Intelligent management method of book warehouse information system

Abstract

The invention discloses an intelligent management method for a book warehouse information system, and relates to the technical field of book management, and the method comprises the steps: calculating a scoring reference index based on user data through building an incidence relation between book types and books; calculating a first predicted total demand number and an error of each book by establishing a fitting equation of time and the total demand number of the books and combining the comprehensive proportion index of the books in the category of the books; based on a score calculation strategy, establishing a comprehensive score and total demand number fitting equation, and calculating to obtain a second predicted total demand number and an error of the next week; and the two predicted total demand numbers are combined to obtain a comprehensive predicted total demand number, and a replenishment judgment strategy is executed to judge whether the books need to be replenished, so that the accuracy and timeliness of inventory management are ensured.

Description

Technical Field

[0001] The invention relates to the technical field of book management, in particular to an intelligent management method for a book warehouse information system. Background Art

[0002] With the continuous development of the book industry, the management of book warehouses has become increasingly complex. Traditional book warehouse management mainly relies on manual experience and simple statistical data to make decisions, which is inadequate when faced with a large number of books and changing market demands. Therefore, the book warehouse information intelligent management system came into being, aiming to optimize warehouse management and improve operational efficiency through information technology and data analysis.

[0003] The existing book warehouse information system management methods usually include basic functions such as book entry, exit, inventory query, and sales statistics. These methods can help managers understand the inventory and sales of books in the warehouse to a certain extent, and provide certain data support for decision-making. However, these methods still have obvious defects in predicting books.

[0004] Existing methods often lack an effective demand forecasting mechanism. They can usually only simply speculate future demand based on historical sales data, but cannot fully consider the impact of book categories and user evaluation factors on book demand. In addition, existing methods may not be able to effectively integrate information from different data sources and lack the ability to conduct in-depth analysis of data. Therefore, they cannot accurately determine whether replenishment operations are needed in advance. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In view of the technical problems in the background technology, the present invention proposes an intelligent management method for a book warehouse information system, which obtains the first predicted total demand for each book by fitting the relationship between time and the total demand for books, and combining the comprehensive proportion index of each book in its category; calculates the comprehensive score of each current book based on the scoring calculation strategy, and establishes a fitting equation between the comprehensive score and the total demand to predict the second predicted total demand for the next week; combines the first predicted total demand with the second predicted total demand to make a replenishment judgment; thereby solving the technical problems recorded in the background technology.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] An intelligent management method for a book warehouse information system, comprising:

[0010] Obtain book category data and all book data under each category, and establish the association between book categories and books; establish several data tables, and calculate the rating reference index of each user based on the data in the user data table;

[0011] Establish a fitting equation between time and total book demand, calculate the total predicted book demand for each book category in the next week; calculate the comprehensive proportion index of each book in the book category to which it belongs, and combine the total predicted book demand of the corresponding book category to obtain the first predicted demand for each book in the next week; calculate the first prediction error of each book;

[0012] Calculate the comprehensive score of each book based on the score calculation strategy; combine the comprehensive score and the actual total demand of each book from the first week to the fourth week respectively, establish a fitting equation for the comprehensive score and the total demand of each book, and calculate the second predicted total demand of each book in the next week; calculate the second prediction error of each book;

[0013] Calculate the weight factors of the first and second predicted demand totals respectively; combine the first and second predicted demand totals with the corresponding weight factors to obtain the comprehensive predicted demand total for each book in the next week; execute the replenishment judgment strategy to determine whether each book needs to be replenished.

[0014] Specifically, all book data under each book category is obtained, all books under each book category are recorded as associated books of the corresponding book category, and the corresponding book category is recorded as an associated book category corresponding to each associated book;

[0015] Create several data tables, including user data table, book inventory table, book borrowing and returning table, book selling table and book evaluation table;

[0016] Based on the book borrowing and returning data and book purchasing data of each user in the user data table, the rating reference index Sri of each user is calculated. The expression is: Among them, n1 and n2 represent the number of books borrowed and purchased by each user in the library respectively; n0 represents the preset threshold of the total number of books.

