Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Man-machine conversation processing method and system and storage medium

A technology of human-machine dialogue and processing method, which is applied in the fields of electrical digital data processing, natural language data processing, special data processing applications, etc., and can solve the problems of ordinary users and dialogue robots and poor user experience.

Pending Publication Date: 2022-05-13
北京力拓飞远科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the existing human-computer dialogue needs to improve the recognition accuracy and recognition speed, resulting in poor interaction effect and user experience between ordinary users and dialogue robots

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
  • Man-machine conversation processing method and system and storage medium
  • Man-machine conversation processing method and system and storage medium
  • Man-machine conversation processing method and system and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] See Figure 1 , the present embodiment provides a method of human-computer dialogue processing, comprising:

[0052] Construct a knowledge base, which includes multiple questions and the corresponding intent categories of the questions; vectorize the questions in the knowledge base and convert the data types, and cache the processed questions in the database; obtain the current questions for vectorization, and at the same time, after traversing the questions from the database and performing the inverse processing of data type conversion, the similarity values of the current question sentences and each question sentence are calculated separately; and the corresponding intent categories of the current question sentences are identified based on the similarity values.

[0053] In the human-machine dialogue processing method provided in the present embodiment, by sorting out the user's question and answer corpus in advance, sorting out the user's various questions and questi...

Embodiment 2

[0096] The present embodiment provides a human-machine dialogue processing system, comprising:

[0097]Knowledge base unit for building a knowledge base, the knowledge base comprises a plurality of questions and the corresponding intent categories of the question;

[0098] Caching unit for vectorization processing and data type conversion processing for the questions in the knowledge base, and caching the completed questions in the database;

[0099] The calculation unit is used to obtain the current question sentence for vectorization processing, and at the same time, after iterating through the question from the database and performing inverse processing of data type conversion, the similarity values of the current question and each of the current question are calculated respectively;

[0100] Identification unit, based on the similarity value to identify the corresponding intent category of the current question.

[0101] Compared with the prior art, the embodiment of the prese...

Embodiment 3

[0103] The present embodiment provides a computer-readable storage medium, a computer-readable storage medium is stored on a computer program, the computer program is run by the processor to perform the steps of the above-described human-machine dialogue processing method.

[0104] The present embodiment provides a computer-readable storage medium, for example, may be - but not limited to - electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the pre...

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 man-machine conversation processing method and system and a storage medium, relates to the technical field of artificial intelligence, and can improve the recognition accuracy and recognition speed of man-machine conversation, improve the man-machine interaction effect and improve the conversation experience of a user. The method comprises the following steps: constructing a knowledge base, wherein the knowledge base comprises a plurality of questions and intention categories corresponding to the questions; vectorization processing and data type conversion processing are carried out on the questions in the knowledge base, and the processed questions are cached in a database; obtaining a current question, carrying out vectorization processing, traversing the questions from the database, carrying out inverse processing of data type conversion, and respectively calculating similarity values between the current question and the questions; and identifying an intention category corresponding to the current question based on the similarity value. The system applies the method provided by the scheme.

Description

Technical field [0001] The present invention relates to the field of artificial intelligence technology, in particular to a human-machine dialogue processing method, a system and a storage medium. Background [0002] At present, deep learning technology has been fully applied to many natural language processing scenarios, becoming an indispensable weapon in academic research and industrial applications, and bringing gratifying results to many application scenarios, including human-computer dialogue, machine translation, automatic writing, machine reading, etc. Among them, human-machine dialogue refers to the use of a conversational robot driven by a software program to conduct a dialogue with ordinary users. [0003] Ordinary users in the use of dialogue robot products, will send a text type message or other types of messages to the dialogue robot but can be recognized, converted into a text type of message, such as the speech sent by ordinary users can be converted into the cor...

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
IPC IPC(8): G06F16/332G06F16/33G06F40/216G06F40/289G06N20/00
CPCG06F16/3329G06F16/3344G06F40/289G06F40/216G06N20/00
Inventor 贺同路高源侯博宇李嘉懿任永旭龚有三
Owner 北京力拓飞远科技有限公司
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
Eureka Blog
Learn More
PatSnap group products