Scene-driven library reader behavior data number-real fusion management method

Abstract

The invention provides a scene-driven library reader behavior data number-real fusion management method, and relates to the technical field of intelligent management, and the method comprises the steps: taking a plurality of reading influence feature sets as association comparison features to carry out big data retrieval, and obtaining a plurality of historical reading record data sets; performing book clustering and reading favor degree analysis to obtain a plurality of book category sets and a plurality of reading favor degree sets; and by taking minimization of the overall user reading distance and maximization of the overall reading favorable sensitivity as expected objectives, evaluating the plurality of alternative book storage schemes, and outputting an optimal book storage scheme for storage management. According to the book storage method and device, the technical problems that a matched book storage scheme cannot be set according to the structural layout of a library in an existing method, the book storage position is unreasonable, and the reading efficiency of a reader is affected can be solved, the scientificity, rationality and accuracy of book storage can be remarkably improved, and the reader can find the needed book more conveniently and rapidly.

Description

Technical Field

[0001] The present application relates to the field of intelligent management technology, and in particular to a scenario-driven digital-real integration management method for library reader behavior data. Background Art

[0002] As modern society places increasing demands on library functions, libraries, as core places for knowledge dissemination, information acquisition, and learning exchanges, are increasingly focusing on improving service quality, optimizing resource allocation, and improving operational efficiency. Therefore, the scientific nature of spatial layout and book storage plans is particularly important.

[0003] Traditional book storage methods mainly classify and organize books based on their subject, category or number of collections. Although this method can ensure the orderly storage of books, it does not take into account the diversity and variability of the library's internal space. For example, different areas of the library (such as reading areas near windows, electronic resource areas, quiet reading areas, lobby areas, etc.) have different characteristics such as light intensity, noise level and usage frequency, which directly affect readers' reading behavior and book borrowing needs.

[0004] In summary, the existing book storage management method for libraries cannot set a matching book storage plan according to the structural layout of the library, resulting in unreasonable book storage locations, affecting readers' reading efficiency and reading experience. Summary of the invention

[0005] The purpose of this application is to provide a scenario-driven digital-real fusion management method for library reader behavior data, in order to solve the technical problem that the existing book storage management method used in libraries cannot set a matching book storage plan according to the structural layout of the library, resulting in unreasonable book storage locations, affecting readers' reading efficiency and reading experience.

[0006] In view of the above problems, the present application provides a scenario-driven digital-real fusion management method for library reader behavior data, including: identifying the architectural structure diagram of the target library, dividing and determining a number of reading areas, and collecting and identifying features for the several reading areas according to reading influence factors to determine a number of reading influence feature sets; combining library management big data, searching with the several reading influence feature sets as associated comparison features to obtain a number of historical reading record data sets, and performing book clustering and reading favorability analysis in combination with the several historical reading record data sets to obtain a number of book category sets and a number of reading favorability sets for the several reading areas; using the architectural structure diagram and bookshelf design information of the target library as book storage condition constraints, combining the size information of the books to be stored to simulate book storage, and generate multiple book alternative storage plans; based on a predetermined dual optimization expectation, evaluating the multiple book alternative storage plans, outputting the optimal book storage plan for storage management, wherein the predetermined dual optimization expectation is to minimize the overall user reading distance and maximize the overall reading favorability.

[0007] Optionally, the scenario-driven digital-physical fusion management method for library reader behavior data also includes: setting the area of ​​the region, the average regional crowd density, hardware comfort, light intensity, light softness and landscape view as reading influencing factors; collecting and identifying features of the several reading areas according to the area of ​​the region, the average regional crowd density, hardware comfort, light intensity, light softness and landscape view, and outputting the several reading influencing feature sets.

[0008] Optionally, the scenario-driven digital-physical fusion management method for library reader behavior data also includes: randomly selecting a first reading impact feature set from the several reading impact feature sets; using the first reading impact feature set as the first associated comparison feature during retrieval, combining with library management big data for information retrieval, and setting historical reading record data that meets the associated similarity threshold as the first historical reading record data; performing iterative retrieval until the expected data volume is reached, obtaining a first historical reading record data set, and adding it to several historical reading record data sets.

