Outbound robot distribution method

Abstract

The invention relates to an outbound robot distribution method, which comprises the following steps that: 1) when a customer calls, the customer selects to enter different incoming call skill groups through a routing module; 2) after entering the call-in skill group, dependent variables are predicted through principal component analysis and multiple regression analysis methods in sequence, i.e., the time required by the robot to dial the task load; and 3) based on the prediction result in the step 2), autonomous machine learning is carried out on the prediction result by using a method of combining a time sequence model and BP neural network weighting, an optimized learning rule is obtained, and then robot seats are distributed. Compared with the prior art, the method has the advantages that the labor cost is reduced, the prediction precision is improved, and the neural network autonomous learning ability is achieved.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a method for assigning an outbound robot. Background technique [0002] The call center is a comprehensive information service system implemented using modern communication and computer technology, which can automatically and flexibly handle a large number of incoming and outgoing calls; in addition, the call center can provide query, summary, Statistical analysis and other functions to assist enterprises in decision-making. At present, call centers are widely used in various industries such as telecommunications, finance, government agencies, electric power, and postal services. [0003] In the call center of the prior art, the telephone customer service system mainly performs the operations of making outbound calls and answering incoming calls through artificial seats; wherein, in the outbound call scenario, the telephone customer service system transfers the connected ...

AI Technical Summary

Problems solved by technology

It can be seen that the scale of the call center is limited by the number of artificial seats. If more outbound calls and incoming calls are to be handled, the call center needs to hire more customer service personnel; relying solely on artificial seats for telephone operations makes Call centers are faced with a large number of personnel recruitment, training, management issues, and increasing wage costs for hiring labor

[0004] With the emergence of voice robots, some companies have begun to use traditional predictive model methods to allocate and manage outbound robots, such as a single regression predictive model or a Kalman filter predictive model, etc. However, traditional predictive models are generally based on rules and mathematical functions Established, there are the following problems: 1. The mathematical logic behind different models is different, and the application scenarios are relatively limited; 2. Based on the causal prediction model, the independence of the equation establishment and local laws is assumed as the basis, and the long-term prediction deviation is relatively large ; 3. Models that do not require a large amount of data to solve problems such as lack of historical data and sequence integrity are only suitable for short-term and medium-term forecasts of exponential growth; 4. Models that predict the future situation of the system only related to the current moment and have nothing to do with historical data are not suitable for medium and long term forecast

The above problems lead to low accuracy of robot assignment results, and it is impossible to realize multi-round dialogue interaction with complex content

Images