Car dealer performance analysis expert system based on neural network
A neural network and expert system technology, applied in the field of classification and diagnosis of automobile dealers' business performance, can solve problems such as no automatic reasoning, difficulty in obtaining decision rules, and low level of artificial intelligence
Inactive Publication Date: 2018-05-18
上海储翔信息科技有限公司
View PDF6 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The present invention aims at the above-mentioned deficiencies of the prior art, utilizes the distributed storage, parallel processing, self-learning and self-organization functions of the BP neural network system, so that the decision-making rules can be extracted from the training data by themselves, and can be automatically calibrated under supervised learning according to the operating data , intelligently update and evolve the decision-making rules, realize the evolution of the decision-making rules, and solve a series of problems in the expert system, such as difficulty in obtaining decision-making rules, no automatic reasoning, and low artificial intelligence level
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 moreExamples
Experimental program
Comparison scheme
Effect test
Embodiment
[0026] Using the judgment results of human experts, but not limited to the rules and reasoning models of human experts, this is the beauty of the neural network expert system.
[0027] The core of the system is composed of three parts. One is the dealer performance analysis model processing tool. This tool replaces the original expert system database and models and classifies the performance classification of auto dealers such as inventory, sales, workshops, after-sales, and finance. Data sampling, partitioning, and normalization for neural network use.
[0028] The second is the neural network classification tool, which uses the BP neural network error backpropagation algorithm, and its main idea is to divide the learning process into two stages: the first stage (forward propagation process), given input information through the input layer Process and calculate the actual output value of each unit layer by layer; the second stage (reverse process), if the expected output valu...
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
Login to View More Abstract
The invention discloses a car dealer performance analysis expert system based on a neural network. By making use of the distributed storage, parallel processing, self-learning, self-organization and other functions of a BP neural network system, decision rules can be extracted by training data, and automatic calibration can be carried out under supervised learning according to running data to intelligently update and evolve the decision rules. Evolution of decision rules is realized. A series of problems in the existing expert system, such as difficulty in obtaining decision, no automatic reasoning and low level of artificial intelligence, are solved.
Description
technical field [0001] The present invention relates to artificial intelligence and expert system, in particular, it is a system for classifying and diagnosing the operating performance of automobile dealers by using neural network algorithm. Background technique [0002] Expert system (ExpertSystem, abbreviated as ES) is also called knowledge-based system. The more common definition now is that an expert system is an intelligent computer program that can use knowledge to reason and solve complex problems that only experts can solve, that is, an expert system is a computer system that can simulate the decision-making ability of human experts. The basic structure of the expert system is roughly divided into three components: knowledge base, reasoning machine and man-machine interface. The specific structure mainly consists of knowledge base, database, reasoning machine, interpreter, knowledge acquisition (learning system) and man-machine interface. Among them, knowledge base...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/06G06N3/08
CPCG06N3/084G06Q10/0637G06Q10/06393
Inventor 徐彬
Owner 上海储翔信息科技有限公司