[0009] Optionally, the scenario-driven digital-physical fusion management method for library reader behavior data also includes: extracting book types from a first historical reading record data set to obtain a first book type set, clustering the first book type set according to predetermined book categories to determine a first book category set; based on the first historical reading record data set, sequentially performing reading favorability analysis on multiple first book categories in the first book category set, outputting multiple first reading favorabilities to form a first reading favorability set; continuing to perform book clustering and reading favorability analysis on the several historical reading record data sets to obtain several book category sets and several reading favorability sets for the several reading areas.

[0010] Optionally, the scenario-driven digital-physical fusion management method for library reader behavior data also includes: extracting reading features from the first historical reading record data set according to the multiple first book categories to obtain multiple first browsing time sets and multiple first book word count sets; calculating the ten thousand-word browsing time based on the multiple first browsing time sets and the multiple first book word count sets to obtain multiple first ten thousand-word browsing times, and setting the multiple first ten thousand-word browsing times as the multiple first reading favorability degrees.

[0011] Optionally, the scenario-driven digital-real fusion management method for library reader behavior data also includes: obtaining predetermined dual optimization expectations, wherein the predetermined dual optimization expectations include minimizing the overall user reading distance and maximizing the overall reading favorability; constructing a book storage plan evaluation formula based on the minimization of the overall user reading distance and maximization of the overall reading favorability; based on the book storage plan evaluation formula, respectively evaluating the multiple alternative book storage plans, and outputting the optimal book storage plan.

[0012] Optionally, the scenario-driven digital-real integration management method for library reader behavior data also includes: the book storage plan evaluation formula is: ; ; Among them, RIT is the book storage adaptability, To obtain the distance weight, is the reading favorability weight, M is the number of book categories to be stored, is the average of several reading favorability values ​​of the m-th book category, is the reading distance of the mth book category, is the distance weight of the horizontal access path, is the vertical reading height weight, N is the number of reading areas, is the favorability of the nth reading area of ​​the mth book category, is the horizontal access path distance of the nth reading area of ​​the mth book category, is the mean vertical reading height of the m-th book category.

[0013] Optionally, the scenario-driven digital-physical fusion management method for library reader behavior data also includes: based on the book storage plan evaluation formula, respectively evaluating the storage fitness of the multiple book alternative storage plans, and outputting multiple book storage fitnesses; setting the book alternative storage plan corresponding to the maximum storage fitness among the multiple book storage fitnesses as the optimal book storage plan.

[0014] The technical solution provided in this application has at least the following technical effects or advantages: By identifying the architectural structure diagram of the target library, a number of reading areas are divided and determined, and the features of the several reading areas are collected and identified according to the reading impact factors, and a number of reading impact feature sets are determined; then, in combination with the library management big data, the several reading impact feature sets are retrieved as the associated comparison features to obtain a number of historical reading record data sets, and book clustering and reading favorability analysis are performed in combination with the several historical reading record data sets to obtain a number of book category sets and a number of reading favorability sets for the several reading areas; further, the architectural structure diagram and bookshelf design information of the target library are used as book storage condition constraints, and book simulation storage is performed in combination with the size information of the books to be stored, and a number of book alternative storage plans are generated; finally, based on the predetermined double optimization expectations, the multiple book alternative storage plans are evaluated, and the optimal book storage plan is output for storage management, wherein the predetermined double optimization expectations are to minimize the overall user reading distance and maximize the overall reading favorability. In other words, by adopting intelligent data analysis, simulated storage and dynamic adjustment technology, a customized book storage plan can be provided for each reading area, making the library's spatial layout and resource allocation more in line with actual needs, thereby significantly improving the scientificity, rationality and accuracy of book storage, enabling readers to find the books they need more conveniently and quickly, and improving library operating efficiency and service quality.

[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0017] Figure 1 This is a flowchart of a scenario-driven digital-real integration management method for library reader behavior data for this application; Figure 2 This is a flowchart for determining several reading influence feature sets in a scenario-driven digital-physical fusion management method for library reader behavior data in this application. DETAILED DESCRIPTION

[0018] This application provides a scenario-driven digital-real integration management method for library reader behavior data, which solves the technical problem that the existing book storage management method used in libraries cannot set a matching book storage plan according to the structural layout of the library, resulting in unreasonable book storage locations and affecting readers' reading efficiency and reading experience. By adopting intelligent data analysis, simulated storage and dynamic adjustment technology, a customized book storage plan can be provided for each reading area, making the library's spatial layout and resource allocation more in line with actual needs, thereby significantly improving the scientificity, rationality and accuracy of book storage, allowing readers to find the books they need more conveniently and quickly, and improving library operation efficiency and service quality.

[0019] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0020] For examples, please see the attached Figure 1 This application provides a scenario-driven digital-real integration management method for library reader behavior data, which specifically includes the following steps: Step 1: Identify the architectural structure diagram of the target library, divide and determine a number of reading areas, and collect and identify features of the reading areas according to reading impact factors to determine a number of reading impact feature sets.

[0021] Further, if Figure 2 As shown, step one of this application also includes: The regional area, the average regional crowd density, the hardware comfort, the light intensity, the light softness and the landscape view are set as reading influencing factors; according to the regional area, the average regional crowd density, the hardware comfort, the light intensity, the light softness and the landscape view, the features of the several reading areas are collected and identified, and the several reading influencing feature sets are output.

[0022] Specifically, first, obtain the architectural structure diagram of the target library, which includes the overall layout of the library, the distribution of various functional areas (such as reading area, bookshelf area, leisure area, electronic resource area, etc.), door and window configurations, etc.; then, based on the architectural structure diagram, accurately measure the area, channel width, lighting conditions, etc. of each area, identify the specific dimensions and spatial characteristics of each area, and provide data basis for subsequent area division and book storage; further, according to the architectural structure diagram and combined with the actual functional needs of the library, divide the entire library area into multiple specific reading areas.

[0023] Then, the reading influencing factors are configured, and the reading influencing factors include regional area, average regional crowd density, hardware comfort, light intensity, light softness and landscape view, among which, regional area refers to the size of the space of each reading area, which directly affects the utilization efficiency and comfort of the space; the average regional crowd density affects the convenience of book storage and the flow efficiency of the library, such as dense areas may need to store more popular books, while low-density areas are suitable for storing unpopular books; hardware comfort refers to the comfort of hardware facilities such as seat comfort, desktop configuration, and number of tables and chairs in the area, which affects the reader's stay time and usage intention; light intensity refers to the light brightness level in the area, which affects the reader's visual comfort and reading efficiency. Too strong or too weak light will affect the reader's reading experience; light softness refers to whether the light source is natural and uniform, avoiding dazzling strong light or dim environment. Soft light can enhance the comfort and reading experience of the area; landscape view includes whether it is possible to appreciate the external scenery through windows or other windows. The landscape has a great psychological impact on the reading experience, especially when reading for a long time, it can provide a sense of relaxation and comfort.

[0024] Further, feature collection and feature identification are performed on the several reading areas according to the area of ​​the area, the average regional crowd density, hardware comfort, light intensity, light softness and landscape view. For example, the area of ​​each area is measured, which can be obtained through architectural drawings or actual measurements; the comfort of hardware equipment such as seats, desks, computer terminals in the area is scored, and evaluation is performed in combination with reader feedback and the configuration of actual facilities; and the several reading areas are feature identified based on the feature collection results to obtain several reading impact feature sets, for example, the feature set of reading area A has an area of ​​50 m2, an average crowd density of 0.8 person / m2, high hardware comfort (score: 4 / 5), a light intensity of 300 lux, medium light softness (score: 3 / 5), and a good landscape view (a garden can be seen outside the window).

[0025] Step 2: In combination with library management big data, the several reading influence feature sets are used as associated comparison features for retrieval to obtain several historical reading record data sets, and the several historical reading record data sets are combined for book clustering and reading favorability analysis to obtain several book category sets and several reading favorability sets for the several reading areas.

[0026] Furthermore, step 2 of this application also includes: A first reading impact feature set is randomly selected from the several reading impact feature sets; the first reading impact feature set is used as the first associated comparison feature during retrieval, information retrieval is performed in combination with library management big data, and historical reading record data that meets the associated similarity threshold is set as the first historical reading record data; iterative retrieval is performed until the expected data volume is reached, and the first historical reading record data set is obtained, and added to the several historical reading record data sets.

[0027] Specifically, first, any one of the plurality of reading influence feature sets is randomly selected as the first reading influence feature set, wherein the first reading influence feature set includes the area of ​​the first region, the average density of the flow of people in the first region, the first hardware comfort, the first light intensity, the first light softness and the first landscape view; then, the area of ​​the first region, the average density of the flow of people in the first region, the first hardware comfort, the first light intensity, the first light softness and the first landscape view are used as the first associated comparison features during retrieval, and information retrieval is performed in combination with the library management big data, that is, the historical reading record data stored in the library management system is used in combination with the above feature set for retrieval, and the reading records that meet the associated similarity threshold are screened out from the historical data by calculating the similarity between the features (such as using cosine similarity, Euclidean distance and other methods), and the associated similarity threshold can be dynamically adjusted according to the actual amount of retrieved data. If the amount of retrieved data is too small, the similarity threshold can be appropriately relaxed to add more historical data for analysis; if the amount of retrieved data is too large, the threshold can be increased to filter out historical data that is not relevant to the target area; and then the historical reading record data with a similarity greater than the associated similarity threshold is set as the first historical reading record data.

[0028] Then, in order to obtain enough historical reading data, iterative retrieval is performed, and the process is repeated until the expected data volume (such as 10,000 data volumes) is reached. Different reading impact feature sets can be selected in each iteration, and information retrieval is continued to obtain the first historical reading record data set. And using the same information retrieval method, several reading impact feature sets of the several reading areas are obtained in turn. By combining library management big data and regional characteristics for intelligent retrieval, historical reading data related to specific reading areas can be effectively obtained, and reader behavior can be further analyzed, thereby providing data support for the optimization of book storage solutions.

[0029] Furthermore, step 2 of this application also includes: The book types are extracted from the first historical reading record data set to obtain a first book type set, and the first book type set is clustered according to a predetermined book category to determine a first book category set.

[0030] Specifically, first, book types are extracted from the first historical reading record data set, that is, relevant type features of books, such as novels, essays, poems, etc., are extracted from the first historical reading record data set to obtain a first book type set; then, the first book type set is clustered according to predetermined book categories (such as science, literature, history, etc.), with the aim of grouping books of similar types, providing data support for subsequent book storage and recommendation, and determining the first book category set.

[0031] Based on the first historical reading record data set, a reading favorability analysis is performed on a plurality of first book categories in the first book category set in turn, and a plurality of first reading favorabilities are output to form a first reading favorability set.

[0032] Furthermore, the present application also includes the following steps: According to the multiple first book categories, reading features are extracted from the first historical reading record data set to obtain multiple first browsing time sets and multiple first book word count sets; based on the multiple first browsing time sets and multiple first book word count sets, ten thousand-word browsing times are calculated to obtain multiple first ten thousand-word browsing times, and the multiple first ten thousand-word browsing times are set as the multiple first reading favorability degrees.

[0033] Specifically, first, according to the multiple first book categories, reading feature extraction is performed on the first historical reading record data set, including browsing time extraction and book word count extraction, wherein browsing time extraction refers to extracting the total browsing time of each book in the historical record, which reflects the reader's attention and interest in the book. For example, the browsing time of a certain book may be longer, indicating that its content is more attractive to readers; book text extraction refers to extracting the word count feature of the book based on the actual number of words or pages of the book. Books with more words may require more time to read, reflecting the depth or length of the book; obtain multiple first browsing time sets and multiple first book word count sets.

