Supercharge Your Innovation With Domain-Expert AI Agents!

Dialogue generation method and system for expanding context into knowledge graph

A technology of knowledge graph and context, applied in the field of dialogue generation methods and systems, can solve problems such as ignoring meaning and not being able to fully grasp specific knowledge, and achieve the effect of ensuring logical consistency

Pending Publication Date: 2021-12-03
SHANDONG NORMAL UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Giving additional relevant knowledge in the dialogue can obviously enrich the dialogue generation, but the knowledge retrieval process is limited to the retrieval of entity words, ignoring the meaning of the entity in the context, and cannot fully grasp the specific knowledge of the current dialogue.

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
  • Dialogue generation method and system for expanding context into knowledge graph
  • Dialogue generation method and system for expanding context into knowledge graph
  • Dialogue generation method and system for expanding context into knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] This embodiment provides a dialogue generation method that expands the context into the knowledge map;

[0050] Dialog generation methods that augment context into knowledge graphs, including:

[0051] S101: Obtain the current statement and several context statements of the current statement;

[0052] S102: Construct a knowledge sub-graph of the current sentence according to the current sentence;

[0053] S103: Filter several contextual statements of the current statement, and filter out important contextual statements;

[0054] S104: According to the important sentences in the context of the current sentence, filter out important words from the knowledge sub-graph of the current sentence;

[0055] S105: Delete the non-important vocabulary in the knowledge sub-graph of the current sentence to obtain an updated knowledge sub-graph; connect the vocabulary obtained after word segmentation of important sentences in the context with the important words in the updated knowl...

Embodiment 2

[0136] This embodiment provides a dialog generation system that expands context into a knowledge map;

[0137] Dialogue generation is the same for augmenting context into knowledge graphs, including:

[0138] An acquisition module configured to: acquire the current statement and several context statements of the current statement;

[0139] A building module configured to: build a knowledge subgraph of the current sentence according to the current sentence;

[0140] An important statement screening module, which is configured to: filter several context statements of the current statement, and filter out context important statements;

[0141] An important vocabulary screening module, which is configured to: filter out important vocabulary from the knowledge sub-graph of the current sentence according to the important sentences in the context of the current sentence;

[0142] The expansion module is configured to: delete non-important words in the knowledge sub-graph of the cur...

Embodiment 3

[0148] This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, the processor is connected to the memory, and the one or more computer programs are programmed Stored in the memory, when the electronic device is running, the processor executes one or more computer programs stored in the memory, so that the electronic device executes the method described in Embodiment 1 above.

[0149] It should be understood that in this embodiment, the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic devices , discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, o...

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 dialogue generation method and system for expanding context into a knowledge graph. The dialogue generation method comprises the following steps: acquiring a current statement and a plurality of context statements of the current statement; constructing a knowledge sub-graph of the current statement according to the current statement; screening a plurality of context statements of the current statement to obtain important context statements; according to a context important statement of the current statement, screening out important vocabularies from the knowledge sub-graph of the current statement; deleting unimportant vocabularies in the knowledge sub-graph of the current statement to obtain an updated knowledge sub-graph; connecting vocabularies obtained after word segmentation of important statements of the context with important vocabularies in the updated knowledge sub-graph to obtain an expanded knowledge graph; generating a response dialogue statement based on the current statement and the expanded knowledge graph; and further generating a reply with rich and smooth information according to the context and knowledge perception.

Description

technical field [0001] The invention relates to the technical field of dialogue generation, in particular to a dialogue generation method and system for extending context into a knowledge graph. Background technique [0002] The statements in this section merely mention the background technology related to the present invention and do not necessarily constitute the prior art. [0003] Human-machine dialogue involves two major subjects, human beings and machines. As a direct embodiment of the communication between the two, the dialogue system is committed to pursuing the fluency and naturalness of dialogue. In recent years, many scholars have been rooted in the generation of dialogue responses in the open field, which involves a wide range of but relatively single results. It is difficult to grasp the consistency of dialogues when they are oriented towards topic migration, and it is impossible to emerge richer information and grasp characters if they are dedicated to the logi...

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): G06F16/36G06F16/34G06N3/04G06N3/08G06N5/02
CPCG06F16/367G06F16/345G06N5/022G06N3/08G06N3/045
Inventor 解福刘悦刘凤鸣徐传杰于凤洋段成志
Owner SHANDONG NORMAL UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com