A method and system for automatically converting normative text into computable logic rules

A technology of computing logic and rules, which is applied in the intersection of construction industry and information technology, can solve the problems of high construction and maintenance costs, low expression ability of regular expressions, and difficult maintenance, etc., and achieves strong semantic recognition ability, improved understandability, The effect of high accuracy

Active Publication Date: 2021-09-17
TSINGHUA UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In fact, the expressive power of regular expressions is low (for example, recursion cannot be expressed), which can easily lead to an increase in the number of uses (for example, a large number of regular expressions are required to express a simple rule), and it becomes difficult to maintain
Therefore, the current automated method has the following defects: 1) the cost of construction and maintenance is high, and it can only be established by manually writing regular expressions one by one, and the coverage of each regular expression is very limited
2) The scalability is low. The improvement of the accuracy of this method is often accompanied by the deepening of the specificity of the applicable field. Therefore, this method has a large limitation in scalability, that is, it is difficult to establish a general-purpose method through regular expressions. Domain Rule Transformation Methods
3) Low maintainability, the lack of recursion in regular expressions can easily lead to an increase in the number of usages and make it difficult to maintain quickly

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 method and system for automatically converting normative text into computable logic rules
  • A method and system for automatically converting normative text into computable logic rules
  • A method and system for automatically converting normative text into computable logic rules

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] like image 3 As shown in, for example, to provide a standardized text automatically to calculate the method of the present embodiment logic rules, comprising the steps of:

[0070] 1) the normative text (such as engineering standards, regulations, regulatory provisions) statements were divided, for example in accordance with a period, semicolon will regulate the text is divided into a number of statements, a number of statements and split by text classification pre-screened specification statement conversion, for example, contain the statements to be represented by the relationship between keywords comparison, there is a relationship like.

[0071] 2) The depth of the neural network (the DNN) model format specification statement convertible semantic annotation specification statement that is switchable word or phrase in semantic tags to represent semantic information, obtained by BIO labeled with statement label, where the label can be associated with a conceptual BIM and t...

Embodiment 2

[0098] This embodiment provides a system that automatically converts the specification text to the calculated logical rules, including:

[0099] The pre-processing module is used to split the specification text, and preprocessing the segmented several statements, filtering out convertible specification statements.

[0100] Semantic labeling module, used to adopt a depth neural network model, plus a semantic label with a semantic label in a word or phrase in a convertible specification statement through the BIO label format.

[0101] The parsing module is used to adopt the context-free method, based on the recognition of the P-R paradigm and its recursive usage, parse the statement with the label, convert the statement with the label to a rule check tree.

[0102] Conversion module for converting rules to the language to a specific format.

Embodiment 3

[0104] This embodiment provides a processing apparatus corresponding to a method of automatically converting a specification text to a method of calculating a logical rule, processing device, such as a mobile phone, laptop, tablet for a client. , Desktop computer, etc. to perform the method of Example 1.

[0105] The processing device includes a processor, a memory, a communication interface, and a bus, a processor, a memory, and a communication interface through a bus connection to complete communication between each other. A computer program that can be stored on a processor is stored in a processor, and the processor is performed to automatically convert the specification text to the calculated logical rule when the processor is running computer program.

[0106] In some implementations, the memory can be a high-speed random access memory (RAM: Random AccessMemory), and may also include non-Volatile memory, such as at least one disk memory.

[0107] In other implementations, th...

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 invention relates to a method and system for automatically converting normative text into computable logic rules, which is characterized in that it includes the following content: 1) performing sentence segmentation on the normative text, and performing preprocessing on several sentences obtained from the segmentation, and screening out Transformable standard sentences; 2) Using the deep neural network model, adding semantic tags to the words or phrases in the convertible standard sentences through the BIO annotation format, to obtain labeled sentences; 3) Using context-free grammar, based on pairwise The recognition of P-R paradigm and recursive usage thereof, the sentence with label is analyzed, the sentence with label is converted into rule check tree; 4) the language that rule check tree is converted into specific format, the present invention can be widely used In the intersection of construction industry and information technology.

Description

Technical field [0001] The present invention relates to a method of automatically converted to text specification rules logic may calculate a method and a system construction cross areas of information technology. Background technique [0002] The entire life cycle of the built environment subject to various laws and regulations, norms and standards constraints, a compliance review of the manual process is time consuming, costly and error-prone. As an alternative to manual inspection, and automatic compliance review (Automated Compliance Checking, ACC) can greatly promote the architecture, engineering and construction industry design process. Nowadays, with the increasing complexity of design, ACC has become crucial in the design process, and has been extensively studied, but it is difficult to observe the ACC application in real projects. Most of the existing ACC systems are dedicated to specific areas or hard-coded method based mechanisms, such methods, such as Singapore, proje...

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): G06F8/41G06F16/35G06F40/117G06F40/253G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06F8/42G06F40/30G06F40/253G06F40/117G06F16/35G06N3/04G06N3/08G06F18/2415
Inventor 林佳瑞周育丞郑哲陆新征
Owner TSINGHUA UNIV
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
Try Eureka
PatSnap group products