[0034] Next, the 10,000-word browsing time is calculated based on the multiple first browsing time sets and the multiple first book word count sets, that is, the 10,000-word browsing time of each book category is calculated as an indicator to measure the reader's reading interest and the attractiveness of the book. The 10,000-word browsing time refers to the time spent reading every 10,000 words, reflecting the reading depth of each book category and the reader's interest level, and multiple first 10,000-word browsing times are obtained. Finally, the multiple first 10,000-word browsing times are set as the multiple first reading favorability to form the first reading favorability set. By analyzing the 10,000-word browsing time of different book categories, the reader's preference for different types of books can be inferred. For example, if the 10,000-word browsing time of a certain category is longer, it indicates that the reader has a higher interest in books of that category.

[0035] Continue to perform book clustering and reading favorability analysis on the plurality of historical reading record data sets to obtain a plurality of book category sets and a plurality of reading favorability sets for the plurality of reading areas.

[0036] Specifically, the same method as that for obtaining the first book category set and the first reading favorability set is used to continue to perform book clustering and reading favorability analysis on the several historical reading record data sets to obtain several book category sets and several reading favorability sets for the several reading areas.

[0037] Step 3: Using the target library's architectural structure diagram and bookshelf design information as constraints for book storage conditions, combined with the size information of the books to be stored, simulate the storage of books and generate multiple alternative book storage plans.

[0038] Specifically, first, obtain the architectural structure diagram of the target library to clarify the size, function, frequency of use and other information of each area; obtain the design information of the library bookshelf, including the capacity, size, placement method, etc. of the bookshelf, as well as the storage requirements of each bookshelf (such as the maximum height, width, depth, etc. of the book). On the other hand, obtain the size information of the books to be stored, including the actual size of each book (such as height, width, thickness, etc.). Then, take the architectural structure diagram and bookshelf design information as the book storage condition constraints, and combine the size information of the books to be stored to simulate the storage of books. Through software simulation, multiple storage plans can be generated, and it can be verified whether these plans meet the actual space restrictions. The plan that meets the book storage condition constraints is set as the book alternative storage plan, and multiple book alternative storage plans are obtained.

[0039] Step 4: Based on the predetermined dual optimization expectations, the multiple alternative book storage plans are evaluated, and the optimal book storage plan is output for storage management, wherein the predetermined dual optimization expectations are to minimize the overall user reading distance and maximize the overall reading favorability.

[0040] Furthermore, step 4 of this application also includes: Obtaining a predetermined dual optimization expectation, wherein the predetermined dual optimization expectation includes minimizing the overall user reading distance and maximizing the overall reading favorability; constructing a book storage plan evaluation formula based on minimizing the overall user reading distance and maximizing the overall reading favorability.

[0041] Furthermore, the present application also includes the following steps: The evaluation formula for the book storage plan is: ; ; Among them, RIT is the book storage adaptability, To obtain the distance weight, is the reading favorability weight, M is the number of book categories to be stored, is the average of several reading favorability values ​​of the m-th book category, is the reading distance of the mth book category, is the distance weight of the horizontal access path, is the vertical reading height weight, N is the number of reading areas, is the favorability of the nth reading area of ​​the mth book category, is the horizontal access path distance of the nth reading area of ​​the mth book category, is the mean vertical reading height of the m-th book category.

[0042] Specifically, first, obtain the predetermined dual optimization expectations, which include minimizing the overall user reading distance and maximizing the overall reading favorability, that is, optimizing the book storage location so that the overall reading distance of readers when borrowing books is minimized. By reducing the walking distance from the current location to the book storage area, the borrowing efficiency can be improved and the reader's waiting time can be reduced; on the other hand, according to the characteristics of the reading area and the type of books, the reader's reading favorability in each area is maximized. Then, based on the minimization of the overall user reading distance and the maximization of the overall reading favorability, a book storage plan evaluation formula is constructed. The book storage plan evaluation formula can comprehensively evaluate the effect of the book storage plan by comprehensively considering factors such as the book category, reading path, regional characteristics, and reading favorability.

[0043] In the book storage plan evaluation formula, RIT is the book storage adaptability, which indicates the quality of the book storage plan. The higher the storage adaptability, the more reasonable the book storage plan is, and the better it can meet the needs of readers and the scientific nature of book storage. is the reading distance weight, which indicates the weight of the reading distance on the overall fitness evaluation. This value determines the importance of the reading distance in the evaluation of the book storage plan. If the reading distance has a greater impact on readers, a higher weight is given, otherwise a lower weight is given. is the reading favorability weight, which indicates the weight of reading favorability on the overall fitness evaluation. This value determines the importance of reading favorability in the evaluation of book storage solutions. If the reader's reading experience (such as comfort, interest, etc.) is more important to the overall evaluation, a higher weight is given, otherwise a lower weight is given; M is the number of book categories to be stored; is the average of several reading favorability of the m-th book category, that is, the average of the reading favorability of the m-th book category in several reading areas; is the reading distance of the mth book category; is the distance weight of the horizontal access path; is the vertical access height weight. For example, in some libraries, the bookshelves are high, and readers need to walk a longer distance or use a ladder. This vertical movement will affect the convenience of taking books. N is the number of reading areas. is the favorability of the nth reading area of ​​the mth book category, is the horizontal access path distance of the nth reading area of ​​the mth book category, is the mean vertical reading height of the m-th book category.

[0044] Based on the book storage plan evaluation formula, the multiple alternative book storage plans are evaluated respectively, and the optimal book storage plan is output.

[0045] Furthermore, the present application also includes the following steps: Based on the book storage plan evaluation formula, the storage fitness of the multiple book storage alternative plans is evaluated respectively, and multiple book storage fitnesses are output; the book storage alternative plan corresponding to the maximum storage fitness among the multiple book storage fitnesses is set as the optimal book storage plan.

[0046] Specifically, according to the book storage plan evaluation formula, the storage fitness of the multiple book storage alternative plans is evaluated respectively, that is, for each book storage plan, the parameters in the formula (such as reading distance, reading favorability, horizontal reading path distance, etc.) will be calculated according to the specific data of the plan to obtain its fitness, and multiple book storage fitness values ​​are output. Each fitness value represents the pros and cons of the plan. A higher fitness means that the plan performs better in satisfying the reading distance and reading favorability. Then, from all the alternative plans, the book storage alternative plan with the largest storage fitness is selected as the optimal book storage plan. This plan can maximize the library space utilization, reader needs and scientific book storage in actual book storage. Finally, book storage management is performed according to the optimal book storage plan.

[0047] In summary, the scenario-driven digital-real fusion management method for library reader behavior data provided by this application has the following technical effects: By adopting intelligent data analysis, simulated storage and dynamic adjustment technology, a customized book storage solution can be provided for each reading area, making the library's spatial layout and resource allocation more in line with actual needs, thereby significantly improving the scientificity, rationality and accuracy of book storage, enabling readers to find the books they need more conveniently and quickly, and improving the library's operating efficiency and service quality.

[0048] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0049] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A scenario-driven digital-real integration management method for library reader behavior data, characterized in that: Methods include: Identify the building structure diagram of the target library, divide and determine a number of reading areas, and collect and identify features of the reading areas according to reading impact factors to determine a number of reading impact feature sets; In combination with the library management big data, the plurality of reading influence feature sets are used as associated comparison features for retrieval to obtain a plurality of historical reading record data sets, and the plurality of historical reading record data sets are combined for book clustering and reading favorability analysis to obtain a plurality of book category sets and a plurality of reading favorability sets for the plurality of reading areas; Taking the target library's architectural structure diagram and bookshelf design information as the constraints for book storage conditions, combined with the size information of the books to be stored, simulated book storage is performed to generate multiple alternative book storage plans; Based on the predetermined dual optimization expectations, the multiple alternative book storage plans are evaluated, and the optimal book storage plan is output for storage management, wherein the predetermined dual optimization expectations are to minimize the overall user reading distance and maximize the overall reading favorability.

