Intelligent response method and device based on module decomposition, medium and equipment

A module decomposition and intelligent technology, applied in the research field of intelligent decision-making of management information system, can solve the problems of input rigidity and limited scope of application, and achieve the effect of reducing management and decision-making costs, clear work scope, and high decision-making stability.

Active Publication Date: 2020-05-12
JINAN UNIVERSITY
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the rule-based expert system still has the problem of input rigidity, and the scope of application is very limited.

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
  • Intelligent response method and device based on module decomposition, medium and equipment
  • Intelligent response method and device based on module decomposition, medium and equipment
  • Intelligent response method and device based on module decomposition, medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] like image 3 As shown, this embodiment provides an intelligent response method based on module decomposition of an enterprise information system. Its purpose is to extract the business logic of its order approval module based on the sales automation information system of an enterprise, and learn it through deep neural network learning. The historical order approval processing case data is used to fit the judgment rules and experience of different experts, and is continuously optimized and improved, so as to realize that the processing plan of a customer order is gradually determined by the machine. Each step will be described in detail below in conjunction with the accompanying drawings.

[0063] (1) Based on the business logic and decision logic from the perspective of the department, divide the modules of the information system and determine the empirical manual decision-making module.

[0064] Enterprise information systems are usually established based on the need...

Embodiment 2

[0100] An embodiment of the present invention provides an intelligent response device based on module decomposition, including:

[0101] Module division module, which is used to decompose the information system into modules according to the business logic and decision logic of the enterprise, and determine the empirical manual decision-making module;

[0102] The data conversion module is used to extract business data from historical data, model the input and output data of the empirical manual decision-making module according to the business data, perform data conversion on the extracted business data, and use the converted data as a model the training set;

[0103] The network construction and model training module is used to use the output as a multi-category label, learn the case data of the training set through deep neural network learning, and continuously optimize and improve until convergence;

[0104] The application module is used to embed the trained deep neural ne...

Embodiment 3

[0107] This embodiment provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the intelligent response method based on module decomposition described in Embodiment 1 above .

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 intelligent response method and device based on module decomposition, a medium and equipment. The method comprises the following steps: performing modular decomposition on an information system according to business logic and decision logic of an enterprise, and determining an experiential artificial decision module; extracting business data from historical data, modeling input and output data of the experiential artificial decision module according to the business data, performing data conversion on the extracted business data, and taking the converted data as a training set of the model; taking the output as a multi-classification label, learning case data of the training set through a deep neural network learning mode, and continuously performing optimizationand improvement until convergence; and embedding the trained deep neural network into the empirical artificial decision module of an original information system, intelligently judging classification problems under new input, and making decision suggestions. According to the invention, the neural network can replace manual decision, the flexibility of an information system is realized, and the service response efficiency is improved.

Description

technical field [0001] The invention relates to the research field of intelligent decision-making of management information systems, in particular to an intelligent response method, device, medium and equipment based on module decomposition. Background technique [0002] The essence of modern business-oriented enterprise activities is to build a huge support structure around the needs of business promotion (concrete as customer orders, partner contracts, employee application forms, etc.). The research on business processes in the history of enterprise management disciplines and information systems disciplines has produced typical expertise such as business process reengineering. The implementation of the information system also pays great attention to the direction of enterprise data flow (information flow), hoping to achieve the optimal effect. However, as the scale of the enterprise increases, the input given by the external environment becomes increasingly complex, and 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 Applications(China)
IPC IPC(8): G06N3/04G06N3/08G06Q10/06
CPCG06N3/08G06Q10/06375G06N3/045
Inventor 汤胤林木兴黄书强
Owner JINAN UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap