Letter element automatic extraction method based on petition letter general situation
An automatic extraction and letter technology, applied in unstructured text data retrieval, biological neural network model, text database index, etc., can solve the complex and huge petition work, the inability to understand the emotional state of petition documents, the lack of emotional indicators in text processing, etc. problems, to achieve the effect of scientific and efficient handling of petitions
Inactive Publication Date: 2020-01-21
TONGFANG KNOWLEDGE NETWORK TECH CO LTD (BEIJING)
View PDF2 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] With the diversification of complaint channels, the work of complaints has become very complex and huge. Manual comparison, analysis, classification, and sorting of traditional complaint reception methods are obviously not enough, and traditional text processing relies entirely on the characteristics of this article. The technical application of text mining such as analysis and trend prediction is relatively insufficient; at the same time, the mining technology itself has limitations. Due to the influence of corpus, mining technology and computer technology, sometimes even if the text mining technology is used correctly, it is often impossible to obtain Expected effect; there is no emotional indicator for the text processing of letters and visits, and it is impossible to understand the emotional state of letters and visits
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
[0012] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the embodiments and accompanying drawings.
[0013] Such as figure 1 As shown, the method of automatic extraction of letter elements based on the general situation of letters and visits includes:
[0014] The automatic generation of elements of letters and visits uses CNLP Chinese natural language processing, big data, machine learning and other technical means to analyze the sentences and emotions expressed in letters and letters, quantify and score, and use artificial intelligence to eliminate subjective bias and summarize The objective law of petition data, so as to automatically digest long letters and visits, and generate concise core content;
[0015] Automatically extract elements of letters and visits, use text mining and advanced CNLP natural language processing model CNN (Convoluti...
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 letter element automatic extraction method based on a petition letter general situation. The method comprises: automatically generating petition letter elements, and generating a large-size petition text into a short petition summary through CNLP Chinese natural language processing, big data and machine learning; and automatically extracting petition letter elements, fragmenting the text by using a text mining technology, and extracting petition basic elements according to requirements. According to the method, the petition letters are intelligently processed, basic elements and summaries of the petition letters are objectively and scientifically extracted, petition processing is scientific and efficient, sentences of petitioners in the petition letters and emotions expressed by words can be analyzed, and the real states of the petitioners can be known.
Description
technical field [0001] The present invention relates to the technical field of text mining and computer information processing, in particular to knowledge element extraction technology, data mining analysis technology, natural language processing technology, fragment indexing and indexing technology, and automatic element extraction method of machine learning technology. Background technique [0002] With the diversification of complaint channels, the work of complaints has become very complex and huge. Manual comparison, analysis, classification, and sorting of traditional complaint reception methods are obviously not enough, and traditional text processing relies entirely on the characteristics of this article. The technical application of text mining such as analysis and trend prediction is relatively insufficient; at the same time, the mining technology itself has limitations. Due to the influence of corpus, mining technology and computer technology, sometimes even if the...
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 Applications(China)
IPC IPC(8): G06F16/35G06F16/31G06F16/34G06N3/04
CPCG06F16/35G06F16/345G06F16/31G06N3/044G06N3/045
Inventor 谢磊张丽焦安琪何义民李飞何志成曹珊刘世旭
Owner TONGFANG KNOWLEDGE NETWORK TECH CO LTD (BEIJING)