Intelligent-robot-oriented dialog system data processing method and device

An intelligent robot and dialogue system technology, applied in the field of human-computer interaction, can solve problems such as poor correlation, boring chat process, affecting the fluency of man-machine dialogue process, etc., to achieve the effect of increasing user stickiness and improving user experience

Active Publication Date: 2016-09-07
BEIJING GUANGNIAN WUXIAN SCI & TECH
View PDF5 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This patented technology allows an autonomous robots (AV) with conversational systems to interact naturally without being limited by preprogrammed commands. It uses various techniques such as speech recognition and natural language understanding algorithms to help users communicate better over virtual environments like chats on web pages. Overall, this innovation enhances how humans work together remotely while still having full sense of what they are doing around them.

Problems solved by technology

The technical problem addressed in this patented text relating to current conversational agents used during interactions between humans and machines is how well they provide relevant responses when there are only partial matches made from spoken words without actually speaking into them. This can lead to frustration if the agent does not respond correctly due to lacking contextual knowledge about what's happening around us (the person being interacted).

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
  • Intelligent-robot-oriented dialog system data processing method and device
  • Intelligent-robot-oriented dialog system data processing method and device
  • Intelligent-robot-oriented dialog system data processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] figure 1 A flow chart of a data processing method for an intelligent robot-oriented dialogue system provided in this embodiment is shown.

[0038] Such as figure 1 As shown, the method firstly extracts a target topic from the interaction topic sequence based on the acquired interaction topic sequence in step S101 according to preset rules.

[0039] Specifically, in this embodiment, when the dialog system determines through decision-making that it is necessary to initiate an active inquiry to the user, it will extract some interactive topics from the previous rounds of dialog data in chronological order, thereby forming an interactive topic sequence. In step S101, the method extracts a target topic from the interactive topic sequence according to preset rules, and the target topic is a topic that the method needs to refer to when generating feedback information. In this way, the feedback information finally generated and output by the method will also be related to the ta

Embodiment 2

[0050] figure 2 A flow chart of the data processing method for the intelligent robot-oriented dialogue system provided in this embodiment is shown.

[0051] Such as figure 2 As shown, in this embodiment, the method acquires an interactive topic sequence in step S201, and sets the parameter i to 1.

[0052] In this embodiment, the method includes multiple interactive topics in the sequence of interactive topics acquired in step S201, and these interactive topics are arranged in chronological order. Among them, the first interactive topic in the interactive topic sequence is the closest interactive topic to the current moment, and the later interactive topics in the interactive topic sequence are farther away from the current moment.

[0053] In step S202, the ith interactive topic in the interactive topic sequence is taken as the target topic, and in step S203, based on the preset knowledge map, associated information corresponding to the target topic is generated according to

Embodiment 3

[0062] The intelligent robot-oriented dialogue system data processing method provided in this embodiment first extracts the target topic from the interactive topic sequence according to the preset rules according to the acquired interactive topic sequence, and then determines the target topic according to the attribute of the target topic. The corresponding output model, and also use the preset knowledge graph to generate associated information according to the attributes of the target topic.

[0063] It should be pointed out that, in this embodiment, the principle and process of extracting the target topic are the same as the principle and process of extracting the target topic described in Embodiment 2, so details will not be repeated here.

[0064] In this embodiment, the related information corresponding to the target topic is generated according to the topic type of the target topic, and the specific generation process is as follows: image 3 shown.

[0065] Such as image

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 an intelligent-robot-oriented dialog system data processing method and device. The method comprises the following steps: 1) based on an obtained interaction topic sequence, extracting a target topic from the interaction topic sequence according to a preset rule; 2) determining a corresponding output module according to the attribute of the target topic, and based on a preset knowledge graph, generating correlation information according to the attribute of the target topic; and 3) generating feedback information corresponding to the target topic according to the correlation information and the output module. Through the method, the dialog system can initiate some related topics actively from time to time for questions of users to allow the users to think the dialog system can understand their dialogue information truly, so that man-machine interaction is allowed to be carried on, and user experience and user viscosity of the dialog system are improved.

Description

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

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
Owner BEIJING GUANGNIAN WUXIAN SCI & 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