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

An automatic question answering method and system

An automatic question answering and image information technology, applied in the computer field, can solve the problems of lack of user image information interaction, affecting the user's overall experience, inability to process image information, etc., to expand processing capabilities, facilitate analysis of user emotions, increase diversity and smoothness sexual effect

Active Publication Date: 2020-07-31
BEIJING HUIJUN TECH CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, the inventors found that there are at least the following problems in the prior art: the existing automatic question answering system can only realize the interaction of text information, and the presentation modes of questions and answers are both text information, which cannot understand image information, and cannot Unable to process image information and lack the ability to interact with users on image information, which affects the overall experience of users

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
  • An automatic question answering method and system
  • An automatic question answering method and system
  • An automatic question answering method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Example 1: In the chatting robot scene, the user sends a "laughing" expression image during the interaction with the automatic question answering system; after the automatic question answering system receives the image information, it inputs it into the expression recognition model to obtain The emoticon type is "laughing". The automatic question answering system is pre-configured with response logic corresponding to various expression types, and all response logic forms a rule tree. Assume that the expression type of "laughing" corresponds to 5 rule nodes in the rule tree, of which the second rule node It is: to detect the chat content before the image information is sent. If it is detected that the user is triggered to reply to the image information after the content is sent by the automatic response system, then the corresponding reply is found from the corpus, such as "It's really funny", "I still want to listen to it." Other paragraphs?"; If it is detected that the...

Embodiment 2

[0055]Embodiment 2: In the e-commerce platform scenario, the user sends an order image during the interaction with the automatic question answering system. After the automatic question answering system receives the image information, it performs expression recognition in step S202, and no effective expression type is detected; it performs text recognition in step S203, and extracts the text information in the image information; after classification processing in step S204, it is obtained The category of this image information is "Order Tracking". The automatic question answering system is pre-configured with the processing logic corresponding to the order image, which forms a rule tree. For example, "order tracking" corresponds to 3 rule nodes in the rule tree, and a rule node is: first, call the OCR text recognition result , detect the order number, user name, delivery status, etc. in the image information; second, call the background order interface to query the logistics st...

Embodiment 3

[0056] Embodiment 3: In the scenario of a story robot, the user sends an image of playing football in a sports field during the interaction with the automatic question answering system. After the automatic question answering system receives the image information, it performs expression recognition in step S202, but no effective expression type is detected; it performs text recognition in step S203, and no valid text information is detected; it performs image classification in step S204 to obtain classification information, such as : character, motion, football etc.; Carry out picture-text conversion through step S205, obtain the text description of this image information; According to image comprehension result, select motion story sub-model from image coding model through step S207, then output motion type through step S208 of story content to users.

[0057] In another preferred embodiment, the output content of the sub-model can also be converted and verified. For example,...

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 an automatic question answering method and system, and relates to the technical field of computers. A specific implementation of the method includes: performing image recognition on the received image information, and performing image understanding on the image information according to the image recognition result to obtain the image understanding result; Select a sub-model in the trained image coding model; input the image information into the sub-model for coding, and output the coding result for the user to reply. This embodiment improves the comprehension and response capabilities of the automatic question and answer, and increases the diversity and fluency of the answer content by adding the understanding of image information and encoding and decoding processing in the automatic question and answer.

Description

technical field [0001] The invention relates to the field of computers, in particular to an automatic question answering method and system. Background technique [0002] With the development of natural language processing technology, automatic question answering system has received great attention. A high-quality automatic question answering system can solve common problems of users and reduce manual overhead. Chatbots based on automatic question-and-answer technology have been widely used in areas such as intelligent customer service, online shopping guide, meal ordering, air ticket booking, and mobile phone recharge. Existing automatic question answering technologies mainly include: automatic speech recognition, text-to-speech, question-and-answer corpus, knowledge base construction, intent recognition, question-answer matching, slot filling, rule tree and other technologies. [0003] In the process of realizing the present invention, the inventors found that there are a...

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): G06F16/583G06F16/332G06K9/00G06K9/32
CPCG06F16/3329G06F16/5846G06V40/174G06V20/63G06V30/287
Inventor 高毅
Owner BEIJING HUIJUN TECH CO LTD