Dialogue control method and system based on subject object tracking and cognitive reasoning, storage medium and server

Abstract

The invention discloses a dialogue control method and system based on subject object tracking and cognitive reasoning, a storage medium and a server. The method comprises the following steps: constructing an event object database; constructing a affair graph corresponding to the event object; comparing the dialog text data with the event object to identify the event object; tracking the event object in real time; constructing an event object database, and constructing a affair graph corresponding to the event object; when a user inputs a dialogue text, the processor controls the recognition module to compare a word vector value of dialogue text data with a word vector value of an event object so as to recognize the event object, and the processor tracks the event object in real time by controlling the tracking module and calls the event map corresponding to the event object. And generating reply contents through text analysis. Through the above settings, the system is endowed with the ability of tracking and cognitive reasoning of the subject object, and the accuracy and logic judgment ability of the robot for session subject recognition are improved.

Description

technical field [0001] The invention relates to the field of customer service centers, in particular to a dialogue control method based on subject object tracking and cognitive reasoning, a system storage medium and a server. Background technique [0002] Artificial intelligence technology plays an important role in today's customer service field. The dialogue robot based on artificial intelligence technology is a new way of interaction between enterprises and customers. In the service process of the dialogue robot, the robot needs to understand the intention in the customer's speech, match it to the corresponding business dialogue process or knowledge point, and complete the reply to the user. [0003] In the dialogue interaction process, due to the customer's colloquial expression, the subject is often missing during multiple rounds of dialogue. It is difficult to correctly match the knowledge points when the subject is missing by using the text similarity calculation mode...

AI Technical Summary

Problems solved by technology

However, there are many restrictions on knowledge points in this scenario, and some knowledge points have multi-layer inclusion relationships at the same time, and the user’s consultation is often incomplete, such as a taxpayer’s consultation: "Can the input tax of my handling fee be deducted?" , the robot recognizes it as the consulting intention of "input tax credit", but the necessary conditions such as taxpayer, invoice type, project / service, etc. are missing, and traditional robots cannot obtain complete information

[0005] Even with complete information, traditional robots can only find the relationship between the upper and lower entities of "input tax" and "tax deduction" by using the knowledge graph method. However, due to the lack of reasoning ability, the robot cannot judge the specific Whether the tax amount can be deducted, the consultant often returns without success

Using the business dialogue process is quite a match, clarifying the restrictions with the user step by step, but there are also shortcomings: because these businesses need to preset various processes and conditions to make the dialogue process, and finally it is an overly large process system , very bloated, and also face the problem of high operating costs in the later stage

Images