Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

User intention recognition method and device

A technology of user intent and recognition method, applied in the field of data analysis, can solve the problems of low recognition accuracy, low recall rate, and inability to know which product the user is targeting, and meets the requirements of real-time response, accuracy and recall rate Improve and avoid the effect of being too slow to respond

Active Publication Date: 2015-09-30
ZHEJIANG TMALL TECH CO LTD
View PDF3 Cites 92 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the process of user chatting, the usual chat corpus is short text, and the pure language model has the disadvantages of low recognition accuracy and low recall rate
In addition, there are many cases of multi-meaning in natural language, and it is difficult for a pure language model to accurately identify user intentions
At the same time, for short texts ("Yes", "Okay", "How about this", "No more", etc.), the language model cannot fully and accurately identify the real intention of the user, for example: the user browsed a product and asked the other party " Is this black available?" The language model can only recognize that the user asks whether the black color of a certain product is in stock, but it cannot know which product the user is targeting
Another example: when the user says "no more" to the other party, the language model can only recognize the user's negative intention, and the specific intention is completely unpredictable

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
  • User intention recognition method and device
  • User intention recognition method and device
  • User intention recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0092] Current dialogue text: Buyer A says to seller B: "Boss, I don't want the sweater anymore."

[0093] Behavior data: Buyer A browses a red sweater model SII12345 in seller B’s store, takes a photo of the sweater and pays for it; one hour later, buyer A asks seller B in the chat tool.

[0094] Textual subject headings identified by the semantic topic model: Rejected goods.

[0095] Behavioral keywords identified by the user behavior model: paid for goods, placed orders for goods, browsed goods.

[0096] Combining text keywords and behavior keywords into a vector is input to the decision maker to identify the real intention of buyer A: to cancel the order.

example 2

[0098] Current dialogue text: Buyer A says to seller B: "Boss, I don't want the sweater anymore."

[0099] Behavioral data: Buyer A browses a red sweater model SII12345 in seller B's store, takes a photo of the sweater and pays for it. The clothes were received 3 days later, and the logistics data showed that they had been signed for. At the same time, buyer A asked seller B in the chat tool in the afternoon.

[0100] Textual subject headings identified by the semantic topic model: Rejected goods.

[0101] Behavioral keywords identified by the user behavior model: goods signed for, goods arrived, goods shipped by the seller, goods paid for, and goods ordered.

[0102] Combining text keywords and behavior keywords into a vector is input to the decision maker to identify the real intention of buyer A: to return the product.

[0103] Comparing Example 1 and Example 2, it can be seen that when a buyer user sends the same dialogue text, different user intentions can be identifie...

example 3

[0105] Current dialogue text: Buyer A said to seller B: "Boss, don't express delivery 1, it is very slow, change express delivery 2 for me".

[0106] Behavioral data: Buyer A browses a red sweater model SII12345 in seller B’s store, takes a photo of the sweater and pays for it at the same time, buyer A asks seller B in the chat tool.

[0107] Text subject words recognized by the semantic topic model: change courier, don't courier, specify courier.

[0108] Behavioral keywords identified by the user behavior model: paid for goods, placed orders for goods, browsed goods.

[0109] Combining text keywords and behavior keywords into a vector is input to the decision maker to identify the real intention of buyer A: to specify the courier (rather than "changing courier" which is the closest semantic model).

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 a user intention recognition method and device. The method includes the steps that in the process that a first user and a second user conduct conversation through an instant messaging tool, a first conversation text sent to the second user by the first user is received; the target text content to be analyzed is determined according to the first conversation text; first behavior data of the operation behavior executed by the first user and related to the second user are obtained in a user behavior database associated with the instant messaging tool; semantic analysis is conducted on the target text content in combination with the first behavior data, and the user intention recognition result is determined. By means of the user intention recognition method and device, the real intension of users can be recognized more accurately.

Description

technical field [0001] The present application relates to the technical field of data analysis, in particular to a method and device for identifying user intentions. Background technique [0002] With the continuous improvement of the e-commerce user behavior database, and the rapid development of traditional communication, mobile communication and other technologies, more and more people obtain the commodities they need through online shopping. All aspects of life provide great convenience for people's life. [0003] In the process of online shopping, buyers often need to communicate with sellers online. For example, after receiving a product, a buyer finds that the color or size is not suitable and needs to be returned or returned. Exchange, at this time, the buyer user can contact the seller's customer service personnel through the online communication tool, and communicate with the customer service personnel about the return and exchange. [0004] Under the traditional...

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): G06F17/27
Inventor 陈俞
Owner ZHEJIANG TMALL TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com