Achievement Conversion Management Method, System, Device and Medium for High-tech Enterprise Management

Abstract

The present invention discloses a method, system, device and medium for achievement conversion management in high-tech enterprise management. The present invention relates to the technical field of scientific and technological achievement information management. Through event-driven decomposition and hierarchical clustering, the association and coupling of achievement conversion information are completed, and achievement conversion-driven data is formed. Then, the association rules between the achievement conversion-driven data are mined from the achievement conversion-driven data to form achievement conversion association rules for associating the R & D form, project status form and intellectual property form, so as to realize the association and coupling between achievement information forms; a high-tech enterprise identification detection model is constructed, and the high-tech enterprise identification detection model is used to identify and detect the high-tech enterprise identification evidence chain to determine whether the high-tech enterprise identification evidence chain is correct and complete, and the results of the identification detection are used to feedback the event-driven decomposition of achievement conversion information and to improve the high-tech enterprise identification evidence chain.

Description

Technical Field

[0001] The present invention relates to the technical field of scientific and technological achievement information management, and particularly to a method, system, device and medium for achievement conversion management for high-tech enterprise management. Background Art

[0002] With the rapid development of technology and the intensification of market competition, the identification and management of high-tech enterprises have become an important means to promote the innovation ability and core competitiveness of enterprises. The identification of high-tech enterprises (hereinafter referred to as "high-tech enterprises") not only involves the R & D investment, quantity and quality of intellectual property rights of enterprises, but also requires enterprises to have efficient management and application capabilities in the transformation of scientific and technological achievements. However, current enterprises face many challenges in the process of achievement conversion management, especially in the management and coordination of R & D forms, project status forms and intellectual property forms.

[0003] In the existing high-tech enterprise management system, R & D forms, project status forms and intellectual property forms are important components in the enterprise management and high-tech enterprise identification process. The R & D form mainly records the R & D investment of the enterprise, the work content of R & D personnel and the progress of R & D projects; the project status form focuses on the overall progress and phased achievements of the project; the intellectual property form records the intellectual property situation of the enterprise such as patents and trademarks; the R & D form and the project status form are usually managed by the R & D department, while the intellectual property form is responsible for by the legal or intellectual property management department. This departmental segmentation leads to data isolation and makes it difficult to achieve information sharing and collaborative management.

[0004] Although the R & D form and the project status form record R & D activities and project progress, they fail to clearly reflect how these activities are transformed into intellectual property achievements; although the intellectual property form records intellectual property information such as patents, it fails to trace its R & D background and project sources, resulting in the lack of support from R & D activities for the output of intellectual property. In the process of high-tech enterprise identification, enterprises need to provide direct correlation evidence between R & D activities and intellectual property achievements. However, due to the weak coupling relationship between the R & D form, the project status form and the intellectual property form, enterprises often have difficulty in providing a complete evidence chain, which affects the passing rate of high-tech enterprise identification.

[0005] The existing achievement conversion management methods for high-tech enterprises have obvious deficiencies in the coupling relationship of the R & D form, the project status form and the intellectual property form, and it is difficult to form a complete evidence chain to support high-tech enterprise identification. Summary of the Invention

[0006] Based on the problems raised in the above background art, the object of the present invention is to provide a result conversion management method, system, device and medium for high-tech enterprise management. By integrating the relationships among the R & D table, the project status table and the intellectual property table, data sharing, logical association and dynamic management are realized, so as to improve the result conversion efficiency and the success rate of high-tech enterprise recognition, and solve the problem that the existing result conversion management method for high-tech enterprises has obvious deficiencies in the coupling relationship among the R & D table, the project status table and the intellectual property table, and it is difficult to form a complete evidence chain to support high-tech enterprise recognition.

[0007] The present invention is realized through the following technical solutions:

[0008] The first aspect of the present invention provides a result conversion management method for high-tech enterprise management, including the following steps:

[0009] Step S1: Obtain high-tech enterprise recognition materials, extract result conversion information from the high-tech enterprise recognition materials, and generate a result information table; the result information table includes: an R & D table, a project status table and an intellectual property table;

[0010] Step S2: Decompose the result conversion information by event-driven to obtain event-driven data, and perform hierarchical clustering on the event-driven data to obtain result conversion-driven data;

[0011] Step S3: Mine association rules for the result conversion-driven data to generate result conversion association rules, and based on the result conversion association rules, associate the R & D table, the project status table and the intellectual property table to generate a high-tech enterprise recognition evidence chain;

[0012] Step S4: Construct a high-tech enterprise recognition detection model, and use the high-tech enterprise recognition detection model to perform recognition detection on the high-tech enterprise recognition evidence chain to obtain a high-tech enterprise recognition result.

[0013] In the above technical solution, first, obtain high-tech enterprise recognition materials from the high-tech enterprise management module in the enterprise management system. The high-tech enterprise recognition materials are collected by the enterprise management system and include various data such as R & D data, project status materials, intellectual property materials, equipment materials, and high-tech enterprise information. Extract the data related to the result conversion information from the high-tech enterprise recognition materials. This data includes R & D data, project status data and intellectual property data, and form a result information table. The result information table includes an R & D table, a project status table and an intellectual property table.

[0014] Since the R & D form, project status form, and intellectual property form are responsible for by different departments, and their filling specifications, filling formats, and naming methods are not the same. Therefore, in this method, the three forms of R & D form, project status form, and intellectual property form are not directly coupled. Instead, through the extracted result conversion information, event-driven decomposition is carried out. Based on each result conversion information, with the result conversion event as the drive, data association and clustering are carried out in the way of hierarchical clustering, so as to form result conversion-driven data; This result conversion-driven data avoids data distortion caused by the filling formats of each department to the data, and prevents errors caused by data distortion when associating the three forms subsequently.

[0015] Through event-driven decomposition and hierarchical clustering, the association and coupling of result conversion information are completed, and result conversion-driven data is formed. Then, association rules between result conversion-driven data are mined from the result conversion-driven data to form result conversion association rules for associating the R & D form, project status form, and intellectual property form, so as to realize the association and coupling between result information forms.

[0016] Build a high-tech enterprise identification detection model, and use the high-tech enterprise identification detection model to identify and detect the high-tech enterprise identification evidence chain to determine whether the high-tech enterprise identification evidence chain is correct and complete, and use the result of the identification detection to feedback on the event-driven decomposition of result conversion information and improve the high-tech enterprise identification evidence chain.

[0017] In an alternative embodiment, the event-driven decomposition of the result conversion information includes the following steps:

[0018] Step S21: Extract result information fields from the result conversion information, and integrate the extracted result information fields into a result information field set;

[0019] Step S22: Traverse the result information field set, analyze the dependency relationship of the result information field set, and construct a result dependency relationship graph based on the dependency analysis result;

[0020] Step S23: Conduct event-driven analysis on the result dependency relationship graph, and form an event-driven relationship chain according to the result of the event-driven analysis.

[0021] In an alternative embodiment, the dependency relationship analysis of the result information field set and the construction of a result dependency relationship graph based on the dependency analysis result include the following steps:

[0022] Step S221: Extract a result information field from the result information field set as an information node, and calculate the correlation between the information node and other result information fields in the result information field set;

[0023] Step S222: Establish the initial dependency relationship between the information node and other result information fields in the result information field set based on the correlation;

[0024] Step S223: Repeat Step S221 to Step S222 until the traversal of the result information field set is completed, generating an initial result field dependency graph;

[0025] Step S224: Conduct a dependency structure analysis on the initial result field dependency graph, and perform dependency relationship calculation on the initial result field dependency graph according to the results of the dependency structure analysis to obtain a dependency relationship value;

[0026] Step S225: Optimize the dependency relationship of the initial result field dependency graph using the dependency relationship value to obtain a result dependency relationship graph.

[0027] In an alternative embodiment, the calculation process of the dependency relationship calculation is as follows:

[0028] ;

[0029] In the above formula, is the dependency degree between the th result information field and the th result information field; is the field similarity between the th result information field and the th result information field; is the dependency relationship value between the th result information field and the th result information field; is the number of dependency connection channels between the th result information field and the th result information field; is the dependency structure value of the th dependency connection channel; is the number of result information fields on the th dependency connection channel; is the set of result information fields on the th dependency connection channel; is the set of result information fields on the th dependency connection channel.

[0030] In an alternative embodiment, the event-driven analysis of the result dependency relationship graph includes the following steps:

[0031] Step S231: Based on the scientific and technological achievement process, perform node division on the result dependency relationship graph to generate several result dependency relationship subgraphs;

[0032] Step S232: Vectorize a number of achievement dependency sub - graphs to generate a number of vectorized achievement dependency sub - graphs;

[0033] Step S233: Extract features from a number of vectorized achievement dependency sub - graphs to obtain event - driven features;

[0034] Step S234: Use the event - driven features to perform event - driven association on a number of vectorized achievement dependency sub - graphs to form an event - driven relationship chain.

[0035] In an alternative embodiment, hierarchical clustering of the event - driven data includes the following steps:

[0036] Step S24: Calculate the node dependency degree of the event - driven relationship chain, and determine the clustering center from the event - driven relationship chain according to the node dependency degree;

[0037] Step S25: Use the k - nearest neighbor clustering algorithm to perform clustering calculation on the event - driven relationship chain starting from the clustering center, and update the event - driven relationship chain according to the clustering calculation result to obtain an updated event - driven relationship chain;

[0038] Step S26: Analyze the stop - clustering condition for the updated event - driven relationship chain. If the stop - clustering condition is not met, use the updated event - driven relationship chain as the event - driven relationship chain and repeat steps S24 to S26.

[0039] In an alternative embodiment, mining association rules for the achievement conversion - driven data includes the following steps:

[0040] Step S31: Obtain a historical high - tech enterprise certification evidence chain, and establish historical association rules using the historical high - tech enterprise certification evidence chain;

[0041] Step S32: Calculate the frequent values in the achievement conversion - driven data, arrange the achievement conversion - driven data in descending order according to the frequent values to generate a frequent - driven data set;

[0042] Step S33: Select the top N achievement conversion - driven data from the frequent - driven data set to form an association - rule data set;

[0043] Step S34: Perform association - rule matching between the association - rule data set and the historical association rules, and determine the achievement conversion association rules according to the results of the association - rule matching.

[0044] The second aspect of the present invention provides an achievement conversion management system for high - tech enterprise management, including:

[0045] An information extraction module, configured to obtain high-tech enterprise certification materials, extract achievement conversion information from the high-tech enterprise certification materials, and generate an achievement information table; the achievement information table includes: a R & D table, a project status table, and an intellectual property table;

[0046] An event-driven module, configured to perform event-driven decomposition on the achievement conversion information to obtain event-driven data, and perform hierarchical clustering on the event-driven data to obtain achievement conversion-driven data;

[0047] A data association module, configured to perform association rule mining on the achievement conversion-driven data to generate achievement conversion association rules, and based on the achievement conversion association rules, associate the R & D table, the project status table, and the intellectual property table to generate a high-tech enterprise certification evidence chain;

[0048] A certification detection module, configured to construct a high-tech enterprise certification detection model, and use the high-tech enterprise certification detection model to perform certification detection on the high-tech enterprise certification evidence chain to obtain a high-tech enterprise certification result.

[0049] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, it implements an achievement conversion management method for high-tech enterprise management.

[0050] A fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements an achievement conversion management method for high-tech enterprise management.

[0051] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0052] 1. Through event-driven decomposition and hierarchical clustering, the association and coupling of achievement conversion information are completed at the data level;

[0053] 2. Mine the association rules between the achievement conversion-driven data from the achievement conversion-driven data, form achievement conversion association rules for associating the R & D table, the project status table, and the intellectual property table, and complete the association and coupling between the achievement information tables at the table level;

[0054] 3. Use the high-tech enterprise certification detection model to perform certification detection on the high-tech enterprise certification evidence chain to determine whether the high-tech enterprise certification evidence chain is correct and complete, and use the result of the certification detection for double feedback on the event-driven decomposition of the achievement conversion information and the high-tech enterprise certification evidence chain. Through the double feedback mechanism, the improvement of the event-driven decomposition process and the supplementation of the missing evidence in the high-tech enterprise certification evidence chain are realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings. In the drawings:

[0056] Figure 1 It is a schematic flowchart of the result conversion management method for high-tech enterprise management provided in Embodiment 1 of the present invention;

[0057] Figure 2 It is a schematic structural diagram of the result conversion management system for high-tech enterprise management provided in Embodiment 2 of the present invention;

[0058] Figure 3 It is a schematic structural diagram of an electronic device provided in Embodiment 3 of the present invention. Detailed implementation manners

[0059] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in combination with the embodiments and the drawings. The illustrative embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0060] Figure 1 It is a schematic flowchart of the result conversion management method for high-tech enterprise management provided in Embodiment 1 of the present invention, as Figure 1 shown. The result conversion management method for high-tech enterprise management includes the following steps:

[0061] Step S1: Obtain high-tech enterprise certification materials, extract result conversion information from the high-tech enterprise certification materials, and generate a result information table; the result information table includes: a research and development table, a project status table, and an intellectual property table;

[0062] Step S2: Decompose the result conversion information by event-driven to obtain event-driven data, and perform hierarchical clustering on the event-driven data to obtain result conversion-driven data;

[0063] Step S3: Mine association rules for the result conversion-driven data to generate result conversion association rules, and based on the result conversion association rules, associate the research and development table, the project status table, and the intellectual property table to generate a high-tech enterprise certification evidence chain;

[0064] Step S4: Construct a high-tech enterprise certification detection model, and use the high-tech enterprise certification detection model to detect the high-tech enterprise certification evidence chain to obtain a high-tech enterprise certification result.

[0065] It should be noted that in the high-tech enterprise certification process, it is necessary to integrate the data in the R & D form, project status form and intellectual property form to form a complete evidence chain for high-tech enterprise certification. However, in an enterprise, the R & D form, project status form and intellectual property form are respectively responsible for and filled in by different departments. During the integration process, there are often problems such as great difficulty in data alignment and easy data loss, resulting in an incomplete evidence chain for high-tech enterprise certification and making it difficult to form a complete evidence chain to support high-tech enterprise certification.

[0066] Therefore, it is necessary to analyze and couple the relevant data in the R & D form, project status form and intellectual property form in high-tech enterprise management to form a complete evidence chain for high-tech enterprise certification. Therefore, in this method, first, obtain the high-tech enterprise certification materials from the high-tech enterprise management module in the enterprise management system. The high-tech enterprise certification materials are collected by the enterprise management system and include various data such as R & D data, project status materials, intellectual property materials, equipment materials, and high-tech enterprise information. Extract the data related to the achievement transformation information from the high-tech enterprise certification materials. This data includes R & D data, project status data, and intellectual property data, and form an achievement information table. The achievement information table includes the R & D form, project status form, and intellectual property form.

[0067] Since the R & D form, project status form, and intellectual property form are responsible for by different departments, their filling specifications, filling formats, and naming methods are not quite the same. Therefore, in this method, the three forms of the R & D form, project status form, and intellectual property form are not directly coupled, but are decomposed by event-driven through the extracted achievement transformation information. Based on each achievement transformation information, with the achievement transformation event as the driving force, the data is associated and clustered through the method of hierarchical clustering, thus forming achievement transformation-driven data; this achievement transformation-driven data avoids the data distortion caused by the filling formats of each department to the data and prevents the error caused by data distortion when associating the three forms later.

