Multi-round dialogue generation method and device, computing equipment and storage medium

By combining Rasa and AntvX6 technologies, using large models to generate multiple rounds of dialogue processes, the problem of building multiple rounds of dialogue processes in the existing technology is solved, and a rapid, intuitive and easy-to-scaling multi-round dialogue generation is achieved, suitable for a wide range of robot services system.

CN118917288APending Publication Date: 2024-11-08BEIJING HONGLIAN 95 INFORMATION IND CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410993078.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

It is difficult for existing technology to quickly build multi-round dialogue processes, especially in robot dialogue, which requires massive data model support, and existing tools such as Rasa lack intuitive interfaces and easy scalability, limiting user operations and integration.

Method used

By combining Rasa and AntvX6 technologies, prompt instructions are generated and large models such as GPT-4 are used to quickly build multi-round dialogue processes, providing intuitive visual interfaces and data mapping rules, simplifying data structure display and adjustment, reducing technical thresholds, and improving scalability and portability.

Benefits of technology

It realizes the ability to quickly generate multiple rounds of dialogue processes, reduces dependence on Rasa data structures, improves the intuitiveness and scalability of user operations, simplifies the integration process, and is suitable for a wide range of robot service systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917288A_ABST
    Figure CN118917288A_ABST
Patent Text Reader

Abstract

The invention discloses a multi-round dialogue generation method and device, computing equipment and a storage medium, the multi-round dialogue generation method is executed in the computing equipment, the method comprises the steps that a dialogue generation request sent by a user is received, and the dialogue generation request at least comprises text description information indicating dialogue content; at least based on the text description information, a prompt instruction is assembled, and the prompt instruction comprises an instruction part, an example part and a problem part; inputting the prompt instructions into a dialogue generation model for processing, so that the dialogue generation model analyzes the prompt instructions and generates first type dialogue stream data and second type dialogue stream data for the text description information according to the example part; and generating multiple rounds of dialogue data for the dialogue content by using the first type of dialogue stream data and the second type of dialogue stream data.
Need to check novelty before this filing date? Find Prior Art