[0017] Specifically, the total number of borrowings and sales of all related books in the same book category in each of the previous four weeks is summed up, and then the total number of borrowings and sales of the same book category in the same week is added up to obtain the total number of book demands for each book category from the first week to the fourth week. The expression is:

[0018]

[0019] Among them, (week) represents the week before the week, and week takes values from {1, 2, 3, 4}, corresponding to the first week before, the second week before, the third week before, and the fourth week before respectively; represents the total number of borrowings of the j-th associated book within the week before the week; represents the total number of sales of the j-th associated book within the week before the week, N i represents the total number of associated books of the i-th book category;

[0020] Based on the total demand for books in each book category within the first four weeks Establish a fitting equation between time and the total demand for books; after substituting the values, calculate the predicted total demand for books in each book category for the next week.

[0021] Furthermore, calculate the proportion of the actual total demand for each book in each previous week to the total demand for books in the associated book category it belongs to The expression is: The actual total demand represents the sum of the total number of borrowings and the total number of sales;

[0022] Combine the proportions of the actual total demand for each book in the first four weeks to the total demand for books in the associated book category it belongs to, to obtain the comprehensive proportion index Zp of each book to the associated book category it belongs to j , the expression is:

[0023] Combine the comprehensive proportion index of each book to the associated book category it belongs to with the predicted total demand for books in the corresponding book category for the next week, to obtain the first predicted demand total Ffd for each book in the next week j .

[0024] Specifically, the scoring calculation strategy includes:

[0025] For the k-th book, obtain the score in each evaluation data respectively and the scoring reference index of the evaluating user Among them, l represents the l-th evaluation data;

[0026] Among the multiple evaluation data of the same book, the scoring reference index of the evaluating user Perform a normalization operation to obtain the unit average reference index of each evaluation data The expression is: Among them, M k represents the total number of evaluation data of the k-th book;

[0027] Combine the score in each evaluation data and the scoring reference index of the evaluating user to obtain the comprehensive score ZSc of the corresponding bookk , the expression is:

[0028] Furthermore, based on the comprehensive scores of each book in the first to fourth previous weeks, and the total demand of each book in the first to fourth previous weeks, a fitting equation between the comprehensive score and the total demand of each book is established;

[0029] Substitute the comprehensive score ZSc of each book k , to obtain the second predicted total demand Sfd of each book in the next week k .

[0030] Specifically, obtain the first predicted total demand and the second predicted total demand of each book in the first to fourth previous weeks respectively, and obtain the actual total demand of each book in the first to fourth previous weeks;

[0031] Record the difference between the actual total demand of each previous week and the first predicted total demand and the second predicted total demand as the first error and the second error of each book in each previous week;

[0032] Perform a mean operation on the first error and the second error of each book in the previous four weeks respectively to obtain the first prediction error Fpe j and the second prediction error Spe k .

[0033] Specifically, combine the first prediction error Fpe q with the second prediction error Spe q , and calculate the weight factors α and β of the first predicted total demand and the second predicted total demand respectively. The expression is:

[0034] Combine the first predicted total demand Ffd q and the second predicted total demand Sfd q of each book in the next week with the corresponding weight factors to obtain the comprehensive predicted total demand Zfd q of each book in the next week. The expression is: Zfd q =α*Ffd q +β*Sfd q .

[0035] Specifically, the replenishment judgment strategy includes:

[0036] Obtain the inventory quantity data In of each book in the warehouse from the book inventory table q , when , perform a replenishment operation on this book;

[0037] When When it is the case, no replenishment operation is performed on the book.

