Literature value evaluation method, system, equipment, medium and product

Abstract

The invention discloses a literature value evaluation method, system and device, a medium and a product, and relates to the technical field of knowledge management, and the method comprises the steps: calculating a subversiveness index which can reflect the value of a to-be-evaluated literature based on the reference relation among the to-be-evaluated literature, all first literatures and all second literatures; calculating a contribution index capable of reflecting the value of the to-be-evaluated literature based on the network diameter of the undirected reference network before and after the to-be-evaluated literature is added and the number of nodes contained in the maximum connected sub-graph; based on the average reference chain length of each third node in the directed reference network after the literature to be evaluated is added, calculating a persistence index capable of reflecting the value of the literature to be evaluated; and calculating a literature value evaluation result of the to-be-evaluated literature according to the subversiveness index, the contribution index and the persistence index, so that the literature value can be objectively evaluated according to three dimensions of subversiveness, contribution and persistence, the accuracy of literature value evaluation is improved, and scientific achievements really having scientific values are effectively identified.

Description

Technical Field

[0001] The present application relates to the field of knowledge management technology, and in particular to a method, system, device, medium and product for evaluating the value of a document based on a mutation of a citation relationship. Background Art

[0002] Document value assessment has an enlightening effect on scientific research management, can help identify key scientific research results, and promote the exploration of engines for future scientific and technological development. Evaluating document value based on document citations is a common method for document value assessment. This common method mainly evaluates document value based on direct citations of documents, such as changes in cumulative citations and citation relationship network characteristics, which is conducive to identifying key scientific research results. However, the above common methods mostly evaluate document value from a single dimension, that is, they mostly determine the scientific value of scientific research results from a single dimension, and the evaluation accuracy is low, and it is impossible to effectively identify scientific research results that are truly scientifically valuable. Summary of the invention

[0003] The purpose of this application is to provide a method, system, equipment, medium and product for document value assessment, which can objectively evaluate the value of documents from multiple dimensions, improve the accuracy of document value assessment, and effectively identify scientific research results that are truly of scientific value.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a method for evaluating the value of a document, the method comprising:

[0006] Based on the citation relationship between the document to be evaluated, all first documents and all second documents, a disruptive index that can reflect the value of the document to be evaluated is calculated; the first document is a document that cites the document to be evaluated and belongs to the same field as the document to be evaluated; the second document is a document that is cited by the document to be evaluated and belongs to the same field as the document to be evaluated;

[0007] Based on the citation relationship between all third documents, each of the third documents is taken as a first node, a first undirected connection edge is drawn between two first nodes having a citation relationship, a first undirected citation network is obtained, and a first network diameter of the first undirected citation network and the number of first nodes included in a first maximum connected subgraph are determined; the third document is a document belonging to the same field as the document to be evaluated;

[0008] Based on the citation relationship between the document to be evaluated and all the third documents, the document to be evaluated and each of the third documents are respectively taken as a second node, a second undirected connection edge is drawn between two second nodes having a citation relationship to obtain a second undirected citation network, and a second network diameter of the second undirected citation network and the number of second nodes included in the second largest connected subgraph are determined;

[0009] Calculating a contribution index that can reflect the value of the document to be evaluated based on the first network diameter, the first number of nodes, the second network diameter, and the second number of nodes;

[0010] Based on the citation relationship between the document to be evaluated and all the third documents, the document to be evaluated and each of the third documents are respectively taken as a third node, a directed connection edge is drawn between two third nodes having a citation relationship to obtain a directed citation network, and an average citation chain length of each third node in the directed citation network is determined; the two third nodes connected by the directed connection edge are respectively recorded as a starting point and an end point, and the directed connection edge points from the starting point to the end point, indicating that the starting point cites the end point;

[0011] Based on the average length of the citation chain of each of the third nodes, calculating a continuity index that can reflect the value of the document to be evaluated;

[0012] The disruptive index, the contribution index and the sustainability index are comprehensively considered to calculate the document value assessment result of the document to be assessed.

[0013] In a second aspect, the present application provides a document value assessment system, the document value assessment system comprising:

[0014] The human-computer interaction module is used to obtain the basic information of the document to be evaluated input by the user, and output the document value evaluation result of the document to be evaluated to the user;

[0015] The value assessment module is used to execute the above-mentioned document value assessment method to assess the document to be assessed and obtain a document value assessment result of the document to be assessed.

[0016] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned document value assessment method.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned document value assessment method when executed by a processor.

[0018] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the above-mentioned document value assessment method when executed by a processor.

[0019] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0020] The present application provides a document value assessment method, system, device, medium and product. Based on the citation relationship between the document to be assessed, all first documents and all second documents, a disruptive index that can reflect the value of the document to be assessed is calculated; based on the network diameter of the undirected citation network before and after the document to be assessed is added and the number of nodes contained in the largest connected subgraph, a contribution index that can reflect the value of the document to be assessed is calculated; based on the average citation chain length of each third node in the directed citation network after the document to be assessed is added, a sustainability index that can reflect the value of the document to be assessed is calculated; the disruptive index, contribution index and sustainability index are combined to calculate the document value assessment result of the document to be assessed, so that the document value can be objectively assessed from the three dimensions of disruptiveness, contribution and sustainability, the accuracy of document value assessment can be improved, and scientific research results with real scientific value can be effectively identified. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 This is an application environment diagram of a document value assessment method provided in Example 1 of the present application.

