Project information processing method and device based on project recommendation model

Abstract

The invention provides a project information processing method based on a project recommendation model, and the method comprises the steps: obtaining project information in a use environment of the project recommendation model, and converting the project information into corresponding recognizable text information; through an encoder network of the project recommendation model and a decoder network of the project recommendation model, according to the hidden variable of the at least one word level and the corresponding fusion feature vector, generating a text processing word corresponding to the hidden variable of the word level and a selected probability of the text processing word; selecting at least one text processing word to form a text processing result corresponding to the text information according to the selected probability of the text processing result; and converting a text processing result into new project information corresponding to the project recommendation model. Theinvention further provides a project information processing device based on the project recommendation model, electronic equipment and a storage medium. According to the method, the new project information generated through the project recommendation model can be matched with the use environment.

Description

technical field [0001] The invention relates to information processing technology, in particular to a training method, device, electronic equipment and storage medium of an item recommendation model. Background technique [0002] Human–Computer Interaction (HCI) refers to the use of a certain dialogue language between humans and computers to determine the information exchange process between humans and computers in a certain interactive way. With the development of human-computer interaction technology, more and more intelligent products based on human-computer interaction technology have emerged. For example, item recommendation can be completed through human-computer interaction during the item recommendation process. However, in the traditional Seq2Seq model, all The items in the generated sequence have high popularity, high frequency of occurrence, and strong versatility. Therefore, due to the limitation of RNN capabilities, it is difficult for the item recommendation mo...

AI Technical Summary

Problems solved by technology

With the development of human-computer interaction technology, more and more intelligent products based on human-computer interaction technology have emerged. For example, item recommendation can be completed through human-computer interaction during the item recommendation process. However, in the traditional Seq2Seq model, all The items in the generated sequence have high popularity, high frequency of occurrence, and strong versatility. Therefore, due to the limitation of RNN capabilities, it is difficult for the item recommendation model to produce high-quality text processing results, which in turn affects the generation of item information and also affects users. experience

Images