Unlock instant, AI-driven research and patent intelligence for your innovation.

Clustering-based patent map making and representing method

A patent map and patent technology, applied in the field of patent map production and representation based on clustering algorithm, can solve the problems of unfavorable patent technology and industrial development, difficult task completion, dependence, etc.

Inactive Publication Date: 2021-03-26
TONGJI UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Subsequently, this technology was also introduced into South Korea, the United States, Singapore and other places, and has been widely used. However, our country has little research and application on it, which is not conducive to the development of my country's patented technology and industry.
The reason for this situation is that on the one hand, insufficient attention has been paid to it, and on the other hand, it is also because of the technical difficulty in making patent maps
[0004] The amount of information involved in the patent map is huge, and the compilation, analysis and production are extremely cumbersome. For ordinary enterprises, such a task is difficult to complete
[0005] In this field, the current method of making patent maps is mainly to first formulate relevant search strategies according to the project fields that require patent analysis, and use this strategy to conduct blanket search and comparison of patent management maps, patent technology maps, patent rights maps, etc. , investigation, and finally summarized into a patent map, which is labor-intensive, time-consuming and labor-intensive; in addition, both structured and unstructured projects are not fully utilized in the production process and presentation of patent maps, and only one of them is used to make patent maps. Not using the other or just adding another information on the completed patent map

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
  • Clustering-based patent map making and representing method
  • Clustering-based patent map making and representing method
  • Clustering-based patent map making and representing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0023] The overall process is as figure 1 shown.

[0024] Each important step is described in detail below.

[0025] 1. Obtain patent text data in the target field.

[0026] Determine the target development field, formulate relevant search strategies, such as keywords, search field scope, etc. to search, and obtain the corresponding unstructured patent text data as the target patent text database, as well as structured information such as corresponding patent applicants and application times.

[0027] 2. Keyword extraction from patent text:

[0028] Note that the target patent text library obtained in step 1 is D={d i},in is a specific patent text in the text database, consisting of several words t, where the word t i In the patent text d j The number of occurrences in is denoted as N i,j According to this, the term frequency (term f...

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

No PUM Login to View More

Abstract

The invention provides a clustering-based patent map making and representing method, which comprises the following steps: extracting features by adopting a text mining technology, mapping unstructuredpatent text information into a low-dimensional space, clustering by adopting a CFSFDP algorithm, and analyzing the features of patent texts in the same cluster by combining unstructured information,therefore, the patent map represented by the directed graph is obtained, and the obtained result can reflect the technical development process of the target technical field more truly and accurately.

Description

technical field [0001] The invention relates to the field of patent map production, in particular to a patent map production and representation technology based on a clustering algorithm. Background technique [0002] Patent map is a form of presenting and summarizing various patent-related information and information, that is, statistical analysis, analysis and arrangement of patent information in the target field, and the results are made into chart information with a similar map pointing function. Compared with other patent management analysis methods, the patent map is more comprehensive, and its presentation form makes it more intuitive and comprehensive, and it is also more convenient and efficient in terms of analysis and utilization. The patent map can point out the direction of technological development for enterprises, and help enterprises analyze and summarize the distribution and use of technologies, thereby helping enterprises to carry out effective intellectual...

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
no application Login to View More
IPC IPC(8): G06F16/30G06F16/35G06F16/29
CPCG06F16/30G06F16/35G06F16/29
Inventor 陈宇飞黄柏如柳先辉赵卫东
Owner TONGJI UNIV