[0023] Figure 2 A flowchart of a method for evaluating the value of a document provided in Example 1 of the present application.

[0024] Figure 3 A flowchart of a method for evaluating the value of a document provided in Example 1 of the present application.

[0025] Figure 4 This is a schematic diagram of an undirected citation network in the same field provided in Example 1 of the present application; wherein: Figure 4 (a) in the figure is an undirected citation network that does not include the literature to be evaluated; Figure 4 (b) in the figure is the undirected citation network including the document to be evaluated.

[0026] Figure 5 A schematic diagram of an undirected citation network of sub-fields provided in Example 1 of the present application; wherein: Figure 5(a) in the field is Field 1 The undirected citation network corresponding to the field that does not include the literature to be evaluated; Figure 5 (b) in the field is Field 1 The undirected citation network corresponding to the field including the literature to be evaluated; Figure 5 (c) in the field is Field 2 The undirected citation network corresponding to the field that does not include the literature to be evaluated; Figure 5 (d) in the field is Field 2 The field corresponds to an undirected citation network that includes the literature to be evaluated.

[0027] Figure 6 A schematic diagram of a directed citation network in the same field provided in Example 1 of the present application.

[0028] Figure 7 A schematic diagram of the functional modules of a document value assessment system provided in Example 2 of the present application.

[0029] Figure 8 A schematic diagram of the structure of a computer device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] Example 1

[0032] The document value assessment method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, the terminal communicates with the server through the network. The data storage system can store the data that the server needs to process. The data storage system can be set up separately, integrated on the server, or placed on the cloud or other servers. The terminal can send the document to be evaluated to the server. After the server receives the document to be evaluated, for the document to be evaluated, the server calculates a disruptive index that can reflect the value of the document to be evaluated based on the citation relationship between the document to be evaluated, all the first documents and all the second documents; generates a first undirected citation network based on the citation relationship between all the third documents, and determines the first network diameter of the first undirected citation network and the number of first nodes included in the first largest connected subgraph; generates a second undirected citation network based on the citation relationship between the document to be evaluated and all the third documents, and determines the second network diameter of the second undirected citation network and the number of second nodes included in the second largest connected subgraph; calculates a contribution index that can reflect the value of the document to be evaluated based on the first network diameter, the first number of nodes, the second network diameter and the second number of nodes; generates a directed citation network based on the citation relationship between the document to be evaluated and all the third documents, and determines the average citation chain length of each third node in the directed citation network; calculates a sustainability index that can reflect the value of the document to be evaluated based on the average citation chain length of each third node; and calculates a document value evaluation result of the document to be evaluated by combining the disruptive index, the contribution index and the sustainability index. The server can feed back the obtained document value assessment result of the document to be assessed to the terminal.

[0033] In addition, in some embodiments, the document value assessment method can also be implemented by a server or a terminal alone. For example, the terminal can directly assess the document to be assessed, or the server can obtain the document to be assessed from a data storage system and assess the document to be assessed.

[0034] The terminal may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The server may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0035] like Figure 2 and Figure 3 As shown, the embodiment of the present application provides a method for evaluating the value of a document. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0036] S1: Based on the citation relationship between the document to be evaluated, all first documents and all second documents, calculate the disruptive index that can reflect the value of the document to be evaluated; the first document is a document that cites the document to be evaluated and belongs to the same field as the document to be evaluated; the second document is a document that is cited by the document to be evaluated and belongs to the same field as the document to be evaluated.

[0037] S2: Based on the citation relationship between all third documents, take each of the third documents as a first node, draw a first undirected connection edge between two of the first nodes with a citation relationship, obtain a first undirected citation network, and determine a first network diameter of the first undirected citation network and the number of first nodes included in a first maximum connected subgraph; the third document is a document belonging to the same field as the document to be evaluated.

[0038] S3: Based on the citation relationship between the document to be evaluated and all the third documents, the document to be evaluated and each of the third documents are respectively taken as a second node, a second undirected connection edge is drawn between two second nodes having a citation relationship to obtain a second undirected citation network, and a second network diameter of the second undirected citation network and the number of second nodes included in the second largest connected subgraph are determined.

[0039] S4: Based on the first network diameter, the first number of nodes, the second network diameter and the second number of nodes, calculate a contribution index that can reflect the value of the document to be evaluated.

[0040] S5: Based on the citation relationship between the document to be evaluated and all the third documents, the document to be evaluated and each of the third documents are respectively taken as a third node, a directed connection edge is drawn between two third nodes having a citation relationship to obtain a directed citation network, and an average citation chain length of each third node in the directed citation network is determined; the two third nodes connected by the directed connection edge are respectively recorded as a starting point and an end point, and the directed connection edge points from the starting point to the end point, indicating that the starting point cites the end point.

[0041] S6: Based on the average length of the citation chain of each of the third nodes, calculate a continuity index that can reflect the value of the document to be evaluated.

[0042] S7: Calculate the document value assessment result of the document to be assessed by comprehensively considering the disruptive index, the contribution index and the sustainability index.

[0043] By implementing the above-mentioned steps S1 to S7, the embodiment of the present application can objectively evaluate the value of the document to be evaluated from the three dimensions of disruptiveness, contribution and sustainability, so as to obtain the document value evaluation result of the document to be evaluated more accurately and effectively identify the scientific research results that are truly of scientific value.

[0044] In the embodiments of the present application, the documents may include scientific research papers, journal articles, etc.

