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

Chat robot system and automatic chat method

A chat robot and server technology, applied in the direction of instruments, special data processing applications, electrical digital data processing, etc., can solve the problems of high cost, low accuracy, poor scalability, etc., to reduce hardware investment costs and improve reply accuracy Effect

Active Publication Date: 2014-01-15
南京麒豹信息科技有限公司
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to provide two kinds of chat robot systems to solve the problems of low accuracy, high cost and poor scalability of existing chat robot systems
[0011] Another object of the present invention is to provide an automatic chat method to solve the problems of low accuracy, high cost and poor scalability of existing chat robot systems

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
  • Chat robot system and automatic chat method
  • Chat robot system and automatic chat method
  • Chat robot system and automatic chat method

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0043] 1. Predefine the phrase "how old" corresponds to "age" in the robot's phrase library.

[0044] 2. When the robot receives a sentence from the user T-A01 "How old is Xiao Wang?"

[0045] 3. First decompose the user's question into: "Xiao, Xiaowang, Xiaowangduo, how old is Xiaowang, how old is Xiaowang, Wang, Wangduo..." By analogy, combine the combination of each word with the predefined phrase library After comparison, it is found that "how old is" has a predefined phrase "age", then "how old is Xiao Wang?" is converted into the standard language: "Xiao Wang's age?"

[0046] 4. Segment the sentences converted into standard language, respectively "Xiao, Xiaowang, Xiaowangnian, Xiaowang's age, Wang, Wangnian..." and so on, and compare the combination of each word with thesaurus , to obtain the morphemes of each word "Xiao Wang (noun-subject)", "age (noun-subject)", "? (interrogative sentence identification)"

[0047] 5. Judging that the sentence is an interrogative sent...

example 2

[0053] 1. The robot receives a sentence from the user T-A02 "Why is the earth so powerful?"

[0054] 2. Same as Example 1, perform phrase comparison and word segmentation, and get the sentence "earth (noun-subject)", "why (event interrogative word-subject)", "strong (adjective-thought expression)""? (interrogative sentence identification) ".

[0055] 3. Judging that the sentence is an interrogative sentence according to the appearance of the interrogative sentence mark (?) in the sentence.

[0056] 4. According to the occurrence of event interrogative words in the sentence, it is judged that the sentence obtains information from the event database.

[0057] 5. Use nouns as the index (Earth), find "Earth" under the knowledge base, and obtain the index mark.

[0058] 6. Find all the events corresponding to the index in the event library according to the index ID, and find "powerful".

[0059] 7. Obtain the "why" attribute in the event according to the event interrogative word...

example 3

[0061] 1. The robot receives a sentence from the user T-A03 "Is Xiao Zhang pretty?"

[0062] 2. Same as the previous example, phrase comparison and word segmentation, get "Xiao Zhang (noun-subject)", "beautiful (adjective-expression of thought)", "do (modal particle)" and "? (interrogative sentence identification)"

[0063] 3. Judging that the sentence is an interrogative sentence according to the appearance of the interrogative sentence mark (?) in the sentence.

[0064] 4. According to the fact that only adjectives appear in the sentence, and there are no other signs, it is judged that the sentence obtains information from the think tank.

[0065] 5. Use the noun as the index (Xiao Zhang), find "Xiao Zhang" under the knowledge base, and obtain the index identifier.

[0066] 6. According to the index logo, find all the corresponding information of the index in the think tank, and find "beautiful".

[0067] 7. If "beautiful" is found, return the description about "beautiful"...

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 chat robot system and an automatic chat method; the chat robot system comprises an interactive platform, a word segmenting module, a language recognition unit, a database and an information search unit, wherein the word segmenting module is connected with the interactive platform and used for segmenting the speech sent by a user; the speech recognition unit is connected with the word segmenting module and used for judging the morpheme of each segmented word and judging the type of a sentence stated by the user; the database further comprises an event base, an action base, a knowledge base and a thought base which are respectively used for storing event information, action information, knowledge information and thought information simulating the human brain; and the information search unit is respectively connected with the language recognition unit, the database and the interactive platform and used for searching the database according to the morpheme of the segmented word and the sentence type, and transmitting the search result to the interactive platform. The chat robot system has the advantages of high accuracy, low cost and strong expandability.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a chat robot system and an automatic chat method. Background technique [0002] In recent years, the means of communication between people have become increasingly abundant. Communication methods such as instant messaging tools and mobile phone text messages are becoming more and more popular. Based on these means of communication, in addition to realizing communication between people, it also makes it possible to communicate between people and artificial intelligence systems. [0003] The chat robot system is an artificial intelligence system that can be online at all times by means of communication and communicate with people through natural language. A chatbot system is essentially an automated question answering system. The automatic question answering system takes natural language understanding technology as the core, involves many disciplines such as computational ...

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): G06F17/30G06F17/27
Inventor 卢玉敏
Owner 南京麒豹信息科技有限公司
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