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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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,...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


