Chatting robot knowledge base and construction method thereof
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A chat robot and construction method technology, applied in the field of automatic chat robot knowledge base and its construction, can solve the problems of unable to chat person personalized reply, not recording chat person attribute information, not recording chat discourse context information, etc.
Inactive Publication Date: 2013-11-13
TIANGE TECH HANGZHOU +1
View PDF4 Cites 54 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
The root cause of these problems in the chatbot is that the chat knowledge base only records the "utterance-reply" information, but does not record the context information of each chat utterance, nor does it record the attribute information of each chatter
[0004] In summary, the existing chatbots have the disadvantages of incoherent chatting process and inability to give personalized replies based on chatter attributes. New technologies need to be developed, especially new chat knowledge bases and their construction methods.
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0036] This embodiment relates to an online video social platform, which is divided into several channels according to social content, and each channel has multiple video chat rooms. Tourists and VIP members can interact with the host in the room. One of the important communication methods is text chat. During the service peak period, the room host can interact and chat with users in person, but during the service peak period, there are too many users in the room, and the room host cannot interact with each user, which seriously affects the user experience. Therefore, it is necessary to develop a chatbot that can simulate the moderator's work to relieve the moderator's work pressure, and a key problem in developing a chatbot is to build a chat knowledge base. First, the text chat records of room hosts and users on the platform are extracted as artificial chat data. The time span is 1 month, and there are more than 30 million chat words in total. Due to system reasons, the art...
example
[0040] [The platform customer logs into the system, the system queries the chat person attribute database to obtain the user's attribute information, the gender is "male", the region is "Zhejiang", and the chat keyword includes "singing"]
[0041] Here is the chat process:
[0042] 1) Chatbot: Brother fellow, we meet again~ [Greeting, the restriction of this greeting is "gender = male", the current user meets the restriction]
[0043] 2) Platform users: yes
[0044] 3) Chatbot: I’m afraid I won’t be able to see you [the user’s words above are only the word “yes”, the amount of information is too small, query the chat discourse database, and determine the most appropriate reply through contextual information matching]
[0045] 4) Platform users: just went out for a while
[0046] 5) Chatbot: Oh, I thought you were asleep [According to the user's words and contextual information, query the chat discourse database to determine the reply words]
[0047] 6) Platform users: beaut...
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
Login to view more
Abstract
The invention discloses a chatting robot knowledge base and a construction method thereof. The knowledge base comprises a chatting word library and a chatting person attribute library, wherein the chatting word library consists of a plurality of chatting word records; each record comprises a chatting word, contextual information of the chatting word, a plurality of replying words of the chatting word and a limiting condition set of each replying word; the chatting person attribute library consists of a plurality of chatting person attribute records; each record contains static attribute and dynamic attribute of each chatting person. The invention also discloses the construction method of the chatting robot knowledge base. The information required by the knowledge base is acquired by using a data mining technology. The candidate chatting words, contextual information and replying words are respectively mined from mass artificial chatting data. The chatting person attributes are dynamically acquired from a chatting process. According to the chatting robot knowledge base and the construction method thereof disclosed by the invention, the defects that the chatting process is incoherent and the personalized reply cannot be given according to the chatting person attributes exiting in the current chatting robot can be overcome and the support can be provided for developing intelligent chatting robots in the specified fields.
Description
technical field [0001] The invention relates to the field of chatting robots, in particular to an automatic chatting robot knowledge base and a construction method thereof in the field. Background technique [0002] In 1950, Turing, the "father of artificial intelligence", published the article "Computing Machines and Intelligence" in the top international academic journal "Mind", proposing that if machines can talk to people in natural language and not be noticed, then the Machines are intelligent. This is the so-called Turing test. The development of robots that can automatically chat with people has always been an important topic in the field of artificial intelligence. The world's first chatbot was born in the 1980s. This robot is called "Elbot" and is written in BASIC language. In 1998, Chris Kwart completed an online chat system "TalkBot" written in javascript and PERL language. In November 1995, Wallace developed a chat program "Alice" and installed it on a web se...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more