Training data generation method and device and searching method and device

Abstract

The invention discloses a training data generation method and device and a searching method and device based on a neural network model. The training data generation method comprises the following steps: obtaining history search data of a user, wherein the history search data comprises history search words and history search results corresponding to the history search words; obtaining history search and click behaviors of the user, and carrying out classification on the history search results corresponding to the history search words according to the history search and click behaviors to generate labels of the history search results; and according to a preset strategy, the labels of the history search results, the history search words and the history search results, generating training data. The method does not need participation of workers, thereby realizing an automation function; and the training data is generated according to the labels of the history search results, and the training data can be more suitable for the neural network model, so that searching can be carried out through the neural network model to obtain a more accurate search result, and search accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of search engines, in particular to a method for generating training data, a search method and device based on a neural network model. Background technique [0002] In information retrieval, LTR (Learning To Rank, learning to rank) is an important sorting method. After the search engine recalls many relevant webpages from the webpage library, it needs to sort these webpage documents and present them to users. In this process, LTR plays a key role. LTR is supervised learning, and the acquisition of training data is particularly critical. At present, LTR generally has three types of methods: single document method (Pointwise), document comparison method (Pairwise), and document list method (Listwise). However, in the above three methods, because the single-document method ignores the relative order between documents, the effect will be poor, while the document list method will have relatively high computatio...

AI Technical Summary

Problems solved by technology

However, in the above three methods, because the single-document method ignores the relative order between documents, the effect will be poor, while the document list method will have relatively high computational complexity during training, and the training data is also difficult to label. Therefore, in practical applications, the document comparison method is often selected, so it is necessary to know the relative order between documents. Because a large amount of labeled data is required, manual labeling is not practical, and because the current neural network model is widely used It has been applied to many fields in the industry, and it is also used for LTR, but LTR is somewhat different from the previous neural network model learning methods and goals, that is, the way of constructing training data is not suitable for neural network models.

Images