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

A dialogue method and system based on free text knowledge

A knowledge and text technology, applied in the field of dialogue methods and systems based on free text knowledge, can solve the problems of volatile information and naturalness, and achieve the effect of improving fluency and naturalness, improving user experience, and enhancing user stickiness

Active Publication Date: 2021-09-17
SHANDONG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies in the prior art and solving the problem of volatile information and naturalness of the current dialogue system based on free text knowledge, one or more embodiments of the present disclosure provide a dialogue method based on free text knowledge and system, which effectively integrates generative and extractive dialogue systems, and has the ability to generate word by word and extract relevant semantic units from text knowledge

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
  • A dialogue method and system based on free text knowledge
  • A dialogue method and system based on free text knowledge
  • A dialogue method and system based on free text knowledge

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] According to an aspect of one or more embodiments of the present disclosure, a dialogue method based on free text knowledge is provided.

[0048] Such as figure 1 As shown, a dialogue method based on free text knowledge, the method includes:

[0049] A dialogue method based on free text knowledge, the method comprising:

[0050] S1: Receive free text knowledge and dialogue context;

[0051] S2: Encode free text knowledge and dialogue context into hidden state representations through knowledge encoder and context encoder, respectively;

[0052] S3: Decode the hidden state representations of the two through a hybrid decoder;

[0053] S4: At each time step of decoding, determine the execution mode of the hybrid decoder through the mode converter;

[0054] S5: After a certain number of decoding time steps, until the final reply sequence is synthesized sequentially from the results of different execution modes.

[0055] In this embodiment, the currently popular encoder-...

Embodiment 2

[0113] According to an aspect of one or more embodiments of the present disclosure, there is provided a computer-readable storage medium.

[0114] A computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor of a terminal device and executing the above-mentioned dialogue method based on free text knowledge.

Embodiment 3

[0116] According to an aspect of one or more embodiments of the present disclosure, a terminal device is provided.

[0117] A terminal device, which includes a processor and a computer-readable storage medium, the processor is used to implement instructions; the computer-readable storage medium is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executing the described one A Dialogue Method Based on Free Text Knowledge.

[0118] These computer-executable instructions, when executed in a device, cause the device to perform the methods or processes described in accordance with various embodiments in the present disclosure.

[0119] In this embodiment, a computer program product may include a computer-readable storage medium carrying computer-readable program instructions for performing various aspects of the present disclosure. A computer readable storage medium may be a tangible device that can retain and store instru...

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 present disclosure discloses a dialogue method and system based on free text knowledge, the method includes: receiving free text knowledge and dialogue context; encoding free text knowledge and dialogue context into hidden state representation through knowledge encoder and context encoder respectively ;Decode the hidden state representations of the two through the hybrid decoder; at each time step of decoding, determine the execution mode of the hybrid decoder through the mode converter; after a certain number of decoding time steps, until the results of different execution modes are jointly pressed sequence to synthesize the final reply sequence. This disclosure combines the essence of generative and extractive dialogue systems, and has the ability to generate word by word and extract relevant semantic units from text knowledge. The reply to the system output is significantly enhanced, and fluency and naturalness are guaranteed. , to maximize the user experience.

Description

technical field [0001] The disclosure belongs to the technical field of intelligent man-machine dialogue, and relates to a dialogue method and system based on free text knowledge. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Human-computer dialogue is a technology that studies how people can interact with computers through human language (that is, natural language). Today, when the artificial intelligence frenzy is sweeping the world, human-machine dialogue has become an important benchmark for measuring the degree of machine intelligence. Its importance is self-evident, and it has been focused on by both academia and industry. In addition, products related to man-machine dialogue are also widely used today, and have brought great convenience to human life. The main product applications include virtual assistants (Apple Siri, Microsof...

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 Patents(China)
IPC IPC(8): G06F16/332
CPCG06F16/3329
Inventor 陈竹敏孟川任鹏杰任昭春马军
Owner SHANDONG UNIV
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