Highly anthropomorphic voice interaction algorithm and emotion interaction algorithm for robot and robot

A technology for voice interaction and emotional communication, applied in the field of intelligent robots, it can solve the problems of unnatural robot interaction and process, and achieve the effect of convenient application, no noise interference, and reducing the influence of surrounding noise.

Inactive Publication Date: 2019-05-10
SHANGHAI YUANQU INFORMATION TECH
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a highly anthropomorphic robot voice interaction algorithm, emotional communication algorithm and robot, which solves the problem that the original robot interaction is not natural enough and the flow is not enough

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

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0053] Robot technology based on highly anthropomorphic human-computer voice interaction realizes voice interaction through the following processes:

[0054]1. When the robot is powered on, start the voice wake-up algorithm in the embedded chip, and the algorithm will run all the time, monitoring whether the user uses the wake-up word to wake up.

[0055] 2. After the user uses the wake-up word, the robot first uses the sound source positioning algorithm according to the user's voice to determine the direction and distance of the user. The head of the robot turns, aligns with the user according to the user's direction, starts the camera, and starts face recognition and track.

[0056] At the same time, the large-scale continuous speech recognition system starts to recognize the user's subsequent voice commands. If there is still the user's voice V after the wake-up word spoken by the user before the large-scale continuous speech recognition system starts, wait for the large-sc...

specific Embodiment 2

[0068] 1) The robot recognizes the text spoken by the user and generates a text sequence: A1, A2, A3, ..., An (here, for Chinese, An can be a Chinese character, such as "中", "国", etc., or it can be Pinyin, such as "zh", "ong1", etc.);

[0069] 2) By calculating whether the multivariate probability P(A1, A2, A3, ..., An) reaches the threshold, the robot detects whether the text sequence A1, A2, A3, ..., An is valid speech; Meta-conditional probability P(A2|A1), P(A3|A2), ... , then P(A1, A2, A3, ..., An) =P(A1)* P(A2|A1)* P(A3 |A2)....* P(An|An-1), the conditional probability of three or more variables is similar;

[0070] 3) If the robot detects that the text sequence is non-speech, it will not respond;

[0071] 4) If the robot detects that the text sequence is speech, it will use the semantic processing module to judge whether the user is talking to the robot (for example, to detect the matching threshold between the text sequence and the robot’s preset question), if it is ...

specific Embodiment 3

[0093] 1) Create a user's attribute list, which includes two categories, one is category, such as what the user likes and dislikes; the other is level category, such as language level (for example, the third grade of kindergarten is 30), mathematics level (for example, The level of the second grade of elementary school is 20), swimming level; this attribute list is established in two ways, one is to give options and let the user fill in; the other is to extract the user's information in the daily voice interaction of the robot, and automatically create it for the user .

[0094] 2) Analyze the user's current question (including the current question and the previous question), see if there is any content in the user attribute list, if not, answer in a normal tone.

[0095] 3) If the analysis of the user's question includes the attribute of whether it is a category, an emotional answer voice is given according to the user's preference.

[0096] 4) If the user's problem is analy...

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 discloses a highly anthropomorphic voice interaction algorithm and an emotion interaction algorithm for a robot and a robot and solves the problem that the interaction of the traditionalroot is not natural and smooth. The robot of the invention has a continuous voice listening and answering mode. In the continuous voice listening and answering mode, a user can either talk to the robot or chat with other people. The robot determines whether the user talks to itself or not through the algorithm, so that the robot can answer. By adopting a positioning algorithm and a microphone array algorithm, voices in the user direction are collected, influence of surrounding noises is reduced, and the robot is not affected by noises. According to an emotion computing method for answering ofthe robot, the robot looks at the user and gives answer with emotion and anthropomorphic expressions according to the emotion computing method. The robot will lock at the counterpart for communication like interpersonal communication and has corresponding expressions and emotions. According to the whole highly anthropomorphic human-machine voice interaction technology, interaction between human and robot is as natural as interpersonal communication, so that the robot is more intelligent and convenient to apply.

Description

technical field [0001] The invention belongs to the field of intelligent robots, and in particular relates to a robot highly anthropomorphic voice interaction algorithm, an emotional communication algorithm and a robot. Background technique [0002] There are many types of artificial intelligence robots that can interact with voice in the existing market, but the interaction method is not natural and smooth compared with humans. For example, when humans and robots send voice commands, they need to use a method similar to WeChat. Press and hold the voice button on the robot to speak, and then release the voice button after speaking. For another example, some robots need to wake up with a wake-up word (such as Tmall Genie) every time they receive a voice command. When there are multiple voice commands, they need to use the wake-up word multiple times, instead of continuous voice commands, which is troublesome to use and interact. [0003] In addition, the probability of succe...

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
IPC IPC(8): G10L15/22G10L17/24G10L25/63B25J11/00
Inventor 张峰吴义坚
Owner SHANGHAI YUANQU INFORMATION TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap