A method for obtaining a field correlation degree based on a scientific knowledge graph and related equipment

Abstract

This invention discloses a method and related equipment for obtaining domain relevance based on a science and technology knowledge graph. The method includes: obtaining a target knowledge graph; obtaining a target node, where the target node is a domain node to be queried in the target knowledge graph; removing a first node and a second node from the target knowledge graph to obtain a first association graph; removing a third node and a fourth node from the first association graph to obtain a target association graph; obtaining a target relevance degree, where the target relevance degree is the relevance between a fifth node and the target node; and sorting the fifth node based on the magnitude of the target relevance degree to obtain a target relevance degree table. The domain relevance acquisition method based on a science and technology knowledge graph provided by this invention can calculate the relevance between different domains, which helps to explore the direction of technological development, promotes the integration of technologies in multiple fields, and thus improves the quality and efficiency of technology transfer and industry-university-research cooperation.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and related equipment for obtaining domain relevance based on a science and technology knowledge graph. Background Technology

[0002] In existing technologies, technology services based on knowledge graphs often only analyze a single technology field, ignoring the connections between fields and the connections between experts in different fields. The utilization rate of knowledge graph information is low, and it often only provides queries for specific nodes or specific relationships. Potential relationships between different nodes are often ignored, resulting in limited practical application scenarios.

[0003] Therefore, existing technologies still need to be improved and enhanced. Summary of the Invention

[0004] To address the aforementioned shortcomings of existing technologies, this paper provides a method and related equipment for obtaining domain relevance based on a science and technology knowledge graph. This aims to solve the problem that existing methods for evaluating science and technology talents often only provide queries for specific nodes or relationships, and cannot obtain the relevance between different technical fields.

[0005] A first aspect of the present invention provides a method for obtaining domain relevance based on a science and technology knowledge graph, comprising:

[0006] Obtain a target knowledge graph, which includes the co-authorship relationships of scientific and technological talents in multiple fields and the corresponding relationships of their scientific and technological achievements;

[0007] Obtain the target node, which is the domain node to be queried in the target knowledge graph;

[0008] Remove the first node and the second node from the target knowledge graph to obtain a first association graph. The first node is a domain node whose number of paths with the target node satisfies a first condition, and the second node is an intermediate node between the target node and the first node.

[0009] Remove the third and fourth nodes from the first association graph to obtain the target association graph. The third node is a domain node in the first association graph whose talent association with the target node satisfies the second condition. The fourth node is an intermediate node between the target node and the third node.

[0010] Obtain the target correlation degree, which is the correlation degree between the fifth node and the target node. Sort the fifth node based on the magnitude of the target correlation degree to obtain a target correlation degree table, wherein the fifth node is a domain node in the target correlation graph other than the target node.

[0011] The method for obtaining domain relevance based on scientific and technological knowledge graphs, wherein the target information includes first information, second information and third information, wherein the first condition is that the number of common paths between the target node and the first node is less than or equal to half the number of relationships of the target node itself.

[0012] The method for obtaining domain relevance based on science and technology knowledge graphs, wherein the second condition is that the talent domain relevance between the target node and the third node is less than or equal to one-quarter of the number of talent cooperation relationships between the target node and the third node.

[0013] The method for obtaining domain relevance based on scientific and technological knowledge graphs, wherein obtaining the target relevance includes:

[0014] Based on the first association graph, obtain the target talent field association degree between the target node and the fifth node;

[0015] Based on the target association graph, obtain the correlation degree between the target node and the fifth node in the target domain;

[0016] The target relevance is obtained based on the relevance of the target talent and the relevance of the target field achievements.

[0017] The method for obtaining domain relevance based on a science and technology knowledge graph, characterized in that obtaining the domain relevance between the target node and the fifth node based on the first relevance graph includes:

[0018] Obtain the first weight and the second weight corresponding to the target talent node. The target talent node is a talent intermediary node that has a cooperative relationship with the talent node associated with the fifth node among the talent intermediary nodes associated with the target node in the first association graph. The first weight is the talent domain weight of the target talent node in the field corresponding to the target node, and the second weight is the talent domain weight of the talent intermediary node that has a cooperative relationship with the target talent node in the field corresponding to the fifth node.

[0019] The relevance of the target talent field is obtained based on the first weight and the second weight.

