Digital library book recommendation and management method

Abstract

The invention relates to the technical field of book management, in particular to a digital library book recommendation and management method, which comprises the following steps: collecting historical data related to user book preference and library operation, performing feature extraction, and outputting a historical user preference feature data set; establishing a book recommendation prediction model, predicting the interestingness of the user to the target book, and outputting a recommendation result; the recommendation result is fed back to the library management platform, and an administrator adjusts a recommendation strategy according to user feedback.

Description

Technical Field

[0001] The present invention relates to the technical field of book management, and in particular to a digital library book recommendation and management method. Background Art

[0002] Traditional digital library recommendation systems often rely solely on single data such as borrowing records, while ignoring multi-dimensional information such as user stay time and ratings. They may also only focus on the basic attributes of books (such as category or publication time), failing to fully utilize the rich data resources within the library. The extraction of user preference features in existing technologies is relatively simple, lacking a deep integration of user behavior data and book attribute data, resulting in the constructed user preference feature dataset being unable to fully reflect the user's true interests and behavior patterns. Many traditional recommendation systems use rules or basic algorithms, which cannot well capture complex user behavior and diverse book attribute information. This simple model may have low accuracy in predicting user ratings and is difficult to meet users' needs for personalized recommendations. In existing systems, recommendation results are often not fed back to the library management platform in a timely manner, resulting in administrators being unable to quickly adjust recommendation strategies based on user feedback. The overall adaptive ability of the system is weak, and continuous optimization cannot be achieved. Summary of the Invention

[0003] The main purpose of the present invention is to provide a digital library book recommendation and management method to effectively solve the above-mentioned problems mentioned in the background technology.

[0004] The technical solutions of the present invention are as follows:

[0005] In the first aspect, a digital library book recommendation and management method is proposed, which includes the following steps:

[0006] S1, collect historical data related to user book preferences and library operations, perform feature extraction, and output a historical user preference feature dataset;

[0007] S2. Build a book recommendation prediction model to predict the user's rating of the target book and output the rating result;

[0008] S3. Feedback the scoring results to the library management platform, and the administrator adjusts the recommendation strategy based on user feedback.

[0009] A further improvement of the present invention is that the historical data in S1 includes user behavior data and book attribute data, the user behavior data includes borrowing records, stay duration, and ratings; and the book attribute data includes category, author, and publication time.

[0010] A further improvement of the present invention is that the feature extraction of S1 includes:

[0011] S11. Extract user ID features, borrowing time features, stay duration features, and rating features from user behavior data;

[0012] S12, extracting book category features, author features, and keyword features from the book attribute data;

[0013] S13. Combining the user ID, stay duration, rating, book category, author, and keywords corresponding to each set of time features into a feature vector to form a historical user preference feature dataset.

[0014] A further improvement of the present invention is that the establishment of the book recommendation prediction model in S2 includes the following specific steps:

[0015] S21, taking the feature vector of S13 as input and the user rating as output target, where the user rating ranges from 0 to 5;

[0016] S22. Establish a book recommendation prediction model, which uses the predicted user rating as output, all feature vectors in the historical user preference feature dataset as input, the actual user rating corresponding to each set of feature vectors as the prediction target, and minimizing the loss function as the training target. The book recommendation prediction model is trained until the loss function converges to the minimum value and the training is stopped.

[0017] A further improvement of the present invention is that the specific steps of training the book recommendation prediction model in S22 are: calculating the gradient of the loss function with respect to each parameter, and updating the parameters using the gradient descent method until the loss function reaches convergence, and then stopping the training.

[0018] A further improvement of the present invention is that the book recommendation prediction model in S2 is any one of a logistic regression model and a neural network model.

[0019] A further improvement of the present invention is that the specific formula of the loss function in S22 is:

[0020]

[0021] Where P is the loss function, m is the number of feature vectors in the historical user preference feature dataset, y is the predicted user rating, and Y is the actual user rating.

[0022] The technical effects of the present invention are as follows:

[0023] A digital library book recommendation and management method has been constructed. The present invention constructs a rich historical user preference feature dataset by collecting a variety of data, including user behavior data (borrowing records, length of stay, ratings) and book attribute data (category, author, publication time, keywords). This not only captures user interests more accurately, but also better reflects the multidimensional characteristics of books. By combining key features in user behavior and book attribute data (such as user ID, borrowing time, length of stay, ratings, book category, author, and keywords) into feature vectors, this solution can construct a more sophisticated and comprehensive user preference model, which helps to improve the personalization and accuracy of recommendations. The recommendation results are fed back to the library management platform, allowing administrators to adjust the recommendation strategy in real time based on user feedback. This feedback mechanism can not only continuously optimize the recommendation model, but also continuously adapt to changes in user preferences, improving the flexibility of the overall system and user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0025] Figure 1 This is a flow chart of a digital library book recommendation and management method according to embodiment 1 of the present invention. DETAILED DESCRIPTION

[0026] A digital library book recommendation and management method has been constructed. The present invention constructs a rich historical user preference feature dataset by collecting a variety of data, including user behavior data (borrowing records, length of stay, ratings) and book attribute data (category, author, publication time, keywords). This not only captures user interests more accurately, but also better reflects the multidimensional characteristics of books. By combining key features in user behavior and book attribute data (such as user ID, borrowing time, length of stay, ratings, book category, author, and keywords) into feature vectors, this solution can construct a more sophisticated and comprehensive user preference model, which helps to improve the personalization and accuracy of recommendations. The recommendation results are fed back to the library management platform, allowing administrators to adjust the recommendation strategy in real time based on user feedback. This feedback mechanism can not only continuously optimize the recommendation model, but also continuously adapt to changes in user preferences, improving the flexibility of the overall system and user satisfaction.

[0027] Example 1:

[0028] This embodiment proposes a digital library book recommendation and management method, such as Figure 1 As shown, the following specific steps are included:

[0029] S1, collect historical data related to user book preferences and library operations, perform feature extraction, and output a historical user preference feature dataset;

[0030] S2. Build a book recommendation prediction model to predict the user's rating of the target book and output the rating result;

[0031] S3. Feedback the scoring results to the library management platform, and the administrator adjusts the recommendation strategy based on user feedback.

[0032] In this embodiment, the historical data in S1 includes user behavior data and book attribute data. The user behavior data includes borrowing records, stay duration, and ratings; the book attribute data includes category, author, and publication time.

[0033] In this embodiment, the feature extraction of S1 includes:

[0034] S11. Extract user ID features, borrowing time features, stay duration features, and rating features from user behavior data;

[0035] S12, extracting book category features, author features, and keyword features from the book attribute data;

[0036] S13. Combining the user ID, stay duration, rating, book category, author, and keywords corresponding to each set of time features into a feature vector to form a historical user preference feature dataset.

[0037] In this embodiment, establishing the book recommendation prediction model in S2 includes the following specific steps:

[0038] S21, taking the feature vector of S13 as input and the user rating as output target, where the user rating ranges from 0 to 5;

[0039] S22. Establish a book recommendation prediction model, which uses the predicted user rating as output, all feature vectors in the historical user preference feature dataset as input, the actual user rating corresponding to each set of feature vectors as the prediction target, and minimizing the loss function as the training target. The book recommendation prediction model is trained until the loss function converges to the minimum value and the training is stopped.

[0040] In this embodiment, the specific steps of training the book recommendation prediction model in S22 are: calculating the gradient of the loss function with respect to each parameter, and updating the parameters using the gradient descent method until the loss function reaches convergence, and then stopping the training.

[0041] In this embodiment, the book recommendation prediction model in S2 is any one of a logistic regression model and a neural network model.

[0042] In this embodiment, the specific formula of the loss function in S22 is:

[0043]

[0044] Where P is the loss function, m is the number of feature vectors in the historical user preference feature dataset, y is the predicted user rating, and Y is the actual user rating.

[0045] Example 2:

[0046] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned digital library book recommendation and management method by calling the computer program stored in the memory.

[0047] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memories store at least one computer program, which is loaded and executed by the processor to implement a digital library book recommendation and management method provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device. For example, the electronic device may also have components such as a wired or wireless network interface and an input / output interface for data input and output. This embodiment will not be described in detail here.

[0048] Those skilled in the art will appreciate that the present invention may be implemented as a system, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the present invention may be implemented in the form of a computer program product embodied in one or more computer-readable media containing computer-readable program code.

[0049] Any combination of one or more computer-readable media may be employed. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0050] The present invention is described with reference to flowcharts and block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process or block in the flowcharts and block diagrams, as well as combinations of processes and blocks in the flowcharts or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts or block diagrams. Figure 1 A process or multiple processes and boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 A process or multiple processes and boxes Figure 1 A step that specifies a function in one or more boxes.

[0052] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which are all protected by the present invention.

Claims

1. A digital library book recommendation and management method, characterized by: The specific steps include: S1, collect historical data related to user book preferences and library operations, perform feature extraction, and output a historical user preference feature dataset; S2. Build a book recommendation prediction model to predict the user's rating of the target book and output the rating result; S3. Feedback the scoring results to the library management platform, and the administrator adjusts the recommendation strategy based on user feedback.

2. A digital library book recommendation and management method according to claim 1, characterized in that: The historical data in S1 includes user behavior data and book attribute data. The user behavior data includes borrowing records, stay duration, and ratings; the book attribute data includes category, author, and publication time.

3. A digital library book recommendation and management method according to claim 2, characterized in that: The feature extraction of S1 includes: S11. Extract user ID features, borrowing time features, stay duration features, and rating features from user behavior data; S12, extracting book category features, author features, and keyword features from the book attribute data; S13. Combining the user ID, stay duration, rating, book category, author, and keywords corresponding to each set of time features into a feature vector to form a historical user preference feature dataset.

4. A digital library book recommendation and management method according to claim 3, characterized in that: The establishment of the book recommendation prediction model in S2 includes the following specific steps: S21, taking the feature vector of S13 as input and the user rating as output target, where the user rating ranges from 0 to 5; S22. Establish a book recommendation prediction model, which uses the predicted user rating as output, all feature vectors in the historical user preference feature dataset as input, the actual user rating corresponding to each set of feature vectors as the prediction target, and minimizing the loss function as the training target. The book recommendation prediction model is trained until the loss function converges to the minimum value and the training is stopped.

5. A digital library book recommendation and management method according to claim 4, characterized in that: The specific steps of training the book recommendation prediction model in S22 are: calculating the gradient of the loss function with respect to each parameter, and updating the parameters using the gradient descent method until the loss function reaches convergence and then stopping the training.

6. A digital library book recommendation and management method according to claim 5, characterized in that: The book recommendation prediction model in S2 is any one of a logistic regression model and a neural network model.

7. A digital library book recommendation and management method according to claim 6, characterized in that: The specific formula of the loss function in S22 is: Where P is the loss function, m is the number of feature vectors in the historical user preference feature dataset, y is the predicted user rating, and Y is the actual user rating.

Images