Method and system for automatically filling work orders based on call abstracts

Abstract

The embodiment of the invention discloses a method and a system for automatically filling a work order. The method comprises the following steps: acquiring voice data of a seat call; converting the voice data of the seat call into a target text based on an automatic voice recognition technology, and identifying the text information in the target text based on the speaker identity; extracting eachpiece of non-structural work order information from the target text; obtaining each piece of structure work order information corresponding to the voice data of the seat call in the call system; and obtaining a target work order based on integration of the unstructured chemical order information and the structured chemical order information. The embodiment of the invention has the advantages thatthe working efficiency and the service quality of the seat are improved, the filling quality of the work order is improved, the work order is more structured, and the subsequent statistical analysis is facilitated.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of natural language processing, and in particular to a method and system for automatically filling in a work order based on a call summary. Background technique [0002] The agent is the operator, responsible for answering and answering the daily customer service hotline calls. At present, the agent mainly refers to the work in the call center or customer service department of the company. The main work content is to handle services, sales, data collection, information investigation, business return visits and other affairs by answering calls or making outbound calls. [0003] The work order filling technology of the agent in the prior art has the following deficiencies: 1. The work efficiency and service quality of the agent are low: the work order needs to be filled with many and complicated contents. Work order information, such as address, event, customer problem type and other inf...

AI Technical Summary

Problems solved by technology

[0003] The work order filling technology of the agent in the prior art has the following deficiencies: 1. The work efficiency and service quality of the agent are low: the work order needs to be filled with many and complicated contents. Work order information, such as address, event, customer problem type and other information, increases the difficulty and workload of the agent, reduces the work efficiency of the agent, and also reduces the service quality of the agent to the customer; 2. The quality of filling the work order is low : Due to the large amount of manually filled content, there are a large number of filling errors in the content of the work order, especially some key information: such as address, problem type, department to be processed, etc., resulting in subsequent work order circulation errors, processing errors, etc.; 3. The format of the work order is not uniform: For some content, the habit of filling in by the agent is different, such as the description of the problem and the way of expressing the address

The same thing, different agents have different expressions, so the existing work orders are not structured enough, which is not conducive to later statistical analysis

Images