Similarity analysis method and device, storage medium and electronic equipment
A similarity analysis and similarity technology, applied in the field of similarity analysis, can solve problems such as inaccurate semantic similarity analysis, difficulty in obtaining sufficient information on word co-occurrence times, etc., and achieve the effect of making up for the lack of modeling information and improving accuracy
Pending Publication Date: 2019-10-18
北京香侬慧语科技有限责任公司
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although the judgment method based on semantic similarity is more consistent with human understanding of natural language, when this traditional method judges some sentences containing rare words, it is difficult to obtain enough information due to the small number of word co-occurrences, resulting in insufficient semantic similarity analysis. precise
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
[0042] In describing the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", " Orientation or position indicated by "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. The relationship is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, therefore It should not be construed as a limitation of the present invention.
[0043] In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indic...
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 similarity analysis method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining a to-be-compared first text, a to-be-compared second text, a first segmented word and a second segmented word; determining a first character image of a first character contained in the first segmented word under multiple fonts, and determining a first glyph vector; similarly, determining a second glyph vector of the second segmented word; generating a first word segmentation vector according to the first glyph vectors of all the first characters contained in the first word segmentation, and similarly generating a second word segmentation vector; and determining the similarity between the first text and the second text according to all thefirst word segmentation vector and all the second word segmentation vector. According to the similarity analysis method and device, the storage medium and the electronic equipment provided by the embodiment of the invention, the glyph characteristics of various fonts are combined, the glyph characteristics contained in the segmented words can be more comprehensively and comprehensively determined,and the glyph characteristics are introduced when the similarity is judged, so that the accuracy of similarity judgment can be improved.
Description
technical field [0001] The present invention relates to the technical field of natural language understanding and processing, in particular to a similarity analysis method, device, storage medium and electronic equipment. Background technique [0002] With the development of natural language understanding and processing technology, more and more text processing requirements have emerged. For example, in scenarios such as document copy inspection, information retrieval, and machine translation, it is necessary to determine whether two texts are the same. [0003] The traditional method of judging whether two texts are the same is to calculate based on semantic similarity; for example, word vectors are obtained based on word co-occurrence information, and then semantic similarity analysis is performed through word vectors. Although the judgment method based on semantic similarity is more consistent with human understanding of natural language, when this traditional method judg...
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): G06F17/27G06K9/32G06K9/62
CPCG06V20/62G06V10/751G06V30/10G06F40/289
Inventor 孟昱先
Owner 北京香侬慧语科技有限责任公司