Dialog generation method and system for user-defined database interaction

Abstract

The invention discloses a self-defined database interaction dialog generation method and system. The method includes: acquiring the action of the last dialogue round, if the action is a receiving operation action, receiving user input text, and extracting user input through a natural language understanding module The intent and entity of the text to update the dialogue state to generate current dialogue information; convert the updated dialogue state into a binary vector, and update it to the historical dialogue information synchronously, and generate execution actions according to the current dialogue information and historical dialogue information; if the execution action is not In order to receive the operation action, judge whether the execution action needs to search the database; if necessary, use the user's expectation as the search condition to search the database, and combine the search results with the preset template to generate a reply action to the user; if not, directly from the Choose one of the predefined templates to generate a reply action to the user. In this method, the user independently selects the query result of the database, which improves the user experience.

Description

Technical field [0001] The present invention relates to the technical field of artificial intelligence, and more particularly to a method and system for generating a dialogue interactive database a custom. Background technique [0002] In recent years, with the rapid development of the industry of artificial intelligence, human-computer dialogue as a sub-field of artificial intelligence direction, more and more attention, layman's terms, interactive technology is to allow natural human language and computer in real time interaction. Task-oriented interactive technology can be applied to set the hotel, restaurant, airline booking, train tickets and other business scenarios with high value and commercial value. The traditional task-based multi-round dialogue system mainly consists of four modules: natural language understanding, dialogue status tracking, strategic planning, natural language generation four modules. Natural language generation module which can utilize artificial int...

AI Technical Summary

Problems solved by technology

But this method is rigid and inflexible. Users can only see a fixed template style, which cannot be well combined with the actual dialogue scene, so the user experience is not friendly enough.

Images