Item pushing method and device based on clustering and matrix decomposition

Abstract

The invention provides an item pushing method and device based on clustering and matrix decomposition. The method comprises the following steps: constructing a user label matrix, then clustering usersto obtain a plurality of user group clusters, then generating a user-to-item scoring matrix for each user group cluster, and then carrying out matrix operation through an ALS matrix decomposition algorithm, thereby carrying out item recommendation. Because label clustering is firstly carried out on the user and then matrix operation is carried out, the calculation amount of the matrix operation can be effectively reduced, and therefore the system resource consumption is reduced. According to the method disclosed in the scheme, the technical problem of low pushing efficiency of existing item pushing is solved, the technical effect of efficient and accurate pushing of government affair items is achieved, and item pushing recall rates are increased.

Description

technical field [0001] The present application belongs to the technical field of big data processing, and in particular relates to a method and device for pushing items based on clustering and matrix decomposition. Background technique [0002] At present, for APPs in the field of government affairs, when recommending items, they are generally based on popular items, and rarely make personalized recommendations for different users. Some government affairs APPs use collaborative filtering algorithms to recommend items. However, using collaborative filtering algorithms is not effective in recommending government affairs. Because the principle of the collaborative filtering algorithm is to find items similar to a certain item, and then recommend them to users. However, in this case, the similar items of almost all items are the most popular items. At this time, only using the collaborative filtering algorithm will cause most users to recommend similar items, which cannot achie...

AI Technical Summary

Problems solved by technology

Some government affairs APPs use collaborative filtering algorithms to recommend items. However, using collaborative filtering algorithms is not effective in recommending government affairs. Because the principle of the collaborative filtering algorithm is to find items similar to a certain item, and then recommend them to users.

However, in this case, the similar items of almost all items are the most popular items. At this time, only using the collaborative filtering algorithm will cause most users to recommend similar items, which cannot achieve the effect of personalized recommendation. The actual recommendation is accurate. rate is not high

[0003] Considering that the existing machine learning algorithms in the e-commerce field can be used in the recommendation of government affairs, however, in practical applications, it is found that there are only about 200 scenarios in the government affairs field. Large correlation, unlike in the e-commerce scene, where the number of items is huge, and the number of alternative products may reach tens of thousands or more; and the correlation between products is very large, as long as the user is sufficiently described for consumption, it can be Conveniently recommend products that users can accept

[0004] Therefore, no matter whether collaborative filtering algorithm or machine learning algorithm is used to recommend government affairs, it is difficult to obtain accurate personalized recommendation effect.

As for how to get accurate personalized recommendation effect, no effective solution has been proposed yet

Images