Answer aggregation method and system facing crowdsourcing scene question-answering system

Abstract

The invention discloses an answer aggregation method and system facing crowdsourcing scene question-answering system. The method comprises the steps of obtaining multiple reply texts with respect to a specified question, wherein each reply text comprises a pro vote and a con vote of other users; conducting text analysis of a theme and key words on each reply text, and further creating a vector set; clustering all vector sets, combining all similar replies into a sort, and calculating the pro votes and the con votes of each sort of similar replies; supplying a questioner with the replies with a preset number of replies in the each sort of similar replies and a calculation result corresponding to the pro votes and the con votes. The answer aggregation method and system facing crowdsourcing scene question-answering system has the advantages that by supplying the questioner with sorts of the answers and the calculation result of the pro votes and the con votes corresponding to the sorts of the answers, redundant time for the questioner to read a lot of answers with similar meanings is saved, a more general level of support of public opinion is presented for the questioner, and the users can be helped to make own judgment and determination more efficiently.

Description

technical field [0001] The invention relates to the technical field of text processing, in particular to a method and system for aggregating answers of a question answering system for crowdsourcing scenarios. Background technique [0002] Currently, problem-solving methods for crowdsourcing are widely used. A large number of people who have difficulties to solve or have questions to answer will go to the Web site that adopts the crowdsourcing model to throw out the questions, and workers (workers) who are distributed all over the world and voluntarily solve the difficulties or problems will work together, paid or unpaid. Propose countermeasures to solve the problem for the questioner's reference. [0003] Question answering system is an advanced form of information retrieval system. It can use accurate and concise natural language to answer questions raised by users in natural language. Common question answering systems include Zhihu, Baidu Zhihu, Beiyouren Forum, etc. [...

AI Technical Summary

Problems solved by technology

However, as we all know, heuristic algorithms like the EM algorithm have high computational complexity. When the website scale is large, and the questions and workers answering the questions reach a certain scale, the time complexity of the EM algorithm will be unacceptable.

[0005] There is still a relatively obvious problem in the question answering system in the crowdsourcing scenario: the number of answers to a popular or topical question may be huge, ranging from dozens to hundreds or thousands, and it is likely to contain a large number of topics For similar answers, if the questioner reads the answer one by one, it will waste a lot of time. How to save the time for the questioner to read the answer to the greatest extent is also an important issue

Images