Application of Cost Sensitive VPRS and Multi Fractal BP Neural Network in Construction of Intelligent Call Center System
International Journal of Database Theory and Application
Intelligent call center is also known as the customer service center or telephone service center, it is a kind of integrated information service system. This paper analyzes the classification method based on cost sensitive variable precision rough set. And in this paper, we use the attribute weighted cost sensitive rough set classification method based on established and customer level, customer history records, agents business related dynamic queuing strategy. In addition, this paper improves
... he multi fractal BP neural network algorithm for the call center customer classification. Improved algorithm is able to use multifractal fluctuation and BP neural network to predict the call center traffic and seat allocation. The paper presents construction of intelligent call center system based on cost sensitive variable precision rough set and multi fractal BP neural network. Experimental results show that novel method proposed can classify customers, reduce the impact of missing data and noise data, and improve the efficiency of customer satisfaction and intelligent call. the model is set up by setting the precision standard parameters  . The variable precision rough set model is applied to the customer classification. The feature extraction can be effectively extracted from the noise and incomplete sample information. The system's anti noise capability can be improved and the complexity of the system can be reduced. Modern call center, the application of computer telephone integration (CTI) technology is to make the call center service functions greatly enhanced. CTI technology is a medium of telephone voice; the user can press the button on the phone to operate the call center computer. Access to the call center can be a subscriber telephone dial-up access, fax access, computer and modem (MODEM) dial-up connection and Internet address (IP address) access, etc., users can receive a call center task prompt, in accordance with the voice of the call center, you can access to the database, access to the required information services. And storage, forwarding, query, exchange, etc. You can complete the transaction through the call center. Call center to use the traditional counter business telephone inquiry way instead of. Call center is able to provide service 24 hours a day, and has a better service than the counter service interface, users do not have to go to the office, as long as the phone can quickly get the information to solve the problem is convenient, fast, increase customer satisfaction for business services. Artificial neural network, which is based on mathematics, neurology, physics, and computer and so on, is a network which is connected by a large number of processing units, which can be used to simulate the basic features of human brain. The combination of rough set attribute reduction and data mapping of neural network can improve the accuracy and efficiency of customer classification. In this paper, using attribute weighted cost sensitive classification method based on rough set, the establishment of dynamic related customer level, customer history, agent business volume queuing strategy to improve the quality of service. In this paper, a (over Internet Protocol) technology is designed to realize the electronic commerce call center management system based on VOIP (Voice). This thesis combines theory with rough set BP neural network to classify the customers and agent queue based on traffic prediction, and optimization of call center scheduling based on chaos and fractal theory. The paper presents construction of intelligent call center system based on cost sensitive variable precision rough set and multi fractal BP neural network. be written as: xk-= a k g K xk+1 where XK is the current weight and bias vector, k g is the current gradient; K A is the learning rate. Determine the function, usually choose a non -linear S-type function (15) establish knowledge base of safety evaluation system by BP neural network learning confirmation network structure includes: input, output and the number of hidden nodes and to reflect the combination of degree of network weights during; that is, with the reasoning mechanism of the safety evaluation of the system knowledge base and are evaluated. (6) The safety assessment of the actual system is trained by the neural network to evaluate the characteristics of the system, and the input to the neural network which has been trained. 136 Copyright ⓒ 2016 SERSC center voice prompt, can access database, access to the required information service, but also can realize the storage, transfer, inquiry, exchange, also can call the center through the completion of the transaction associated. The paper presents construction of intelligent call center system based on cost sensitive variable precision rough set and multi fractal BP neural network. In intelligent call center business characteristics, project based on rough set theory combined with BP neural network to queue the customer classification and agents using chaotic and fractal theory forecast traffic and optimization of call center scheduling. The system will voice query, self-service, artificial service closely integrated, the shopping website sales, distribution of resources, supply chain resources, customer resources, such as through the network integration, establish a rapid response mechanism of online shopping, enhance customer groups and shopping website interaction, resources to achieve uniform distribution and utilization, so as to achieve the maximum profit for the enterprise.