[0020] The method for obtaining domain relevance based on a science and technology knowledge graph, wherein obtaining the relevance between the target node and the fifth node in the target domain based on the target relevance graph includes:

[0021] Obtain the number of first scientific and technological achievements, the number of second scientific and technological achievements, and the number of third scientific and technological achievements, wherein the number of first scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements associated with the target node in the target association graph, the number of second scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements associated with the fifth node in the target association graph, and the number of third scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements in the path between the target node and the fifth node in the target association graph;

[0022] The correlation degree of the achievements in the target field is obtained based on the number of the first scientific and technological achievements, the number of the second scientific and technological achievements, and the number of the third scientific and technological achievements.

[0023] The method for obtaining domain relevance based on science and technology knowledge graphs, wherein obtaining the target relevance based on the target talent relevance and the target domain achievement relevance includes:

[0024] The relevance of the target talent is calculated according to the first formula;

[0025] The first formula is:

[0026]

[0027] Where Score(A,B) represents the relevance of the target talent, and R... AB Q represents the relevance of the target talent; AB n represents the relevance of the results in the target domain. c The number of talent cooperation relationships between the target node and the fifth node; α and β are the correlation weights, where α+β=1, α>β.

[0028] A second aspect of the present invention provides a domain relevance acquisition device based on a science and technology knowledge graph, comprising:

[0029] The graph acquisition module is used to acquire a target knowledge graph, which includes the co-authorship relationships of scientific and technological talents in multiple fields and the corresponding relationships of their scientific and technological achievements.

[0030] A node acquisition module is used to acquire target nodes, which are domain nodes to be queried in the target knowledge graph.

[0031] The first elimination module is used to eliminate the first node and the second node in the target knowledge graph to obtain a first association graph. The first node is a domain node whose number of paths with the target node satisfies a first condition, and the second node is an intermediate node between the target node and the first node.

[0032] The second elimination module is used to eliminate the third node and the fourth node in the first association graph to obtain the target association graph. The third node is a domain node in the first association graph whose talent association degree with the target node meets the second condition. The fourth node is an intermediate node between the target node and the third node.

[0033] The sorting module is used to obtain the target relevance, which is the relevance between the fifth node and the target node. The fifth node is sorted based on the target relevance to obtain a target relevance table. The fifth node is a domain node in the target relevance graph other than the target node.

[0034] A third aspect of the present invention provides a terminal, the terminal including a processor and a computer-readable storage medium communicatively connected to the processor, the computer-readable storage medium being adapted to store a plurality of instructions, the processor being adapted to invoke the instructions in the computer-readable storage medium to execute the steps of the domain relevance acquisition method based on scientific and technological knowledge graph as described in any of the preceding claims.

[0035] In a fourth aspect, the present invention provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the domain relevance acquisition method based on scientific and technological knowledge graphs as described in any of the preceding claims.

[0036] Beneficial Effects: Compared with existing technologies, this invention provides a method and related equipment for obtaining domain relevance based on a scientific and technological knowledge graph. The method involves acquiring a target knowledge graph, which includes co-authorship relationships between scientific and technological personnel in multiple fields and their corresponding scientific and technological achievements. Then, the target node to be queried is determined. Next, the first and second nodes in the target knowledge graph are removed to obtain a first association graph. The first node is a domain node whose path number with the target node satisfies a first condition, and the second node is an intermediate node between the target node and the first node. The third and fourth nodes in the first association graph are removed to obtain a target association graph. The third node is a domain node in the first association graph whose talent relevance with the target node satisfies a second condition, and the fourth node is an intermediate node between the target node and the third node. Finally, the target relevance is obtained, which is the relevance between a fifth node and the target node. The fifth node is sorted based on the magnitude of the target relevance to obtain a target relevance table. The fifth node is a domain node in the target association graph other than the target node. The method for obtaining domain relevance based on scientific and technological knowledge graphs provided by this invention can calculate the relevance between different domains, which helps to explore the direction of technological development, promote the integration of technologies in multiple fields, and thus improve the quality and efficiency of scientific and technological achievements transformation and industry-university-research cooperation. Attached Figure Description

[0037] Figure 1 A flowchart illustrating an embodiment of the domain relevance acquisition method based on scientific and technological knowledge graphs provided by the present invention;

[0038] Figure 2 An example diagram of the knowledge graph in an embodiment of the domain relevance acquisition method based on scientific and technological knowledge graph provided by the present invention;

[0039] Figure 3 A schematic diagram of node filtering in an embodiment of the domain relevance acquisition method based on scientific and technological knowledge graph provided by the present invention;

[0040] Figure 4 A flowchart illustrating the calculation process in an embodiment of the domain relevance acquisition method based on scientific and technological knowledge graphs provided by the present invention;

[0041] Figure 5 A schematic diagram of an embodiment of the domain relevance acquisition device based on scientific and technological knowledge graph provided by the present invention;

[0042] Figure 6 A schematic diagram of the structure of an embodiment of the terminal provided by the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0044] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0045] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0046] The present invention provides a method for obtaining domain relevance based on scientific and technological knowledge graphs, which can be applied to terminals with computing capabilities. The terminal can execute the method for obtaining domain relevance based on scientific and technological knowledge graphs provided by the present invention to obtain a relevance table of the target domain, so as to obtain a domain ranking table associated with the target domain.

[0047] Example 1

[0048] This embodiment provides a method for obtaining domain relevance based on a science and technology knowledge graph. For example... Figure 1 As shown, the method for obtaining domain relevance based on scientific and technological knowledge graphs provided by this invention includes the following steps:

[0049] S100. Obtain the target knowledge graph, which includes the co-authorship relationships of scientific and technological talents in multiple fields and the corresponding relationships of their scientific and technological achievements.

[0050] Specifically, the target knowledge graph includes nodes in multiple different fields and their sub-fields. Each field is associated with scientific and technological talents and scientific and technological achievements. Scientific and technological talents are also associated with each other through co-authorship relationships and their scientific and technological achievements.

[0051] Reference Figure 2 , Figure 2 This is a small example selected from the target knowledge graph, taking Electronic Information (IT) and Biotechnology (BT) as examples. The IT and BT fields can be subdivided into many specific research or technical fields. Different scientific and technological talents belong to different research fields, and these talents may have collaborative relationships within the same field (talent D and talent E) or across fields (talent B and talent C). Furthermore, scientific and technological achievements and talents have publication or invention relationships (the author of achievement A is talent B), and scientific and technological achievements may also involve multiple fields. It can be seen that the target knowledge graph constructed in this way includes the co-authorship relationships of scientific and technological talents in multiple fields and the corresponding relationships of their scientific and technological achievements, which can fully express the interrelationships between talents and scientific and technological achievements in various fields.

[0052] Specifically, knowledge graphs are a knowledge management technology with great application prospects. Currently, some platforms have launched technology services based on scientific and technological knowledge graphs to explore the combined application of knowledge graphs and technology services. However, research on the application type of calculating and querying the correlation between different technical fields is almost non-existent.

[0053] Existing technology services based on knowledge graphs utilize natural language processing (NLP) to understand the semantics and context of queries, transforming natural language queries into graph-specific query statements. Leveraging the technological advantages of knowledge graphs for information retrieval and querying, they improve query speed and accuracy compared to traditional database-based search engine systems. However, they have a low utilization rate of graph information, often only enabling queries for specific nodes or relationships, and struggle to calculate and query the relationships between nodes of the same type, thus limiting their practical application scenarios.

[0054] The technology knowledge graph provided in this embodiment organically integrates knowledge from multiple fields, including relationships between domain technologies, the relationship between research personnel and achievements and the technology field, and the collaborative relationships between research personnel. Based on this, the calculation of the correlation between different fields helps to explore the direction of technological development, promote the integration of technologies across multiple fields, and thus improve the quality and efficiency of technology transfer and industry-academia-research cooperation. By constructing connections between different technology fields and introducing collaborative relationships between scientific and technological personnel from different fields, connections between different fields are built.

[0055] S200. Obtain the target node, which is the domain node to be queried in the target knowledge graph.

[0056] The target node is the domain node in the target knowledge graph corresponding to the target domain to be queried in this embodiment. When a user needs to query the correlation between a target domain and other domains, they can enter keywords of the target domain to be directed to the target node, and then perform subsequent query calculation steps based on the target node.

[0057] S300. Remove the first node and the second node from the target knowledge graph to obtain a first association graph. The first node is a domain node whose number of paths with the target node satisfies a first condition, and the second node is an intermediate node between the target node and the first node.

[0058] The first condition is that the number of common paths between the target node and the first node is less than or equal to half the number of relationships between the target node itself.

[0059] Specifically, after obtaining the target knowledge graph and the target node, path filtering is first performed on the target knowledge graph. In the path filtering stage, the path search method of the graph is used to quickly find the relationship paths between the query nodes, and the number of paths is calculated. The number of paths is then the total number of common relationships between two different nodes, filtering out a first candidate set that has a certain degree of relevance to the target domain corresponding to the target node.

[0060] First, if there are no common relationships between two domains, the correlation between the two domains can be approximated as 0. Second, if the number of common relationships between two nodes is very small, the correlation between the two domains can be considered low, and the corresponding nodes can be removed so that they are not within the scope of the query set.

[0061] Specifically, the first node and the second node in the target knowledge graph are obtained, wherein the first node is a domain node whose number of paths with the target node satisfies a first condition, and the second node is an intermediate node between the target node and the first node. The first condition is that the number of common paths between the target node and the first node is less than or equal to half the number of relationships of the target node itself. The first node and the second node are then removed from the target knowledge graph to obtain the first association graph.

[0062] Specifically, refer to Figure 3Let `self` be the number of self-relations of the target node, and `U` be the number of common paths with the node to be calculated. Considering that `self` and `U` are different for different nodes, we take `U > self / 2` as the filtering condition. In this embodiment, the first condition is that the number of common paths between the target node and the first node is less than or equal to half the number of self-relations of the target node. That is, when `U ≤ self / 2`, it is equivalent to satisfying the first condition. Figure 3 As shown, assuming the target node has 3 neighbor nodes, its own relationships are 3, and the number of common paths between the target and its associated domain nodes is 2, satisfying the filtering condition. However, the number of common paths between non-associated nodes is 1, meaning the filtering condition is not satisfied. It is easy to see that... Figure 3 In this context, the non-associated node is the first node, and the intermediate node 3 is the second node. This reduces the number of query entities to be calculated through path search filtering, thereby improving computational efficiency.

[0063] S400. Remove the third node and the fourth node from the first association graph to obtain the target association graph. The third node is a domain node in the first association graph whose talent association degree with the target node satisfies the second condition. The fourth node is an intermediate node between the target node and the third node.

[0064] The second condition is that the talent field relevance between the target node and the third node is less than or equal to one-quarter of the number of talent cooperation relationships between the target node and the third node.

[0065] Specifically, to avoid differences in talent relevance between the target domain and the candidate related domains due to varying numbers of talent collaboration relationships, this embodiment sets a dynamic threshold to filter the candidate set of related domains. Specifically, the talent relevance between the target domain and the domains in the first candidate set is calculated, and the query candidate set is further filtered to obtain the target candidate set.

[0066] Specifically, the third node and the fourth node are obtained in the first association graph. The third node is a domain node in the first association graph whose talent association with the target node satisfies the second condition. The fourth node is an intermediate node between the target node and the third node.

[0067] Assuming the number of talent collaboration relationships between the two fields is nc, then a threshold is set. If the talent domain correlation between the target domain and the domain in the first candidate set is less than a corresponding threshold, it is removed from the candidate set obtained in step one, further narrowing the scope of the candidate set for related domains. In this embodiment, the second condition is that the talent domain correlation between the target node and the third node is less than or equal to one-quarter of the number of talent cooperation relationships between the target node and the third node. That is, when the talent domain correlation between the target node and the third node is less than or equal to the set threshold T... d (n c When the condition is met, the second condition is satisfied. At this time, the third node that satisfies the second condition and its corresponding fourth node are removed to obtain the target association graph.

[0068] S500. Obtain the target correlation degree, which is the correlation degree between the fifth node and the target node. Sort the fifth node based on the magnitude of the target correlation degree to obtain a target correlation degree table, wherein the fifth node is a domain node in the target correlation graph other than the target node.

[0069] The acquisition of target relevance includes:

[0070] S510. Based on the first association graph, obtain the correlation degree between the target node and the fifth node in the target talent field.

[0071] The step of obtaining the target talent domain relevance between the target node and the fifth node based on the first association graph includes:

[0072] Obtain the first weight and the second weight corresponding to the target talent node. The target talent node is a talent intermediary node that has a cooperative relationship with the talent node associated with the fifth node among the talent intermediary nodes associated with the target node in the first association graph. The first weight is the talent domain weight of the target talent node in the field corresponding to the target node, and the second weight is the talent domain weight of the talent intermediary node that has a cooperative relationship with the target talent node in the field corresponding to the fifth node.

[0073] The relevance of the target talent field is obtained based on the first weight and the second weight.

[0074] Specifically, since the same talent may belong to two or more fields simultaneously, this embodiment establishes the concept of talent field weight to represent the talent's level of ability in a certain technical field. The calculation method for field talent relevance is as follows:

[0075] Assume that the target talent T has a total of N scientific and technological achievements. TLet p be the set of scientific and technological achievements belonging to the domain G corresponding to the target node. i Let p be an element of the set of scientific and technological achievements. i They may belong to multiple fields, p i The number of fields is n pi Then the scientific and technological achievements p i The weight of a property belonging to the domain G is 1 / n pi .

[0076] In this embodiment, the domain weight w corresponding to the target talent node is... TG for:

[0077]

[0078] Based on this, in this embodiment, the domain talent correlation degree between the target domain A and the related domain B is:

[0079]

[0080] In this embodiment, the first weight is The second weight is P A The set of talents that have a cooperative relationship with the target domain A corresponding to the target node and the associated domain B corresponding to the fifth node; T i For P A The i-th talent node in the middle; For T i A set of talents with cooperative relationships within the associated domain B corresponding to the fifth node; T j for The j-th talent node.

[0081] S520. Based on the target association graph, obtain the correlation degree between the target node and the target domain results of the fifth node.

[0082] The step of obtaining the correlation degree between the target node and the fifth node in the target domain based on the target association graph includes:

[0083] Obtain the number of first scientific and technological achievements, the number of second scientific and technological achievements, and the number of third scientific and technological achievements, wherein the number of first scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements associated with the target node in the target association graph, the number of second scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements associated with the fifth node in the target association graph, and the number of third scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements in the path between the target node and the fifth node in the target association graph;

[0084] The correlation degree of the achievements in the target field is obtained based on the number of the first scientific and technological achievements, the number of the second scientific and technological achievements, and the number of the third scientific and technological achievements.

[0085] Specifically, it is assumed that there are N scientific and technological achievements in the target domain A corresponding to the target node. A The number of the first scientific and technological achievements is N. A In the target candidate set, the associated field B corresponding to the fifth node has a total of N scientific and technological achievements. B The number of the second scientific and technological achievements is N. B N scientific and technological achievements are simultaneously related to both domain A and domain B. AB The number of the third scientific and technological achievements is N. AB Then the correlation between the results of domain A and domain B is:

[0086]

[0087] S530. Obtain the target relevance based on the target talent relevance and the target field achievement relevance.

[0088] The process of obtaining the target relevance based on the target talent relevance and the target field achievement relevance includes:

[0089] The relevance of the target talent is calculated according to the first formula;

[0090] The first formula is:

[0091]

[0092] Where Score(A,B) represents the relevance of the target talent, and R... AB Q represents the relevance of the target talent; AB n represents the relevance of the results in the target domain. c The number of talent cooperation relationships between the target node and the fifth node; α and β are the correlation weights, where α+β=1, α>β.

[0093] Reference Figure 4 , Figure 4 This is a flowchart of the overall process for domain-related queries. Through this process, it can be seen that the relevance of the target talent determines the size of the target candidate set and should have a larger weight in calculating the total relevance score. The relevance of the domain results only affects the total relevance score of the query candidate set. Let the relevance weights be α and β (where α + β = 1, α > β), then the formula for calculating the total relevance between domain A and domain B is:

[0094]

[0095] After multiple experimental verifications and corrections, it was ensured that the domain relevance score Score(A, B) ∈ [0, 1]. The total relevance score between the target domain and each domain in the target candidate set was calculated to obtain the relevance score between the target node and each of the fifth nodes. The fifth nodes were sorted based on the magnitude of the relevance score, and the associated domains corresponding to the fifth nodes and their relevance scores were arranged in descending order in the output table to obtain the target relevance score table. The fifth node is a domain node in the target relevance graph other than the target node.

[0096] Specifically, a maximum of 50 related domains corresponding to the fifth node are listed in the target correlation table. This allows us to obtain a correlation table showing the potential relationships between the target domain and different domains.

[0097] It is easy to see that this embodiment is based on the established domain connections and talent connections to realize the query of domain-related information, calculate the degree of correlation between different domains with potential connections, and provide a reference for cross-domain integration and development, transformation and application of scientific and technological achievements.

[0098] Specifically, in this embodiment, based on knowledge graph technology, and addressing the problem that current knowledge graph-based technology service applications are limited in type and neglect potential connections between different technology fields, a method for obtaining domain relevance based on technology knowledge graphs is designed. This method allows for the calculation of relevance between different fields, further enabling the querying of domain-related information. (Refer to...) Figure 4 In this embodiment, the specific process of the domain relevance acquisition method based on scientific and technological knowledge graph can be divided into four steps: 1) Path filtering: Limiting the number of public relations of nodes to eliminate nodes with low relevance, narrowing the scope of domain relevance calculation, and obtaining the first candidate set. 2) Domain talent relevance calculation: Calculating domain talent relevance based on talent domain weight and cross-domain cooperation relationship, while further narrowing the calculation scope, to obtain the target candidate set. 3) Domain achievement relevance calculation: Calculating domain achievement relevance based on the subordinate relationship between scientific and technological achievements and technical fields. 4) Total domain relevance calculation: Assigning weights to the domain talent relevance and achievement relevance obtained in steps 2) and 3) and calculating the total domain relevance.

[0099] Based on this, new application scenarios are provided on the basis of existing science and technology services. By introducing cross-domain scientific and technological achievements and author cooperation relationships, conditions are created for discovering the correlation between different fields. This solves the limitation of existing science and technology services that only target a single field and provides new reference information for the expansion of technical routes.

[0100] In summary, this embodiment provides a method for obtaining domain relevance based on a science and technology knowledge graph. It involves acquiring a target knowledge graph, which includes co-authorship relationships between scientific and technological personnel in multiple fields and their corresponding scientific and technological achievements. Then, the target node to be queried is determined. Next, the first and second nodes in the target knowledge graph are removed to obtain a first association graph. The first node is a domain node whose path number with the target node satisfies a first condition, and the second node is an intermediate node between the target node and the first node. The third and fourth nodes in the first association graph are then removed to obtain a target association graph. The third node is a domain node in the first association graph whose talent relevance with the target node satisfies a second condition, and the fourth node is an intermediate node between the target node and the third node. Finally, the target relevance is obtained, which is the relevance between a fifth node and the target node. The fifth node is sorted based on the magnitude of the target relevance to obtain a target relevance table. The fifth node is a domain node in the target association graph other than the target node. The domain relevance acquisition method based on scientific and technological knowledge graphs provided in this embodiment can calculate the relevance between different domains, which helps to explore the direction of technological development, promote the integration of technologies in multiple fields, and thus improve the quality and efficiency of scientific and technological achievements transformation and industry-university-research cooperation.

[0101] It should be understood that although the steps in the flowcharts shown in the accompanying drawings are displayed sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of the steps in this invention, and these steps can be executed in other orders. Moreover, at least a portion of the steps in this invention may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0102] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0103] Example 2

[0104] Based on the above embodiments, the present invention also provides a domain relevance acquisition device based on a science and technology knowledge graph, the functional module diagram of which is shown below. Figure 5 As shown, the domain relevance acquisition device based on science and technology knowledge graph includes:

[0105] The knowledge graph acquisition module is used to acquire a target knowledge graph, which includes the co-authorship relationships of scientific and technological talents in multiple fields and the corresponding relationships of their scientific and technological achievements, as described in Embodiment 1.

[0106] A node acquisition module is used to acquire target nodes, which are domain nodes to be queried in the target knowledge graph, as specifically described in Embodiment 1;

[0107] The first elimination module is used to eliminate the first node and the second node in the target knowledge graph to obtain a first association graph. The first node is a domain node whose number of paths with the target node satisfies a first condition, and the second node is an intermediate node between the target node and the first node, as specifically described in Embodiment 1.

[0108] The second elimination module is used to eliminate the third node and the fourth node in the first association graph to obtain the target association graph. The third node is a domain node in the first association graph whose talent association degree with the target node meets the second condition. The fourth node is an intermediate node between the target node and the third node, as specifically described in Embodiment 1.

[0109] The sorting module is used to obtain the target relevance, which is the relevance between the fifth node and the target node. The fifth node is sorted based on the target relevance to obtain a target relevance table. The fifth node is a domain node in the target association graph other than the target node, as described in Embodiment 1.

[0110] Example 3

[0111] Based on the above embodiments, the present invention also provides a terminal, such as... Figure 6 As shown, the terminal includes a processor 10 and a memory 20. Figure 6 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0112] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Further, the memory 20 may include both internal and external storage devices. The memory 20 is used to store application software and various types of data installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a domain relevance acquisition program 30 based on a science and technology knowledge graph, which can be executed by the processor 10 to implement the domain relevance acquisition method based on a science and technology knowledge graph in this application.

[0113] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other chip, used to run program code stored in the memory 20 or process data, such as executing the domain relevance acquisition method based on the science and technology knowledge graph.

[0114] In one embodiment, when the processor 10 executes the domain relevance acquisition program 30 based on the science and technology knowledge graph in the memory 20, the following steps are performed:

[0115] Obtain a target knowledge graph, which includes the co-authorship relationships of scientific and technological talents in multiple fields and the corresponding relationships of their scientific and technological achievements;

[0116] Obtain the target node, which is the domain node to be queried in the target knowledge graph;

[0117] Remove the first node and the second node from the target knowledge graph to obtain a first association graph. The first node is a domain node whose number of paths with the target node satisfies a first condition, and the second node is an intermediate node between the target node and the first node.

[0118] Remove the third and fourth nodes from the first association graph to obtain the target association graph. The third node is a domain node in the first association graph whose talent association with the target node satisfies the second condition. The fourth node is an intermediate node between the target node and the third node.

[0119] Obtain the target correlation degree, which is the correlation degree between the fifth node and the target node. Sort the fifth node based on the magnitude of the target correlation degree to obtain a target correlation degree table, wherein the fifth node is a domain node in the target correlation graph other than the target node.

[0120] The target information includes first information, second information, and third information. The first condition is that the number of common paths between the target node and the first node is less than or equal to half the number of relationships between the target node itself.

[0121] The second condition is that the talent field relevance between the target node and the third node is less than or equal to one-quarter of the number of talent cooperation relationships between the target node and the third node.

[0122] The acquisition of target relevance includes:

[0123] Based on the first association graph, obtain the target talent field association degree between the target node and the fifth node;

[0124] Based on the target association graph, obtain the correlation degree between the target node and the fifth node in the target domain;

[0125] The target relevance is obtained based on the relevance of the target talent and the relevance of the target field achievements.

[0126] The feature is that obtaining the target talent field correlation degree between the target node and the fifth node based on the first correlation graph includes:

[0127] Obtain the first weight and the second weight corresponding to the target talent node. The target talent node is a talent intermediary node that has a cooperative relationship with the talent node associated with the fifth node among the talent intermediary nodes associated with the target node in the first association graph. The first weight is the talent domain weight of the target talent node in the field corresponding to the target node, and the second weight is the talent domain weight of the talent intermediary node that has a cooperative relationship with the target talent node in the field corresponding to the fifth node.

[0128] The relevance of the target talent field is obtained based on the first weight and the second weight.

[0129] The step of obtaining the target domain result correlation degree between the target node and the fifth node based on the target association graph includes:

[0130] Obtain the number of first scientific and technological achievements, the number of second scientific and technological achievements, and the number of third scientific and technological achievements, wherein the number of first scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements associated with the target node in the target association graph, the number of second scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements associated with the fifth node in the target association graph, and the number of third scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements in the path between the target node and the fifth node in the target association graph;

[0131] The correlation degree of the achievements in the target field is obtained based on the number of the first scientific and technological achievements, the number of the second scientific and technological achievements, and the number of the third scientific and technological achievements.

[0132] The step of obtaining the target relevance based on the target talent relevance and the target field achievement relevance includes:

[0133] The relevance of the target talent is calculated according to the first formula;

[0134] The first formula is:

[0135]

[0136] Where Score(A,B) represents the relevance of the target talent, and R... AB Q represents the relevance of the target talent; AB n represents the relevance of the results in the target domain. c The number of talent cooperation relationships between the target node and the fifth node; α and β are the correlation weights, where α+β=1, α>β.

[0137] Example 4

[0138] The present invention also provides a storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the domain relevance acquisition method based on scientific and technological knowledge graphs described in the above embodiments.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for obtaining domain relevance based on scientific and technological knowledge graphs, characterized in that, include: Obtain a target knowledge graph, which includes the co-authorship relationships of scientific and technological talents in multiple fields and the corresponding relationships of their scientific and technological achievements; Obtain the target node, which is the domain node to be queried in the target knowledge graph; Remove the first node and the second node from the target knowledge graph to obtain a first association graph. The first node is a domain node whose number of paths with the target node satisfies a first condition, and the second node is an intermediate node between the target node and the first node. Remove the third and fourth nodes from the first association graph to obtain the target association graph. The third node is a domain node in the first association graph whose talent domain association with the target node satisfies the second condition. The fourth node is an intermediate node between the target node and the third node. Obtain the target relevance, which is the relevance between the fifth node and the target node. Sort the fifth nodes based on the target relevance to obtain a target relevance table, wherein the fifth node is a domain node in the target relevance graph other than the target node. The first condition is that the number of common paths between the target node and the first node is less than or equal to half the number of relationships between the target node itself; The second condition is that the talent field relevance between the target node and the third node is less than or equal to one-quarter of the number of talent cooperation relationships between the target node and the third node; The acquisition of target relevance includes: Based on the first association graph, obtain the target talent field association degree between the target node and the fifth node; Based on the target association graph, obtain the correlation degree between the target node and the fifth node in the target domain; The target relevance is obtained based on the relevance of the target talent field and the relevance of the target field achievements; The process of obtaining the target relevance based on the relevance of the target talent field and the relevance of the target field achievements includes: The target correlation degree is calculated according to the first formula; The first formula is: in, The target correlation degree, The relevance of the target talent field; The relevance of the results in the target domain; The number of talent cooperation relationships between the target node and the fifth node; α and β The relevance is the proportion, where, α + β =1, α > β .

