A Rule-Based General Text Information Extraction and Information Generation Method
A text information and information extraction technology, applied in digital data information retrieval, unstructured text data retrieval, special data processing applications, etc., can solve problems such as rapid delivery of unfavorable software, difficult reuse of extraction rules, and high maintenance costs. , to achieve the effect of easy reuse and sharing, good analysis and mining, and improved efficiency
Active Publication Date: 2021-07-13
NANJING UNIV
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The problem faced by more enterprises is: a lot of information comes from semi-structured texts, and this part of the texts still lacks good information extraction tools. At present, many information entry methods are realized by manual entry or complex extraction logic. , manual input consumes a lot of manpower and material resources, and the effect is not good. Although the complex extraction logic has a high extraction accuracy, it brings high maintenance costs, and the extraction rules are difficult to reuse, and the whole process requires a long cycle. , which is not conducive to the rapid delivery of software
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0092] The technical solutions provided by the present invention will be described in detail below in conjunction with specific examples. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.
[0093] figure 1 It is a flow chart of the present invention, roughly including an initialization stage, an information labeling stage, a stage of writing extraction rules, and a template editing and text generation stage,
[0094] Among them, in the initialization phase, it is mainly to load the pre-configured information dictionary and word package from the database and other storages into the system, and at the same time connect the rule parser, dependency analyzer and rule executor of the rule engine to complete the initialization of the rule engine , connect the meta-template, the predefined template directive and the template engine to complete the initializ...
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 provides a rule-based general text information extraction and information generation method, including: initializing information dictionary context, rule word bag, rule engine and template engine; marking text information; defining information extraction algorithm and writing rule script code ; Generation rules depend on directed graphs; Execute text extraction rules and fine-tune according to extraction accuracy; Define information to generate meta-templates; Customize template rule selection and text generation. The invention realizes the modularization of the extraction rules, improves the possibility of sharing the extraction rules, can analyze and mine the structure of complex text information, and greatly improves the efficiency of extracting information and generating text from external information, and is especially suitable for legal Documents and other fields that require a large amount of information text for information extraction and generation. The method of the invention can significantly improve the efficiency and accuracy of text extraction, optimize the complexity of text extraction and improve the efficiency of information text generation.
Description
technical field [0001] The invention relates to the field of software engineering and rule engine, and relates to a rule-based general text information extraction and text generation method, more specifically, a rule-based general text information extraction and information generation method. Background technique [0002] With the improvement of the information level of various enterprises, the traditional information entry has a better solution. The problem faced by more enterprises is: a lot of information comes from semi-structured texts, and this part of the texts still lacks good information extraction tools. At present, many information entry methods are realized by manual entry or complex extraction logic. , manual input consumes a lot of manpower and material resources, and the effect is not good. Although the complex extraction logic has a high extraction accuracy, it brings high maintenance costs, and the extraction rules are difficult to reuse, and the whole proce...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/335G06F16/36G06F40/186
CPCG06F40/186
Inventor 骆斌卢坚伏晓
Owner NANJING UNIV