[0045] Scientific research results that are truly of scientific value may break through the cognition of the original knowledge in a certain field, cause a mutation in the knowledge network in that field, and have a lasting impact on scientific research. Based on this, the embodiment of the present application provides a method for evaluating the value of a document based on the mutation of citation relationships. It analyzes the subversive ability of a document to the existing knowledge structure from the subversive dimension, identifies the degree of expansion and integration of the document to the existing knowledge system from the contribution dimension, and studies the degree of continuity of the role played by the knowledge content of the document from the sustainability dimension. The three dimensions can be combined to achieve an integrated evaluation of the true value of the document.

[0046] The following is an introduction to the construction process of the three indexes used in the embodiments of the present application:

[0047] 1. Constructing a disruptive index:

[0048] Calculate the proportion of references that do not cite the literature to be evaluated among the literature that cites it, and analyze whether the literature to be evaluated has achieved sublimation or innovation of existing knowledge. This proportion measures the proportion of literature that has added knowledge of the literature to be evaluated but has not continued to add relevant historical knowledge of the literature to be evaluated. Therefore, it can represent the ability of the literature to be evaluated to subvert the knowledge structure before its publication.

[0049] The specific steps to construct the Disruptive Index include:

[0050] Calculate the proportion of references that do not cite the document A (i.e., the documents cited by the document A) among all the documents that cite the document A to be evaluated, and use this as the subversive index. The documents cited by the document A to be evaluated represent the historical knowledge related to the document A to be evaluated before the publication of the document A to be evaluated. After the publication of the document A to be evaluated, the documents that cite the document A to be evaluated are the documents that need to be added to the knowledge related to the document A to be evaluated. Therefore, after the publication of the document A to be evaluated, the proportion of documents that no longer cite the documents cited by the document A to be evaluated in the collection of documents that cite the document A to be evaluated can be used to illustrate the ability of the document A to be evaluated to subvert the knowledge structure before its publication. If a document only cites the document A to be evaluated but does not cite the references of the document A to be evaluated, it means that the document believes that the document A to be evaluated has sublimated or innovated the content and ideas of its references, and is more valuable than its references.

[0051] The disruptive index reflects the overall situation of all documents that cite document A to be evaluated. The calculation formula of the disruptive index is:

[0052]

[0053] In formula (1), DIS is the subversiveness index, which ranges from 0 to 1. The larger the value, the stronger the subversiveness; n is the number of second documents; r i is the number of first documents that cite the i-th second document; R is the number of first documents.

[0054] For example, in this embodiment, the reference documents in the same field as the document A to be evaluated (i.e., the second document) include B 1 , B 2 and B 3 , the documents that cite the document A to be evaluated and are in the same field as the document A to be evaluated (i.e. the first document) include A 1 , A 2 and A 3 , where A 3 Citations of both references A and B 3 , so n is 3 (B 1 , B 2 , B 3 ), R is 3(A 1 , A 2 , A 3 ), r 1 is 0, r 2 is 0, r 3 =1(A 3 ),and then,

[0055] The documents in the same field as the document A to be evaluated refer to documents that have the same Chinese Library Classification Number or WoS (Web of Science) subject classification name as the document A to be evaluated. 1 and Field 2 , then all the Chinese Library Classification Numbers are Field 1 、Field 2 and Field 1 and Field 2 The documents are all in the same field as the document A to be evaluated.

[0056] 2. Constructing the Contribution Index:

[0057] By comparing the increase in the network diameter and the number of nodes contained in the largest connected subgraph before and after the document to be evaluated is added to the undirected citation network, we can analyze whether the document to be evaluated has promoted the integration of domain knowledge. The network diameter reflects the scope of the knowledge system, and the number of nodes contained in the largest connected subgraph reflects the similarity of knowledge. Therefore, after the publication of the document to be evaluated, the increase in the network diameter and the number of nodes contained in the largest connected subgraph can represent the degree to which the document to be evaluated promotes the expansion and integration of the existing knowledge system.

[0058] The specific steps to construct the contribution index include:

[0059] (1) Constructing an undirected citation network in the same field:

[0060] Construct an undirected reference network Network 1 (i.e., the first undirected citation network), which contains all documents in the same field as the document A to be evaluated (i.e., the third document) and their citation relationships, except for the document A to be evaluated. 1 In the above, a node represents a document in the same field as the document A to be evaluated, and an undirected edge represents a citation relationship. If there is a citation relationship between two nodes, there is an undirected edge between the two nodes.

[0061] In Network 1 On the basis of , add the document A to be evaluated, specifically add node A, and establish undirected edges between the document A to be evaluated and its references, and between the document A to be evaluated and the documents that cite the document A to be evaluated. The undirected citation network after adding node A and the corresponding undirected edges is recorded as Network 2 (i.e. the second undirected citation network).

[0062] For example, in this embodiment, Network 1 and Network 2 Corresponding to Figure 4 (a) and Figure 4 (b) in. Figure 4 In the example, node A 21 and node A 2 Respectively represent document A 21 and Literature A 2 , due to the literature A 21 Cited reference A 2 , so the corresponding node A 21 and node A 2 There are undirected connecting edges between them.