[0068] Through event-driven decomposition and hierarchical clustering, the association and coupling of the achievement transformation information are completed, and achievement transformation-driven data is formed. Then, mine the association rules between the achievement transformation-driven data from the achievement transformation-driven data to form achievement transformation association rules for associating the R & D form, project status form, and intellectual property form, so as to realize the association and coupling between the achievement information tables.

[0069] Construct a high-tech enterprise certification detection model, and use the high-tech enterprise certification detection model to detect the high-tech enterprise certification evidence chain to determine whether the high-tech enterprise certification evidence chain is correct and complete, and use the result of the detection to feedback the event-driven decomposition of the achievement transformation information and improve the high-tech enterprise certification evidence chain.

[0070] In an alternative embodiment, the event-driven decomposition of the achievement transformation information includes the following steps:

[0071] Step S21: Extract the result information fields from the result conversion information, and integrate the extracted result information fields into a set of result information fields;

[0072] Step S22: Traverse the set of result information fields, perform a dependency analysis on the set of result information fields, and construct a result dependency graph based on the dependency analysis results;

[0073] Step S23: Perform an event-driven analysis on the result dependency graph, and form an event-driven relationship chain according to the results of the event-driven analysis.

[0074] In this embodiment, the coupling between data depends to a large extent on the dependency relationship between data. To achieve the coupling of the result conversion information, it is necessary to perform a dependency analysis between its various fields. Therefore, first, extract the result information fields from the result conversion information, and then preliminarily analyze the dependency relationship between the result information fields to form a preliminary result dependency graph. For example: The data generated during the R & D stage includes the name, goal, start and end time, budget, person in charge, etc. of the project. The data generated during the intellectual property stage includes the name, application date, application status, authorization date of the intellectual property. Among them, the goal, start and end time, budget, and person in charge of the project depend on the name of the project, and the application date, application status, and authorization date of the intellectual property depend on the name of the intellectual property. There is also a certain dependency relationship between the project name and the intellectual property name. Therefore, in this embodiment, there is a dependency relationship between the above data, and based on this dependency relationship, a result dependency graph is constructed with data fields as nodes and the dependency relationship between data fields as edges.

[0075] Since there is a sequential and driving relationship among project R & D, project status, and intellectual property, therefore, in this embodiment, it is necessary to consider the event-driven nature of the data, and perform an event-driven analysis on the result dependency graph based on this event-driven nature to form an event-driven relationship chain. This event-driven relationship chain not only includes the surface relationship between data, but also includes the process logic relationship between data during the result conversion process, further overcoming the defect of weak coupling between current data.

[0076] In an alternative embodiment, performing a dependency analysis on the set of result information fields and constructing a result dependency graph based on the dependency analysis results includes the following steps:

[0077] Step S221: Extract a result information field from the set of result information fields as an information node, and calculate the correlation between the information node and other result information fields in the set of result information fields;

[0078] Step S222: establishing an initial dependency relationship between the information node and other achievement information fields in the achievement information field set based on the correlation;

[0079] Step S223, repeating step S221 to step S222 until the traversal of the achievement information field set is completed, and an initial achievement field dependency graph is generated;

[0080] Step S224: performing dependency structure analysis on the initial achievement field dependency graph, and performing dependency relationship calculation on the initial achievement field dependency graph according to the result of the dependency structure analysis to obtain a dependency relationship value;

[0081] Step S225: Utilize the dependency values ​​to perform dependency optimization on the initial achievement field dependency graph to obtain an achievement dependency graph.

[0082] In this embodiment, the dependency between the achievement information fields is preliminarily analyzed through the correlation between the fields. For example, the project's goal, start and end time, budget, and person in charge are dependent on the project's name. Then, the correlation between the project's goal, start and end time, budget, person in charge, and the project's name is increased by 1, indicating that there is a correlation between them. Then, all information nodes whose correlation is not 0 are connected to form an initial achievement field dependency graph.

