Recommendation index calculation device and method for periodical and book resource recommendation

Abstract

The invention discloses a recommendation index calculation device and method for journal and book resource recommendation, and belongs to the technical field of recommendation index calculation. Collecting performance indicators of journal or book resources of the library; the library assigns corresponding weights to various indexes used for calculating the recommendation indexes; recommendation indexes of various types of periodicals or book resources are calculated in a normalized mode, so that the accuracy and comprehensiveness of a recommendation system are improved, and academic research requirements and interest preferences of users are better met.

Description

Technical Field

[0001] The present invention belongs to the technical field of recommendation index calculation, and in particular relates to a recommendation index calculation device and method for recommending periodical and book resources. Background Art

[0002] In the era of information explosion, journals and book resources, as important carriers of academic research and knowledge dissemination, have experienced explosive growth in number and variety. However, faced with a vast amount of resources, users often find it difficult to quickly and accurately find high-quality journals or books that meet their needs. Traditional resource recommendation methods rely on manual screening or simple keyword matching, which are not only inefficient, but also tend to ignore the complex relationships between resources and deep-seated quality differences.

[0003] Therefore, it is particularly important to develop a scientific, efficient and accurate journal and book resource recommendation device. The device needs to be able to comprehensively consider multiple core indicators of resources (such as JCR impact factor, CiteScore value, SNIP value, SJR value, book BCR value, Chinese Journal Science and Technology Citation Report impact factor, etc.) and performance indicators (such as downloads, citations, publications, etc.), and calculate a recommendation index with wide applicability and high accuracy through advanced algorithm models to assist users in making more informed choices.

[0004] At present, although some recommendation devices based on machine learning, deep learning and other technologies have achieved remarkable results in e-commerce, social media and other fields, their application in the field of journal and book resource recommendation is still in its infancy. The recommendation index methods used in the existing technical solutions such as the patent publication number "CN115206450B" often lack an in-depth understanding of the particularity of academic resources, and it is difficult to effectively capture the academic associations and quality differences between resources. In other words, there is a lack of comprehensive recommendation mechanisms: current recommendation devices usually rely on a single indicator, such as the number of citations or click-through rates of articles. This method ignores important factors such as the quality of article content, the utilization rate of the school, and the impact factor of the journal, resulting in a lack of comprehensiveness and accuracy in the recommendation results; a single indicator cannot be compared across types: a single indicator such as a journal has an impact factor, but a book does not, so when mixed recommendations are made for resources, there is no common indicator for consistency evaluation, so this application scenario cannot be realized.

[0005] The present invention mainly aims at these defects of the prior art and proposes a recommendation index calculation device and method for journal and book recommendations, aiming to improve the accuracy and comprehensiveness of the recommendation system to better meet the academic research needs and interest preferences of users. Summary of the invention

[0006] In order to solve the defects existing in the prior art, the present invention proposes a recommendation index calculation device and method for journal and book resource recommendation, which collects the core indicators of the journals or book resources of the library; collects the performance indicators of the journals or book resources of the library; the library assigns corresponding weights to various indicators used to calculate the recommendation index; and normalizes and calculates the recommendation index of each type of journal or book resource, so as to improve the accuracy and comprehensiveness of the recommendation system and better meet the academic research needs and interest preferences of users.

[0007] The present invention uses the following technical solutions.

[0008] A method for calculating a recommendation index for recommending periodical and book resources, comprising:

[0009] Step 1: Collect the core indicators of the library's journals or book resources;

[0010] Step 2: Collect performance indicators of the library's journal or book resources;

[0011] Step 3: The library assigns corresponding weights to various indicators used to calculate the recommendation index;

[0012] Step 4: Normalize and calculate the recommendation index of each type of journal or book resource.

[0013] Preferably, in step 1, the core indicators of journal or book resources include their JCR impact factor, CiteScore value, SNIP value, SJR value, book BCR value, and Chinese Journal Science and Technology Citation Report impact factor.

[0014] Preferably, in step 2, the performance indicators of the journal or book resources include their download volume, citation volume, and publication volume.

[0015] Preferably, the core indicators of the journal or book resources and the various indicators within the performance indicators of the journal or book resources constitute the various indicators used to calculate the recommendation index.

[0016] Preferably, in step 3, the method of assigning corresponding weights to various indicators used to calculate the recommendation index is that the user defines the weights according to his / her own needs.

[0017] Preferably, in step 4, the numerical range of the recommendation index of each type of journal or book resource is controlled within the range of 0-100.

[0018] Preferably, in step 4, the formula for normalizing and calculating the recommendation index of each type of journal or book resource is:

[0019] Assume R i is the recommendation index of the i-th journal or book resource, W jis the weight of the jth indicator, V ij is the normalized value of the i-th resource on the j-th indicator (ranging between 0 and 1), then:

[0020]

[0021] Preferably, the normalized value V ij The normalization methods include minimum-maximum normalization and Z-score standardization.

[0022] Preferably, ∑W j =1, j takes values ​​from 1 to n, where n is the total number of indicators used to calculate the recommendation index.

[0023] Preferably, V ij The value range is between 0 and 1.

[0024] A recommendation index calculation device for recommending periodical and book resources, comprising:

[0025] Collection module 1, which is used to collect the core indicators of the library's journals or book resources;

[0026] Collection module 2, which is used to collect performance indicators of journals or book resources of the library;

[0027] The weight module is used by the library to assign corresponding weights to various indicators used to calculate the recommendation index;

[0028] The normalization module is used to normalize and calculate the recommendation index of various types of journals or book resources.

[0029] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include:

[0030] The key advantages of the present invention lie in its comprehensive evaluation method and personalized service capabilities. By collecting and integrating multiple core indicators and performance indicators, such as JCR impact factor, download volume, citation volume, etc., the recommendation index calculation device for journal and book resource recommendation can comprehensively evaluate the quality and influence of journal and book resources. At the same time, users can adjust the tendency of the recommendation index according to their needs and preferences to achieve personalized resource recommendation services. This method not only improves the efficiency of resource management, but also ensures the fairness and accuracy of the evaluation results, providing users with more accurate and effective information resource selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of the method for calculating the recommendation index for recommending periodical and book resources described in the present invention;

[0032] Figure 2It is a partial structural diagram of the recommendation index calculation device for recommending periodical and book resources described in the present invention. DETAILED DESCRIPTION

[0033] For example, the method used for the recommendation index in the prior art solution with patent publication number "CN115206450B" often lacks an in-depth understanding of the particularity of academic resources, and it is difficult to effectively capture the academic connections and quality differences between resources.

[0034] In view of this, the present invention proposes a device and method for calculating a recommendation index for journal and book resource recommendation. The method constructs a multi-dimensional and multi-level indicator system and uses advanced data processing and algorithm models to conduct a comprehensive and in-depth evaluation of journal and book resources, thereby calculating a recommendation index that can objectively reflect resource quality and user needs. The device and method not only improve the accuracy and efficiency of resource recommendation, but also provide users with a more personalized and intelligent recommendation service, which has important academic value and practical application significance.

[0035] In order to make the purpose, technical solution and advantages of the present invention clearer, the following will be combined with the drawings in the embodiments of the present invention to clearly and completely express the technical solution of the present invention. The embodiments expressed in the present invention are only some embodiments of the present invention, not all embodiments. According to the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the protection scope of the present invention.

[0036] like Figure 1 As shown, the method for calculating the recommendation index for recommending periodical and book resources of the present invention comprises:

[0037] Step 1: Collect the core indicators of the library's journals or book resources;

[0038] In a preferred but non-limiting embodiment of the present invention, in step 1, the core indicators of journal or book resources include its JCR impact factor, CiteScore value, SNIP value, SJR value, book BCR value, and Chinese Journal Science and Technology Citation Report impact factor. This library is this library.

[0039] Step 2: Collect performance indicators of the library's journal or book resources;

[0040] In a preferred but non-limiting embodiment of the present invention, in step 2, the performance indicators of the journal or book resources include their download volume, citation volume, and publication volume.

[0041] In a preferred but non-limiting embodiment of the present invention, the core indicators of the journal or book resources and the various indicators within the performance indicators of the journal or book resources constitute various indicators for calculating the recommendation index.

[0042] Step 3: The library can assign corresponding weights to various indicators used to calculate the recommendation index and customize the tendency of the recommendation index;

[0043] In a preferred but non-limiting embodiment of the present invention, in step 3, the method of assigning corresponding weights to various indicators used to calculate the recommendation index is the weights defined by the user according to his own needs.

[0044] Step 4: Normalize and calculate the recommendation index of each type of journal or book resource.

[0045] In a preferred but non-limiting embodiment of the present invention, in step 4, the numerical range of the recommendation index of each type of journal or book resource is controlled within the range of 0 to 100. The calculated recommendation index can be compared across types.

[0046] In a preferred but non-limiting embodiment of the present invention, in step 4, the calculation formula for normalizing and calculating the recommendation index of each type of journal or book resource is:

[0047] Assume R i is the recommendation index of the i-th journal or book resource, W j is the weight of the jth index (satisfying ∑W j =1, j ranges from 1 to n, where n is the total number of indicators used to calculate the recommendation index), V ij is the normalized value of the i-th resource on the j-th indicator (ranging between 0 and 1), then:

[0048]

[0049] In a preferred but non-limiting embodiment of the present invention, the normalized value V ij :The raw value of each indicator needs to be normalized to the range of 0-100. The normalization method depends on the nature and distribution of the indicator. Common normalization methods include minimum-maximum normalization, Z-score normalization, etc., but here it is assumed that the normalized value has been obtained.

[0050] Weight W j :The weighting is subjective and depends on the library's strategy and goals. For example, if the library places more emphasis on academic impact, then the weighting of indicators such as JCR impact factor and CiteScore value may be higher.

[0051] In a preferred but non-limiting embodiment of the present invention, ∑W j =1, j takes values ​​from 1 to n, where n is the total number of indicators used to calculate the recommendation index.

[0052] In a preferred but non-limiting embodiment of the present invention, V ij The value range is between 0 and 1.

[0053] like Figure 2 As shown, the recommendation index calculation device for recommending periodical and book resources of the present invention comprises:

[0054] Collection module 1, which is used to collect the core indicators of the library's journals or book resources;

[0055] Collection module 2, which is used to collect performance indicators of journals or book resources of the library;

[0056] The weight module is used by the library to assign corresponding weights to various indicators used to calculate the recommendation index;

[0057] The normalization module is used to normalize and calculate the recommendation index of various types of journals or book resources.

[0058] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include:

[0059] The key advantages of the present invention lie in its comprehensive evaluation method and personalized service capabilities. By collecting and integrating multiple core indicators and performance indicators, such as JCR impact factor, download volume, citation volume, etc., the recommendation index calculation device for journal and book resource recommendation can comprehensively evaluate the quality and influence of journal and book resources. At the same time, users can adjust the tendency of the recommendation index according to their needs and preferences to achieve personalized resource recommendation services. This method not only improves the efficiency of resource management, but also ensures the fairness and accuracy of the evaluation results, providing users with more accurate and effective information resource selection.

[0060] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not deviate from the spirit and scope of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for calculating a recommendation index for recommending periodical and book resources, characterized in that: include: Step 1: Collect the core indicators of the library's journals or book resources; Step 2: Collect performance indicators of the library's journal or book resources; Step 3: The library assigns corresponding weights to various indicators used to calculate the recommendation index; Step 4: Normalize and calculate the recommendation index of each type of journal or book resource.

2. The method for calculating the recommendation index for recommending periodical and book resources according to claim 1, characterized in that: In step 1, the core indicators of journals or book resources include their JCR impact factor, CiteScore value, SNIP value, SJR value, book BCR value, and Chinese Journal Science and Technology Citation Report impact factor.

3. The method for calculating the recommendation index for recommending periodical and book resources according to claim 2, characterized in that: In step 2, the performance indicators of journal or book resources include their downloads, citations, and publications.

4. The method for calculating the recommendation index for recommending periodical and book resources according to claim 3, characterized in that: The core indicators of journals or book resources and the various indicators within the performance indicators of journals or book resources constitute the various indicators used to calculate the recommendation index.

5. The method for calculating the recommendation index for recommending periodical and book resources according to claim 4, characterized in that: In step 3, the method of assigning corresponding weights to various indicators used to calculate the recommendation index is the weights defined by the user according to his own needs.

6. The method for calculating the recommendation index for recommending periodical and book resources according to claim 5, characterized in that: In step 4, the numerical range of the recommendation index of each type of journal or book resource is controlled within the range of 0-100.

7. The method for calculating the recommendation index for recommending periodical and book resources according to claim 6, characterized in that: In step 4, the formula for normalizing and calculating the recommendation index of each type of journal or book resource is: Assume R i is the recommendation index of the i-th journal or book resource, W j is the weight of the jth indicator, V ij is the normalized value of the i-th resource on the j-th indicator (ranging between 0 and 1), then:

8. The method for calculating the recommendation index for recommending periodical and book resources according to claim 7, characterized in that: Normalized value V ij The normalization methods include minimum-maximum normalization and Z-score standardization.

9. The method for calculating the recommendation index for recommending periodical and book resources according to claim 8, characterized in that: ∑W j =1, j ranges from 1 to n, where n is the total number of indicators used to calculate the recommendation index; V ij The value range is between 0 and 1.

10. A device for calculating a recommendation index for recommending periodical and book resources, characterized in that: include: Collection module 1, which is used to collect the core indicators of the library's journals or book resources; Collection module 2, which is used to collect performance indicators of journals or book resources of the library; The weight module is used by the library to assign corresponding weights to various indicators used to calculate the recommendation index; The normalization module is used to normalize and calculate the recommendation index of various types of journals or book resources.

Images