[0038] (III) Beneficial effects

[0039] The present invention provides an intelligent management method for a library warehouse information system, having the following beneficial effects:

[0040] 1. By systematically collecting and organizing book categories, book data, user behavior data, and evaluation data, a comprehensive data foundation is established; providing accurate and complete data support for subsequent prediction and decision-making, ensuring that the system can perform precise analysis and judgment based on actual data, thereby improving the reliability and effectiveness of the entire management system;

[0041] 2. By analyzing historical borrowing and selling data, a fitting equation between time and the total number of book demands is established, and then the book demands for each book category in the next week are predicted; it can help the library understand the demand trends of various books in advance, providing a scientific basis for inventory management and replenishment decision-making, effectively reducing inventory backlogs and out-of-stock phenomena, and improving the utilization rate and satisfaction rate of books;

[0042] 3. Based on user evaluation data, the comprehensive score of each book is calculated, and a fitting equation between the comprehensive score of the book and the total number of demands is established, thereby predicting the demand for each book in the next week; making full use of user feedback information, making the prediction closer to the actual needs of users, and improving the accuracy and pertinence of the prediction; by comprehensively considering the popularity of the book and market demand, providing strong support for the library's procurement and recommendation strategies;

[0043] 4. Combining the first and second predicted total demand numbers and their weight factors, calculating the comprehensive predicted total demand number of each book in the next week, and judging whether replenishment is needed based on this; comprehensively considering various prediction factors, improving the scientificity and accuracy of the replenishment decision-making; by real-time monitoring of the inventory situation and predicted demand, potential out-of-stock risks can be discovered and addressed in a timely manner, ensuring the sufficient supply of books, enhancing user satisfaction and service quality; transforming the prediction and replenishment operations into an algorithm model for learning, further optimizing the prediction ability and decision-making efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flowchart of the steps of an intelligent management method for a library warehouse information system provided by the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0046] Referring to Figure 1 , the present invention provides an intelligent management method for a book warehouse information system, including:

[0047] Step 1: Obtain book category data and all book data under each category, and establish an association relationship between book categories and books; establish user data tables, book inventory tables, book borrowing and returning tables, book sales tables, and book evaluation tables; calculate a scoring reference index for each user based on the data in the user data tables.

[0048] The first step includes the following steps:

[0049] Step 101: Obtain all book category data in the library, including book category data such as philosophy and religion, politics and law, military, economy, etc.

[0050] Obtain all book data under each book category, record all books under each book category as associated books corresponding to the book category, and record the corresponding book category as the associated book category corresponding to each associated book; each book category contains several associated books, and each type of book also belongs to only one book category.

[0051] Step 102: Establish user data tables, book inventory tables, book borrowing and returning tables, book sales tables, and book evaluation tables.

[0052] Among them, the user data table stores relevant data of all users in the library, including multiple book borrowing and returning data, book purchase data, and book evaluation data.

[0053] The book inventory table stores the inventory quantity data of all books in the library in the warehouse.

[0054] The book borrowing and returning table stores the borrowing and returning data of each book. One piece of data includes user data, one or more book data, that is, the user borrowed multiple books at one time, as well as the borrowing time and the required return time data.

[0055] The book sales table stores the sales data of each book. Similarly, one piece of data may include one or more book data, that is, the user purchased multiple books at one time.

[0056] The book evaluation table stores the evaluation data of the corresponding books, including the evaluation users, ratings, and comment data. When users borrow or purchase books, they can evaluate the corresponding books.

[0057] The user data table is associated with the book borrowing and returning table, the book selling table, and the book evaluation table through the user name data;

[0058] Step 103: Based on the book borrowing and returning data and book purchasing data of each user in the user data table, calculate the rating reference index Sri of each user, expressed as: Among them, n1 and n2 represent the number of books borrowed and purchased by each user in the library respectively; n0 represents the preset threshold of the total number of books, which is used to determine whether the rating of each user is meaningful and to prevent malicious ratings by users. The specific value is set by the library administrator.

[0059] By systematically collecting and organizing book categories, book data, user behavior data, and evaluation data, a comprehensive data foundation has been established; accurate and complete data support has been provided for subsequent predictions and decisions, ensuring that the system can conduct accurate analysis and judgment based on actual data, thereby improving the reliability and effectiveness of the entire management system.