[0063] (2) Constructing the expansion effect index:

[0064] An undirected citation network is a system of mutual citations between documents. The network diameter is the longest citation chain between all documents. The network diameter refers to the maximum value of the shortest path between any two nodes in the undirected citation network. In other words, the network diameter is the distance between the two farthest nodes in the undirected citation network, reflecting the size of the knowledge scope in the system. If the network diameter of the undirected citation network increases significantly after adding the document A to be evaluated, it means that the document A to be evaluated has promoted the expansion of the existing knowledge system. Based on this, compared with Network 2 and Network 1 The size of the network diameter is used to evaluate the contribution of the document A to be evaluated in expanding the existing knowledge system. The calculation formula of the expansion effect index is as follows:

[0065]

[0066] In formula (2), VAL' 1 is the expansion effect coefficient; D 1 Network 1 The network diameter, i.e. the first network diameter; D 2 Network 2 The network diameter is the second network diameter.

[0067] When the field to which the document A to be evaluated belongs is not unique (i.e. the number of the Chinese Library Classification Number / WoS Subject Classification Name of the document A to be evaluated is greater than 1), then the document A to be evaluated may have a negative impact on the Network 1 The network diameter has little impact on 1 The network diameter of the undirected citation network in a certain field is greatly affected. Based on this, the expansion effect index is corrected to obtain the corrected expansion effect index. The calculation formula of the corrected expansion effect index is as follows:

[0068]

[0069] In formula (3), VAL 1 is the modified extension effect index; m represents the total number of fields to which the document A to be evaluated belongs, i represents the i-th field to which the document A to be evaluated belongs; di 1 represents the network diameter of the undirected citation network corresponding to the i-th field that does not include the document A to be evaluated; di 2 Represents the network diameter of the undirected citation network corresponding to the i-th field including the document A to be evaluated.

[0070] For example, according to Figure 4 In this embodiment, m is 2 (Field 1 and Field 2 ), D 1 and D 28 and 10 respectively, according to Figure 5 , for the field Field 1 For example, 11 and d 12 3 and 7 respectively, for the field Field 2 For example, 21 and d 22 are 8 and 8 respectively. Therefore,

[0071] It should be noted that when the field of the document A to be evaluated is not unique, Network 1 The fields of the documents included in are multiple, and the undirected citation network corresponding to the i-th field that does not include the document A to be evaluated is, in Network 1 In the Network, the undirected citation network consisting of all documents belonging to the i-th field (i.e., documents in the same field as the document A to be evaluated, whose Chinese Library Classification Number or WoS Subject Classification Name is the i-th field) and their undirected connecting edges does not include the document A to be evaluated. The undirected citation network corresponding to the i-th field including the document A to be evaluated is, 2 In the undirected citation network, all documents belonging to the i-th field and their undirected connecting edges constitute the undirected citation network, which includes the document A to be evaluated.

[0072] For example, according to Figure 4 In this embodiment, the Chinese Library Classification Number of the document A to be evaluated is Field 1 and Field 2 , which includes two categories: one is that the Chinese Library Classification Number contains Field 1 The literature with the Chinese Library Classification Code Field 1 , or Field 1 and Field 2 The second is that the Chinese Library Classification Number contains Field 2 The literature with the Chinese Library Classification Code Field 2 , or Field 1 and Field 2 Therefore, the field 1 The corresponding undirected citation network consists of white nodes (such as B 2 ), light gray nodes (such as A 3 ) and its undirected connecting edges, Field 2 The corresponding undirected citation network consists of light grey nodes (such as A 3 ), dark gray nodes (such as B 3 ) and its undirected connecting edges.

[0073] (3) Constructing the Fusion Effect Index:

[0074] The maximum connected subgraph is the maximum size of the direct citation relationship between documents. The number of nodes contained in the maximum connected subgraph can reflect the similarity of knowledge. After the publication of the document A to be evaluated, the degree to which the number of nodes contained in the maximum connected subgraph increases represents the degree to which the document A to be evaluated promotes the integration of the existing knowledge system. Based on this, the comparison of Network 2 and Network 1 The number of nodes contained in the largest connected subgraph in is used to evaluate the contribution of the document A to be evaluated in promoting the integration of existing knowledge. The calculation formula is as follows:

[0075]

[0076] In formula (4), VAL' 2 is the fusion effect index; N 1 Network 1 The number of nodes contained in the largest connected subgraph, that is, the number of first nodes; N 2 Network 2 The number of nodes contained in the largest connected subgraph in , that is, the second number of nodes.

[0077] When the field of the document A to be evaluated is not unique, the document A to be evaluated may have a significant impact on the network. 1 The influence on the number of nodes contained in the largest connected subgraph of the domain is small, but the influence on the number of nodes contained in the largest connected subgraph in the undirected reference network of a certain field is large. Based on this, the fusion effect index is corrected to obtain the corrected fusion effect index. The calculation formula of the corrected fusion effect index is:

[0078]

[0079] In formula (5), VAL 2 is the corrected fusion effect index; m is the total number of fields to which the document A to be evaluated belongs, i represents the i-th field to which the document A to be evaluated belongs; n i1 n represents the number of nodes contained in the largest connected subgraph of the undirected citation network corresponding to the i-th field that does not include the document A to be evaluated; i2 Represents the number of nodes contained in the largest connected subgraph of the undirected citation network corresponding to the i-th field, including the document A to be evaluated.

[0080] For example, according to Figure 4 In this embodiment, m is 2 (Field 1 and Field 2 ), Network 1 The maximum connected subgraph consists of node A 3 Node A31 All dark gray nodes (such as B 3 ) and the corresponding undirected connecting edges, Network 2 The maximum connected subgraph of is equal to itself, so N 1 is 12, N 2 is 26. Similarly, according to Figure 5 , for the field Field 1 For example, 11 and n 12 5 and 16 respectively, for the field Field 2 For example, 21 and n 22 are 12 and 13 respectively, so,

[0081] (4) Constructing the contribution index:

[0082] If the addition of document A to be evaluated increases the network diameter of the undirected citation network or the number of nodes contained in the largest connected subgraph, it means that document A to be evaluated has contributed to the expansion and integration of the existing knowledge system. Based on this, a contribution index is constructed. The calculation formula of the contribution index is:

[0083] VAL=VAL 1 ×VAL 2 (6)

[0084] In formula (6), VAL is the contribution index; VAL 1 VAL is the modified expansion effect index; 2 is the corrected fusion effect index.

[0085] 3. Construction of sustainability index:

[0086] Analyze whether the average citation chain length of the document to be evaluated exceeds the average level of the documents in the same field, and whether it shows an increasing trend over time, so as to evaluate the sustainability of the value of the document to be evaluated. The length of the subsequent citation chain of the document to be evaluated (i.e., the average citation chain length) reflects the continuation and development of the relevant knowledge. The longer the chain, the more vital its knowledge content. Therefore, the difference between the length of the subsequent citation chain of the document to be evaluated and the average level of the documents in the same field, as well as its development trend over time, can reflect the sustainability of the role played by the content of the document to be evaluated in the relevant field.

[0087] The specific steps to construct the persistence index include:

[0088] (1) Constructing a directed citation network in the same field:

[0089] Build a directed reference network Network 3(i.e., directed citation network), covering the document A to be evaluated and all documents in the same field as the document A to be evaluated, as well as the citation relationships between the documents. 3 In Network, nodes represent documents, and directed edges represent citation relationships. 3 Literature in P 1 And its references 2 For example, the directed edges are P 1 As the starting point, with P 2 For the end point.

[0090] For example, in this embodiment, Network 3 correspond Figure 6 ,exist Figure 6 In the example, node A 1 and node A represent document A 1 and document A to be evaluated. Since document A 1 The document A to be evaluated is cited, so the corresponding node is A 1 There is a directed edge between node A and node A, and the directed edge starts from node A. 1 is the starting point and node A is the end point.

[0091] (2) Constructing an overall sustainability index:

[0092] According to Network 3 , compare the citation chain lengths of the document A to be evaluated and the documents in the same field, and record the result as the overall persistence index CON' A The length of the subsequent citation chain of a document reflects the continuity and development of relevant knowledge. If the length of the citation chain of document A to be evaluated is higher than the average level in the same field, it means that compared with other documents in the same field, the knowledge content of document A to be evaluated has a longer vitality, and the research questions that can be extended to document A to be evaluated are more, and it has a higher value of continuous exploration. The calculation formula of the overall sustainability index is as follows:

[0093] CON' A =AV A / AV O (7)

[0094] In formula (7), CON' A Represents the overall persistence index; AV A Represents Network 3 The average citation chain length of the document A to be evaluated is AV O Represents Network 3 The average of the average citation chain lengths of each document.

[0095] Among them, the length of the citation chain of the document A to be evaluated refers to the length of the citation chain in the Network3 The shortest number of edges required to reach node A from other nodes.

[0096] For example, according to Figure 6 In this example, there are 6 documents with reference links to the document A to be evaluated, namely A 1 , A 2 , A 3 , A 21 , A 31 and A 211 The lengths of the citation chains between the document A to be evaluated and the above 6 documents are 1(A 1 →A)、1(A 2 →A)、1(A 3 →A)、2(A 21 →A 2 , A 2 →A)、2(A 31 →A 3 , A 3 →A) and 3(A 211 →A 21 , A 21 →A 2 , A 2 →A). Therefore, the average citation chain length of the document A to be evaluated is Similarly, we can find Network 3 The average citation chain length of other documents in the article is further calculated using AVO.

[0097] (3) Constructing trend index:

[0098] Considering that some documents involving hot issues but without actual value may have longer citation chains, and the overall sustainability index may overestimate the value of these documents, the overall sustainability index is revised. Since the citation chains of documents without actual value often cannot grow continuously, a trend index is constructed to analyze the changes in the average citation chain length of document A to be evaluated over the years to revise the overall sustainability index. The calculation formula of the trend index is as follows:

[0099]

[0100] In formula (8), Tr A Represents the trend index of the literature to be evaluated, A is the literature to be evaluated; Y Ar Y represents the number of years that the average citation chain length of document A to be evaluated increases after the document A to be evaluated is published; A Indicates the number of years included in the preset period, that is, the publication date of the document A to be evaluated is this year; Y ARIt indicates the number of years in which the average citation chain length of document A increased significantly after the publication of document A. Whether the increase was significant was determined by the Mann-Kendall mutation test.

[0101] For example, in this embodiment, the publication of document A to be evaluated was 5 years ago, and one year after publication, it was replaced by document A. 1 Cited and cited by Literature A 2 years later 2 Cited and cited by Literature A 3 years later 3 Cited and cited by Literature A 4 years later 21 and A 31 Cited, and 5 years later, by Literature A 211 According to this, one year after the publication of the document A to be evaluated, it was cited by document A. 1 (corresponding to a reference chain length of 1) citation, the average reference chain length is Two years after its publication, it was included in the literature 1 and A 2 Citations (corresponding to citation chain lengths of 1 and 1 respectively), the average citation chain length is By analogy, we can get the average citation chain lengths of the document A to be evaluated 1 to 5 years after publication are 1, 1, 1, 1.4 and 1.6666 respectively. Therefore, the number of years in which the average citation chain length increases is 2 (the 4th and 5th years), that is, Y Ar The average citation chain length data of previous years were tested for mutation points, and it was found that the number of years in which the average citation chain length of the document A to be evaluated increased significantly was 1 (the 4th year), that is, Y AR is 1. Therefore,

[0102] (4) Constructing a sustainability index:

[0103] If the average citation chain length of the document A to be evaluated is higher than the average level in the same field, and its citation chain shows an overall growth trend, it means that the knowledge content of the document A to be evaluated has a long life span, can continue to play a role in the relevant field, and has the value of being continuously explored. Based on this, the calculation formula of the sustainability index is:

[0104]

[0105] In formula (9), CON is the persistence index; CON' A is the overall persistence index of the literature to be evaluated.

[0106] After constructing the disruptive index, contribution index and sustainability index, this embodiment further constructs a comprehensive value index, specifically calculating the average value of the disruptive index, contribution index and sustainability index, and using it as the comprehensive value index of the document A to be evaluated, so as to evaluate the true value of the document A to be evaluated to social development. The calculation formula of the comprehensive value index is:

[0107]

[0108] In formula (10), IV is the comprehensive value index, that is, the document value evaluation result of this embodiment. The value range of IV is [0, 1]. The larger the value, the higher the comprehensive value of the document A to be evaluated in terms of subversion, contribution and sustainability.

[0109] In this embodiment, the documents cited by the document to be evaluated represent the historical knowledge related to the document to be evaluated before the document to be evaluated is published. After the document to be evaluated is published, the documents that cite the document to be evaluated are the documents that need to be added to the knowledge of the document to be evaluated. Therefore, after the document to be evaluated is published, the proportion of documents in the collection of documents that cite it that no longer cite the documents cited by the document to be evaluated can represent the ability of the document to be evaluated to subvert the knowledge structure before its publication; the undirected citation network is a system of mutual citations between documents. The network diameter is the longest citation chain between all documents, reflecting the size of the knowledge scope in the system. The largest connected subgraph is the network with direct citations between documents. The maximum size of the system, the number of nodes contained in it can reflect the similarity of knowledge. After the publication of the document to be evaluated, the degree to which the network diameter and the number of nodes contained in the largest connected subgraph increase represents the degree to which the document to be evaluated has promoted the expansion and integration of the existing knowledge system; the length of the subsequent citation chain of the document reflects the continuation and development of the relevant knowledge. The longer the chain, the longer the vitality of its knowledge content. Therefore, the difference between the length of the subsequent citation chain of the document to be evaluated and the average level of documents in the same field, and whether it continues to grow over time, can reflect the sustainability of the role played by the content of the document to be evaluated in the relevant field. Based on this, the subversive index, contribution index and sustainability index defined in this embodiment are all objectively related to the value of the document. This relationship is not transferred by human will. Therefore, by calculating the subversive index, contribution index and sustainability index, the value of the document can be objectively evaluated.

[0110] In S4, based on the first network diameter, the first number of nodes, the second network diameter and the second number of nodes, a contribution index that can reflect the value of the document to be evaluated is calculated, specifically including: calculating the ratio of the first network diameter and the second network diameter to obtain a first ratio, and calculating the difference between 1 and the first ratio to obtain the expansion effect index of the document to be evaluated; calculating the ratio of the first number of nodes to the second number of nodes to obtain a second ratio, and calculating the difference between 1 and the second ratio to obtain the fusion effect index of the document to be evaluated; calculating the product of the expansion effect index and the fusion effect index to obtain a contribution index that can reflect the value of the document to be evaluated.

[0111] Before calculating the product of the expansion effect index and the fusion effect index, the document value assessment method of this embodiment also includes: determining whether the document to be assessed belongs to only one field; if not, using the first correction formula to correct the expansion effect index to obtain the corrected expansion effect index, and using the corrected expansion effect index as the new expansion effect index, using the second correction formula to correct the fusion effect index to obtain the corrected fusion effect index, and using the corrected fusion effect index as the new fusion effect index. Among them, the first correction formula is formula (3), and the second correction formula is formula (5).

[0112] In S6, based on the average citation chain length of each third node, a sustainability index that can reflect the value of the document to be evaluated is calculated, specifically including: calculating the average value of the average citation chain length of each third node, and calculating the ratio of the average citation chain length of the document to be evaluated to the average value, to obtain the overall sustainability index of the document to be evaluated; calculating the trend index of the document to be evaluated based on the average citation chain length of the document to be evaluated in each year in a preset time period, the preset time period being the time period from the publication date of the document to be evaluated to the evaluation date of the document to be evaluated; based on the overall sustainability index and the trend index, calculating the sustainability index that can reflect the value of the document to be evaluated.

[0113] This embodiment provides a document value assessment method based on citation relationship mutation, which aims to anchor the document value and discover the core driving force of scientific and technological development. The scientific value of the document is assessed mainly from three aspects: subversion, contribution, and sustainability. Subversion analyzes the knowledge innovation of the document from the perspective of the number of citations. Contribution evaluates the knowledge integration of the document from the perspective of changes in the citation network structure. Sustainability evaluates the depth of influence of the document from the perspective of the length of the citation chain and its changes. Finally, the average of the three results is used as the comprehensive value, so as to objectively evaluate the document value from multiple dimensions and improve the accuracy of the document value.

[0114] Compared with the prior art, the beneficial effects of this embodiment are:

[0115] This embodiment is different from the previous single-dimensional scientific research results value assessment method. From the perspective of subversion, contribution and sustainability, this embodiment comprehensively assesses the impact of the document on the existing knowledge system and citation network structure, and analyzes the sustainability of the above impact, which can achieve a comprehensive assessment of the true value of the document. This embodiment focuses on mutations to assess the value of documents. Different from the previous incremental scientific research results assessment method, this embodiment can effectively identify subversive scientific research results. It has a wide range of applications and can be applied to scientific research results management and talent management systems in different scenarios. For example, it helps decision makers identify high-value scientific research results in various fields.

[0116] The embodiment of the present application also provides an application scenario, which applies the above-mentioned document value assessment method. Specifically, the document value assessment method provided by this embodiment can be applied in a document value assessment scenario, which includes a document input link, a value assessment link, and a result display link. The document to be evaluated is determined through the document input link, and the document to be evaluated is evaluated using the value assessment link to obtain the document value assessment result of the document to be evaluated, and the document value assessment result is output through the result display link. The document value assessment method provided by this embodiment belongs to the value assessment link.

[0117] Example 2

[0118] Based on the same inventive concept, the embodiment of the present application also provides a document value assessment system for implementing the document value assessment method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in the document value assessment system embodiment provided below can refer to the limitations of the document value assessment method above, and will not be repeated here.

[0119] like Figure 7 As shown, the embodiment of the present application provides a document value assessment system, including a human-computer interaction module, a database module and a value assessment module. The human-computer interaction module provides the functions of inputting document information and outputting assessment results. The database module is used to store document information in all fields. The value assessment module is the core of the system. The functions of each module are as follows:

[0120] The human-computer interaction module is used to obtain the basic information of the document to be evaluated input by the user, and output the document value evaluation results of the document to be evaluated to the user. Among them, the user can enter one or more of the following basic information, including: document name, digital object unique identifier (DOI number), publication year, China Library Classification Number, WoS subject classification name, author name, any keyword, abstract and full text excerpt. According to the basic information of the document to be evaluated input, the human-computer interaction module will match the corresponding documents and display the matching results. According to the matching results, the user can select the document to be evaluated that needs to be analyzed.

[0121] In this embodiment, for the document A to be evaluated, the user can enter only the name or publication date of the document A to be evaluated, or can enter both the name and publication date of the document A to be evaluated. The more accurate the basic information entered by the user, the more accurate the matching result. The system will match the documents in the database module based on the input basic information, and display the matching results through the human-computer interaction module. The user can choose to display the matching results according to the document relevance or the publication date of the document, and select the document to be evaluated that needs to be analyzed based on the matching results.

[0122] The database module is used to store the basic information of multiple documents and provide underlying data support. It uses the WoS database and the China National Knowledge Infrastructure database as data sources to store the basic information and citation information of the documents. The basic information includes the document name, DOI number, publication year, China Library Classification Number, WoS subject classification name, author name, keywords, abstract and full text. The citation information includes the number of citations of the document over the years, the cited document information (i.e. the documents that cite the document) and the reference information (i.e. the documents cited by the document).

[0123] In this embodiment, for the document A to be evaluated, after receiving the document information transmitted by the human-computer interaction module, the database module will transmit the publication year and month, China Library Classification Number / WoS Subject Classification Name, the number of citations over the years, the cited document information and the reference information of the document A to be evaluated to the value assessment module to provide data support for further value assessment.

[0124] The value assessment module is used to execute the document value assessment method described in Example 1 to assess the document to be assessed and obtain the document value assessment result of the document to be assessed. The value assessment module is the core part of this system and is used to systematically assess the value of the document. Specifically, according to the document to be assessed input by the human-computer interaction module, the basic information data such as the publication year and month and the China Library Classification Number of the database module, as well as the citation information data, are matched and retrieved to comprehensively evaluate the true value of the document to social development from the three aspects of subversion, contribution and sustainability.

[0125] In this embodiment, for the document A to be evaluated, after receiving the document information transmitted by the human-computer interaction module and the database module, the value evaluation module will sequentially evaluate the disruptive index, contribution index and sustainability index of the document A to be evaluated. On this basis, the comprehensive value index of the document A to be evaluated is calculated to obtain the document value evaluation result, and then the document value evaluation result of the document A to be evaluated is displayed to the user through the human-computer interaction module.

[0126] Example 3

[0127] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store document data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for evaluating the value of a document is implemented.

[0128] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0129] In an exemplary embodiment, a computer device is also provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the document value assessment method described in Example 1.

[0130] Example 4

[0131] An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the document value assessment method described in Embodiment 1 is implemented.

[0132] Example 5

[0133] An embodiment of the present application provides a computer program product, including a computer program, which implements the document value assessment method described in Example 1 when executed by a processor.

