Multilayer scientific research cooperation relationship network construction method based on professional papers and patent literatures

Abstract

The invention discloses a multi-layer scientific research cooperation relationship network construction method based on professional papers and patent literatures, relates to the technical field of knowledge base construction, and aims to solve the problem of inaccurate acquisition of correlation data between the professional papers and the patent literatures. According to the invention, through key data confirmation and multiple matching strategies, the recognition precision of the cooperation relationship is improved. Particularly, for the name duplication problem, mechanism matching is introduced as a supplement, misjudgment is effectively reduced, first to fifth different types of cooperation relationship data are constructed, each type of data reflects different aspects of scientific research cooperation from different angles, and through network overlapping and integration, the scientific research cooperation can be effectively completed. The internal cooperation relationship between the professional papers and the patent literatures is reserved, and the direct and indirect cooperation relationship between the professional papers and the patent literatures is also disclosed.

Description

Technical Field

[0001] The present invention relates to the technical field of knowledge base construction, and in particular to a method for constructing a multi-layer scientific research cooperation relationship network based on professional papers and patent documents. Background Art

[0002] Professional papers and patent documents scientific research cooperation relationship mainly refers to the cooperation and connection formed between different researchers or research teams in the field of scientific research through the publication and application of professional papers and patent documents.

[0003] The patent application with publication number CN110533253B discloses a method for predicting scientific research cooperation relationships based on heterogeneous information networks. The method mainly uses a graph autoencoder model to obtain vector representations of nodes. The method solves the problem of high dimensionality caused by sparse vectors in scientific research cooperation networks. By integrating two similarity calculation methods, the method avoids the calculation error caused by using only one similarity, thereby improving the accuracy of author cooperation relationship prediction. Although the above patent solves the problem of scientific research prediction, the following problems still exist in actual operation:

[0004] 1. After obtaining the original data of professional papers and patent documents, the data is not further processed, resulting in poor data quality and inability to conduct accurate analysis later.

[0005] 2. Failure to conduct a more detailed analysis of the correlation between professional papers and patent documents resulted in the inability to confirm the cooperative relationship.

[0006] 3. There is no effective judgment on the correlation between professional papers and patent documents, which leads to the inability to clearly understand the correlation between the two. Summary of the invention

[0007] The purpose of the present invention is to provide a multi-layer scientific research cooperation network construction method based on professional papers and patent documents, which improves the recognition accuracy of cooperation relationships through key data confirmation and multiple matching strategies. In particular, for the problem of duplicate names, institutional matching is introduced as a supplement, which effectively reduces misjudgment and constructs the first to fifth different types of cooperation relationship data. Each type of data reflects different aspects of scientific research cooperation from different angles. Through network overlap and integration, not only the cooperation relationships within professional papers and patent documents are retained, but also the direct and indirect cooperation relationships between them are revealed. This multi-level cooperation relationship disclosure method helps to fully understand the complexity and diversity of scientific research cooperation and can solve problems in the prior art.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents, comprising the following steps:

[0010] S1: Acquisition of scientific research cooperation data: Obtain professional papers and patent documents from different data acquisition centers, confirm the basic information of professional papers and patent documents, and mark the professional papers and patent documents with confirmed basic information as scientific research data to be processed;

[0011] S2: Scientific research cooperation data processing: pre-process the scientific research data to be processed, and obtain the cooperation data to be extracted after the data pre-processing is completed;

[0012] S3: Confirmation of cooperative relationship: Confirm the key data of the cooperative data to be extracted, and extract the relationship based on the confirmed key data. After the relationship extraction is completed, the target cooperative relationship data is obtained;

[0013] S4: Cooperation relationship network construction: The target cooperation relationship data is used to construct the network of professional papers and patent documents respectively. After the network construction of professional papers and patent documents is completed, the network is overlapped. After the network is merged, the overlapping network of professional papers and patent document networks is obtained and marked as the target multi-layer scientific research data;

[0014] S5: Network construction relationship analysis: Perform relationship network analysis on the target multi-layer scientific research data, obtain the cooperation characteristic data of professional papers and patent documents after the relationship network analysis, and display the cooperation characteristic data on the mobile terminal.

[0015] Preferably, in S1, professional papers and patent documents are obtained from different data acquisition centers respectively, and basic information of professional papers and patent documents is confirmed, including:

[0016] Obtain professional papers from journal databases and patent documents from patent databases;

[0017] In addition, the basic information of the obtained professional papers and patent documents is confirmed respectively;

[0018] Among them, the basic information of professional papers includes the paper title, paper field, paper content, author name, publishing organization and publication date;

[0019] The basic information of patent documents includes patent name, patent field, patent institution, patent content, names of applicants and inventors, application date and publication date;

[0020] Match the acquired professional papers and patent documents as well as their basic information, and after matching, uniquely code and label them;

[0021] Professional papers and patent documents with unique coding numbers and their basic information are marked as scientific research data to be processed.

[0022] Preferably, data preprocessing is performed on the scientific research data to be processed in S2, including:

[0023] Carry out data cleaning, data integration and data conversion on the scientific research data to be processed;

[0024] Among them, data cleaning includes removing duplicate values, missing values, outliers and noise data from the scientific research data to be processed;

[0025] After data cleaning, data integration is performed. Data integration is to integrate the research data to be processed after data cleaning into one data set;

[0026] After data integration, data conversion is performed to unify the format of the scientific research data to be processed after data integration;

[0027] After the data conversion is completed, the pre-processed scientific research data to be processed is obtained and marked as cooperative data to be extracted.

[0028] Preferably, confirming key data of the cooperation data to be extracted in S3, and extracting relationships based on the confirmed key data, includes:

[0029] Confirm the key data in the cooperation data to be extracted, where the key data includes the basic information of professional papers and patent documents;

[0030] After key data is confirmed, relationship extraction is performed;

[0031] Among them, the author name and the applicant or inventor name of the professional paper and patent document are first obtained from the basic information;

[0032] Use string matching to match the author names and applicant or inventor names of professional papers and patent documents;

[0033] When the retrieved name is successfully matched, the first partnership data is obtained;

[0034] When there are duplicate names, institutional matching is performed based on the publishing institutions and patent institutions of professional papers and patent documents. When the patent institution and the publishing institution have a cooperative relationship, the institutional matching is successful and the second cooperative relationship data is obtained.

[0035] Preferably, the key data of the cooperation data to be extracted in S3 is confirmed, and the relationship extraction is performed according to the confirmed key data, and further includes:

[0036] Obtain the content of professional papers and patent documents and patent contents from basic information;

[0037] Use data mining methods to conduct correlation mining on the content of papers and patents. If there is a correlation between professional papers and patent documents, the common authors, common fields and common institutions of professional papers and patent documents can be obtained after correlation mining.

[0038] And the professional papers and patent documents after association mining are used as the third cooperative relationship data;

[0039] Based on the third-party cooperative relationship data, the citation relationship between the paper content and the patent content of professional papers and patent documents is searched;

[0040] When there are mutual citations in the references and cited documents in the paper content and patent content, the professional paper and patent document will be regarded as the fourth cooperative relationship data.

[0041] Preferably, the key data of the cooperation data to be extracted in S3 is confirmed, and the relationship extraction is performed according to the confirmed key data, and further includes:

[0042] Obtain the publication date and application date of professional papers and patent documents from basic information;

[0043] The cross-correlation analysis method is used to analyze the cross-correlation coefficients of the publication date and the application date, and the correlation data and time delay data between professional papers and patent documents are obtained after analysis;

[0044] Determine whether there is a correlation between professional papers and patent documents based on correlation data. If there is a correlation between professional papers and patent documents, determine the time sequence between them based on time delay data.

[0045] The professional papers and patent documents completed in chronological order are regarded as the fifth cooperative relationship data;

[0046] The first cooperative relationship data, the second cooperative relationship data, the third cooperative relationship data, the fourth cooperative relationship data and the fifth cooperative relationship data are uniformly marked as target cooperative relationship data.

[0047] Preferably, the target cooperative relationship data in S4 is subjected to network construction of professional papers and patent documents respectively, and after the network construction of professional papers and patent documents is completed, the network is merged, including:

[0048] Generate nodes for professional papers and patent documents based on target partnership data;

[0049] Among them, thesis nodes are generated for thesis in professional papers;

[0050] After the paper node is generated, the patent sub-node is established according to the cooperation relationship data with the patent document in the target cooperation relationship data. After the patent sub-node is established, the cooperation relationship edges between the paper node and several patent sub-nodes are obtained;

[0051] The cooperation relationship between the paper node and several patent sub-nodes is extended to the edge, and the Pajek tool in graph theory is used to construct a cooperation network for professional papers;

[0052] After the cooperation network of professional papers is constructed, the professional paper cooperation relationship network is obtained.

[0053] Preferably, the target cooperative relationship data is respectively constructed into networks of professional papers and patent documents in S4, and after the networks of professional papers and patent documents are constructed, the networks are merged, which further includes:

[0054] Generate patent nodes from patent documents;

[0055] After the patent node is generated, the paper sub-node is established according to the cooperation relationship data with the professional paper in the target cooperation relationship data. After the paper sub-node is established, the cooperation relationship edges between the patent node and several paper sub-nodes are obtained;

[0056] The cooperation relationship between the patent node and several paper sub-nodes is extended to the edge, and the Pajek tool in graph theory is used to construct a cooperation network of patent documents;

[0057] After the cooperation network of patent documents is constructed, the patent document cooperation relationship network is obtained.

[0058] Preferably, the target cooperative relationship data is respectively constructed into networks of professional papers and patent documents in S4, and after the networks of professional papers and patent documents are constructed, the networks are merged, which further includes:

[0059] Overlap the patent literature cooperation network and the professional paper cooperation network;

[0060] When the patent literature cooperation network and the professional paper cooperation network overlap, overlapping nodes are generated when there are co-authors and public institutions;

[0061] If there is a direct cooperative relationship between the patent literature cooperative relationship network and the professional paper cooperative relationship network, add corresponding edges to the nodes with cooperative relationships in the overlapping nodes;

[0062] If there is an indirect cooperation relationship between the patent literature cooperation network and the professional paper cooperation network, the co-citation analysis method is used to add potential edges in the overlapping nodes;

[0063] After the network nodes of the patent literature cooperation network and the professional paper cooperation network are overlapped and generated, network integration is performed to obtain the target multi-layer scientific research data.

[0064] Preferably, a relationship network analysis is performed on the target multi-layer scientific research data in S5, and the cooperation characteristic data of professional papers and patent documents are obtained after the relationship network analysis, including:

[0065] Perform topological structure analysis on network nodes in target multi-layer scientific research data;

[0066] Among them, topological structure analysis is to use node degree analysis method to confirm the number of each network node and edge in the target multi-layer scientific research data;

[0067] Then, cluster coefficient analysis is used to confirm the close cluster groups between each network node in the target multi-layer scientific research data;

[0068] Finally, the path length analysis method is used to confirm the average shortest path length between any two nodes in each network in the target multi-layer scientific research data;

[0069] Based on the number of each network node and the number of edges, the tight cluster groups between each network node and the average shortest path length between any two nodes, the cooperation characteristics data between professional papers and patent documents are obtained.

[0070] Compared with the prior art, the present invention has the following beneficial effects:

[0071] 1. The present invention provides a multi-layer scientific research cooperation network construction method based on professional papers and patent documents, which improves the recognition accuracy of cooperation relationships through key data confirmation and multiple matching strategies. In particular, for the problem of duplicate names, institution matching is introduced as a supplement, which effectively reduces misjudgment and constructs the first to fifth different types of cooperation relationship data, each of which reflects different aspects of scientific research cooperation from different angles.

[0072] 2. The present invention provides a multi-layered scientific research cooperation relationship network construction method based on professional papers and patent documents. Through network overlap and integration, it not only retains the cooperation relationship within each professional paper and patent document, but also reveals the direct and indirect cooperation relationship between them. This multi-level cooperation relationship disclosure method helps to fully understand the complexity and diversity of scientific research cooperation. The Pajek tool in graph theory is used for network construction and visualization, making the presentation of scientific research cooperation relationships more intuitive and clear.

[0073] 3. The present invention provides a method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents. Through node degree analysis, clustering coefficient analysis and path length analysis, the topological structure of the scientific research cooperation network is comprehensively and deeply analyzed. This comprehensive analysis can reveal the complex relationship between each node in the network, as well as the overall structural characteristics of the network. By comparing the cooperation characteristics data of different networks or different time periods, the changes and evolution laws of scientific research cooperation trends can be revealed. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic diagram of the steps of the cooperation between the professional papers and patent documents of the present invention;

[0075] Figure 2 It is a schematic diagram of the cooperation process between the professional papers and patent documents of the present invention. DETAILED DESCRIPTION

[0076] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] In order to solve the problem in the prior art that after obtaining the original data of professional papers and patent documents, the data is not further processed, resulting in poor data quality and inability to perform accurate analysis later, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0078] A method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents, comprising the following steps:

[0079] S1: Acquisition of scientific research cooperation data: Obtain professional papers and patent documents from different data acquisition centers, confirm the basic information of professional papers and patent documents, and mark the professional papers and patent documents with confirmed basic information as scientific research data to be processed;

[0080] Among them, obtaining professional papers and patent documents and their detailed information provides a rich data source for building a multi-layer scientific research cooperation network;

[0081] S2: Scientific research cooperation data processing: pre-process the scientific research data to be processed, and obtain the cooperation data to be extracted after the data pre-processing is completed;

[0082] Among them, the characteristics of professional papers and patent documents are fully considered in the data preprocessing process, so that the constructed multi-layer scientific research cooperation network can more comprehensively reflect the actual situation of scientific research cooperation;

[0083] S3: Confirmation of cooperative relationship: Confirm the key data of the cooperative data to be extracted, and extract the relationship based on the confirmed key data. After the relationship extraction is completed, the target cooperative relationship data is obtained;

[0084] Among them, the recognition accuracy of cooperative relationships is improved through key data confirmation and multiple matching strategies;

[0085] S4: Cooperation relationship network construction: The target cooperation relationship data is used to construct the network of professional papers and patent documents respectively. After the network construction of professional papers and patent documents is completed, the network is overlapped. After the network is merged, the overlapping network of professional papers and patent document networks is obtained and marked as the target multi-layer scientific research data;

[0086] Among them, through network overlap and integration, not only the cooperation relationship within professional papers and patent documents is preserved, but also the direct and indirect cooperation relationship between them is revealed;

[0087] S5: Network construction relationship analysis: Perform relationship network analysis on the target multi-layer scientific research data, obtain the cooperation characteristic data of professional papers and patent documents after relationship network analysis, and display the cooperation characteristic data on the mobile terminal;

[0088] Among them, by comparing the cooperation characteristics data of different networks or different time periods, the changes and evolution of scientific research cooperation trends can be revealed. By analyzing the cooperation characteristics data, researchers can understand their position and influence in the network.

[0089] Obtain professional papers and patent documents from different data acquisition centers in S1, and confirm the basic information of professional papers and patent documents, including:

[0090] Obtain professional papers from journal databases and patent documents from patent databases;

[0091] In addition, the basic information of the obtained professional papers and patent documents is confirmed respectively;

[0092] Among them, the basic information of professional papers includes the paper title, paper field, paper content, author name, publishing organization and publication date;

[0093] The basic information of patent documents includes patent name, patent field, patent institution, patent content, names of applicants and inventors, application date and publication date;

[0094] Match the acquired professional papers and patent documents as well as their basic information, and after matching, uniquely code and label them;

[0095] Professional papers and patent documents with unique coding numbers and their basic information are marked as scientific research data to be processed.

[0096] Specifically, obtaining professional papers and patent documents from different data acquisition centers (such as journal databases and patent databases) can ensure the comprehensiveness and extensiveness of the data. This multi-channel data collection method helps to reduce data omissions and biases, matches the basic information of professional papers and patent documents, and uniquely codes and labels them, which helps to achieve data standardization and unification. This processing method facilitates subsequent data analysis and relationship network construction, avoids analysis difficulties caused by inconsistent data formats, obtains professional papers and patent documents and their detailed information, and provides a rich data source for building a multi-layer scientific research cooperation network. Through in-depth analysis of these data, scientific research cooperation relationships at different levels can be revealed.

[0097] Data preprocessing is performed on the scientific research data to be processed in S2, including:

[0098] Carry out data cleaning, data integration and data conversion on the scientific research data to be processed;

[0099] Among them, data cleaning includes removing duplicate values, missing values, outliers and noise data from the scientific research data to be processed;

[0100] After data cleaning, data integration is performed. Data integration is to integrate the research data to be processed after data cleaning into one data set;

[0101] After data integration, data conversion is performed to unify the format of the scientific research data to be processed after data integration;

[0102] After the data conversion is completed, the pre-processed scientific research data to be processed is obtained and marked as cooperative data to be extracted.

[0103] Specifically, data cleaning, data integration and data conversion avoid analysis bias caused by duplicate data, ensure that the nodes and edges in the network are unique, thereby improving the accuracy and reliability of the network. Through appropriate filling or deletion operations, the impact of incomplete data on the analysis results is reduced, the integrity of the network is ensured, outliers or noise data are identified and corrected, their interference with the network structure is reduced, and the accuracy of network analysis is improved. The cleaned data from different sources are integrated into a data set, which simplifies the complexity of the data and makes subsequent data analysis and network construction more efficient and convenient. By unifying the data format, all data meet the requirements of subsequent analysis algorithms, improving the compatibility and operation efficiency of the algorithm. Since the characteristics of professional papers and patent documents are fully considered in the data preprocessing process, the constructed multi-layer scientific research cooperation network can more comprehensively reflect the actual situation of scientific research cooperation.

[0104] In order to solve the problem that the correlation between professional papers and patent documents is not analyzed in detail in the prior art, which leads to the inability to confirm the cooperative relationship, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0105] Confirm the key data of the cooperation data to be extracted in S3, and extract the relationship based on the confirmed key data, including:

[0106] Confirm the key data in the cooperation data to be extracted, where the key data includes the basic information of professional papers and patent documents;

[0107] After key data is confirmed, relationship extraction is performed;

[0108] Among them, the author name and the applicant or inventor name of the professional paper and patent document are first obtained from the basic information;

[0109] Use string matching to match the author names and applicant or inventor names of professional papers and patent documents;

[0110] When the retrieved name is successfully matched, the first partnership data is obtained;

[0111] When there are duplicate names, institutional matching is performed based on the publishing institutions and patent institutions of professional papers and patent documents. When the patent institution and the publishing institution have a cooperative relationship, the institutional matching is successful and the second cooperative relationship data is obtained.

[0112] Obtain the content of professional papers and patent documents and patent contents from basic information;

[0113] Use data mining methods to conduct correlation mining on the content of papers and patents. If there is a correlation between professional papers and patent documents, the common authors, common fields and common institutions of professional papers and patent documents can be obtained after correlation mining.

[0114] And the professional papers and patent documents after association mining are used as the third cooperative relationship data;

[0115] Based on the third-party cooperative relationship data, the citation relationship between the paper content and the patent content of professional papers and patent documents is searched;

[0116] When there are mutual citations in the references and cited documents in the paper content and patent content, the professional paper and patent document will be regarded as the fourth cooperative relationship data.

[0117] Obtain the publication date and application date of professional papers and patent documents from basic information;

[0118] The cross-correlation analysis method is used to analyze the cross-correlation coefficients of the publication date and the application date, and the correlation data and time delay data between professional papers and patent documents are obtained after analysis;

[0119] Determine whether there is a correlation between professional papers and patent documents based on correlation data. If there is a correlation between professional papers and patent documents, determine the time sequence between them based on time delay data.

[0120] The professional papers and patent documents completed in chronological order are regarded as the fifth cooperative relationship data;

[0121] The first cooperative relationship data, the second cooperative relationship data, the third cooperative relationship data, the fourth cooperative relationship data and the fifth cooperative relationship data are uniformly marked as target cooperative relationship data.

[0122] Specifically, using string matching to match the author names and applicant or inventor names of professional papers and patent documents is an efficient and relatively simple method. This method can quickly identify potential cooperative relationships and provide a basis for subsequent in-depth analysis. When name matching is difficult or uncertain, institution matching is used to supplement and verify the cooperative relationship, providing more basis for the confirmation of the cooperative relationship. Through data mining, the paper content and patent content are associated and mined to identify the common authors, common fields and common institutions between professional papers and patent documents. This method is not limited to superficial cooperative information (such as co-authorship), but also goes deep into the content level, revealing a deeper level of scientific research cooperation, further searching for references and cited documents in the paper content and patent content, identifying mutual citation relationships, and using professional papers and patent documents with citation relationships as the fourth cooperative relationship data. This expands the boundaries of cooperative relationships, including indirect cooperative relationships based on knowledge flow. In addition to traditional cooperative information such as authors and institutions, the content of papers and patents are also introduced as data dimensions, making the data basis for network construction richer and more comprehensive. Since the association and citation relationship at the content level are considered in the process of network construction, the subsequent analysis work can be more in-depth and meticulous. For example, the flow of knowledge between different fields can be analyzed, the efficiency and quality of scientific research cooperation can be evaluated, and the cross-correlation coefficient between the publication date of professional papers and the application date of patent documents can be analyzed to reveal the temporal correlation and potential influence relationship between the two. This analysis method can enhance the ability to identify scientific research cooperation relationships and discover those cooperative relationships that may be overlooked by traditional methods. The calculation of time delay data enables us to determine the time sequence between professional papers and patent documents, which helps to understand the temporal characteristics of scientific research activities. In scientific research cooperation, sometimes a study may be published in the form of a paper first and then apply for patent protection; or vice versa, the proposal of patent technology may inspire subsequent research papers. This time dimension analysis provides an important perspective for understanding the dynamic process of scientific research cooperation. Combining correlation data and time delay data, it can more accurately determine whether there is a real connection between professional papers and patent documents. This avoids the misjudgment that may be caused by matching author or institution information alone, and improves the accuracy of the cooperative relationship. In summary, through key data confirmation and multiple matching strategies, the recognition accuracy of the cooperative relationship is improved. In particular, for the problem of duplicate names, institutional matching is introduced as a supplement, which effectively reduces misjudgment and constructs the first to fifth different types of cooperative relationship data, each of which reflects different aspects of scientific research cooperation from different angles.

[0123] In order to solve the problem that the correlation between professional papers and patent documents is not effectively judged in the prior art, which leads to the inability to clearly understand the correlation between the two, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0124] For the target cooperative relationship data in S4, the network of professional papers and patent documents is constructed respectively. After the network construction of professional papers and patent documents is completed, the network is merged, including:

[0125] Generate nodes for professional papers and patent documents based on target partnership data;

[0126] Among them, thesis nodes are generated for thesis in professional papers;

[0127] After the paper node is generated, the patent sub-node is established according to the cooperation relationship data with the patent document in the target cooperation relationship data. After the patent sub-node is established, the cooperation relationship edges between the paper node and several patent sub-nodes are obtained;

[0128] The cooperation relationship between the paper node and several patent sub-nodes is extended to the edge, and the Pajek tool in graph theory is used to construct a cooperation network for professional papers;

[0129] After the cooperation network of professional papers is constructed, the professional paper cooperation relationship network is obtained.

[0130] Generate patent nodes from patent documents;

[0131] After the patent node is generated, the paper sub-node is established according to the cooperation relationship data with the professional paper in the target cooperation relationship data. After the paper sub-node is established, the cooperation relationship edges between the patent node and several paper sub-nodes are obtained;

[0132] The cooperation relationship between the patent node and several paper sub-nodes is extended to the edge, and the Pajek tool in graph theory is used to construct a cooperation network of patent documents;

[0133] After the cooperation network of patent documents is constructed, the patent document cooperation relationship network is obtained.

[0134] Overlap the patent literature cooperation network and the professional paper cooperation network;

[0135] When the patent literature cooperation network and the professional paper cooperation network overlap, overlapping nodes are generated when there are co-authors and public institutions;

[0136] If there is a direct cooperative relationship between the patent literature cooperative relationship network and the professional paper cooperative relationship network, add corresponding edges to the nodes with cooperative relationships in the overlapping nodes;

[0137] If there is an indirect cooperation relationship between the patent literature cooperation network and the professional paper cooperation network, the co-citation analysis method is used to add potential edges in the overlapping nodes;

[0138] After the network nodes of the patent literature cooperation network and the professional paper cooperation network are overlapped and generated, network integration is performed to obtain the target multi-layer scientific research data.

[0139] Specifically, node generation and cooperative relationship construction for professional papers and patent documents respectively can more accurately reflect the cooperation within these two types of documents. This refined network construction method helps to deeply explore the cooperation characteristics of each party and provide a solid foundation for subsequent network overlap and integration. In the process of network overlap, overlapping nodes are generated by identifying co-authors and public institutions, which can accurately reflect the direct connection between professional papers and patent documents. At the same time, the co-citation analysis method is used to add potential edges to the indirect cooperation relationship, which further enhances the effect of network overlap and makes the integrated network more comprehensive and accurate. Through network overlap and integration, not only the cooperation relationship within professional papers and patent documents is retained, but also the direct and indirect cooperation relationship between them is revealed. This multi-level cooperation relationship disclosure method helps to fully understand the complexity and diversity of scientific research cooperation. The Pajek tool in graph theory is used for network construction and visualization, making the presentation of scientific research cooperation relationships more intuitive and clear.

[0140] We conducted a relationship network analysis on the multi-layer scientific research data of the target in S5, and obtained the cooperation characteristics data of professional papers and patent documents after the relationship network analysis, including:

[0141] Perform topological structure analysis on network nodes in target multi-layer scientific research data;

[0142] Among them, topological structure analysis is to use node degree analysis method to confirm the number of each network node and edge in the target multi-layer scientific research data;

[0143] Then, cluster coefficient analysis is used to confirm the close cluster groups between each network node in the target multi-layer scientific research data;

[0144] Finally, the path length analysis method is used to confirm the average shortest path length between any two nodes in each network in the target multi-layer scientific research data;

[0145] Based on the number of each network node and the number of edges, the tight cluster groups between each network node and the average shortest path length between any two nodes, the cooperation characteristics data between professional papers and patent documents are obtained.

[0146] Specifically, the topological structure of the scientific research cooperation network was comprehensively and deeply analyzed through node degree analysis, clustering coefficient analysis and path length analysis. This comprehensive analysis can reveal the complex relationship between each node in the network (i.e., professional papers and patent documents) and the overall structural characteristics of the network. Through node degree analysis, we can understand the activity of each network node (i.e., professional papers or patent documents), that is, its influence and participation in the network. Clustering coefficient analysis reveals the close clustering groups between nodes, that is, which nodes are more likely to form close cooperative relationships. Path length analysis provides the "distance" information between any two nodes in the network, which helps to understand the efficiency of information dissemination and the diversity of cooperation paths, and presents the cooperation characteristics data in a quantitative form, such as node degree, clustering coefficient and average shortest path length. These quantitative data are not only intuitive and easy to understand, but also convenient for subsequent data processing and analysis. By comparing the cooperation characteristics data of different networks or different time periods, the changes and evolution of scientific research cooperation trends can be revealed. By analyzing the cooperation characteristics data, researchers can understand their position and influence in the network, as well as the cooperation potential and obstacles with other nodes.

[0147] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0148] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents, characterized in that: The steps include: S1: Acquisition of scientific research cooperation data: Obtain professional papers and patent documents from different data acquisition centers, confirm the basic information of professional papers and patent documents, and mark the professional papers and patent documents with confirmed basic information as scientific research data to be processed; S2: Scientific research cooperation data processing: pre-process the scientific research data to be processed, and obtain the cooperation data to be extracted after the data pre-processing is completed; S3: Confirmation of cooperative relationship: Confirm the key data of the cooperative data to be extracted, and extract the relationship based on the confirmed key data. After the relationship extraction is completed, the target cooperative relationship data is obtained; S4: Cooperation network construction: The target cooperation data is used to construct the network of professional papers and patent documents respectively. After the network construction of professional papers and patent documents is completed, the network is overlapped. After the network is merged, the overlapping network of professional papers and patent documents is obtained and marked as the target multi-layer scientific research data; S5: Network construction relationship analysis: Perform relationship network analysis on the target multi-layer scientific research data, obtain the cooperation characteristic data of professional papers and patent documents after the relationship network analysis, and display the cooperation characteristic data on the mobile terminal.

2. According to claim 1, a method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents is characterized in that: Obtain professional papers and patent documents from different data acquisition centers in S1, and confirm the basic information of professional papers and patent documents, including: Obtain professional papers from journal databases and patent documents from patent databases; In addition, the basic information of the obtained professional papers and patent documents is confirmed respectively; Among them, the basic information of professional papers includes the paper title, paper field, paper content, author name, publishing organization and publication date; The basic information of patent documents includes patent name, patent field, patent institution, patent content, names of applicants and inventors, application date and publication date; Match the acquired professional papers and patent documents as well as their basic information, and after matching, uniquely code and label them; Professional papers and patent documents with unique coding numbers and their basic information are marked as scientific research data to be processed.

3. A method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents according to claim 2, characterized in that: Data preprocessing is performed on the scientific research data to be processed in S2, including: Carry out data cleaning, data integration and data conversion on the scientific research data to be processed; Among them, data cleaning includes removing duplicate values, missing values, outliers and noise data from the scientific research data to be processed; After data cleaning, data integration is performed. Data integration is to integrate the research data to be processed after data cleaning into one data set; After data integration, data conversion is performed to unify the format of the scientific research data to be processed after data integration; After the data conversion is completed, the pre-processed scientific research data to be processed is obtained and marked as cooperative data to be extracted.

4. A method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents according to claim 3, characterized in that: Confirm the key data of the cooperation data to be extracted in S3, and extract the relationship based on the confirmed key data, including: Confirm the key data in the cooperation data to be extracted, where the key data includes the basic information of professional papers and patent documents; After key data is confirmed, relationship extraction is performed; Among them, the author name and the applicant or inventor name of the professional paper and patent document are first obtained from the basic information; Use string matching to match the author names and applicant or inventor names of professional papers and patent documents; When the retrieved name is successfully matched, the first partnership data is obtained; When there are duplicate names, institutional matching is performed based on the publishing institutions and patent institutions of professional papers and patent documents. When the patent institution and the publishing institution have a cooperative relationship, the institutional matching is successful and the second cooperative relationship data is obtained.

5. A method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents according to claim 4, characterized in that: Confirm the key data of the cooperation data to be extracted in S3, and extract the relationship based on the confirmed key data, which also includes: Obtain the content of professional papers and patent documents and patent contents from basic information; Use data mining methods to conduct correlation mining on the content of papers and patents. If there is a correlation between professional papers and patent documents, the common authors, common fields and common institutions of professional papers and patent documents can be obtained after correlation mining. And the professional papers and patent documents after association mining are used as the third cooperative relationship data; Based on the third-party cooperative relationship data, search for the citation relationship between the paper content and patent content of professional papers and patent documents; When there are mutual citations in the references and cited documents in the paper content and patent content, the professional paper and patent document will be regarded as the fourth cooperative relationship data.

6. A method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents according to claim 5, characterized in that: Confirm the key data of the cooperation data to be extracted in S3, and extract the relationship based on the confirmed key data, which also includes: Obtain the publication date and application date of professional papers and patent documents from basic information; The cross-correlation analysis method is used to analyze the cross-correlation coefficients of the publication date and the application date, and the correlation data and time delay data between professional papers and patent documents are obtained after analysis; Determine whether there is a correlation between professional papers and patent documents based on correlation data. If there is a correlation between professional papers and patent documents, determine the time sequence between them based on time delay data. The professional papers and patent documents completed in chronological order are regarded as the fifth cooperative relationship data; The first cooperative relationship data, the second cooperative relationship data, the third cooperative relationship data, the fourth cooperative relationship data and the fifth cooperative relationship data are uniformly marked as target cooperative relationship data.

7. A method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents according to claim 6, characterized in that: For the target cooperative relationship data in S4, the network of professional papers and patent documents is constructed respectively. After the network construction of professional papers and patent documents is completed, the network is merged, including: Generate nodes for professional papers and patent documents based on target partnership data; Among them, thesis nodes are generated for thesis in professional papers; After the paper node is generated, the patent sub-node is established according to the cooperation relationship data with the patent document in the target cooperation relationship data. After the patent sub-node is established, the cooperation relationship edges between the paper node and several patent sub-nodes are obtained; The cooperation relationship between the paper node and several patent sub-nodes is extended to the edge, and the Pajek tool in graph theory is used to construct a cooperation network for professional papers; After the cooperation network of professional papers is constructed, the professional paper cooperation relationship network is obtained.

8. The method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents according to claim 7, characterized in that: In S4, the target cooperative relationship data is respectively constructed into networks of professional papers and patent documents. After the networks of professional papers and patent documents are constructed, the networks are merged, which also includes: Generate patent nodes from patent documents; After the patent node is generated, the paper sub-node is established according to the cooperation relationship data with the professional paper in the target cooperation relationship data. After the paper sub-node is established, the cooperation relationship edges between the patent node and several paper sub-nodes are obtained; The cooperation relationship between the patent node and several paper sub-nodes is extended to the edge, and the Pajek tool in graph theory is used to construct a cooperation network of patent documents; After the cooperation network of patent documents is constructed, the patent document cooperation relationship network is obtained.

9. The method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents according to claim 8, characterized in that: In S4, the target cooperative relationship data is respectively constructed into networks of professional papers and patent documents. After the networks of professional papers and patent documents are constructed, the networks are merged, which also includes: Overlap the patent literature cooperation network and the professional paper cooperation network; When the patent literature cooperation network and the professional paper cooperation network overlap, overlapping nodes are generated when there are co-authors and public institutions; If there is a direct cooperative relationship between the patent literature cooperative relationship network and the professional paper cooperative relationship network, add corresponding edges to the nodes with cooperative relationships in the overlapping nodes; If there is an indirect cooperation relationship between the patent literature cooperation network and the professional paper cooperation network, the co-citation analysis method is used to add potential edges in the overlapping nodes; After the network nodes of the patent literature cooperation network and the professional paper cooperation network are overlapped and generated, network integration is performed to obtain the target multi-layer scientific research data.

10. A method for constructing a multi-layer scientific research cooperation network based on professional papers and patent documents according to claim 9, characterized in that: We conducted a relationship network analysis on the multi-layer scientific research data of the target in S5, and obtained the cooperation characteristics data of professional papers and patent documents after the relationship network analysis, including: Perform topological structure analysis on network nodes in target multi-layer scientific research data; Among them, topological structure analysis is to use node degree analysis method to confirm the number of each network node and edge in the target multi-layer scientific research data; Then, cluster coefficient analysis is used to confirm the close cluster groups between each network node in the target multi-layer scientific research data; Finally, the path length analysis method is used to confirm the average shortest path length between any two nodes in each network in the target multi-layer scientific research data; Based on the number of each network node and the number of edges, the tight clustering groups between each network node and the average shortest path length between any two nodes, the cooperation characteristics data between professional papers and patent documents are obtained.

Images