关键词: 产学研合作绩效评价, 模糊统计, 多空间域映射, 卷积神经网络, 模型自优化策略

Abstract: In view of the existing Industry-University-Research performance evaluation system and methods, there are problems such as single coverage of evaluation indicators, insufficient expression of evaluation sample characteristics, and self-optimization ability of evaluation models to be improved, the evaluation system and methods of subjective and objective intelligently evaluating the comprehensive performance of Industry-University-Research were proposed. Firstly, Around the three-party cooperation subjects, the factors and their connections that affect performance in the process of industry-university-research cooperation were excavated, and the three-level evaluation system of subjective and objective performance of Industry-University-Research was constructed independently. Secondly, the characterization of discrete samples was enhanced by mapping the collected discrete sequence evaluation samples to different high-dimensional spatial domains, such as polar coordinate space and Markov transfer matrix. Then, through the chaotic optimization strategy design based on elite reverse somersault foraging, the depth model redundancy compression and hyperparameter global optimization efficiency were improved, and the ParNet classification model of lightweight compression and high-dimensional super parameter Adaptive optimization was constructed(AParNet). Finally, the model was applied to Industry-University-Research performance evaluation to achieve high-performance intelligent performance evaluation. The experimental results show that this method fits well with the application of discrete sequence non-linear classification and improves the classification performance while reducing the computational load when an optimization strategy is added to the model. Specifically, compared to ParNet, AParNet reduces the number of parameters by 12.1%, effectively achieving model compression, and its classification accuracy in performance evaluation of enterprises, universities, and research institutions can reach 98.6%. Therefore, in the application of intelligent performance evaluation in Industry-University-Research, the proposed method improves the adaptive ability of the evaluation model and can achieve accurate and efficient performance evaluation of Industry-University-Research.

Key words: performance evaluation of industry-university-research cooperation, fuzzy statistics, multi-spatial domain mapping, convolutional neural network, model self-optimization strategy