User intention identification method and user intention identification system

A technology of user intent and recognition method, applied in special data processing applications, instruments, unstructured text data retrieval, etc., can solve problems such as poor model scalability and inability to understand user business needs, and achieve a comprehensive recognition effect

Active Publication Date: 2018-07-20
CHINA UNIONPAY
View PDF10 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Conversational artificial intelligence oriented to general-purpose scenarios can chat with users, but cannot understand users' business needs, and often resorts to the Internet to obtain answers from user dialogue information; on the other hand, although it can meet business needs for specific scenarios, it is difficult A large amount of manpower is required to analyze the characteristics of user dialogues to build rule templates. The workload required for multi-business scenarios is skyrocketing, and the scalability of the model is not good.

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 identification method and user intention identification system
  • User intention identification method and user intention identification system
  • User intention identification method and user intention identification system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] This embodiment mainly involves the transfer scenario, for example, "transfer one hundred yuan to my dad".

[0082] (1) Step 1: key entity identification, the implementation steps are as follows:

[0083] 1.1 Word segmentation, part-of-speech tagging, and named entity recognition:

[0084] Give / p me / r dad / n transfer / v a hundred / m yuan / q money / n, the named entity set is empty.

[0085] 1.2 Get intent parameter candidates:

[0086] It can be seen from the word segmentation and part-of-speech tagging results that one hundred dollars is a combination of numeral m + quantifier q + noun n, and the noun "money" belongs to the money intention parameter, then money=one hundred dollars can be set.

[0087] 1.3 Intent parameter candidate standardization:

[0088] Since there are no intent parameters such as country and currency in the named entity collection, the default currency of money is RMB, and money=100 RMB.

[0089] (2) Step 2: Judgment of user intent, the implementat...

Embodiment 2

[0104] Example 2 involves the exchange rate query business scenario: the user puts forward a demand "I withdraw 1,000 Canadian dollars in Canada, and the deduction is more today than yesterday. I want to check the exchange rate?".

[0105] (1) Step 1: key entity identification, the implementation steps are as follows:

[0106] 1.1 Word segmentation, part-of-speech tagging, and named entity recognition:

[0107] I / r in / p 2: Canada / ns took / v / u 1000 / m block / q, / wp today / nt than / p yesterday / nt deducted / v got / u more / a, / wp me / r Want to / v check / v about the / m exchange rate / n? / wp;

[0108] The collection of named entities is {Canada / S-Ns}.

[0109] 1.2 Get intent parameter candidates:

[0110] From the word segmentation and part-of-speech tagging results, it can be seen that 1000 yuan is a combination of numeral m+quantifier q, and the quantifier "chunk" belongs to the money intention parameter, then money=1000 yuan can be set;

[0111] The part-of-speech tag of ...

Embodiment 3

[0132] Embodiment 3 involves the business scenario of introducing preferential activities: the user puts forward a demand "What preferential activities are there for UnionPay cards at Seoul Airport and Incheon Airport in South Korea?".

[0133] (1) Step 1: key entity identification, the implementation steps are as follows:

[0134] 1.1 Word segmentation, part-of-speech tagging, and named entity recognition:

[0135] UnionPay card / n at / pKorea / ns Seoul / ns airport / n and / cIncheon / ns airport / n have / vwhat / r discounts / vevents / v? / wp;

[0136] Named entity collection is empty {Seoul Airport / Ns, Incheon Airport / Ns}.

[0137] 1.2 Get intent parameter candidates:

[0138] From the results of word segmentation and part-of-speech tagging, it can be seen that "what" is used as a question word, and ques_tag=what;

[0139] "Promotion" and "Activity" are saved as the intent parameters of promotional activity introduction;

[0140] The set of named entities is {Seoul Airport / Ns, Incheon ...

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 relates to a user intention identification method and system. The method comprises a key entity identification step of performing natural language processing technology analysis for userconversation texts by taking words as units to obtain named entities, which serve as user intention parameter candidates, and a user intention judgment step of performing dependency grammar analysison the user conversation texts, performing word-by-word fuzzy matching according to a preset user intention key candidate set to obtain an intention keyword, judging a dependency relationship betweenthe intention keyword and the user intention parameter candidates obtained in the key entity identification step, and outputting a user intention identification result only in the presence of the dependency relationship. According to the method and the system, a user intention can be identified more accurately and comprehensively.

Description

technical field [0001] The invention relates to data processing and analysis technology, in particular to a user intention identification method and a user intention identification system. Background technique [0002] At this stage, the implementation schemes of conversational semantic understanding technology are mainly divided into general-purpose scenarios and specific scenarios. The former mainly uses the knowledge graph as the data basis, and according to the retrieval needs of users in the form of text, obtains intent parameters through natural language processing technologies such as named entity recognition and entity linking, supplemented by the method of intent recognition keyword matching (what, where, how, etc.) Carry out knowledge map retrieval and feedback corresponding answers; the latter uses professional knowledge base as the data basis, expands existing knowledge points in the form of rule templates, performs pattern matching according to user business int...

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): G06F17/30
CPCG06F16/3344G06F16/36
Inventor 佘萧寒万四爽费志军王宇张莉敏张琦邱雪涛乐旭刘想
Owner CHINA UNIONPAY
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