Semantic comprehension method, device and equipment and storage medium

A semantic understanding and semantic technology, applied in the field of semantic understanding methods, devices, equipment and storage media, can solve problems such as the inability to accurately understand the user's real semantics

Pending Publication Date: 2020-10-23
IFLYTEK CO LTD
View PDF9 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the diversity and complexity of human language, there may be many forms of language expression for an intention, and the existing semantic understanding methods are still unable to accurately understand the true semantics of the content expressed by the user

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
  • Semantic comprehension method, device and equipment and storage medium
  • Semantic comprehension method, device and equipment and storage medium
  • Semantic comprehension method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0077] See figure 1 , Which shows a schematic flowchart of a semantic understanding method provided by an embodiment of the present application, which may include:

[0078] Step S101: Obtain the target text.

[0079] Among them, the target text is the text that requires semantic understanding. Optionally, during human-computer interaction, the user usually inputs a voice, and the target text may be a recognized text obtained by performing voice recognition on the user input voice, and the target text may be a sentence.

[0080] It should be noted that the target text in this application is a text that meets the following two conditions:

[0081] First, the target text is the text of a specific field, not the text of an open field.

[0082] Exemplarily, "what color is the apple" is the text in the open field, and "I want to check the repayment details of my credit card" is the text in the specific field.

[0083] Second, the target text contains at least two fragments, one of which is a ...

no. 2 example

[0098] The foregoing embodiment mentioned that the target knowledge semantic tree is generated based on the knowledge semantic tree template, and this embodiment introduces the knowledge semantic tree template in detail.

[0099] See figure 2 , A schematic diagram showing an example of the knowledge semantic tree template, such as figure 2 As shown, the knowledge semantic tree template includes multiple types of entities and relationships between multiple types of entities. It should be noted that the knowledge semantic tree template is composed of a number of entity nodes and the edges between the entity nodes. Among them, the entity nodes of the knowledge semantic tree template are various types of entities, and each edge of the knowledge semantic tree template represents its location. There is a relationship between the two connected entity nodes, and the type of edge is the relationship between the entity nodes. It should be noted that in addition to the entity nodes, the kn...

no. 3 example

[0106] This embodiment introduces the "Step S102: Generate a semantic knowledge tree that can reflect the semantics of the target text according to the target text and the knowledge semantic tree template constructed in advance for the domain to which the target text belongs, as the target knowledge semantic tree" in the first embodiment. .

[0107] See image 3 , Shows a schematic diagram of the process of generating a knowledge semantic tree that can reflect the semantics of the target text according to the target text and the knowledge semantic tree template constructed in advance for the field of the target text, which may include:

[0108] Step S301: Use the target text, the knowledge semantic tree template, and the pre-built semantic refinement model to obtain multiple target entities that can reflect the semantics of the target text, the entity types corresponding to the multiple target entities, and the relationship between the multiple target entities.

[0109] Among them, t...

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 provides a semantic comprehension method, device and equipment and a storage medium, and the method comprises the steps of obtaining a target text; according to the target text and a knowledge semantic tree template constructed in advance for the field to which the target text belongs, generating a knowledge semantic tree capable of reflecting the semantics of the target text as thetarget knowledge semantic tree, wherein the knowledge semantic tree template comprises a plurality of entities capable of embodying semantics in the field to which the target text belongs, entity types corresponding to the plurality of entities respectively, and relationships among the plurality of entities, wherein the target knowledge semantic tree comprises a plurality of target entities capable of reflecting target text semantics, entity types corresponding to the plurality of target entities respectively and relationships among the plurality of target entities; and determining a standardtext corresponding to the target text from the standard text set according to the target knowledge semantic tree. The semantic comprehension method provided by the invention can correctly understand the real semantics of the content expressed by the target text.

Description

Technical field [0001] This application relates to the technical field of natural language understanding, and in particular to a semantic understanding method, device, device and storage medium. Background technique [0002] With the rapid development of artificial intelligence technology, the application of human-computer interaction systems with intelligent voice interaction as the core has become more and more extensive, such as smart home, intelligent customer service, chat robots, and early education robots. To realize human-computer interaction, the machine needs to understand the semantics of the corpus input by the user. [0003] Semantic understanding means that the machine understands the user's intention according to the natural language given by the user, and can further respond on this basis. However, due to the diversity and complexity of human language, the language expression for an intention may have many forms, and the existing semantic understanding methods are ...

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): G06F40/30G06F40/279G06F40/216
CPCG06F40/30G06F40/279G06F40/216
Inventor 王琳博胡加学刘加新宋时德
Owner IFLYTEK 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