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

Method and device for pushing objects to users based on reinforcement learning model

A technology of reinforcement learning and objects, applied in the field of machine learning, to achieve the effect of improving the click-through rate

Active Publication Date: 2020-08-21
TAOBAO CHINA SOFTWARE
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of this specification aims to provide a more effective solution for determining the push object list for users based on the reinforcement learning model, so as to solve the deficiencies 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
  • Method and device for pushing objects to users based on reinforcement learning model
  • Method and device for pushing objects to users based on reinforcement learning model
  • Method and device for pushing objects to users based on reinforcement learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Embodiments of this specification will be described below with reference to the accompanying drawings.

[0051] figure 1 A schematic diagram of an object pushing system 100 according to an embodiment of the present specification is shown. The object push system is, for example, a question prediction system, which enables a user to automatically predict a list of questions that the user may want to ask when contacting customer service, and display the list of questions on the customer service page to improve user experience and Save manual customer service costs. It can be understood that the object push system 100 according to the embodiment of the present specification is not limited to push the list of inquiry questions, but can be used to push lists of various objects, such as commodities, film and television works, news and so on. Such as figure 1 As shown, the system 100 includes a model unit 11 , a training unit 12 and a sorting unit 13 . The model unit 11 inc...

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

A method and device for determining a push object list for a user based on a reinforcement learning model. The method comprises: for each group of object lists, obtaining the ith state feature vector (S202); inputting the ith state feature vector into the reinforcement learning model to enable the reinforcement learning model to output a weight vector corresponding to the ith state feature vector (S204); obtaining sorting feature vectors of objects in a candidate object set corresponding to the group of object lists (S206); calculating scores of the objects in the candidate object set on the basis of a point product of the sorting feature vectors of the objects in the candidate object set and the weight vector (S208); and for the M groups of object lists, determining updated M groups of object lists on the basis of the scores of the objects in M candidate object sets corresponding to the M groups of object lists (S210), wherein each group of object lists in the updated M groups of object lists comprises i objects.

Description

technical field [0001] The embodiments of this specification relate to the field of machine learning, and more specifically, relate to a method and an apparatus for determining a push object list for a user based on a reinforcement learning model. Background technique [0002] Traditional customer service is manpower / resource intensive and time consuming, therefore, it is important to build intelligent assistants that can automatically answer questions users face. Recently, there has been increased focus on how to use machine learning to better build such intelligent assistants. As the core function of customer service robots, user intent prediction aims to automatically predict the questions that users may want to ask, and present candidate questions to users for their choice to reduce the cognitive load of users. More specifically, the user intent prediction task can be viewed as a Top N item recommendation task, where each predetermined question is an intent class. Curr...

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 Patents(China)
IPC IPC(8): G06F16/9535G06N20/00
CPCG06F16/9535G06N20/00
Inventor 陈岑胡旭傅驰林张晓露
Owner TAOBAO CHINA SOFTWARE