Method and system for processing information facing question answering robot

An information processing method and robot technology, applied in the direction of electrical digital data processing, special data processing applications, instruments, etc., can solve problems that affect the user experience effect, the answer is not intuitive enough, the content is not rich enough, etc., to achieve rich content and improve user experience , Rich media information accurate effect

Inactive Publication Date: 2016-10-12
BEIJING GUANGNIAN WUXIAN SCI & TECH
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: the answers related to the questions output by the traditional qu

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
  • Method and system for processing information facing question answering robot
  • Method and system for processing information facing question answering robot
  • Method and system for processing information facing question answering robot

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0051] Example one

[0052] figure 1 A schematic flowchart of an information processing method for question answering robots according to an embodiment of the present invention is shown. Such as figure 1 As shown, the information processing method for question answering robots in the embodiment of the present invention mainly includes steps 101 to 104.

[0053] In step 101, the question information input by the user is received.

[0054] Specifically, the front-end module first obtains the voice information or text information input by the user, and the front-end module preprocesses the obtained information (for example, voice recognition processing, etc.) to obtain the problem information in text format. Then the front-end module sends the obtained question information to the question and answer robot.

[0055] In step 102, semantic analysis is performed on the question information to obtain a semantic analysis result.

[0056] Specifically, the question answering robot performs sem...

Example Embodiment

[0063] Example two

[0064] On the basis of the first embodiment, this embodiment further limits the semantic analysis result, and further optimizes the step of extracting rich media information from multimedia (ie, step 103).

[0065] In this embodiment, the semantic analysis result is a semantic set corresponding to the question information. For example, the semantic analysis of the above question "I want to hear Dad speak", the semantic analysis result obtained is the following semantic set (ie semantic set): I want father, father speaks, I listen to father speak, father wants to speak, And father's voice.

[0066] figure 2 A schematic flowchart of a method for extracting rich media information from a multimedia knowledge base in an embodiment of the present invention is shown. Such as figure 2 As shown, the method for extracting rich media information matching the semantic analysis result in the multimedia knowledge base in the embodiment of the present invention mainly incl...

Example Embodiment

[0079] Example three

[0080] This embodiment further optimizes the method of determining the target semantics from the semantic set on the basis of the above-mentioned first embodiment or second embodiment.

[0081] image 3 A schematic flowchart of a method for determining target semantics from a semantic set in an embodiment of the present invention is shown. Such as image 3 As shown, the method for determining target semantics from a semantic set in the embodiment of the present invention mainly includes step 301 and step 302.

[0082] In step 301, the semantics with the highest similarity to the question information in the current semantic set is calculated.

[0083] In step 302, the calculated semantics is determined as the target semantics.

[0084] Specifically, this embodiment adopts a semantic similarity method to determine the target semantics from a semantic set containing multiple semantics, and the target semantics is the semantics with the highest similarity to the que...

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 method and a system for processing information facing a question answering robot. The method comprises: receiving question information input by a user; performing semantic parsing on the question information, to obtain a semantic parsing result; extracting rich media information which is in a multimedia knowledge base and is matched with the semantic parsing result; and outputting the rich media information. According to the question information input by a user, the corresponding rich media information is extracted from multimedia information and is output, so as to solve problems that character answering information output by an existing question answering robot is not intuitive enough, and content is not rich enough, and user experience effect is not good enough, so that the rich media information fed back to the user is more accurate and more intuitive, and content is more enriched, and use experience of the user is greatly improved, and requirement of the user on information acquisition visualization is satisfied.

Description

technical field [0001] The invention relates to the technical field of intelligent robots, in particular to an information processing method oriented to a question-answering robot, and also to an information processing system oriented to a question-answering robot. Background technique [0002] Question answering bots are an advanced form of information retrieval systems. It can answer questions raised by users in natural language in accurate and concise natural language. The main reason for the rise of its research is people's demand for fast and accurate access to information. [0003] At present, research on question-answering robots is still focused on text information, and both questions and answers are expressed in text information. Specifically, the question-answering robot usually extracts the text-formatted answer to the question input by the user from the traditional knowledge base, and then outputs the answer. [0004] It can be seen that the existing question-...

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): G06F17/30
CPCG06F16/90332
Inventor 孙永超
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

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