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

Method and device for generating knowledge base in target domain and answering questions

A technology for target fields and problems, applied in unstructured text data retrieval, instruments, computing, etc., can solve problems such as inability to generate answers

Active Publication Date: 2022-03-25
HUAWEI TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] This application provides a method and device for generating a knowledge base in the target field and answering questions, which is used to solve the problem that the question answering system in the prior art cannot generate an answer if the content of the user's question does not exist in the original knowledge base

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
  • Method and device for generating knowledge base in target domain and answering questions
  • Method and device for generating knowledge base in target domain and answering questions
  • Method and device for generating knowledge base in target domain and answering questions

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0161] The embodiment of the present application provides a way of representing knowledge in the field of financial operation and accounting rules. The field of operation and accounting rules mainly defines accounting rules or accounting calibers for the main operation indicators of the company. The hardware platform used in the implementation of this application may be a general PC computer, the software may be implemented using Python 3.5, and the steps of constructing the target domain knowledge base may include:

[0162] Determine three types of knowledge representation: concept words, events, and predicate logic formulas. Concept words include concept instances or concepts, which are abstractions of objects in target domain knowledge and express static knowledge. Events describe the behavior, actions, or states of objects, expressing dynamic knowledge. The predicate logic formula is an abstract description of the rules in the target domain knowledge (for example, the nor...

example 1

[0179] Specifically, the service cost rules include: Expenses incurred by activities or personnel directly related to the delivery of the service contract shall be recorded in the cost of services, including the expenditure incurred by directly engaging in the service and directly managing and supporting the personnel engaged in the service.

[0180] In the service cost rule, identifiable events include: generating expenditure events, contract delivery events, and service cost confirmation events. Examples of identifiable concepts include: activities and personnel. Therefore, the service cost rule can be expressed as: ЭxЭy(generating expenditure(X,Y)Λcontract delivery(X)Λ(activity expenditure(Y)∨personnel expenditure(Y)))->service cost(Y)

[0181] According to the generation rule of the predicate logic, it is determined that the rule header included in the service cost rule is the service cost confirmation event. The rule body includes: generating expenditure events, contract ...

example 2

[0191] Manpower cost rules, including mainly referring to company-owned and outsourced manpower expenditures engaged in delivery activities, can include wages, bonuses, social insurance, water and electricity costs, communication costs, travel expenses, etc.

[0192] In the labor cost rule, the events that can be identified include: generating expenditure events, contract delivery events, and labor cost confirmation events. The concepts that can be identified include: company-owned manpower, outsourced manpower, expenditure content: wages, bonuses, social insurance, Water, electricity, communication, travel, etc. Therefore, the predicate logic formula corresponding to the labor cost rule can be expressed as: ЭxЭy (generation expenditure (X, Y) Λ contract delivery (X) Λ (company personnel expenditure (Y)∨ outsourcing personnel expenditure (Y))) -> labor cost (Y)

[0193] In the labor cost rule, the rule header is the service cost confirmation event. The rule body includes: ge...

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

This application discloses a method and device for generating a knowledge base in the target field and answering questions. According to the knowledge type of the target field knowledge, the application determines the concept map, the event map and the predicate logic formula of the target field knowledge; and then generates the target field knowledge base. The concept graph is used to represent the static relationship between concept words; the event graph is used to represent the order of events and the relationship between events; the predicate logic formula is used to represent the business rules in the target domain knowledge. The problem-solving method includes: determining the M events triggered by the N word-segment phrases in the problem from the reasoning map, and determining the slots of the M event slots according to the K word-segment phrases matching the concept map in the N word-segment phrases value; according to the M events and the slot values ​​of the slots of the M events, the predicate logic formula corresponding to the query object of the question is calculated; and then the answer to the question is determined.

Description

technical field [0001] The present application relates to the field of computer technology, mainly to natural language processing technology in artificial intelligence, and in particular to a method and device for generating a knowledge base in a target domain and answering questions. Background technique [0002] The core step of the question answering system is to search for relevant knowledge from the existing reserve knowledge base, and then generate the answer. In the prior art, knowledge can be classified according to the scope of the problem, and a knowledge map can be established. Alternatively, directly face the question-and-answer instance of the application, establish a Frequently Asked Questions (FAQ) library, or combine the knowledge graph with the FAQ library, and establish links between the nodes of the knowledge graph and the content-related FQA. However, whether it is a search by FAQ or a search by integrating FAQ and ontology, the answer can only be obtain...

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): G06F16/36G06F16/332G06F40/289G06F40/284
CPCG06F16/367G06F16/3329
Inventor 胡康兴段戎张明仕郭定平
Owner HUAWEI TECH CO LTD
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