature and characteristics of the industrial operation. The nodes are extracted from baseline, domain-specific, and implementation specific industrial knowledge data sources using various analytics for structured and unstructured data. The customized industrial graph knowledge base further includes edges representing relationships between nodes that are either inter-dimensional or intra-dimensional. The importance of each node to the industrial operation is further quantified using a graph model and is included in the graph database as a composite filtering parameter.

Multi-dimensional industrial knowledge graph

Direct measurement and simulation of real-time production rates of chemical products in complex chemical plants is complex. A predictive model developed based on machine learning algorithms using historical sensor data and production data provides accurate real-time prediction of production rates of chemical products in chemical plants. An optimization model based on machine learning algorithms using clustered historical sensor data and production data provides optimal values for controllable parameters for production maximization.

Growing community of inventors

Beijing, China

Yikai Wu