Recommendation method, recommendation device and electronic equipment

A recommendation method and recommendation algorithm technology, applied in the computer field, can solve the problems of poor novelty and diversity of recommendation results, achieve the effect of improving novelty and diversity, and improving user experience

Active Publication Date: 2017-11-28
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] This application provides a method to solve the problem of poor novelty and diversity of recommendation results existing in the prior art

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
  • Recommendation method, recommendation device and electronic equipment
  • Recommendation method, recommendation device and electronic equipment
  • Recommendation method, recommendation device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] A recommended method disclosed in this embodiment, such as figure 1 As shown, the method includes: step 100 to step 120.

[0025] Step 100: Establish a recommendation algorithm pool based on the first preset optimization index, wherein the recommendation algorithm pool includes M recommendation algorithms, and M is an integer greater than or equal to 2.

[0026] The first preset optimization index is a business index for measuring the optimization result of the recommendation algorithm. For example, for search and information recommendation services, the first preset optimization indicators of the recommendation algorithm include but are not limited to: click rate (CTR: Click Through Rate), conversion rate (CVR: Click Value Rate), traffic (PV (Page View) Any one or more of them. By calculating the historical data of the recommendation algorithm running online for a period of time, the value of the first preset optimization index can be obtained, and it can be judged wh...

Embodiment 2

[0035] A recommended method disclosed in this embodiment, such as figure 2 As shown, the method includes: Step 200 to Step 240.

[0036] Step 200: Establish a recommendation algorithm pool based on the first preset optimization index, wherein the recommendation algorithm pool includes M recommendation algorithms, and M is an integer greater than or equal to 2.

[0037] In this embodiment, the first preset optimization index is: Click Through Rate (CTR: Click Through Rate) and Conversion Rate (CVR: Click Value Rate) as examples to illustrate a specific scheme for selecting a recommendation algorithm.

[0038] The industry generally measures the quality of a recommendation algorithm through online AB testing, that is, running multiple recommendation algorithms online at the same time, such as 20, after running online for a period of time, such as after a quarter, according to different recommendation algorithms The value of the optimization index can judge whether the recommen...

Embodiment 3

[0088] A recommendation device disclosed in this embodiment, such as Figure 4 As shown, the device includes:

[0089] The algorithm pool establishment module 300 is used to establish a recommended algorithm pool based on the first preset optimization index, wherein the recommended algorithm pool includes M recommended algorithms, and M is an integer greater than or equal to 2;

[0090] The recommendation algorithm selection module 310 is used to select a recommendation algorithm in the recommendation algorithm pool according to the number of calls of the recommendation engine;

[0091] The recommendation module 320 is configured to recommend information to the user through the selected recommendation algorithm.

[0092] The recommendation device disclosed in the embodiment of the present application establishes a recommendation algorithm pool based on the first preset optimization index, and selects a recommendation algorithm in the recommendation algorithm pool according to...

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 invention provides a recommendation method, and belongs to the technical field of computers. By the aid of the recommendation method, the problems of poor novelty and diversity of existing recommendation results in the prior art can be solved. The recommendation method includes establishing recommendation algorithm pools on the basis of first preset optimization indexes; selecting a recommendation algorithm in the recommendation algorithm pools according to called times of recommendation engines; recommending information to users by the aid of the selected recommendation algorithm. The recommendation method has the advantages that the recommendation algorithm is dynamically selected according to the called times of the recommendation engines, in other words, the recommendation algorithm is dynamically selected according to application page access times of the users, accordingly, the business index optimization requirements can be assuredly met, the novelty and the diversity of recommendation results can be effectively improved, and the experience of the users further can be enhanced.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a recommendation method and device, and electronic equipment. Background technique [0002] The recommendation system in the existing technology will combine the user's portrait, location, scene and other information to carry out multi-dimensional information recall, and then perform a unified ranking, and then return the search results to the user. Even if multiple recommendation algorithms are set in the recommendation system and multiple recommendation lists can be generated, due to the use of fixed recommendation algorithms, for the same user, the presented top recommendation results usually do not change, and the novelty is poor. Moreover, the same result is always recommended to users, and the recommendation result is too monotonous and lacks diversity, which may lead to the loss of users. [0003] It can be seen that the recommendation methods in the prior art...

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): G06F17/30
CPCG06F16/951
Inventor 曹佐陈文石刘志权潘强李春阳潘晖朱今朝吴尚
Owner BEIJING SANKUAI ONLINE TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap