Question recommendation method, device and system

A recommendation method and question technology, applied in the field of question recommendation methods, devices and systems, can solve problems such as remote points of interest, inability to match related interests, and concentrated user points of interest, and achieve the effect of improving the answering rate of questions

Active Publication Date: 2015-04-29
TENCENT TECH (SHENZHEN) CO LTD
View PDF3 Cites 64 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] However, for some inactive users, because their behavior data is very little (some even have no), then these users cannot obtain their user interests through mining methods, and they cannot match interest-related questions; in addition, there are Even if a large number of users can extract their in

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
  • Question recommendation method, device and system
  • Question recommendation method, device and system
  • Question recommendation method, device and system

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0036] image 3 It is a schematic flowchart of the problem recommendation method in the first embodiment of the present invention. Please refer to image 3 , the question recommendation method in the embodiment of the present invention includes:

[0037] Step S11: The server constructs the user's interest vector according to the user's short-term interest, long-term interest, and group interest, and the interest vector includes multiple interest items.

[0038] Among them, the user's short-term interest can be obtained according to the user's real-time answer records, and the user's short-term interest within a predetermined period of time can be calculated online to quickly perceive the interest changes reflected in the user's behavior. Among them, the real-time answer record records which questions the user has answered in a short period of time, and the length of time can be set by the designer. Short-term interest reflects the accumulation of interest items reflected in t...

no. 2 example

[0051] Figure 4 It is a schematic flowchart of the problem recommendation method in the second embodiment of the present invention. Figure 5 For the functional block diagram of the problem recommendation method of the second embodiment of the present invention, please refer to Figure 4 and Figure 5 , the question recommendation method in the embodiment of the present invention includes:

[0052] Step S21: Calculate the user's short-term interests according to the user's real-time answer records within a predetermined time period from the current time.

[0053] The interest of the user can be represented by an interest vector, and the short-term interest of the user can be represented by a corresponding short-term interest vector, and the short-term interest of the user is calculated according to the weight of each interest item (interest keyword or interest classification) in the short-term interest vector, for example , with C u to represent the short-term interest of...

no. 3 example

[0126] See Figure 13 , is a schematic structural diagram of a question recommendation device provided in the third embodiment of the present invention; the device can run on the server in the above embodiment, and the device 30 includes: an interest vector calculation module 31, a candidate recommendation question acquisition module 32, a waiting Recommend a question acquisition module 33 and a question recommendation module 34 .

[0127] Wherein, the interest vector calculation module 31 is used to construct the user's interest vector according to the user's short-term interest, long-term interest and crowd interest, and the interest vector of the user includes a plurality of interest items;

[0128] The candidate recommendation question acquisition module 32 is used to acquire candidate recommendation questions from the problem set to be solved according to the plurality of interest items;

[0129] The question to be recommended acquisition module 33 is used to estimate th...

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 present invention relates to a question recommendation method, device and system. The method comprises: according to a short-term interest, a long-term interest and a crowd interest of a user, a server constructing an interest vector of the user, the interest vector of the user comprising a plurality of interest entries; according to the plurality of interest entries, acquiring a candidate recommendation question from a set of questions to be solved; according to a click rate model, predicting the probability of the user answering the candidate recommendation question, and according to the predicted probability, selecting a question to be recommended; and recommending the question to be recommended to a client. In this way, a real-time and comprehensive recommendation result can be obtained, and the rate for answering questions of an interactive question and answer platform can be increased as well.

Description

technical field [0001] The invention relates to the technical field of computer internet, in particular to a method, device and system for recommending questions. Background technique [0002] Now more and more interactive question-and-answer communities provide a question-and-answer interactive platform for the majority of users. Its characteristics are: some users ask questions in the community as questioners, and other users who have the ability to answer find and answer these questions as answerers, and solve the questions of the questioners; while the questions and answers will be deposited on the platform, Form a knowledge base, which can directly provide answers for subsequent "askers" who have the same questions. In the interactive question-and-answer community, hundreds of thousands of questions are raised every day. In order to allow these questions to be answered quickly and effectively, there is a need for a way for the answerers to find questions that match the...

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): G06F17/30G06N20/00
CPCG06F16/9535G06N20/00G06F16/24578G06N5/022
Inventor 冯扬李京生孙拔群
Owner TENCENT TECH (SHENZHEN) CO LTD
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