A multi-dimensional fusion strategy similarity measure method for patent application technology disclosure document.

Patent application technology disclosure document is one of the important bases for judging patent novelty and uniqueness. Automated evaluation can effectively solve the problems of long time and strong subjectivity of human evaluation. The text similarity evaluation algorithm based on corpus and deep learning technology has problems such as insufficient amount of cross-library learning data and insufficient core content tendency in the similarity judgment of patent application technology disclosure document, which limits their performance and practical application.

[FTIR-based vehicles paint comparison].

In order to determine a range on vehicle types by the vehicle paints left on the accident site, 940 infrared spectra of vehicle paint from 287 vehicle samples were collected, and then the infrared spectrum database on vehicle body paint was established. The vehicle paints comparison was implemented by characteristic peaks method and correlation coefficient method, and the comparison tests on different vehicle scrap paints were carried out. The test results show that the key of vehicle paint comparison is the spectrum of topcoat layer and the coating layer for the integrated scrap paint, and spectrum should be searched after layer separating for partial scrap paint.

[Infrared spectrum characteristics of vehicle body paint].

Two hundred eighty seven samples of vehicle paint were collected, and 940 spectra were obtained by Fourier transform infrared micro spectrometer. The spectral features of varnish, finish layer, and coated layers of different models and different color were analyzed, and the spectra similarities were compared. The results show that the varnish similarity on the same models with different color is 99.