Voice interaction method and device, equipment and storage medium

By using speech recognition and instruction generation models in target applications, identifying and generating target application instructions, the problem of the inability to recognize complex voice interaction instructions in the prior art is solved, and the accuracy and experience of voice interaction are improved.

CN119741921APending Publication Date: 2025-04-01BEIJING 58 INFORMATION TTECH CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202411846064.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-13
Publication Date
2025-04-01

AI Technical Summary

Technical Problem

Existing voice interaction schemes fail to recognize and execute complex voice interaction instructions initiated for specific applications, resulting in poor user-application voice interaction experience.

Method used

A voice interaction method is provided, by receiving voice interaction instructions initiated by a user on the current page of the target application, using the voice recognition model to recognize the text of the instruction, and combining the current page information to generate target application instructions through the instruction generation model, so as to achieve accurate execution of complex functions.

Benefits of technology

Improves the voice interaction experience between users and applications, enhances the accuracy of response to voice interaction instructions, and can accurately perform complex in-app operations.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The embodiment of the invention provides a voice interaction method and device, equipment and a storage medium. In the embodiment of the invention, current page information of a target application when a voice interaction instruction is initiated can be obtained, a voice interaction text corresponding to the voice interaction instruction is recognized by using a voice recognition model, the current page information and the voice interaction text are input to an instruction generation model, and a target application instruction corresponding to the voice interaction text is generated. And analyzing the target application instruction into the target execution logic by the target application, executing the target execution logic, and realizing voice interaction with the target user. Therefore, the target application instruction capable of being recognized by the target application can be generated by utilizing the instruction generation model based on the voice interaction text and the current page information of the target application, so that the target application can accurately determine the target execution logic pointed by the voice interaction instruction, the response accuracy of the voice interaction instruction can be improved, and the user experience is improved. And the voice interaction experience between the user and the application program is improved.
Need to check novelty before this filing date? Find Prior Art