[0060] Step 2: Obtain the total number of borrowings and sales of the associated books of each book category in each of the previous four weeks; establish a fitting equation between time and total book demand, and calculate the predicted total book demand of each book category in the next week; calculate the comprehensive proportion index of each book in the book category to which it belongs, and combine the predicted total book demand of the corresponding book category to obtain the first predicted total demand of each book in the next week; calculate the first prediction error of each book;

[0061] The step 2 includes the following steps:

[0062] Step 201, filter out the associated books of each book category; obtain the historical borrowing record and historical sales record data of each associated book under each book category from the book borrowing and returning table and the book sales table, and count the total number of borrowings and sales of each associated book in each of the previous four weeks; sum up the total number of borrowings and sales of all associated books belonging to the same book category in each of the previous four weeks, and then add the total number of borrowings and sales of the same week and the same book category to obtain the total number of book demands for each book category in the previous first week, the previous second week, the previous third week, and the previous fourth week. The expression is:

[0063] Among them, (week) represents the week before the current week, where week takes values from {1, 2, 3, 4}, corresponding to the first week before, the second week before, the third week before, and the fourth week before respectively; represents the total number of borrowings of the j-th associated book within the week before the current week; represents the total number of sales of the j-th associated book within the week before the current week, N i represents the total number of associated books of the i-th book category;

[0064] Step 202: Put the total book demand of each book category within the first four weeks into the time series graph corresponding to the book category. The abscissa of the time series graph represents time, in weeks, and the ordinate represents the total book demand; Fit the relationship between time (i.e., the number of weeks) and the total book demand based on the linear fitting method;

[0065] It should be noted that linear fitting is a commonly used data analysis method for finding an optimal fitting line to describe the trend relationship between data points;

[0066] Assume that there is a linear relationship between time and the total book demand, that is, y i = a i x + b i . Denote the independent variable of the fourth week before as 1, the independent variable of the third week before as 2, and so on. Use the linear regression algorithm to calculate the parameters a i and b i , and then obtain the linear relationship between time and the total book demand of each book category, that is, the fitting equation of time - total book demand; Substitute x = 5 into the linear relationship to calculate the predicted total book demand of each book category for the next week;

[0067] Step 203: Calculate the sum of the total number of borrowings and the total number of sales of each book in each week before, that is, the actual demand total, and calculate the proportion of it in the total book demand of the associated book category The expression is:

[0068]

[0069] Based on the proportion combination of the sum of the total number of borrowings and the total number of sales of each book within the first four weeks in the total book demand of the associated book category, obtain the comprehensive proportion index Zp of each book in the associated book category j , and the expression is:

[0070]

[0071] Combine the comprehensive proportion index of each book in its affiliated related book category with the total predicted book demand of the corresponding book category in the next week to obtain the total first predicted demand Ffd of each book in the next week j ;

[0072] Step 204: Obtain the total first predicted demand of each book in the first to fourth previous weeks respectively. Specifically, by combining the total borrowing and selling numbers of each book in the fifth to eighth previous weeks and performing the operations of steps 201 - 203; and obtain the total actual demand of each book in the first to fourth previous weeks respectively. Denote the difference between the total actual demand of each previous week and the total first predicted demand as the first error of each book in each previous week. Perform a mean operation on the first errors of each book in the previous four weeks to obtain the first predicted error Fpe of each book j 。

[0073] By analyzing historical borrowing and selling data, a fitting equation between time and the total book demand is established, and then the book demand of each book category in the next week is predicted; it can help the library understand the demand trends of various books in advance, provide a scientific basis for inventory management and replenishment decisions, effectively reduce inventory backlogs and out - of - stock phenomena, and improve the utilization rate and satisfaction rate of books

[0074] Step three: Calculate the comprehensive score of each current book based on the scoring calculation strategy; obtain the comprehensive scores of each book in the first to fourth previous weeks respectively, and combine the total actual demand of each book in the first to fourth previous weeks to establish a fitting equation between the comprehensive score and the total demand of each book; calculate the total second predicted demand of each book in the next week based on the comprehensive score of each current book; calculate the second predicted error of each book

[0075] The steps in step three include the following steps

[0076] Step 301: Statistically obtain all evaluation data of each book from the book evaluation form, including the evaluating users and scores of each evaluation data, and execute the scoring calculation strategy

[0077] Execute the scoring calculation strategy: For the k - th book, obtain the scores in each evaluation data respectively and the score reference index of the evaluating user where l represents the l - th evaluation data

[0078] Among the multiple evaluation data of the same book, normalize the score reference index of the evaluating user to obtain the unit average reference index of each evaluation data The expression is where M kRepresents the total number of evaluation data for the k-th book;

[0079] For each evaluation data, the rating and the rating reference index of the evaluating user are combined to obtain the comprehensive rating ZSc of the corresponding book k , and the expression is:

[0080] Step 302: Obtain all the evaluation data of each book except the first week, and execute the rating calculation strategy according to Step 301 to obtain the comprehensive rating of each book in the first week; Obtain all the evaluation data of each book except the first week and the second week, and execute the rating calculation strategy to obtain the comprehensive rating of each book in the second week; Obtain all the evaluation data of each book except the first week to the third week, and execute the rating calculation strategy to obtain the comprehensive rating of each book in the third week; Obtain all the evaluation data of each book except the first week to the fourth week, and execute the rating calculation strategy to obtain the comprehensive rating of each book in the fourth week;

[0081] It should be noted that the comprehensive rating in the first week represents the comprehensive rating of each book at the beginning of the first week; The meanings of the comprehensive ratings in the second week, the third week, and the fourth week are the same;

[0082] Obtain the total actual demand of each book in the first week, the second week, the third week, and the fourth week;

[0083] Step 303: Based on the linear regression equation Y k = c k X k + d k fit the comprehensive ratings of each book from the first week to the fourth week, and the total demand of each book from the first week to the fourth week, where X k represents the comprehensive ratings of each book from the first week to the fourth week, and Y k represents the total demand of each book from the first week to the fourth week; Calculate the slope c k and the intercept d k of the fitted line by the least squares method, and then obtain the comprehensive rating - total demand fitting equation of each book;

[0084] Substitute the comprehensive rating ZSc of each book calculated based on all the evaluation data k into the comprehensive rating - total demand fitting equation of the corresponding book to obtain the second predicted total demand Sfd of each book in the next week k ;

[0085] Step 304: Obtain the total second predicted demand of each book in the first to fourth weeks before. Specifically, it is obtained by combining the evaluation data of each book in the fifth to eighth weeks before and performing the operations in Steps 301 - 303; and obtain the total actual demand of each book in the first to fourth weeks before. Denote the difference between the total actual demand of each week before and the total second predicted demand as the second error of each book in each week before. Perform a mean operation on the second errors of each book in the first four weeks to obtain the second predicted error Spe of each book. k 。

[0086] Based on user evaluation data, calculate the comprehensive score of each book and establish a fitting equation between the comprehensive score of the book and the total demand, so as to predict the demand of each book in the next week; make full use of user feedback information, making the prediction closer to the actual needs of users, and improving the accuracy and pertinence of the prediction; by comprehensively considering the popularity of the book and market demand, it provides strong support for the procurement and recommendation strategies of the library.

[0087] Step Four: Calculate the weight factors of the first and second predicted total demands respectively; combine the first and second predicted total demands with the corresponding weight factors to obtain the comprehensive predicted total demand of each book in the next week; execute a replenishment judgment strategy to judge whether each book needs to be replenished.

[0088] The steps in Step Four include the following steps:

[0089] Step 401: Align the indicators of the first predicted total demand and the second predicted total demand of each book in the next week based on the book name to obtain the first predicted total demand Ffd of each book in the next week q 、the second predicted total demand Sfd q 、the first predicted error Fpe q and the second predicted error Spe q ;

[0090] Combine the first predicted error Fpe q with the second predicted error Spe q to calculate the weight factors α and β of the first predicted total demand and the second predicted total demand respectively. The expressions are:

[0091] It should be noted that calculating the weight factors α and β of the first predicted total demand and the second predicted total demand is used to optimize the accuracy and reliability of the prediction model by comparing and analyzing the differences between the predicted demand and the actual demand of the book;

[0092] Step 402: The first predicted total demand Ffd of each book in the next week q, the total second predicted demand Sfd q Combine with the corresponding weight factors to obtain the total comprehensive predicted demand Zfd for each book in the next week q , and the expression is: Zfd q = α * Ffd q + β * Sfd q ;

[0093] Step 403, execute the replenishment judgment strategy at the beginning of the next week. Specifically, obtain the inventory quantity data In of each book in the warehouse from the book inventory table q , based on the total comprehensive predicted demand Zfd of each book in the next week q , the first prediction error Fpe q and the second prediction error Spe q , combine with the inventory quantity data In q to judge whether replenishment operation needs to be carried out for the book;

[0094] When , it means that the inventory of this book is insufficient, and replenishment operation is carried out for this book;

[0095] When , it means that the inventory of this book is sufficient, and no replenishment operation is carried out for this book;

[0096] It should be noted that combining the first prediction error Fpe q and the second prediction error Spe q with the total comprehensive predicted demand Zfd q is used to more accurately evaluate whether the book inventory meets future demands, prevent the inventory of books from being insufficient due to unexpected events, and thus avoid the occurrence of out-of-stock situations;

[0097] Step 404, input the above first and second prediction operations and replenishment judgment operations for the demand of each book in the next week into the machine for learning. These operations can be converted into an algorithm model, and historical data is used to train the model so that the model can learn the prediction rules of book demand and accurately judge whether a book needs to be replenished.

[0098] Combine the first and second total predicted demands and their weight factors to calculate the total comprehensive predicted demand for each book in the next week, and judge whether replenishment is needed accordingly; comprehensively consider various prediction factors, improve the scientificity and accuracy of replenishment decisions; by monitoring the inventory situation and predicted demand in real time, potential out-of-stock risks can be discovered and addressed in a timely manner, ensuring the sufficient supply of books, improving user satisfaction and service quality; convert the prediction and replenishment operations into an algorithm model for learning, further optimizing the prediction ability and decision-making efficiency of the system.

[0099] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer storage medium or transmitted through a computer storage medium.

[0100] The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (e.g., infrared, wireless, microwave, etc.). The computer storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)), etc.

[0101] As described above, the above are only the specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An intelligent management method for a library warehouse information system, characterized in that: Including: Obtain book category data and all book data under each category, and establish the association relationship between book categories and books; Establish several data tables, and calculate the rating reference index of each user based on the data in the user data table; Establish a fitting equation between time and the total number of book demands, and calculate the predicted total number of book demands for each book category in the next week; Calculate the comprehensive proportion index of each book in its corresponding book category respectively, and combine it with the predicted total number of book demands for the corresponding book category to obtain the first predicted total demand for each book in the next week; Calculate the first prediction error of each book; Calculate the comprehensive rating of each current book based on the rating calculation strategy; Respectively combine the comprehensive ratings and the actual total demand numbers of each book in the first to fourth previous weeks to establish a fitting equation between the comprehensive rating and the total demand number of each book, and calculate the second predicted total demand for each book in the next week; Calculate the second prediction error of each book; Calculate the weight factors of the first and second predicted total demand numbers respectively; Combine the first and second predicted total demand numbers with the corresponding weight factors to obtain the comprehensive predicted total demand for each book in the next week; Execute the replenishment judgment strategy to judge whether each book needs to be replenished.

2. The intelligent management method of a book warehouse information system according to claim 1, characterized in that: Obtain all book data under each book category, record all books under each book category as the associated books of the corresponding book category, and record the corresponding book category as the associated book category of each associated book; Establish several data tables, including a user data table, a book inventory table, a book borrowing and returning table, a book sales table, and a book evaluation table; Based on the book borrowing and returning data and book purchase data of each user in the user data table, calculate the rating reference index Sri for each user, and the expression is: Among them, n1 and n2 respectively represent the number of books borrowed by each user in the library and the number of books purchased; n0 represents the preset total number threshold of books.

