Accenture Global Solutions Limited

Accenture Global Services Gmbh

Xiaopei Cheng

Fang Hou

Yan Gao

Guo Ma

Yikai Wu

Hui Shen

Zhihui Yang

Qin Zhou

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.

Real-time industrial plant production prediction and operation optimization

A real-time data management system for accessing data in a power grid that controls a transmission delay of real-time data delivered via a real-time bus, and delivers real-time data in a power grid. A unified data model covering various organizations and various data resource may be included. Multi-bus collaboration and bus performance optimization approaches may be used to improve efficiency and performance of the buses. An event integration and complex event process component may be included to provide status of the power grid. A high volume of real-time data and events may be managed to provide data transmission with a low latency, provide flexible extension of the number of data clusters and the number of databases to ensure high volume data storage, and achieve a high speed and transparent data access. Additionally, rapid design and development of analytical applications, and the near real-time enterprise decision-making may be enabled.

Real-time data management for a power grid

A method and system for analyzing equipment degradation for maintaining the equipment are provided. The method and system receive and store equipment and sensor data associated with operational equipment, generate a display signal to display a relationship analysis window, a residual error window, a performance condition window, and a maintenance trigger window, and evaluate a coordinated relationship between the equipment sensor data and the environmental data, determine residual errors and determine a Historical Health Condition Index (HHCI) for the operational equipment and generate a Future Health Condition Index (FHCI) from the HHCI, and generate an equipment maintenance trigger for the operational equipment by establishing a trigger threshold for maintenance.

Analyzing equipment degradation for maintaining equipment

A real-time data management system, a system, method, apparatus and tangible computer readable medium for accessing data in a power grid are described for controlling a transmission delay of real-time data delivered via a real-time bus, and for delivering real-time data in a power grid. A unified data model covering various organizations and various data resource is described. Further, a management scheme for clustered data is described to provide a transparent and high speed data access. The solutions described may efficiently manage the high volume of real-time data and events, provide data transmission with a low latency, provide flexible extension of both the number of data clusters and the number of databases to ensure high volume data storage, and achieve a high speed and transparent data access. Additionally, rapid design and development of analytical applications, and the near real-time enterprise decision-making business may be enabled.

Growing community of inventors

Beijing, China

Xiaopei Cheng