2. The method for obtaining domain relevance based on scientific and technological knowledge graphs according to claim 1, characterized in that, The step of obtaining the target talent domain relevance between the target node and the fifth node based on the first association graph includes: Obtain the first weight and the second weight corresponding to the target talent node. The target talent node is a talent intermediary node that has a cooperative relationship with the talent node associated with the fifth node among the talent intermediary nodes associated with the target node in the first association graph. The first weight is the talent domain weight of the target talent node in the field corresponding to the target node, and the second weight is the talent domain weight of the talent intermediary node that has a cooperative relationship with the target talent node in the field corresponding to the fifth node. The relevance of the target talent field is obtained based on the first weight and the second weight.

3. The method for obtaining domain relevance based on scientific and technological knowledge graphs according to claim 1, characterized in that, The step of obtaining the correlation degree between the target node and the fifth node in the target domain based on the target association graph includes: Obtain the number of first scientific and technological achievements, the number of second scientific and technological achievements, and the number of third scientific and technological achievements, wherein the number of first scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements associated with the target node in the target association graph, the number of second scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements associated with the fifth node in the target association graph, and the number of third scientific and technological achievements is the number of intermediate nodes of scientific and technological achievements in the path between the target node and the fifth node in the target association graph; The correlation degree of the achievements in the target field is obtained based on the number of the first scientific and technological achievements, the number of the second scientific and technological achievements, and the number of the third scientific and technological achievements.

4. A device for acquiring domain relevance based on a science and technology knowledge graph, characterized in that, The device includes: The graph acquisition module is used to acquire a target knowledge graph, which includes the co-authorship relationships of scientific and technological talents in multiple fields and the corresponding relationships of their scientific and technological achievements. A node acquisition module is used to acquire target nodes, which are domain nodes to be queried in the target knowledge graph. The first elimination module is used to eliminate the first node and the second node in the target knowledge graph to obtain a first association graph. The first node is a domain node whose number of paths with the target node satisfies a first condition, and the second node is an intermediate node between the target node and the first node. The second elimination module is used to eliminate the third node and the fourth node in the first association graph to obtain the target association graph. The third node is a domain node in the first association graph whose talent association degree with the target node meets the second condition. The fourth node is an intermediate node between the target node and the third node. A sorting module is used to obtain the target relevance, which is the relevance between the fifth node and the target node. The fifth node is sorted based on the target relevance to obtain a target relevance table. The fifth node is a domain node in the target relevance graph other than the target node. The first condition is that the number of common paths between the target node and the first node is less than or equal to half the number of relationships between the target node itself; The second condition is that the talent field relevance between the target node and the third node is less than or equal to one-quarter of the number of talent cooperation relationships between the target node and the third node; The acquisition of target relevance includes: Based on the first association graph, obtain the target talent field association degree between the target node and the fifth node; Based on the target association graph, obtain the correlation degree between the target node and the fifth node in the target domain; The target relevance is obtained based on the relevance of the target talent field and the relevance of the target field achievements; The process of obtaining the target relevance based on the relevance of the target talent field and the relevance of the target field achievements includes: The target correlation degree is calculated according to the first formula; The first formula is: in, The target correlation degree, The relevance of the target talent field; The relevance of the results in the target domain; The number of talent cooperation relationships between the target node and the fifth node; α and β The relevance is the proportion, where, α + β =1, α > β .

5. A terminal, characterized in that, The terminal includes: a processor and a computer-readable storage medium communicatively connected to the processor. The computer-readable storage medium is adapted to store multiple instructions, and the processor is adapted to call the instructions in the storage medium to execute the steps of the domain relevance acquisition method based on scientific and technological knowledge graph as described in any one of claims 1-3.

6. A storage medium, characterized in that, The storage medium stores one or more programs, which can be executed by one or more processors to implement the steps of the domain relevance acquisition method based on scientific and technological knowledge graphs as described in any one of claims 1-3.

Images