[0134] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0135] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0136] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0137] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0138] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for evaluating the value of a document, characterized in that: The document value assessment method includes: Based on the citation relationship between the document to be evaluated, all first documents and all second documents, a disruptive index that can reflect the value of the document to be evaluated is calculated; the first document is a document that cites the document to be evaluated and belongs to the same field as the document to be evaluated; the second document is a document that is cited by the document to be evaluated and belongs to the same field as the document to be evaluated; Based on the citation relationship between all third documents, each of the third documents is taken as a first node, a first undirected connection edge is drawn between two first nodes having a citation relationship, a first undirected citation network is obtained, and a first network diameter of the first undirected citation network and the number of first nodes included in a first maximum connected subgraph are determined; the third document is a document belonging to the same field as the document to be evaluated; Based on the citation relationship between the document to be evaluated and all the third documents, the document to be evaluated and each of the third documents are respectively taken as a second node, a second undirected connection edge is drawn between two second nodes having a citation relationship to obtain a second undirected citation network, and a second network diameter of the second undirected citation network and the number of second nodes included in the second largest connected subgraph are determined; Calculating a contribution index that can reflect the value of the document to be evaluated based on the first network diameter, the first number of nodes, the second network diameter, and the second number of nodes; Based on the citation relationship between the document to be evaluated and all the third documents, the document to be evaluated and each of the third documents are respectively taken as a third node, a directed connection edge is drawn between two third nodes having a citation relationship to obtain a directed citation network, and an average citation chain length of each third node in the directed citation network is determined; the two third nodes connected by the directed connection edge are respectively recorded as a starting point and an end point, and the directed connection edge points from the starting point to the end point, indicating that the starting point cites the end point; Based on the average length of the citation chain of each of the third nodes, calculating a continuity index that can reflect the value of the document to be evaluated; The disruptive index, the contribution index and the sustainability index are comprehensively considered to calculate the document value assessment result of the document to be assessed.

2. The method for evaluating the value of a document according to claim 1, characterized in that: The calculation formula of the disruptive index is: Where DIS is the subversiveness index; n is the number of second documents; r i is the number of first documents that cite the i-th second document; R is the number of first documents.

3. The document value assessment method according to claim 1, characterized in that: Based on the first network diameter, the first number of nodes, the second network diameter, and the second number of nodes, calculating a contribution index that can reflect the value of the document to be evaluated, specifically including: Calculating the ratio of the first network diameter to the second network diameter to obtain a first ratio, and calculating the difference between 1 and the first ratio to obtain the expansion effect index of the document to be evaluated; Calculating the ratio of the first number of nodes to the second number of nodes to obtain a second ratio, and calculating the difference between 1 and the second ratio to obtain the fusion effect index of the document to be evaluated; The product of the expansion effect index and the fusion effect index is calculated to obtain a contribution index that can reflect the value of the document to be evaluated.

4. The method for evaluating the value of a document according to claim 3, characterized in that: Before calculating the product of the expansion effect index and the fusion effect index, the document value assessment method further includes: Determine whether the document to be evaluated belongs to only one field; If not, the expansion effect index is corrected by using the first correction formula to obtain a corrected expansion effect index, and the corrected expansion effect index is used as a new expansion effect index. The fusion effect index is corrected by using the second correction formula to obtain a corrected fusion effect index, and the corrected fusion effect index is used as a new fusion effect index. The first correction formula is: Among them, VAL1 is the modified extension effect index; D1 is the first network diameter; D2 is the second network diameter; m is the total number of fields to which the literature to be evaluated belongs; d i1 is the network diameter of the undirected citation network corresponding to the ith field, excluding the literature to be evaluated; d i2 is the network diameter of the undirected citation network corresponding to the i-th field including the literature to be evaluated; The second correction formula is: Among them, VAL2 is the corrected fusion effect index; N1 is the number of first nodes; N2 is the number of second nodes; m is the total number of fields to which the literature to be evaluated belongs; n i1 is the number of nodes contained in the largest connected subgraph of the undirected citation network corresponding to the i-th field that does not include the literature to be evaluated; n i2 is the number of nodes contained in the largest connected subgraph of the undirected citation network corresponding to the i-th field that includes the literature to be evaluated.

5. The document value assessment method according to claim 1, characterized in that: Based on the average citation chain length of each of the third nodes, a sustainability index that can reflect the value of the document to be evaluated is calculated, specifically including: Calculate the average value of the average citation chain length of each of the third nodes, and calculate the ratio of the average citation chain length of the document to be evaluated to the average value, to obtain the overall persistence index of the document to be evaluated; Calculate the trend index of the document to be evaluated according to the average citation chain length of the document to be evaluated in each year in a preset period; the preset period is the time period from the publication date of the document to be evaluated to the evaluation date of the document to be evaluated; Based on the overall persistence index and the trend index, a persistence index that can reflect the value of the document to be evaluated is calculated.

6. The method for evaluating the value of a document according to claim 5, characterized in that: The calculation formula of the trend index is: Among them, Tr A is the trend index of the literature to be evaluated, A is the literature to be evaluated; Y Ar The number of years added to the average citation chain length of the literature to be evaluated; Y A is the number of years included in the preset period; AR The number of years in which the average citation chain length of the literature to be evaluated increased significantly. Whether the increase was significant was determined by the Mann-Kendall mutation test; The calculation formula of the persistence index is: Among them, CON is the persistence index; CON' A is the overall persistence index of the literature to be evaluated.

7. A document value assessment system, characterized in that: The document value assessment system comprises: The human-computer interaction module is used to obtain the basic information of the document to be evaluated input by the user, and output the document value evaluation result of the document to be evaluated to the user; The value assessment module is used to execute the document value assessment method described in any one of claims 1 to 6 to evaluate the document to be evaluated and obtain a document value assessment result of the document to be evaluated.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the document value assessment method described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the document value assessment method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the document value assessment method described in any one of claims 1 to 6 is implemented.

Images