An industry automatic classification method and system
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
An automatic classification and industrial technology, applied in the field of document analysis, can solve the problems of missing in-depth information, loss, etc., and achieve the effect of reducing the amount of annotation, improving computing efficiency and classification accuracy.
Active Publication Date: 2021-09-24
BEIJING BENYING TECH CO LTD
View PDF6 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
The disadvantage of this method is that the natural language processing method used loses the information on the word order relationship, does not use the hierarchical vector generated by the abstract, claims and specification, and misses the in-depth information contained in the patent text
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0084] like figure 1 , 2 Shown, step 1000, using industry tree generation module 200 defines the target tree industry, a range to be determined manually Patent divided needed.
[0085] Step 1100, validation module 210 determines a target using patentable scope. The need to define the tree industry: I = {i 1 , ..., i j , ..., i n }, Where, i j ∈I is an industry j is the number one industry, 1≤j≤n, n is the number of I at all leaf nodes. I is a set of any non-leaf node i jkl… = {I jkl…1 , ..., i jkl…t }, Other nodes of the outer leaf node ≧ 2, where, k is the number two industry, l is a three sector number, t is the penultimate stage number industry.
[0086] Step 1200, using the tag generation module 220 generates a marker at the target tree industry, resource constraints determine the number p can be marked according to the patent, p≥N, each leaf node of a tree of at least marking industry patent belongs to the node, wherein, N is the number of a last sector.
[0087] Step 1300, c...
Embodiment 2
[0115] A method for automatic classification of industries, including the following steps:
[0116] 1, define the target tree industry. The need to define the tree industry: I = {i 1 , ..., i n }, Where i j ∈I as an industry, we can continue to be divided into two sectors, i j = {I j1 , ..., i jm }, And so on, any of a non-leaf node I i jkl… = {I jkl…1 , ..., i jkl…t }. According to other nodes outside of general practice by sector, leaf nodes ≥2. Let N be the number of all I leaf nodes.
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 provides an industry automatic classification method and system, wherein the method includes determining the target patent scope, and further includes the following steps: defining a target industry tree; generating marks on the target industry tree; using the marks to perform rough classification of target patents; Carry out target patent sub-classification according to the rough classification results. The industry automatic classification method and system proposed by the present invention use the direct push learning method to realize the full mining of small label information; use the information of IPC to enrich the information dimension and reduce the amount of calculation; use abstract, The hierarchical vectors generated by claims and descriptions retain information on word order relationships and dig deeper into patent texts.
Description
Technical field [0001] Technical Field The present invention relates to a document analysis, more particularly to a method and system for automatic classification industry. Background technique [0002] Bring a surge of new industries and emerging patent text of the rapid development of science and technology. In order to analyze the development of technology in the industry background, industry needs to be marked with labels to patents. Manual annotation method is slow and costly, but high accuracy. Therefore a need for a smaller amount of labeling, higher computational efficiency, tap more fully automatic classification of indexed information. [0003] Existing methods are either require a larger amount of manual annotation, or completely without manual tagging and thus can not directly establish a correspondence between the target industry. Patent conventional methods generally used for natural language processing text, informative and important dimension calculation ipc omitt...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more