Service object sorting method and device

A technology of business objects and sorting methods, applied in the network field, can solve problems such as poor recall effect, high time complexity and data sparsity

Active Publication Date: 2020-01-03
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, due to the use of user behavior to calculate product similarity, the collaborative filtering algorithm has high time complexity and data sparsity when calculating the similarity of multiple sets, resulting in poor recall effect based on user behavior

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
  • Service object sorting method and device
  • Service object sorting method and device
  • Service object sorting method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] refer to figure 1 , which shows a flow chart of specific steps of a method for sorting business objects provided in Embodiment 1 of the present invention.

[0031] Step 101, acquiring historical behavior records.

[0032] The embodiment of the present invention can be used to determine the sorting scores of the business objects in the historical behavior records according to the historical behavior records, so as to recommend the business objects with higher ranking scores to the users.

[0033] Wherein, the business objects include but are not limited to commodities, information, and the like.

[0034] Historical behavior records include but are not limited to: users' browsing records of business objects, order records, settlement records, etc. within the historical time period. In practical applications, when a user places an order on the application platform, he often browses many business objects, and the platform will record the business objects that the user has...

Embodiment 2

[0052] refer to figure 2 , which shows a flow chart of specific steps of a method for sorting business objects provided by Embodiment 2 of the present invention.

[0053] Step 201, setting the training parameters of the ranking score prediction model, and training the ranking score prediction model through the business object feature sample set.

[0054] Among them, the training parameters include: input layer discrete feature dictionary size, output layer prediction sequence dictionary size, Embedding dimension, number of hidden nodes, number of network layers, operating environment, number of discrete features, number of continuous features, discrete feature embedding Combination method, parameter initialization method, optimization method selection, regularization penalty parameter size, drop probability, batch normalization, sequence length.

[0055] The input layer discrete feature dictionary size and the output layer prediction sequence dictionary size, Embedding dimen...

Embodiment 3

[0115] refer to image 3 , which shows a structural diagram of an apparatus for sorting business objects provided by Embodiment 3 of the present invention, and the details are as follows.

[0116] A data acquisition module 301, configured to acquire historical behavior records.

[0117] The feature information extraction module 302 is configured to extract feature information of at least one business object from the historical behavior records, wherein the feature information includes at least one discrete feature information and / or continuous feature information.

[0118] The ranking score prediction module 303 is used to input the discrete feature information and / or continuous feature information of each business object into the ranking score prediction model obtained in advance training, and predict the ranking score of each business object;

[0119] The sorting module 304 is configured to sort the business objects according to the sorting scores of the business objects. ...

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 service object sorting method and apparatus. The method comprises the steps of obtaining a historical behavior record; extracting feature information of at least one service object from the historical behavior record, wherein the feature information at least comprises one piece of discrete feature information and / or continuous feature information; inputting the discrete feature information and / or the continuous feature information of each service object into a pre-trained sorting score prediction model, and predicting a sorting score of each service object; and sortingthe service objects according to the sorting scores of the service objects. The problems of relatively high time complexity, relatively poor data sparsity and relatively poor recall effect caused bya collaborative filtering algorithm in the prior art are solved. According to the method, the pre-trained sorting score prediction model is adopted to predict the sorting scores of the service objects, and sorting is performed to guide recommendation, so that the time complexity is reduced, the problem of data sparsity is solved, and the recall effect is improved.

Description

technical field [0001] The embodiments of the present invention relate to the field of network technology, and in particular to a method and device for sorting business objects. Background technique [0002] For the field of neural network technology, personalized recommendation can recommend information to users and solve the problem of information overload for users. In the food delivery industry, personalized recommendations often recommend to users some products that users may care about based on their historical orders and current search terms. A personalized recommendation system mainly includes a recall module and a ranking module. Among them, the recall module retrieves candidate products from the system according to the user's historical behavior and real-time behavior, and the sorting module sorts the candidate products and presents them to the user. [0003] In the prior art, the steps of product recall through the collaborative filtering algorithm mainly includ...

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): G06F16/955G06F16/9535G06N3/04G06N3/08G06Q10/04G06Q30/06
CPCG06N3/049G06N3/08G06Q10/04G06Q30/0631G06F16/9535G06F16/955G06Q30/06G06F17/00G06Q30/0282G06N3/048G06N3/044
Inventor 钟超刘怀军刘海文
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