Unlock instant, AI-driven research and patent intelligence for your innovation.

A human-computer voice interaction method, device and storage medium

A voice interaction, man-machine technology, applied in voice analysis, voice recognition, instruments, etc., can solve problems such as inflexibility and inability to meet the individual needs of users, so as to improve the speed of machine reply, reduce the difficulty of calculation and processing, and improve fluency degree of effect

Active Publication Date: 2020-11-20
深圳艾比仿生机器人科技有限公司 +1
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Traditional man-machine voice interaction speech recognition can complete simple communication and answer, but the content of these answers is only some rigid answers set by the robot manufacturer, which cannot meet the individual needs of each user

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A human-computer voice interaction method, device and storage medium
  • A human-computer voice interaction method, device and storage medium
  • A human-computer voice interaction method, device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0026] According to the applicant's research, the traditional human-computer voice interaction speech recognition can complete simple communication and answer, but the content of these answers is only some rigid answers set by the robot manufacturer, lacking personalized chat for each customer Content, once it is necessary to personalize the chat design program for each user, it will require a lot of cost, which discourages many companies, but the lack of such customized interaction will affect the user experience. In order to solve the above problems, the first embodiment of the present invention provides a method for man-machine voice interaction.

[0027] Please refer to figure 1 , figure 1 It is a flow chart of a human-computer voice interaction method provided by the first embodiment of the present invention. As an optional implementation manner, the specific steps of the human-computer voice interaction method are as follows:

[0028] Step S10: After analyzing the inp...

Embodiment approach

[0036] For step S10, the semantics are obtained after analyzing the input speech information input by the user. Please refer to figure 2 , figure 2 It is a flow chart of the input voice information analysis steps provided by the first embodiment of the present invention. As an implementation manner, the input voice information analysis step is specifically as follows:

[0037] Step S11: converting the input voice information input by the user into input text information through the voice recognition API.

[0038] Step S12: Call the word segmentation API to convert the input text information into word segmentation information, and use the word vector representation method to analyze the word segmentation information to obtain semantics.

[0039] For step S11, API (Application Programming Interface, Application Programming Interface) is some predefined functions, the purpose of which is to provide applications and developers with the ability to access a set of routines base...

no. 2 example

[0046] In order to better cooperate with the human-machine voice interaction method provided in the first embodiment of the present invention, the second embodiment of the present invention provides a human-machine voice interaction device 100 .

[0047] Please refer to image 3 , image 3 It is a block diagram of a human-machine voice interaction device provided by the second embodiment of the present invention.

[0048] The human-machine voice interaction device 100 includes a semantic analysis module 110 , a best answer judgment module 120 , an output text information acquisition module 130 and a voice output module 140 .

[0049] The semantic analysis module 110 is configured to analyze the input voice information input by the user to obtain semantic meaning.

[0050] The best answer sentence judging module 120 is configured to judge whether the user-defined database includes the best answer sentence corresponding to the semantics.

[0051] The output text information o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a man-machine voice interaction method and device and a storage medium, and relates to the technical field of man-machine voice interaction robots. The man-machine voice interaction method comprises the steps of firstly, analyzing input voice information input by a user to obtain semantics, and judging whether or not a user-defined database of the user includes an optimal reply statement corresponding to the semantics; if yes, based on the optimal reply statement, obtaining output text information, conducting voice synthesis on the output text information to obtain output voice information, and outputting the output voice information to the user. By means of the man-machine voice interaction method, by using the user-defined database of the user, the individualized degree of man-machine voice interaction is improved.

Description

technical field [0001] The present invention relates to the technical field of human-machine voice interaction robots, in particular to a method, device and storage medium for human-machine voice interaction. Background technique [0002] With the rapid development of the Internet and the popularization and application of mobile terminals such as mobile phones, a large amount of text or speech corpus can be obtained from multiple channels, which provides abundant resources for the training of language models and acoustic models in speech recognition. It is possible to build general large-scale language models and acoustic models. In speech recognition, the matching and richness of training data is one of the most important factors to promote the improvement of system performance, but the labeling and analysis of corpus requires long-term accumulation and precipitation. With the advent of the era of big data, large-scale corpus resources Accumulation will be raised to a stra...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G10L15/22G10L15/30G10L15/18G06F16/332
CPCG10L15/1822G10L15/22G10L15/30G10L2015/223
Inventor 谢伟纯郭瀚阳李志关毅江沈云辉谢俊育
Owner 深圳艾比仿生机器人科技有限公司