Book interview method based on deep reinforcement learning

Abstract

The invention provides a book interview method based on deep reinforcement learning, which is applied to book interview work of a library and improves book interview efficiency and quality. The methodcomprises the following steps: firstly, acquiring historical bill data, historical order data and historical borrowing data; preprocessing the data, including format conversion and unification, nullvalue filling, redundancy and error removal and the like, and matching and marking the corresponding data; then, constructing a deep reinforcement learning model applied to book interview, and converting book information contained in the historical book list into a representation form of a vector; training a pre-constructed deep reinforcement learning model by utilizing the states, actions and rewards of the books in the historical bills; and finally, converting the information of the to-be-processed book, and inputting the converted information into the trained deep reinforcement learning model to obtain a book interview result for the to-be-processed book. According to the method, the constructed deep reinforcement learning model can be used for carrying out book interview decision making on the books, and the book interview efficiency and accuracy can be improved.

Description

technical field [0001] The invention belongs to the field of recommendation algorithms in deep learning, and in particular relates to a book acquisition method based on deep reinforcement learning. Background technique [0002] The acquisition work of the library refers to the purchase and visit of books and books, and is the work of the library to collect books. "Acquisition" refers to extensive collection through various channels, and "interview" refers to extensive and systematic research and investigation. . The construction of the library's collection of books has a direct and important relationship with the book acquisition work. The quality of the book acquisition work determines the quality of the library collection. [0003] The existing book acquisition work mainly has the following problems: [0004] (1) Funds are limited, and funds need to be effectively used for the construction of collection resources; [0005] (2) The existing book acquisition mode is main...

AI Technical Summary

Problems solved by technology

[0004] (1) Funds are limited, and funds need to be effectively used for the construction of collection resources;

[0005] (2) The existing book acquisition mode is mainly based on the combination of subject experts’ recommendations and interviewers’ experience in purchasing. Manual interviews are less efficient and have greater subjectivity;

[0006] (3) Relying on manual experience for collection has high requirements for the knowledge, experience, and skills of the interviewers, and it is easy to ignore some information, resulting in incomplete information collected, which in turn affects the accuracy of the procurement plan

It can be seen that the method in the prior art has the technical problems of low efficiency and low accuracy.

Images