Technical competition and patent early warning analysis method based on knowledge discovery

A technology for knowledge discovery and early warning analysis, applied in the fields of technology competition and patent early warning analysis, which can solve the problems of high accuracy requirements and poor user-friendliness of retrieval methods.

Inactive Publication Date: 2017-06-27
TONGJI UNIV
View PDF3 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problems of poor user-friendliness and high requirements for retrieval accuracy in traditional patent analysis, the present invention proposes a clustering method based on an improved neural network in the data mining step, allowing users to relax the accuracy restrictions on retrieval expressions

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
  • Technical competition and patent early warning analysis method based on knowledge discovery
  • Technical competition and patent early warning analysis method based on knowledge discovery
  • Technical competition and patent early warning analysis method based on knowledge discovery

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Figure 4 It is a flow chart of the patent early warning method of the present invention. The user needs to input the search formula, the file to be warned, and the warning threshold. Specifically include the following steps ( figure 1 ):

[0058] Step 1 In the data extraction stage, according to the search formula input by the user, extract and analyze in the intellectual property database and the domain knowledge base to obtain the patent special database.

[0059] Step 2 data preprocessing stage, its steps include:

[0060] Extract the title and abstract of the patent, and then perform Chinese word segmentation, part-of-speech tagging, merging synonyms, removing stop words, and word frequency statistics.

[0061] Step 3 data mining stage, its steps include:

[0062] Step 3.1 Carry out SOM self-organizing learning training on the patent vector text, and obtain the output node vector set Y. Here, we use SOM to map high-dimensional patent text data into a two-dim...

Embodiment 2

[0066] Figure 6 It is a flow chart of patent strategy coordinate analysis of the present invention. The user needs to enter a search query. Specifically include the following steps:

[0067] Steps 1, 2, and 3 are the same as in Embodiment 1.

[0068] Step 4 Result interpretation and analysis stage: analyze the strategic coordinates of patents of different subjects obtained after clustering, and send the technology strategic coordinates map to the user. In the technical strategy coordinate diagram, the centripetal degree represents the link strength between this type of patent and other types of patents, and the calculation method can be obtained by calculating the link strength between its characteristic words and other types of characteristic words. Density indicates whether the subject of this category of patents is closely related. The calculation method can be obtained by calculating the average number of times each pair of feature words appears in different documents ...

Embodiment 3

[0070] Figure 7 It is a flow chart of patent strategy coordinate analysis of the present invention. The user needs to enter a search query. Specifically include the following steps:

[0071] Steps 1, 2, and 3 are the same as in Embodiment 1.

[0072] In step 4, in the result interpretation and analysis stage, the clustered patent topics are analyzed. Each type of patent represents a different topic, and the internal similarity of the patent topics is high. Conduct technical life cycle analysis on patents with different themes, and send the obtained indicator curves and technology maturity data to users.

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 relates to the relevant technical field of patent information processing, in particular to a technical competition and patent early warning analysis method based on knowledge discovery. The invention provides an intelligent patent analysis method based on the knowledge discovery, and provides an analysis result with a high visual degree for a user. In brief, an intellectual property database and an industrial field knowledge library are extracted and analyzed to establish a thematic database and form a corresponding dataset. On the basis, data mining and knowledge discovery tools, including a vector space, a neural network, mathematical statistics and the like, are utilized to disclose deep information which is contained behind data, and a visual statement is provided for users. Finally, through patent early warning analysis, patent theme strategy coordinate analysis and patent theme life cycle analysis, technical competition and patent early warning are realized.

Description

technical field [0001] The present invention relates to the relevant technical field of patent information processing, specifically a technology competition and patent early warning analysis method. Background technique [0002] Today's society is in an innovative era, the Internet is becoming more and more popular, and high-tech is developing rapidly. The key to how an enterprise can keep ahead in the fierce technological competition environment is to improve the overall level of innovation of the enterprise. In a certain sense, the patent level of an enterprise represents the overall level of innovation of the enterprise. Therefore, enterprises can realize technological competition and patent early warning by analyzing existing patents. [0003] Most of the current popular technology competition and patent early warning analysis methods are manually operated, which is time-consuming and labor-intensive. The basic process is to manually set the retrieval formula, retriev...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06Q50/18
CPCG06Q50/184G06F16/33G06F16/35
Inventor 柳先辉陈宇飞王新梅洪晶赵卫东
Owner TONGJI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap