Subject cross measurement method based on keywords

Abstract

The invention relates to the field of interdisciplinary, in particular to a subject interdisciplinary measurement method based on keywords. The measurement method mainly carries out analysis from three dimensions: semantic analysis: processing a corpus in two modes to obtain a matrix and a vector sequence, and carrying out cosine calculation on the matrix and the vector sequence to obtain an index reflecting the similarity of subject knowledge; the hierarchical structure analysis is to analyze and determine subject keyword contribution degree and quantify knowledge distance based on a hierarchical structure, and calculate the subject keyword contribution degree and the knowledge distance to obtain an interdisciplinary measurement index; the network structure analysis comprises the following steps: researching a keyword network to obtain an influence index of a node in the network, applying the index to multiple subjects, and calculating to obtain an interdisciplinary intensity measurement index based on a network structure; and finally, carrying out multi-index synthesis on the three dimensions through an entropy weighting method so as to carry out evaluation on the interdisciplinary interaction strength. According to the method, the problems of insufficient fine granularity and insufficiency in current subject cross detection are solved.

Description

Technical Field

[0001] The present invention relates to the field of interdisciplinary subjects, and in particular to a keyword-based interdisciplinary measurement method. Background Art

[0002] Interdisciplinary research involves the integration of multidisciplinary knowledge. It is an indispensable means to solve contemporary complex social challenges and promote scientific innovation. It is also a key factor in creating high-impact knowledge and practical innovation. With the rapid development of science and technology, the solutions and breakthroughs required to solve today's complex scientific problems often go beyond the limitations of a single discipline and need to rely on the integration of multidisciplinary theories or technologies for interdisciplinary research. According to statistics in 2017, 49.07% of Nobel Prize research results were based on interdisciplinary cooperation. Therefore, exploring the nature, form and laws of interdisciplinary cross-discipline is of great significance to promoting the development of science and social progress.

[0003] Through the investigation of relevant literature on interdisciplinary measurement at home and abroad, it is found that existing studies mainly use two methods: analyzing the academic background of researchers or the cooperation mode between authors, or examining publications and their citations. These studies use scholar information surveys, institution or journal subject category mapping, and calculate different interdisciplinary measurement indicators to obtain the size of specific interdisciplinary degree. For example, Liu et al. in Science, Technology and Dialectics, 6, 105-109 revealed the decisive role of interdisciplinary research in original scientific results by counting the number of degrees obtained by Nobel Prize winners in Physiology or Medicine outside their majors. Zhang et al. in Journal of Information Science, 37(3), 231-242 took the research results of highly cited scholars in the field of social sciences from 2014 to 2016 as an example to measure the degree of interdisciplinary between different disciplinary institutions in scientific cooperation, proving that interdisciplinary institutional cooperation has a certain role in promoting the output of interdisciplinary scientific results. Wang et al. in Scientometrics, 111, 2023-2039 took 60 prolific authors in the three fields of applied mathematics, computational science, and operations research and management science in the WOS database as examples, and measured their interdisciplinary degree based on target literature, references, and citing literature.

[0004] However, most current studies, including those mentioned above, focus mainly on interdisciplinary studies at the macro level, while research on interdisciplinary knowledge structures at the micro level is relatively limited. At the micro level, paper keywords are regarded as the most basic knowledge carriers, which can simply and directly reflect the ideas and themes of research papers. Compared with discipline-level or subject-level methods, keywords adopt a more fine-grained perspective when studying the knowledge connections between interdisciplinary fields and their constituent disciplines. The collection of disciplinary keywords covers the main research focus of a discipline. Therefore, cross-keywords from two or more disciplines can reveal the content of interdisciplinary research. This concept is the basis for this study to choose to explore interdisciplinary intersections with keywords as the guide, so as to delve into the subtle interactions and knowledge structures that emerge at this fine-grained level. Summary of the invention

[0005] The purpose of the present invention is to overcome the problems of insufficient granularity of research subjects and defects in comprehensiveness of measurement methods in existing interdisciplinary measurement technologies, and to provide an interdisciplinary measurement method based on keywords.

[0006] In a first aspect, the present invention provides a calculation method for multi-index synthesis, which uses an entropy weighting method to integrate the indicators obtained based on the semantic analysis, the hierarchical structure analysis and the network structure analysis, and includes the following steps:

[0007] S1: Extract keywords of subject papers;

[0008] S2: By performing semantic analysis on the obtained subject paper keyword dataset, we can obtain an index reflecting the similarity of subject knowledge. By analyzing the hierarchical structure of the obtained subject paper keywords, we can obtain an index measuring the interdisciplinarity between different subjects. By analyzing the network structure of the obtained subject paper keywords, we can obtain an index measuring the interdisciplinarity strength.

[0009] S3: The semantic analysis index, the hierarchical structure analysis index, and the network structure analysis index are integrated using an entropy weighting method. The greater the discreteness of the resulting index, the smaller the entropy value, and the greater the impact of the index on the comprehensive evaluation.

[0010] Preferably, step S1 comprises the following steps:

[0011] S11: Remove meaningless words from subject paper titles and abstracts based on the stop word list;

[0012] S12: The processed data is used as input of the natural language processing tool Yake keyword extractor to extract the noun phrases therein.

[0013] Preferably, the semantic analysis in step S2 further comprises the step of: calculating the semantic analysis index using cosine similarity.

[0014] Preferably, the semantic analysis is to process the sorted corpus separately to obtain a matrix and a vector sequence, and perform cosine calculation on the two to obtain the semantic analysis index.

[0015] Further preferably, the semantic analysis comprises the following steps:

[0016] StepA: Filter the keywords whose frequency in the titles and abstracts of papers of the subject is lower than the specified threshold;

[0017] Step B: Use the term frequency-inverse document frequency algorithm to calculate the term frequency-inverse document frequency of each keyword in documents of different disciplines, thereby constructing a discipline-key term matrix; input the corpus into a Word2Vec model for training, and use the CBOW method to convert the discipline key terms in the document data into points in a low-dimensional vector space to generate a keyword vector sequence of a specified dimension;

[0018] Step C: Perform L2 normalization on both the matrix and the vector, and multiply the normalized subject keyword matrix with the keyword vector to obtain the subject keyword vector;

[0019] Step D: Use cosine similarity to calculate the similarity between subject keyword vectors to quantify the semantic relationship between subjects. The calculation result is recorded as P Semantic , represents the semantic similarity of subject knowledge between subject X and subject Y, that is, it reflects the degree of interdisciplinary interaction between subject X and subject Y based on document content.

[0020]

[0021] Preferably, the hierarchical structure analysis in step S2 includes: calculating the hierarchical structure analysis index based on the TaxoGen model.

[0022] Preferably, the hierarchical structure analysis is to determine the contribution of topic keywords and quantify the knowledge distance based on the hierarchical structure, and the hierarchical structure analysis index is obtained by calculating the two.

[0023] Further preferably, the hierarchical analysis comprises the following steps:

[0024] StepA: Building a hierarchical structure based on the TaxoGen model;

[0025] Step B: By analyzing the representativeness of keywords to topics at each level and the probability of keyword distribution within a topic, we can define the hierarchical topic-keyword contribution. Combining the subject-topic and the corresponding topic-keyword distribution probability, we can determine the contribution of each subject keyword to the topic at each subject level. From this, we can derive the subject contribution Ctk of keyword k under topic t:

[0026] C tk =D t ×f tk

[0027] Where: Dt represents the document frequency of topic t, ftk represents the frequency of keyword k appearing in the subject corpus under topic t;

[0028] Step C: By matching different topics at different levels based on the same keyword, the sum of the hierarchical depths represents the interdisciplinary knowledge interaction and communication path. The longer the distance between two concepts, the lower the correlation range and similarity of disciplinary knowledge. The knowledge distance can be quantified by the following formula:

[0029]

[0030] Where: KD is the quantitative value of the knowledge distance, wtk is the keyword k under a subject t, f is the transfer function between d and l, l is the shortest path length between them, and d is the depth of the includer in the hierarchical semantic network, that is, the depth of the lowest common ancestor between two keywords;

[0031] Step D: The measurement index is constructed by subject keyword contribution and knowledge distance. The hierarchical structure analysis index can be obtained based on the hierarchical structure calculation. The calculation formula is:

[0032]

[0033] Where: P Hierarchy is the hierarchical structure analysis index, KD is the quantitative value of the knowledge distance, n(X,Y) is the number of common keywords between subject X and subject Y, It is the number of possible paths that can be combined in the process of knowledge association based on common keywords, and T represents the number of keywords in the subject of a certain subject unit.

[0034] Preferably, the network structure analysis in step S2 further includes: obtaining the network structure analysis index based on the subject co-word network calculation.

[0035] Preferably, the network structure analysis is to obtain the influence index of the node in the network by studying the keyword network, and apply the index to multiple disciplines to obtain the network structure analysis index based on the network structure through calculation.

[0036] Further preferably, the network structure analysis comprises the following steps:

[0037] Step A: Extract the common keywords between subjects X and Y to construct the set of intermediary entities with the same keywords V k ;

[0038] V k =V X ∩V Y

[0039] Where: V X represents the keyword set of subject X, V Y A set of keywords representing subject Y;

[0040] Step B: According to the betweenness centrality of the keyword nodes in the calculation set obtained in C1 in the network as the importance of the node, the indicator Bet(v) is calculated to determine whether the node v has a high-influence keyword in the discipline; the calculation formula of Bet(v) is:

[0041]

[0042] Where: Bet(v) is an indicator to determine whether node v has a high-impact keyword in the discipline, σ st is the total number of shortest paths from node s to node t, σ st (v) is the number of paths passing through node v;

[0043] Step C: Combine the characteristics of nodes and edges as the endogenous variables of the interdisciplinary network, and calculate the index L used to measure the influence of the node in the A network through the formula A (v), calculated as:

[0044]

[0045] Where: L A represents an indicator to measure the influence of the node in the A network, Bet(v) is the indicator of the keyword to determine whether node v has high influence in the discipline, Γ(v) represents the set of neighbor nodes of node v, and link(v,p) is the co-occurrence intensity between node v and node v's neighbor node p;

[0046] Step D: Considering the factors between node pairs and the structural information of nodes embedded in the overall network, calculate the interdisciplinary strength measurement index P based on network structure network (X,Y), this indicator measures the relative importance of shared keywords as bridge nodes for interdisciplinary interaction in the knowledge network of disciplines X and Y. The calculation formula is:

[0047]

[0048] Where: P Network is the network structure analysis index, L X (v) represents the index to measure the influence of the node in the X network, L Y (v) represents the index to measure the influence of the node in the Y network, V X 、V Y Represent the keyword nodes in subject X and subject Y respectively.

[0049] Preferably, step S3 specifically comprises the following steps:

[0050] S31: Normalizing indicators, converting the absolute values ​​of indicators into relative values ​​to solve the homogeneity of heterogeneous indicators; considering that the values ​​of positive and negative indicators represent opposite meanings, different algorithms are used for data normalization;

[0051] If the jth index is a positive index:

[0052]

[0053] If the jth indicator is a negative indicator:

[0054]

[0055] Where: x' ij are the semantic analysis indicators, the hierarchical structure analysis indicators and the network structure analysis indicators that need to be normalized, i is a natural number used to measure the number of disciplines, and j is a natural number used to measure the number of indicators;

[0056] S32: Calculate the ratio of the i-th subject to the j-th indicator:

[0057]

[0058] Where: P ij is the ratio of the i-th subject to the j-th indicator, x' ij are the semantic analysis index, the hierarchical structure analysis index and the network structure analysis index that require normalization of the index, i is a natural number used to measure the number of disciplines, and j is a natural number used to measure the number of indicators;

[0059] S33: Calculate the entropy of the jth indicator, where e j ≥0:

[0060]

[0061] Where: e j is the entropy of the jth index, P ij is the ratio of the i-th subject to the indicator under the j-th indicator, i is a natural number used to measure the number of subjects, and j is a natural number used to measure the number of indicators;

[0062] S34: Calculate information entropy redundancy:

[0063] d j =1-e j

[0064] Where: d j is the information entropy redundancy of the jth indicator, e j is the entropy of the j-th indicator, where j is a natural number used to measure the number of indicators;

[0065] S35: Calculate the weight of each indicator:

[0066]

[0067] Where: w j is the weight of the jth indicator, d j is the information entropy redundancy of the j-th indicator, and j is a natural number used to measure the number of indicators;

[0068] S36: The hierarchical structure analysis index is calculated as follows:

[0069] P Interdisciplinarity (X,Y)=α*P Semantic (X,Y)+β*P Hierarchy (X,Y)+(1-α-β)*P Network (X,Y)

[0070] Where: P Interdisciplinarity is the hierarchical structure analysis index, X and Y are used to represent subject X and subject Y respectively, P Semantic is the semantic analysis index, P Hierarchy is the hierarchical structure analysis index, P Network is the network structure analysis index, α and β are probability ratio adjustment factors, and the weights calculated by S35 are used for setting, where α=w1, β=w2.

[0071] Preferably, the interdisciplinary measurement method is based on the three dimensions of the semantic analysis, the hierarchical structure analysis and the network structure analysis, which solves the problems of insufficient granularity and lack of comprehensiveness of existing interdisciplinary measurement methods, and also helps to better explore the subtle interactions and deep interaction mechanisms between disciplines.

[0072] Compared with the prior art, the present invention has the following beneficial effects:

[0073] The present invention provides a method for measuring interdisciplinary studies based on keywords. Through three-dimensional analysis and calculation, three-level indicators for measuring the intensity of interdisciplinary studies are obtained from the three perspectives of semantic analysis, hierarchical structure analysis, and network structure analysis. The three indicators are integrated by an entropy weighting method to obtain a comprehensive measurement indicator. This method can achieve a more fine-grained and comprehensive study of interdisciplinary studies, solve the limitation of the existing interdisciplinary studies only from a macroscopic perspective, and has great promotion significance and application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a method step diagram of the interdisciplinary measurement comprehensive framework in the present invention;

[0075] Figure 2 It is a schematic diagram of a method for constructing hierarchical knowledge distance in hierarchical structure analysis in the present invention;

[0076] Figure 3 It is a schematic diagram of a method for constructing a subject-shared keyword network diagram in network analysis in the present invention;

[0077] Figure 4 It is a comprehensive measure of the intensity of interdisciplinary interaction between the discipline of “library and information science” and the other six disciplines over three periods;

[0078] Figure 5 It is a comparison of the ranking results of each indicator from 2005 to 2009;

[0079] Figure 6 It is a comparison of the ranking results of each indicator from 2010 to 2014;

[0080] Figure 7 It is a comparison of the ranking results of each indicator from 2015 to 2019; DETAILED DESCRIPTION

[0081] The present invention is further described in detail below in conjunction with test examples and specific implementation methods. However, this should not be understood as the scope of the above subject matter of the present invention being limited to the following embodiments, and all technologies realized based on the content of the present invention belong to the scope of the present invention.

[0082] Example 1

[0083] Take the interdisciplinary research of seven specific disciplines, namely "library and information science", "economics", "computer science, information systems", "education and educational research", "geography", "social science, interdisciplinary" and "management" as an example. The English research literature of seven specific disciplines, namely "library and information science", "economics", "computer science, information systems", "education and educational research", "geography", "social science, interdisciplinary" and "management" from 2005 to 2019, was crawled from the SCI-EXPANDED and SSCI databases of Web of Science (WOS), totaling 209,062 documents. This method measures the interdisciplinary research with library and information science as the center, and studies the interdisciplinary intensity with the other six disciplines. In order to better clarify the development and change trend of interdisciplinary research, the data set is divided into three stages according to time: 2005-2009, 2010-2014 and 2015-2019.

[0084] A keyword-based interdisciplinary measurement method, the flow chart is as follows Figure 1 As shown, the following steps are included:

[0085] S1: Extract keywords of subject papers;

[0086] S2: From the perspective of semantic analysis, the titles and abstracts of papers in various disciplines are integrated into a corpus, and the subject keyword matrix and keyword vector are obtained by processing the corpus with algorithms and model training, and finally the semantic analysis index is obtained by cosine similarity calculation; from the perspective of hierarchical structure analysis, the subject keyword contribution and knowledge distance are obtained by constructing a hierarchical structure, and the hierarchical structure analysis index is constructed based on the subject keyword contribution and knowledge distance; from the perspective of network structure analysis, a subject co-word network is constructed and the network structure analysis is performed in combination with the features of points and edges to obtain the network structure analysis index;

[0087] S3: Use the entropy weighting method to integrate the semantic analysis indicators obtained based on semantic analysis, the hierarchical structure analysis indicators obtained based on hierarchical structure analysis, and the network structure analysis indicators obtained based on network structure analysis. The greater the discreteness of the resulting indicators, the smaller the entropy value, and the greater the impact of the indicators on the comprehensive evaluation.

[0088] The step S1 of processing the obtained abstract and title in the measurement method comprises the following steps:

[0089] S11: Remove meaningless words from subject paper titles and abstracts based on the stop word list;

[0090] S12: The processed data is used as input of the natural language processing tool Yake keyword extractor to extract the noun phrases therein.

[0091] The entropy weighting method described in step S3 is used to integrate the indicators obtained from the three-dimensional analysis and calculate the final indicator for measuring the intensity of disciplinary interaction, which includes the following steps:

[0092] S31: Normalizing indicators, converting the absolute values ​​of indicators into relative values ​​to solve the homogeneity of heterogeneous indicators; considering that the values ​​of positive and negative indicators represent opposite meanings, different algorithms are used for data normalization;

[0093] If the jth index is a positive index:

[0094]

[0095] If the jth indicator is a negative indicator:

[0096]

[0097] Where: x' ij are the semantic analysis indicators, the hierarchical structure analysis indicators and the network structure analysis indicators that need to be normalized, i is a natural number used to measure the number of disciplines, and j is a natural number used to measure the number of indicators;

[0098] S32: Calculate the ratio of the i-th subject to the j-th indicator:

[0099]

[0100] Where: P ij is the ratio of the i-th subject to the j-th indicator, x' ij are the semantic analysis index, the hierarchical structure analysis index and the network structure analysis index that require normalization of the index, i is a natural number used to measure the number of disciplines, and j is a natural number used to measure the number of indicators;

[0101] S33: Calculate the entropy of the jth indicator, where e j ≥0:

[0102]

[0103] Where: e j is the entropy of the jth index, P ij is the ratio of the i-th subject to the indicator under the j-th indicator, i is a natural number used to measure the number of subjects, and j is a natural number used to measure the number of indicators;

[0104] S34: Calculate information entropy redundancy:

[0105] d j =1-ej

[0106] Where: d j is the information entropy redundancy of the jth indicator, e j is the entropy of the j-th indicator, where j is a natural number used to measure the number of indicators;

[0107] S35: Calculate the weight of each indicator:

[0108]

[0109] Where: w j is the weight of the jth indicator, d j is the information entropy redundancy of the j-th indicator, and j is a natural number used to measure the number of indicators;

[0110] S36: The hierarchical structure analysis index is calculated as follows:

[0111] P Interdisciplinarity (X,Y)=α*P Semantic (X,Y)+β*P Hierarchy (X,Y)+(1-α-β)*P Network (X,Y)

[0112] Where: P Interdisciplinarity is the hierarchical structure analysis index, X and Y are used to represent subject X and subject Y respectively, P Semantic is the semantic analysis index, P Hierarchy is the hierarchical structure analysis index, P Network is the network structure analysis index, α and β are probability ratio adjustment factors, and the weights calculated by S35 are used for setting, where α=w1, β=w2.

[0113] The comprehensive interdisciplinary interaction intensity scores among disciplines in the three periods calculated by S36 in the entropy weighted method are as follows: Figure 4 The specific calculation formula is:

[0114] Composite score=-0.081+0.215*Semantic_based+0.416*Hierarchy_based+

[0115] 0.378*Network_based

[0116] Four mainstream interdisciplinary indicators were selected from the perspectives of knowledge network topology characteristics and knowledge integration content characteristics, and compared with the comprehensive results of the keyword-based measurement method adopted by this invention. These four indicators are Rao-Stirling, TI value, overlap and eigenvector centrality. Detailed information is shown in Figure 5-Figure 7 As shown, Figure 5-Figure 7 The main purpose is to show the value results of each method in the subject measurement and the ranking of the measurement results, so as to show the advantages and disadvantages of different measurement methods. Comprehensive comparative analysis shows that the measurement method based on the Rao-Stirling index can effectively reveal the differences between disciplines, but in some situations, its accuracy in reflecting the actual interdisciplinary interaction is slightly inferior; the measurement method based on the three indicators of TI value, overlap and eigenvector centrality performs poorly in generating interdisciplinary rankings, which is quite different from the expected evaluation effect; through Figure 5-Figure 7 Judging from the displayed results and rankings, compared with the three measurement indicators used in the current commonly used measurement methods, the comprehensive data and rankings of the present invention are better than the current solutions. The interdisciplinary measurement method adopted shows higher accuracy in measuring interdisciplinary interactions and has stronger explanatory power for actual real situations.

[0117] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A keyword-based interdisciplinary measurement method, characterized in that: The following steps are involved: S1: Extract subject paper keywords and construct subject paper keyword dataset; S2: by performing semantic analysis on the subject paper keyword dataset, an index reflecting the similarity of subject knowledge is obtained, which is defined as a semantic analysis index; by performing hierarchical structure analysis on the subject paper keyword dataset, an index measuring the interdisciplinarity between different subjects is obtained, which is defined as a hierarchical structure analysis index; by performing network structure analysis on the subject paper keyword dataset, an interdisciplinarity strength measurement index is obtained, which is defined as a network structure analysis index; S3: The semantic analysis index, the hierarchical structure analysis index and the network structure analysis index are integrated using an entropy weighting method, and the output is an interdisciplinary interaction intensity measurement result.

2. A keyword-based interdisciplinary measurement method according to claim 1, characterized in that: The step S1 specifically includes the following steps: S11: When extracting keywords of subject papers, firstly, meaningless words in the titles and abstracts of subject papers are deleted according to the preset stop word list. S12: Using the data processed by S11 as input of a natural language processing tool, Yake keyword extractor, and extracting noun phrases from the data processed by S11.

3. The measuring method according to claim 1, characterized in that: The semantic analysis in step S2 is to process the subject paper keyword data set separately to obtain a matrix and a vector sequence, and perform cosine similarity calculation on the two to obtain the semantic analysis index.

4. The measuring method according to claim 3, characterized in that: The semantic analysis comprises the following steps: StepA: Filter the keywords whose frequency in the titles and abstracts of papers of the subject is lower than the specified threshold; Step B: Use the term frequency-inverse document frequency algorithm to calculate the term frequency-inverse document frequency of each keyword in documents of different disciplines, thereby constructing a discipline-key term matrix; input the keywords into a Word2Vec model for training, and use the CBOW method to convert the discipline key terms in the document data into points in a low-dimensional vector space to generate a keyword vector sequence of a specified dimension; Step C: Perform L2 normalization on both the matrix and the vector, and multiply the normalized subject keyword matrix with the keyword vector to obtain the subject keyword vector; Step D: Use cosine similarity to calculate the similarity between subject keyword vectors to quantify the semantic relationship between subjects. The calculation result is recorded as P Semantic , represents the semantic similarity of subject knowledge between subject X and subject Y, that is, it reflects the degree of interdisciplinary interaction between subject X and subject Y based on document content. Where: P Semantic (X, Y) is the semantic analysis index, X and Y represent different subjects respectively, i is a natural number used to measure the number of subjects, and n is the total number of subjects to be calculated, which is a natural number.

5. The measuring method according to claim 1, characterized in that: The hierarchical structure in step S2 is based on the hierarchical structure to analyze and determine the topic keyword contribution and quantify the knowledge distance, and the hierarchical structure analysis index is obtained by calculating the two.

6. The measuring method according to claim 5, characterized in that: The hierarchical analysis includes the following steps: StepA: Building a hierarchical structure based on the TaxoGen model; Step B: By analyzing the representativeness of keywords to topics at each level and the probability of keyword distribution within a topic, we can define the hierarchical topic-keyword contribution. Combining the subject-topic and the corresponding topic-keyword distribution probability, we can determine the contribution of each subject keyword to each subject-level topic. From this, we can derive the subject contribution Ctk of keyword k under topic t: C tk =D t ×f tk Where: D t represents the document frequency of topic t, f tk represents the frequency of keyword k appearing in the subject corpus under topic t; Step C: By matching different topics at different levels based on the same keyword, the sum of the hierarchical depths of the matching results represents the interdisciplinary knowledge interaction and communication path. The longer the distance between two concepts, the lower the correlation range and similarity of disciplinary knowledge. The knowledge distance can be quantified by the following formula: Where: KD is the quantitative value of the knowledge distance, is the keyword k under a subject t, i is a natural number measuring the number of subject t, f is the transfer function of d and l, l is the shortest path length between them, and d is the depth of the includer in the hierarchical semantic network, that is, the depth of the lowest common ancestor between two keywords; Step D: The measurement index is constructed by subject keyword contribution and knowledge distance. The hierarchical structure analysis index can be obtained based on the hierarchical structure calculation. The calculation formula is: Where: P Hierarchy (X, Y) is the hierarchical structure analysis index, is the subject contribution of keyword k under subject topic t, i is a natural number measuring the number of subject topics t, KD is the quantitative value of the knowledge distance, n(X, Y) is the number of common keywords between subject X and subject Y, It is the number of possible paths that can be combined in the process of knowledge association based on common keywords, and T represents the number of keywords in the subject of a certain subject unit.

7. The measuring method according to claim 1, characterized in that: The network structure analysis in step S2 is to obtain the influence index of the node in the network by studying the keyword network, and apply the influence index to multiple disciplines to obtain the network structure analysis index based on the network structure through calculation.

8. The measuring method according to claim 7, characterized in that: The network structure analysis includes the following steps: Step A: Extract the common keywords between subject X and subject Y to construct the set of intermediary entities with the same keywords V k ; V k =V X ∩V Y Where: V X represents the keyword set of subject X, V Y A set of keywords representing subject Y; Step B: Based on the betweenness centrality of the keyword nodes in the calculation set obtained in C1, the indicator Bet(v) is calculated to determine whether node v has a high-influence keyword in the discipline. The calculation formula of Bet(v) is: Where: Bet(v) is an indicator to determine whether node v has a high-impact keyword in the discipline, σ st is the total number of shortest paths from node s to node t, σ st (v) is the number of paths passing through node v; Step C: Combining the characteristics of nodes and edges as endogenous variables of the interdisciplinary network, the indicator LA(v) used to measure the influence of the node in the A network can be calculated by the formula: Where: LA is an indicator for measuring the influence of the node in the A network, Bet(v) is an indicator for judging whether node v has a high-influence keyword in the subject, Γ(v) is a set of neighbor nodes of node v, and link(v, p) is the co-occurrence intensity between node v and node v's neighbor node p; Step D: Comprehensively consider the factors between node pairs and the structural information of nodes embedded in the overall network, and calculate the network structure analysis index based on the network structure. The network structure analysis index measures the relative importance of shared keywords as bridge nodes for interdisciplinary interaction in the knowledge network of disciplines X and Y. The calculation formula is: Where: P Network is the network structure analysis index, L X (v) represents the index to measure the influence of the node in the X network, L Y (v) represents the index to measure the influence of the node in the Y network, V X 、V Y Represent the keyword nodes in subject X and subject Y respectively.

9. The measuring method according to claim 1, characterized in that: Step S3 specifically includes the following steps: S31: normalizing the indicators, converting the absolute values ​​of the semantic analysis indicator, the hierarchical structure analysis indicator, and the network structure analysis indicator into relative values ​​to solve the homogeneity of the heterogeneous indicators; considering that the values ​​of the positive and negative indicators represent opposite meanings, different algorithms are used to normalize the indicators; If the jth index is a positive index: If the jth indicator is a negative indicator: Where: x' ij are the semantic analysis indicators, the hierarchical structure analysis indicators and the network structure analysis indicators that need to be normalized, i is a natural number used to measure the number of disciplines, and j is a natural number used to measure the number of indicators; S32: Calculate the ratio of the i-th subject to the j-th indicator: Where: P ij is the ratio of the i-th subject to the j-th indicator, x' ij are the semantic analysis index, the hierarchical structure analysis index and the network structure analysis index that require normalization of the index, i is a natural number used to measure the number of disciplines, and j is a natural number used to measure the number of indicators; S33: Calculate the entropy of the jth indicator, where e j ≥0: Where: e j is the entropy of the jth index, P ij is the ratio of the i-th subject to the indicator under the j-th indicator, i is a natural number used to measure the number of subjects, and j is a natural number used to measure the number of indicators; S34: Calculate information entropy redundancy: d j =1-e j Where: d j is the information entropy redundancy of the jth indicator, e j is the entropy of the j-th indicator, where j is a natural number used to measure the number of indicators; S35: Calculate the weight of each indicator: Where: w j is the weight of the jth indicator, d j is the information entropy redundancy of the j-th indicator, and j is a natural number used to measure the number of indicators; S36: The hierarchical structure analysis index is calculated as follows: P Interdisciplinarity (X,Y)=α*P Semantic (X,Y)+β*P Hierarchy (X,Y)+(1-α-β)*P Network (X,Y) Where: P Interdisciplinarity is the hierarchical structure analysis index, X and Y are used to represent subject X and subject Y respectively, P Semantic is the semantic analysis index, P Hierarchy is the hierarchical structure analysis index, P Network is the network structure analysis index, α and β are probability ratio adjustment factors, and the weight calculated by S35 is used for setting, where α=w1, β=w2.

10. A measurement method, characterized in that: It comprises at least one integrated method, and three analytical methods connected to the at least one integrated method; the integrated method needs to be based on the three analytical methods, and the three analytical methods are processed by the at least one integrated method so that the at least one integrated method can perform the method described in any one of claims 1 to 12.

Images