In view of the disadvantages of the existing popular RFID (Radio Frequency Identification) book inventory in the industry, such as expensive equipment, low accuracy, and high business threshold, this paper proposes a deep neural network-based inventory framework. By loading different deep neural network algorithm modules, the proposed framework is able to complete target detection of 1D/2D barcodes in photos or video streams. Faster R-CNN is used for 2D barcode and SSD-ResNet for 1D barcode. Then the target barcode and the coordinates of the barcode are intercepted, the books are sorted by the barcode coordinates, and the values are obtained through the barcode recognition to realize the book inventory. Through inventory test on 1D/2D barcode book, the accuracy and recall rate of the framework reached above 99%, with precision rate close to 100%. Compared with RFID inventory, the proposed deep neural network based inventory method is more accurate and precise, and increased the processing speed by around 35%.

Determining the number of service facilities to be purchased or allocated, in order to relieve the contradiction between reader waiting time and effective use of facilities, has always been a hot topic of research. As a service organization, there are various types of service facilities in library, such as access control system, self-service loan and return system, information desk, and even books can be used as service facilities in a broad sense. In this paper, we attempt to apply a queuing model to determine the library resource allocation based on the quality of reader service. In the model, the quantitative measurement of library resource allocation can be determined through the birth and death process of the number of readers. The initial model was improved by using to determine the number of access control channels in our library, thus promoting the effective allocation of library facilities.