Unlock instant, AI-driven research and patent intelligence for your innovation.

Personalized recommendation method and device, computer equipment and storage medium

A recommendation method and preset technology, applied in computer parts, calculation, special data processing applications, etc., can solve problems affecting the accuracy of recommendation results, achieve the effect of improving recommendation accuracy and reducing computational complexity

Inactive Publication Date: 2020-05-29
HAIER DIGITAL TECH (SHANGHAI) CO LTD
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, there are some problems in the existing collaborative filtering recommendation algorithm, and the recommended results often require the accumulation of historical data
Since the original data has no corresponding historical data and the historical data has the characteristics of high dimensionality and sparseness, these factors seriously affect the accuracy of the recommendation results

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Personalized recommendation method and device, computer equipment and storage medium
  • Personalized recommendation method and device, computer equipment and storage medium
  • Personalized recommendation method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] figure 1 It is a flowchart of a personalized recommendation method provided by the first embodiment of the present invention. This embodiment is suitable for accurately making personalized recommendations to users. The method can be executed by a personalized recommendation device, which can be implemented by software and / Or hardware. Correspondingly, such as figure 1 As shown, the method includes the following operations:

[0033] S110: Perform clustering processing on the original sample data set by using a preset clustering algorithm to obtain a target data set.

[0034] Among them, the preset clustering algorithm may be a clustering algorithm selected according to actual needs, and the original sample data may be historical data associated with the user, for example, related data such as e-commerce products or movies and TV series that the user has browsed through a browser.

[0035] In the embodiment of the present invention, before personalized recommendation is made ...

Embodiment 2

[0043] figure 2 It is a flowchart of a personalized recommendation method provided in the second embodiment of the present invention. This embodiment is concreted on the basis of the above-mentioned embodiment. In this embodiment, a preset clustering algorithm is used to analyze the original sample data. The specific implementation of the target data set is obtained by clustering the data set. Correspondingly, such as figure 2 As shown, the method of this embodiment may include:

[0044] S210: Perform clustering processing on the original sample data set by using a preset clustering algorithm to obtain a target data set.

[0045] In an optional embodiment of the present invention, the preset clustering algorithm may adopt an improved K-means clustering algorithm. Correspondingly, S210 may specifically include the following operations:

[0046] S211. Randomly select k objects in the original sample data set as initial cluster centers.

[0047] In the embodiment of the present inve...

Embodiment 3

[0069] Figure 3a It is a flowchart of a personalized recommendation method provided in the third embodiment of the present invention. This embodiment is concreted on the basis of the above-mentioned embodiment. In this embodiment, an optimized random forest algorithm is used to analyze the target The data set is classified and processed to obtain the specific implementation method of the target recommendation object. Corresponding, such as Figure 3a As shown, the method of this embodiment may include:

[0070] S310: Perform clustering processing on the original sample data set by using a preset clustering algorithm to obtain a target data set.

[0071] S320: Perform classification processing on the target data set through an optimized random forest algorithm to obtain a target recommendation object.

[0072] Correspondingly, S320 may specifically include the following operations:

[0073] S321. Perform data preprocessing on the target data set to obtain a training set and a test se...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the invention discloses a personalized recommendation method and device, computer equipment and a storage medium, and the method comprises the steps: carrying out the clustering of an original sample data set through a preset clustering algorithm, and obtaining a target data set; performing classification processing on the target data set through an optimized random forest algorithm to obtain a target recommendation object; and performing TopN recommendation on the target recommendation object through a collaborative filtering recommendation algorithm. According to the technical scheme of the embodiment of the invention, the calculation complexity of the recommendation algorithm can be reduced, and the recommendation precision of the recommendation algorithm is improved.

Description

Technical field [0001] The embodiments of the present invention relate to the field of data mining technology, and in particular, to a personalized recommendation method, device, computer device, and storage medium. Background technique [0002] With the advancement of technology and the rapid development of related technologies in the field of artificial intelligence, informatization and intelligence will become the main signs of the Internet era. The rapid development of the Internet will also cause problems such as huge amount of information and rapid exponential growth. For the challenge of the Internet—information overload, the recommendation algorithm can solve this problem to a certain extent, and it has been widely used in many fields. For example, when a user is shopping online, the merchant recommends the products of interest to the user based on the user's browsing history and purchase history. However, user requirements are usually uncertain and vague, so excellent r...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9535G06K9/62
CPCG06F18/23213G06F18/24323
Inventor 陈录城张俊普孙兆群汪洪涛刘希军王浩宇
Owner HAIER DIGITAL TECH (SHANGHAI) CO LTD