Information recommendation method and apparatus
An information recommendation and information library technology, applied in the field of information interaction, can solve problems such as poor semantic understanding, low accuracy and recall, and achieve improved accuracy and recall, improved accuracy and recall, and increased semantic understanding effect of ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 example
[0077] Combine below figure 1 and figure 2 A flowchart of an information recommendation method in the first embodiment of the present invention will be described. Such as figure 1 An information recommendation method shown may include the following steps:
[0078] Step S101: After n times of question-and-answer interactions with the user, receive the user's current question, and extract the core words corresponding to each question input by the user to form a core word sequence corresponding to the user's question sequence; where n is greater than the natural number of 0;
[0079] Step S102: searching for a set of candidate questions corresponding to the current question from the knowledge base;
[0080] Step S103: searching for a target related question sequence corresponding to the core word sequence from the related question sequence information database, and extracting a current related question corresponding to the current question from the target related question se...
no. 2 example
[0121] Combine below figure 2 and image 3 The second embodiment of the present invention will be described, image 3 is a flowchart of an information recommendation method in the second embodiment of the present invention, and the information recommendation method may include:
[0122] Step S301: After n times of question-and-answer interactions with the user, receive the user's current question, and extract the core words corresponding to each question input by the user to form a core word sequence corresponding to the user's question sequence; where n is greater than the natural number of 0;
[0123] Step S302: searching for a set of candidate questions corresponding to the current question from the knowledge base;
[0124] Step S303: searching for the target related question sequence corresponding to the core word sequence from the related question sequence information database, and extracting the current related question sentence corresponding to the current question ...
no. 3 example
[0135] Figure 4 is a schematic structural diagram of an information recommendation device in the third embodiment of the present invention. The information recommendation device 40 as shown in the figure may include: a user question core word sequence acquisition unit 401, a candidate question set search unit 402, a target related question sequence search unit 403, a similarity calculation unit 404, and an answer information recommendation unit 405 and associated question sequence information library acquisition unit 406.
[0136] The user question core word sequence acquisition unit 401 is adapted to receive the user's current question after n times of question-and-answer interactions with the user, and extract the core words corresponding to each question input by the user to form a user question The core word sequence corresponding to the sequence; wherein n is a natural number greater than 0;
[0137] The candidate question set search unit 402 is adapted to search the c...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com