Supercharge Your Innovation With Domain-Expert AI Agents!

Object push method and device

An object and target object technology, applied in the field of Internet applications, can solve the problems of inability to effectively distinguish keywords and low reliability

Active Publication Date: 2016-03-30
北京小度互娱科技有限公司
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method relies on the context information of keywords, and for keywords lacking context information, it will not be able to effectively distinguish the entities referred to by keywords. Therefore, in the prior art, it is determined based on context information The entity's object push method is less reliable

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 push method and device
  • Object push method and device
  • Object push method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0140] Take the keyword "Egg Fried Rice" as an example. This keyword may refer to food, or it may refer to Yu Chengqing's MV work "Egg Fried Rice".

[0141] Among them, there may be the title information of the webpage "Gourmet World - How to Make Egg Fried Rice", and the search term "Yu Chengqing Egg Fried Rice" may also exist. Title information of related web pages may be utilized as context information.

[0142] For the above-mentioned keywords, if only based on the title information, it is sometimes difficult to determine which target object to give the user the priority to match the referred entity. If you refer to other contextual information, you can determine the referred entity. For example, for the title information is The target object related to the picture of "egg fried rice" can be easily obtained based on the context information of the picture that the title information is that the picture of "egg fried rice" refers to food, not music. For example, if the user ...

Embodiment 2

[0148] Such as Figure 4 As shown, the following takes the keyword "egg fried rice" as an example and the context information as the title information "egg fried rice glory days" as an example, and describes the method of obtaining the weight value of the entity referred to by the keyword "egg fried rice" in the context information .

[0149] Such as Figure 4 As shown, by matching in the knowledge graph, two entities that the keyword "egg fried rice" can refer to can be obtained, namely "food / egg fried rice" and "music / egg fried rice". Similarly, by matching in the knowledge graph, related entities of the keyword "egg fried rice" can be obtained, that is, two entities that can be referred to by other keywords "glory years" that co-occur with the keyword "egg fried rice" in the context information , namely Music / Glory Days and Movies / Glory Days.

[0150] The goal is to obtain weight values ​​like this:

[0151] the s t (Food / Egg Fried Rice|Egg Fried Rice)

[0152] the s ...

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 provides an object push method. The method comprises following steps: obtaining corresponding keywords of a client; obtaining M entities representing keywords, wherein M is an integer larger than or equal to 2; adjusting first probability of the ith entity of the M entities based on historical records of a user for the client in order to obtain second probability of the ith entity; sequencing target objects matching the M entities based on second probabilities of the M entities in order to obtain a sequencing result; and pushing the sequencing result to the client. The embodiment of the invention further provides an object push device. The technical scheme provided by the embodiment of the invention helps to improve reliability of object push.

Description

【Technical field】 [0001] The invention relates to Internet application technology, in particular to an object pushing method and device. 【Background technique】 [0002] In the current retrieval technology and recommendation technology, it often happens that a keyword can refer to multiple entities at the same time. For example, "apple" can refer to a kind of food or a kind of mobile phone. In this case, according to the search term entered by the user, when pushing the searched target object to the user, or actively recommending the target object to the user , it is necessary to first determine which entity matches the target object to be pushed, or to determine which entity matches the target object to be pushed first. [0003] In the prior art, the words in the context information of the keywords are used to match in the entity library to obtain the similarity between the words and each entity, and then when displaying the target objects that match the keywords, they are ...

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): G06F17/30
Inventor 马小龙
Owner 北京小度互娱科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More