A data processing method, electronic device and storage medium for text verification
A data processing and text verification technology, applied in the field of data processing, can solve the problems of difficult conversion of semi-structured text data, affecting the data verification process, low data comparison efficiency and accuracy, and reducing extraction and other data. interference, extensive use value, and the effect of easy comparison
Active Publication Date: 2022-03-04
北京中电汇智科技有限公司 +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In some application scenarios, especially in the settlement audit scenario of the power system, it is necessary to compare structured text data and semi-structured text data, that is, to judge whether the structured data in the settlement document conforms to the semi-structured data in the contract. However, due to the difficulty of converting semi-structured text data into the table structure of relational databases, manual comparisons are usually used in the prior art, which will result in low efficiency and accuracy of data comparisons and affect to the verification process of the data
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
[0018] In order to further explain the technical means and effects of the present invention to achieve the intended purpose of the invention, the following in conjunction with the accompanying drawings and preferred embodiments, a data processing method for text verification, electronic equipment and The specific implementation of the storage medium and its functions are described in detail below.
[0019] An embodiment of the present invention provides a data processing method for text verification, the method also includes the following steps, such as figure 1 Shown:
[0020] S100. Obtain m first texts from the first text set of the text database as sample texts, and construct a sample text list A=(A 1 , A 2 , A 3 ,...,A m ), A i refers to the i-th sample text, i=1...m, and when A i When there is a keyword consistent with any preset keyword in the preset keyword list, set A i The keyword positions are marked as specifying the starting position and the A i The end pos...
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 present invention relates to a data processing method, electronic equipment and storage medium for text verification. The method includes the following steps: obtaining a list of sample texts from a text database, and when any sample text exists in the preset keyword list When any preset keyword is the same keyword, the keyword position of the sample text is marked as the specified start position and the end position of the sample text is marked as the specified end position, and the value between the specified start position and the specified end position is The segment of the target segment is used as the target segment, and the sample text based on the target segment is used as the training set data to form a training set; the training set is input into the preset language model for training, and the trained language model is obtained; The trained language model obtains the knowledge map of the target text, so that it can be compared with the preset verification data according to the knowledge map. The invention can improve the accuracy and efficiency of comparing structured text data and semi-structured text data.
Description
technical field [0001] The invention relates to the technical field of data processing, in particular to a data processing method for text verification, electronic equipment and a storage medium. Background technique [0002] In the prior art, text data is divided into three types: structured text data, random text data and semi-structured text data; among them, in the structured text data, the text data at a specific position has a specific meaning and is easy to be read. Converted to a table structure in a relational database, such as text data in cvs format, invoice text data after OCR processing, or settlement statement data in a specific field of power system, etc.; in random text data, the text data at each text position has random meanings , for example, text data such as news, novels, prose and other literary works spread on the Internet; semi-structured text data is between structured text data and random text data, and text data at a specific location can have spec...
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): G06F40/226G06F16/31G06F16/36
CPCG06F40/226G06F16/31G06F16/367
Inventor 刘远陈旻晖
Owner 北京中电汇智科技有限公司