3. The intelligent management method of a book warehouse information system according to claim 1, characterized in that: Sum the total number of borrowings and the total number of sales for each week within the first four weeks for all associated books belonging to the same book category. Then add the total number of borrowings and the total number of sales for the same week and belonging to the same book category to obtain the total demand for books in each book category from the first week to the fourth week. The expression is: Among them, (week) represents the week week before, and week takes values from {1, 2, 3, 4}, corresponding to the first week before, the second week before, the third week before, and the fourth week before respectively; represents the total number of borrowings of the j-th associated book within the week week before; represents the total number of sales of the j-th associated book within the week week before, N i represents the total number of associated books of the i-th book category; Based on the total number of book demands for each book category in the previous four weeks Establish a fitting equation for the establishment time and the total number of book demands; after substituting the values, calculate the predicted total number of book demands for each book category in the next week.

4. The intelligent management method of a book warehouse information system according to claim 3, characterized in that: Calculate the total actual demand for each book in each of the previous weeks, as a proportion of the total demand for books in the associated book category to which it belongs The expression is: The total actual demand represents the sum of the total number of borrowings and the total number of sales; Combine the proportion of the total actual demand of each book in the first four weeks to the total demand of books in the associated book category to obtain the comprehensive proportion index Zp of each book in the associated book category j , and the expression is: Combine the comprehensive proportion index of each book in its associated book category with the total predicted book demand for the corresponding book category in the next week to obtain the first total predicted demand Ffd for each book in the next week j 。 5. The intelligent management method of a book warehouse information system according to claim 1, characterized in that: The rating calculation strategy includes: For the k-th book, obtain the ratings in each evaluation data respectively and the rating reference index of the evaluating user where l represents the l-th evaluation data Among the multiple evaluation data of the same book, the scoring reference index of the evaluating user is normalized to obtain the unit average reference index of each evaluation data The expression is: where M k represents the total number of evaluation data of the k-th book; Combine the ratings in each evaluation data and the rating reference index of the evaluating user to obtain the comprehensive rating ZSc of the corresponding book k , and the expression is:

6. The intelligent management method of a book warehouse information system according to claim 5, characterized in that: Based on the comprehensive ratings of each book in the first to fourth previous weeks and the total demand numbers of each book in the first to fourth previous weeks, establish a fitting equation between the comprehensive rating and the total demand number of each book; Substitute the comprehensive score ZSc of each book k to obtain the total second predicted demand Sfd of each book for the next week k .

7. The intelligent management method of a book warehouse information system according to claim 1, characterized in that: Respectively obtain the first predicted total demand number and the second predicted total demand number of each book in the first to fourth previous weeks, and obtain the actual total demand number of each book in the first to fourth previous weeks; Record the difference between the actual total demand number of each previous week and the first predicted total demand number and the second predicted total demand number as the first error and the second error of each book in each previous week; Perform mean operations on the first error and the second error of each book in the first four weeks respectively to obtain the first prediction error Fpe of each book j and the second prediction error Spe k .

8. The intelligent management method of a book warehouse information system according to claim 1, characterized in that: Combine the first prediction error Fpe q with the second prediction error Spe q to calculate the weight factors α and β of the total first predicted demand and the total second predicted demand respectively. The expressions are as follows: Total the first predicted demand Ffd for each book in the next week q and the total second predicted demand Sfd q and combine them with the corresponding weight factors to obtain the total comprehensive predicted demand Zfd for each book in the next week q , with the expression: Zfd q = α * Ffd q + β * Sfd q .

9. The intelligent management method of a book warehouse information system according to claim 8, characterized in that: The replenishment judgment strategy includes: Obtain the inventory quantity data of each book in the warehouse from the book inventory table In q , when perform a replenishment operation on this book; When Do not restock this book.

Images