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

Product recommendation method, apparatus, terminal and computer readable storage medium

A recommendation method and product technology, applied in the field of artificial intelligence, can solve problems such as inability to recommend suitable products for users, inability to identify user intentions, etc., and achieve the effect of saving labor costs

Pending Publication Date: 2019-01-29
ONE CONNECT SMART TECH CO LTD SHENZHEN
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of this application is to at least solve one of the above-mentioned technical defects, especially in the form of automatic chat product recommendation, based on the existing product recommendation method, it is impossible to automatically and accurately identify effective user intentions from a large number of dialogue contents, so as to Technical defects that make it impossible to recommend suitable products to users based on identified user intent

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
  • Product recommendation method, apparatus, terminal and computer readable storage medium
  • Product recommendation method, apparatus, terminal and computer readable storage medium
  • Product recommendation method, apparatus, terminal and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] The embodiment of the present application provides a product recommendation method, such as figure 1 As shown, the method includes:

[0032] Step S101: Input the first dialogue text information for the product into a preset text classification model, and determine the user intent type corresponding to the first dialogue text information.

[0033] The first dialogue text information is dialogue text information generated by the interaction between the user and the automatic chat system in the automatic chat mode.

[0034] Step S102, when the user's intention type is the tendency type, acquire second dialogue text information for the product.

[0035] Wherein, the user's intention type is the tendency type, indicating that the user has a tendency to purchase the product; wherein, the second dialogue text information may be the same dialogue text information as the first dialogue text information, or may be dialogue text different from the first dialogue text information ...

Embodiment 2

[0041] The embodiment of the present application provides another possible implementation manner. On the basis of the first embodiment, the method shown in the second embodiment is also included, wherein,

[0042] Further, input the preset text classification model for the first dialogue text information of the product, and determine the user intent type corresponding to the first dialogue text information, including:

[0043] The dialog type of the first dialog text information is determined by using a preset text classification model.

[0044] According to the dialogue type, the user intent type corresponding to the first dialogue text information is determined.

[0045] The text classification model is a pre-established model based on the dialogue text information and the dialogue type, and is used to determine the dialogue type corresponding to the dialogue text information, and different dialogue types correspond to different user intent types.

[0046] Further, in step S1...

Embodiment 3

[0129] The embodiment of the present application provides a product recommendation device 30, such as image 3 As shown, the product recommendation device 30 may include: a user intention type determination module 301, a dialogue text information acquisition module 302, a user intention information determination module 303, and a product recommendation module 304, wherein,

[0130] The user intent type determination module 301 is configured to input the first dialogue text information for the product into a preset text classification model, and determine the user intent type corresponding to the first dialogue text information.

[0131] The dialogue text information acquisition module 302 is configured to acquire the second dialogue text information for the product when the user's intention type is the tendency type.

[0132] Among them, the user's intention type is the tendency type, indicating that the user has the tendency to purchase the product.

[0133] The user intent ...

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

Embodiments of the present application provide a product recommendation method, apparatus, terminal, and computer-readable storage medium. The method includes: inputting first session text informationfor a product into a preset text classification model to determine a user intention type corresponding to the first session text information; acquiring a second conversation text information for theproduct when the user intention type is a tendency type; inputting the second dialog text information into a preset intention recognition model to determine user intention information corresponding tothe second dialog text information; and generating product recommendation information corresponding to user intention information. According to the invention, purchase tendency judgment is made preliminarily based on the user intention type of the first conversation text information, when the type of the user's intention is tendency type, the second conversation text information is determined andthe user intention information of the second conversation text information is determined. The user's intention information can accurately reflect the user's purchase intention, and then the user canbe recommended the appropriate product according to the user's intention information.

Description

technical field [0001] The present application relates to the field of artificial intelligence technology, and in particular, the present application relates to a product recommendation method, device, terminal, and computer-readable storage medium. Background technique [0002] In the prior art, the way of recommending products is usually in the form of recommending products to users based on a search system or recommending products to users based on manual customer service. Search the system to match product information that matches product keywords; implement product recommendation based on the matched product information; recommend products to users based on manual customer service. purchase propensity to achieve product recommendations. [0003] However, the product recommendation form based on the automatic chat mode, that is, recommending products to the user through the content of the dialogue between the system and the user, because the amount of information in the...

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): G06Q30/02G06F16/35
CPCG06Q30/0269
Inventor 柳明辉徐国强邱寒
Owner ONE CONNECT SMART TECH CO LTD SHENZHEN