Method and device for evaluating effect of recommendation model

A model and recommendation data technology, applied in the computer field, can solve problems such as inaccurate evaluation results and achieve accurate evaluation results

Pending Publication Date: 2022-05-31
SHANGHAI HODE INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, an effect evaluation method, device, computer equipment and computer-readable storage medium of a recommended model are now provided to solve the problem of inaccurate evaluation results obtained by existing evaluation methods

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 evaluating effect of recommendation model
  • Method and device for evaluating effect of recommendation model
  • Method and device for evaluating effect of recommendation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The advantages of the present application will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0057] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

[0058] The terminology used in the present disclosure is for the purpose of describing particular embodiments only, and is not intended to limit the present disclosure. As used in this disclosure and the appended claims, the singula...

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 discloses an effect evaluation method for a recommendation model. The method comprises the following steps: acquiring first historical interaction data and a historical behavior log of each to-be-tested user for each piece of recommendation data, and determining a text emotion value of each to-be-tested user for each piece of recommendation data according to the first historical interaction data and the historical behavior log; acquiring second historical interaction data and historical relationship data of each to-be-tested user for an uploader of each piece of recommended data in the to-be-tested dynamic set, and determining a user emotion value of each to-be-tested user for the uploader of each piece of recommended data according to the first historical interaction data, the second historical interaction data and the historical relationship data; according to the text emotion value and the user emotion value, determining an emotion tendency value of each to-be-tested user for each piece of recommended data; and determining the recommendation effect of the recommendation model according to the emotion tendency values of the first preset number of to-be-tested users to the second preset number of recommendation data. The accuracy can be improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a method and device for evaluating the effect of a recommendation model. Background technique [0002] Currently, short video platforms such as Douyin and Kuaishou use a large number of decentralized recommendation models (recommendation algorithms) for content distribution. In order to design a better recommendation model, in the existing technology, after the recommendation model is designed, it usually adopts the method of rapid iteration and online A / B Test, and obtains the user's behavior log online under the condition of user authorization. , and then evaluate the relevant indicators according to the user's behavior log, and then evaluate the designed recommendation model according to the relevant indicators. For example, the recommendation model is evaluated through user behavior indicators, among which user behavior indicators include exposure, page views, cl...

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): G06F16/335G06F16/38G06F40/242G06F16/18
CPCG06F16/335G06F16/38G06F40/242G06F16/1815
Inventor 程浩宇沈湘
Owner SHANGHAI HODE INFORMATION 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