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

Named entity determination method, electronic equipment and computer storage medium

A technology for naming entities and determining methods, applied in the computer field, can solve problems such as inability to obtain information, and achieve the effects of improving accuracy, improving efficiency, and accurately collecting

Pending Publication Date: 2022-03-11
ALIBABA DAMO (HANGZHOU) TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, in the process of information query (such as querying order status, querying telephone charges or querying electricity charges, etc.) However, due to pronunciation, homophones, or environmental noise, it is impossible to obtain accurate information that users want to express.

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
  • Named entity determination method, electronic equipment and computer storage medium
  • Named entity determination method, electronic equipment and computer storage medium
  • Named entity determination method, electronic equipment and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0019] In this embodiment, it will be described by taking the method as an example where the method can be applied to an intelligent dialogue system or other self-service systems (such as a self-service inquiry system). The intelligent dialogue system can conduct multiple rounds of dialogues with the user. During the dialogue, it uses an external knowledge base to perform fine-grained text recognition on each slot in the named entity (such as each character in the named entity), and combines multiple rounds of named entity Accumulation of information and selection of dialogue strategies to obtain accurate named entity information.

[0020] In a usage scenario, such as Figure 1A As shown, the user performs voice interaction with the intelligent dialogue system through the intelligent device 100 (such as a smart phone, a smart speaker, etc.). The intelligent dialogue system includes a data processing device 200 and a knowledge base 300 for data processing, and candidate knowled...

Embodiment 2

[0043] refer to Figure 2A , shows a flow chart of the steps of the method for determining a named entity in Embodiment 2 of the present application.

[0044] In this embodiment, for ease of understanding, before describing the steps of the method in detail, the framework for implementing the method is briefly described as follows:

[0045] The structure of the intelligent dialogue system is as follows: Figure 2B As shown, it includes several main parts such as intent recognition module, dialog strategy module and state accumulation module. Among them, the intention recognition module is mainly used for intention extraction, knowledge point extraction and matching. The state accumulation module is mainly used for state accumulation of named entity information and state accumulation of system actions. The dialog strategy module is mainly used to determine the dialog strategy and answer sentences.

[0046] In an example, the intent recognition module includes an extraction ...

Embodiment 3

[0109] refer to image 3 , shows a structural block diagram of an apparatus for determining a named entity in Embodiment 3 of the present application.

[0110] In this embodiment, an apparatus for determining a named entity is provided, including:

[0111] The first acquiring module 302 is used to acquire the user's historical dialogue information and current reply sentence;

[0112] The second acquisition module 304 is configured to perform intent extraction and knowledge point extraction on the current reply sentence based on the historical dialogue information, so as to obtain intent information and knowledge points for determining characters in the named entity;

[0113] A matching module 306, configured to match the knowledge point with preset candidate knowledge points to obtain a matching result;

[0114] The determining module 308 is configured to determine the named entity information and the response sentence corresponding to the reply sentence according to the mat...

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 embodiment of the invention provides a named entity determination method, electronic equipment and a computer storage medium. The named entity determination method comprises the following steps: acquiring historical dialogue information and a current reply statement of a user; performing intention extraction and knowledge point extraction on the current reply statement based on the historical dialogue information to obtain intention information and knowledge points used for determining characters in a named entity; matching the knowledge point with a preset candidate knowledge point to obtain a matching result; and determining named entity information and a response statement corresponding to the reply statement according to the matching result and the intention information. According to the method, accurate information of the named entity can be obtained.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, and in particular, to a method for determining a named entity, electronic equipment, and a computer storage medium. Background technique [0002] Existing intelligent dialogue systems obtain information through interaction with users, and then provide users with required services. For example, in the process of information query (such as querying order status, querying telephone charges or querying electricity charges, etc.) However, due to pronunciation, homonyms, or environmental noise, it is impossible to obtain accurate information that the user wants to express. Therefore, there is an urgent need for a method that can accurately obtain information about named entities during voice dialogue interaction. Contents of the invention [0003] In view of this, an embodiment of the present application provides a named entity determination solution to at least partia...

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): G06F40/295G06F16/332G06F16/335G06N3/04
CPCG06F40/295G06F16/3329G06F16/335G06N3/044
Inventor 戴音培武玉川李永彬孙健
Owner ALIBABA DAMO (HANGZHOU) 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