Information recommendation method and device

A technology for information recommendation and recommendation information, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as user recommendation, poor user experience, and neglect.

Active Publication Date: 2016-07-20
ALIBABA (CHINA) CO LTD
View PDF12 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, since the above-mentioned recommendation method ignores the most valuable recent user request and the user's current focus (point of interest) reflected by it, it is impossible to make timely feedback and differentiated display of the user's current behavior and interest transfer. Therefore, it is impossible to recommend content that meets the user's current concerns, and the user experience is poor.

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
  • Information recommendation method and device
  • Information recommendation method and device
  • Information recommendation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] figure 1 A flowchart showing an information recommendation method according to an embodiment of the present invention. Such as figure 1 As shown, the information recommendation methods mainly include:

[0059] Step S100, according to the feature set of each first object requested by the user within a predetermined time period and the request time, determine the feature set of the second object that the user is currently interested in;

[0060] Step S110, determine the common features of the feature set of the second object and the feature sets of the third objects in the initial recommendation information, and calculate the similarity between the corresponding third object and the second object according to the common features;

[0061] Step S120, respectively adjusting the object weights of the corresponding third objects according to the calculated similarities; and

[0062] Step S130 , according to the adjusted object weights of the third objects, re-sort the ob...

Embodiment 2

[0086] The main difference between this embodiment and the foregoing Embodiment 1 is that, in this embodiment, the foregoing step S1002 may be executed specifically by the following formula 2.

[0087] p l = Σ k = 1 n βpt l k / ( t h - ti l k ) Formula 1

[0088] Among them, t l Indicates the feature to be processed, n indicates that there is an object feature to be processed in all the first objects t l The number of the first object, pt lk Indicates the characteristics of the object to be processed t l The feature t of the object to be processed in each first object where it is located l The feature weights o...

Embodiment 3

[0101] image 3 A diagram showing a specific application example of the information recommendation method according to an embodiment of the present invention. In this embodiment, the information recommendation method can be implemented using the following six entities: initial recommendation information list, object feature information, user request sequence (recent), user's current point of interest, filter, and sorter. Among them, an information recommendation process for a user may correspond to a list of recommended information, a sequence of service requests, a determination of a user's point of interest, reading of object characteristics multiple times, and running a filter and a sorter once. The specific implementation method is as image 3 As shown, the specific process is as follows.

[0102] 1) According to the user's past behavior data stored in the user's past behavior log, the initial recommendation information list calculated online or read offline based on the...

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 an information recommendation method and device.The method comprises the steps of determining the characteristic set of a second object in which a user is interested currently according to the characteristic set of each first object requested by the user within a preset time period and requesting time; determining the common characteristic of the characteristic set of the second object and the characteristic set of each third object in initial recommended information, and calculating the similarity of each third object and the second object according to the corresponding common characteristic; adjusting the weight of each third object according to the corresponding similarity which is calculated; conducting object ranking on the initial recommended information again according to the adjusted weight of each third object, and recommending information to the user again according to the ranking result.By the adoption of the method and device, content according with the current concern of the user can be recommended to the user, and user experience is improved.

Description

technical field [0001] The present invention relates to the technical field of information recommendation, in particular to an information recommendation method and device. Background technique [0002] The recommendation system of the current website usually uses the service log generated by the user's past behavior as a data set, and generates a specific product recommendation list for the user or product after calculation and processing based on data mining and machine learning, that is, the information recommendation list. When a user initiates a service request, the recommendation system directly reads the recommendation list based on the user or the product information he is browsing and displays it to the user. [0003] However, since the above-mentioned recommendation method ignores the most valuable recent user request and the user's current focus (point of interest) reflected by it, it is impossible to make timely feedback and differentiated display of the user's c...

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
CPCG06F16/9535
Inventor 吴航盖炳帅尹玉宗林岳顾思斌姚键潘柏宇王冀
Owner ALIBABA (CHINA) 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