2. The scenario-driven digital-real integration management method for library reader behavior data according to claim 1 is characterized in that: According to the reading impact factors, the features of the plurality of reading areas are collected and identified to determine a plurality of reading impact feature sets, including: The area, average regional traffic density, hardware comfort, light intensity, light softness and landscape view are set as reading influencing factors; The features of the plurality of reading areas are collected and identified according to the area, average regional crowd density, hardware comfort, light intensity, light softness and landscape view, and the plurality of reading impact feature sets are output.

3. The scenario-driven digital-real integration management method for library reader behavior data according to claim 2 is characterized in that: Combined with the library management big data, the several reading impact feature sets are used as associated comparison features for retrieval to obtain several historical reading record data sets, including: Randomly selecting a first reading impact feature set from the plurality of reading impact feature sets; Using the first reading impact feature set as the first associated comparison feature during retrieval, combining with the library management big data to perform information retrieval, and setting the historical reading record data that meets the associated similarity threshold as the first historical reading record data; Iterative retrieval is performed until the expected data volume is reached, and a first historical reading record data set is obtained and added to the plurality of historical reading record data sets.

4. The scenario-driven digital-real integration management method for library reader behavior data according to claim 3 is characterized in that: Combining the plurality of historical reading record data sets to perform book clustering and reading favorability analysis, a plurality of book category sets and a plurality of reading favorability sets for the plurality of reading areas are obtained, including: Extracting book types from the first historical reading record data set to obtain a first book type set, clustering the first book type set according to predetermined book categories to determine a first book category set; Based on the first historical reading record data set, sequentially performing reading favorability analysis on a plurality of first book categories in the first book category set, outputting a plurality of first reading favorabilities to form a first reading favorability set; Continue to perform book clustering and reading favorability analysis on the plurality of historical reading record data sets to obtain a plurality of book category sets and a plurality of reading favorability sets for the plurality of reading areas.

5. The scenario-driven digital-real integration management method for library reader behavior data according to claim 4 is characterized in that: Based on the first historical reading record data set, reading favorability analysis is performed on a plurality of first book categories in the first book category set in sequence, and a plurality of first reading favorability scores are output, including: According to the plurality of first book categories, extracting reading features from the first historical reading record data set to obtain a plurality of first browsing time sets and a plurality of first book word count sets; Ten thousand-word browsing times are calculated according to the multiple first browsing time sets and the multiple first book word count sets to obtain multiple first ten thousand-word browsing times, and the multiple first ten thousand-word browsing times are set as the multiple first reading favorability degrees.

6. The scenario-driven digital-real integration management method for library reader behavior data according to claim 1 is characterized in that: Based on the predetermined dual optimization expectation, the multiple alternative book storage solutions are evaluated and the optimal book storage solution is output, including: Obtaining a predetermined dual optimization expectation, wherein the predetermined dual optimization expectation includes minimizing the overall user reading distance and maximizing the overall reading favorability; Constructing a book storage plan evaluation formula based on minimizing the overall user access distance and maximizing the overall reading favorability; Based on the book storage plan evaluation formula, the multiple alternative book storage plans are evaluated respectively, and the optimal book storage plan is output.

7. The scenario-driven digital-real integration management method for library reader behavior data according to claim 6 is characterized in that: The evaluation formula for the book storage plan is: ； ； Among them, RIT is the book storage adaptability, To obtain the distance weight, is the reading favorability weight, M is the number of book categories to be stored, is the average of several reading favorability values ​​of the m-th book category, is the reading distance of the mth book category, is the distance weight of the horizontal access path, is the vertical reading height weight, N is the number of reading areas, is the favorability of the nth reading area of ​​the mth book category, is the horizontal access path distance of the nth reading area of ​​the mth book category, is the mean vertical reading height of the m-th book category.

8. The scenario-driven digital-real integration management method for library reader behavior data according to claim 6 is characterized in that: Based on the book storage plan evaluation formula, the multiple alternative book storage plans are evaluated respectively, and the optimal book storage plan is output, including: Based on the book storage plan evaluation formula, respectively evaluate the storage fitness of the multiple alternative book storage plans, and output multiple book storage fitness; The alternative book storage plan corresponding to the maximum storage fitness among the multiple book storage fitnesses is set as the optimal book storage plan.

Images