Design And Implementation Of Research Team Discovery System Based On Patent Information

With the rapid development of science and technology,the number of patents is growing,and the way of scientific research cooperation between inventors is increasingly affecting the output of results.In the field of patent analysis,team discovery is one of the important research directions.In the face of massive patent data,it is often difficult for people to quickly and effectively mine the information of scientific research team,and the mature patent analysis website on the market does not provide such functions.Therefore,how to design and implement an interactive system to help users find scientific and efficient research teams in a certain technical field and understand their related information and development status is the key problem to be solved in this paper.The main work of this paper is as follows:(1)Using APScheduler framework and Requests library to realize the patent data collection,the original data is analyzed,the main patent information is extracted and stored in the database to complete the automatic update of the system data.(2)Compared with the traditional label propagation algorithm based on no right network,the accuracy of the algorithm used in this paper is improved.The degree centrality,intermediate centrality and patent quantity of nodes are combined to evaluate the importance of inventors in the team.The textrank algorithm is used to extract the keywords from the related patents of the research team,which indicates the main research direction of the research team.(3)According to the system development process of software engineering,the requirements analysis,architecture design,key technology selection,functional module division and interaction design,detailed module design,system development and testing of the whole system are completed.The front end of the system is based on Vue.js Based on Django framework,the back-end is developed separately.The database uses MySQL and ElasticSearch to store different types of data.The function modules of this system include data acquisition module,team discovery module,patent retrieval module and system management module.Finally,the system test results show that the system meets the expected results,can meet the needs of users,and has high practical value.