Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Object recommendation method and device based on intelligence, and storage medium

A recommendation method and object technology, applied in character and pattern recognition, special data processing applications, instruments, etc., can solve problems such as poor anti-noise ability, inability to accurately and comprehensively mine object features, and lack of global distribution characteristics of objects

Active Publication Date: 2020-07-07
TENCENT TECH (SHENZHEN) CO LTD
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, it is generally possible to generate an object relationship network based on the user's operations on objects, and a trained relationship mining model can be used to mine the relationship between objects. However, the existing relationship mining models are based on the object relationship network. Mining the relationship between the object and other objects locally lacks the global distribution characteristics of the object in the object relationship network, so it cannot accurately and comprehensively mine the characteristics between objects. In addition, because the training of the relationship mining model is a black box, so Poor noise immunity in relationship mining

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
  • Object recommendation method and device based on intelligence, and storage medium
  • Object recommendation method and device based on intelligence, and storage medium
  • Object recommendation method and device based on intelligence, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] In this embodiment, description will be made from the perspective of an object relationship mining device, and the object relationship mining device may specifically be integrated in a network device, such as a terminal or a server. In the following embodiments, the object relationship mining device will be integrated in the server for detailed description.

[0046] An embodiment of the present invention provides an object relationship mining method, including: generating an object relationship network between the objects according to the user's operation information on the objects; Local correlation feature extraction to obtain the initial feature information of the object; according to the initial feature information of the object, perform global distribution feature extraction on the objects in the object relationship network to obtain the global distribution feature information of the object; The global distribution feature information is updated to update the param...

Embodiment 2

[0136] According to the methods described in the foregoing embodiments, an example will be given below to further describe in detail the situation of performing object recommendation based on the target feature information. In this embodiment, description will be made by taking the recommendation apparatus specifically integrated in a network device as an example.

[0137] Such as Figure 2b As shown, based on the above-mentioned trained model, the specific process of the vehicle recognition method can be as follows:

[0138] 201. When detecting a user's operation on a target object, the network device acquires target feature information of the object.

[0139] The network device can be a terminal or a server.

[0140] The network device can acquire the target feature information or the adjusted target feature information of the object from the block chain.

[0141] Wherein, the object refers to all objects used for training, and the target object refers to the object curre...

Embodiment 3

[0150]In order to better implement the above method, an embodiment of the present invention also provides an object recommendation device, and the vehicle identification device may specifically be integrated into a network device, such as a terminal or a server.

[0151] For example, if image 3 As shown, the object recommendation device includes a generation unit 301, a local feature extraction unit 302, a global distribution feature information extraction unit 303, an update unit 304, a target feature information extraction unit 305, and a recommendation unit 306, as follows:

[0152] (1) a generating unit 301, configured to generate an object relationship network between the objects according to the user's operation information on the objects;

[0153] (2) The local feature extraction unit 302 extracts local associated features from the objects in the object relationship network according to a preset relationship mining model to obtain initial feature information of the obj...

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

An embodiment of the invention discloses an object recommendation method and an object recommendation device based on intelligence, and a storage medium. The object recommendation method comprises thesteps of: generating an object relationship network according to operation information of a user for an object; performing local association feature extraction on the object in the object relationship network to obtain initial feature information of the object according to a preset relationship mining model; performing global distribution feature extraction on the object in the object relationship network to obtain global distribution feature information of the object according to the initial feature information of the object; updating parameter information of the preset relationship mining model according to the global distribution feature information to obtain a target relationship mining model; performing feature extraction on the object relationship network according to the target relationship mining model to obtain target feature information of the object; and performing object recommendation according to the target feature information. According to the object recommendation method and the object recommendation device, the association relationship between the objects can be mined more comprehensively and accurately, so that the objects can be recommended to the user more accurately.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an object recommendation method, device and storage medium based on intelligence. Background technique [0002] In recent years, with the continuous popularization of the Internet, more and more users are participating in network activities. Therefore, the user's operation information on different objects on the Internet has increased massively, such as browsing a certain product or song or a user, Operational information such as commenting and sharing. At this stage, the user's operation information on objects has become more and more valuable. By analyzing the user's operation information on objects, it can help the system understand the relationship between objects more comprehensively, and then recommend to users based on user operations. Associated objects to better serve users. [0003] At present, it is generally possible to generate an object rel...

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
IPC IPC(8): G06F16/2458G06F16/9535G06K9/62G06N3/04
CPCG06F16/9535G06F16/2465G06N3/045G06F18/214
Inventor 陈思宏牟帅肖万鹏鞠奇
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products