Grading prediction method and grading prediction system

Abstract

The invention discloses a grading prediction method and a grading prediction system. The grading prediction method comprises the steps of acquiring historical comment data, constructing a subject term distribution table by virtue of a method based on word vectors, counting comment character representation of an appointed user to a first object according to the subject term distribution table, simultaneously, acquiring historical grading data, counting a correction average score of the appointed user to a first object as one of the characteristics, counting the weight and the error offset of each characteristic by taking the correction average score and a subject characteristic as the characteristics of a linear regression model, firstly counting the comment character representation and the correction average score of a second user to a second object aiming at the to-be-predicted score of the second user to the second object, and acquiring the score of the second user to the second object by combining the subject weight with the error offset. According to the grading prediction method, the subject term table is constructed by virtue of a term vector method, is predicted and scored according to comment contents and is simultaneously considered from the angles of the users and the objects, and a combined recommend model is obtained by virtue of a collaborative filtering method, so that a prediction result is relatively accurate comprehensive.

Description

Technical field [0001] The present invention relates to the field of recommendation systems, in particular to a method and system for scoring prediction. Background technique [0002] The recommendation system is a system that recommends information or products that users are interested in based on the user's historical behavior and interest characteristics. The recommendation system is generally implemented by scoring prediction, that is, recommending products with high predicted scores to users. [0003] Traditional recommendation algorithms include content-based recommendation and collaborative filtering. Content-based recommendation is to dig out the descriptive characteristics of items, and then recommend items with similar characteristics to the user according to the user's choice. For example, if the user buys a certain brand of clothes, he will recommend the brand of pants to him. Collaborative filtering is to recommend products to users based on their historical behavior...

AI Technical Summary

Problems solved by technology

[0004] However, the traditional recommendation algorithms mentioned above have certain limitations.

Content-based recommendation algorithms rely too much on the descriptive features of users and items, and cannot take advantage of user feedback

The collaborative filtering algorithm guesses the user's preferences for items based on the user's historical behavior, without digging deep into the characteristics of users or items. Delicious dishes, another thought the service was attentive

[0005] At present, there are some algorithms that can predict the user's rating of the item based on the user's comment on the item, but they cannot consider the user's angle and the item's angle in the comment information at the same time.

Images