[0083] It should be emphasized that the initial achievement field dependency graph is directional. Therefore, there are multiple structures in the initial achievement field dependency graph. For example, there is a bidirectional dependency between the project name and the intellectual property name. At this time, the two data are in a close dependency structure; if there is a data loop between the data, then the data are in a closed-loop dependency structure; if data A points to data B, data B points to data C, and data A points to data C, then an open-loop dependency structure is formed between data A, data B, and data C; if data A points to data B, and data B points to data C, then a transitive dependency structure is formed between data A, data B, and data C.

[0084] Therefore, a dependency structure analysis is performed on the initial achievement field dependency graph, and dependency calculation is performed on the initial achievement field dependency graph based on the results of the dependency structure analysis, so as to mine the structural dependencies between data and obtain dependency values. The dependency values ​​are then used to optimize the initial achievement field dependency graph, and the dependencies between data are further mined, thus avoiding the defect of poor data coupling caused by a single dependency.

[0085] In an optional embodiment, the calculation process of the dependency calculation is as follows:

[0086] ;

[0087] In the above formula, For the The dependency degree of the th achievement information field and the th achievement information field; The field similarity between the th achievement information field and the th achievement information field; The dependency relationship value between the th achievement information field and the th achievement information field; The number of dependency connection channels between the th achievement information field and the th achievement information field; The dependency structure value of the th dependency connection channel; The number of achievement information fields on the th dependency connection channel; The set of achievement information fields on the th dependency connection channel; The set of achievement information fields on the

[0088] In this embodiment, the dependency relationship value is mainly composed of two aspects. One is the dependency degree between achievement information fields, and the other is the field similarity between achievement information fields. The higher the dependency degree and field similarity, the higher the dependency relationship value. Then these two achievement information fields have a strong dependency relationship. In the subsequent process of improving the evidence chain, when one achievement information field is needed, the other achievement information field is probably also needed. By calculating the dependency degree and similarity between fields, the dependency relationship between achievement information fields is optimized.

[0089] Among them, the number of dependency connection channels refers to the number of connection relationships between the th achievement information field and the th achievement information field. Let the th achievement information field be data a, and the One achievement information field is data e. From data a to data e, there are three routes: the route from data a to data b to data c to data e, the route from data a to data e, and the route from data a to data c to data e. Then the number of dependent connection channels is 3. The dependent structure value of a dependent connection channel refers to the dependent structure formed by the dependent connection channel. In this embodiment, the dependent structure values of the tight dependent structure and the closed-loop dependent structure are set to 10; the dependent structure values of the open-loop dependent structure and the transitive dependent structure are set to 5. The reason for this setting is that the closed-loop type of structure has a higher degree of dependence compared to the open-loop type of structure. Another aspect of the degree of dependence depends on the number of achievement information fields on the dependent connection channel. The more achievement information fields there are on the dependent connection channel, the greater the degree of dependence, and the smaller the degree of dependence.

[0090] The field similarity is used to measure the similarity degree of the achievement information fields on the dependent connection channel between two achievement information fields, and its value ranges from 0 to 1.

[0091] In an optional embodiment, performing event-driven analysis on the achievement dependency graph includes the following steps:

[0092] Step S231: Based on the scientific and technological achievement process, perform node partitioning on the achievement dependency graph to generate several achievement dependency subgraphs;

[0093] Step S232: Vectorize several achievement dependency subgraphs to generate several vectorized achievement dependency subgraphs;

[0094] Step S233: Extract features from several vectorized achievement dependency subgraphs to obtain event-driven features;

[0095] Step S234: Use the event-driven features to perform event-driven association on several vectorized achievement dependency subgraphs to form an event-driven relationship chain.

[0096] In this embodiment, based on the scientific and technological achievement process, perform node partitioning on the achievement dependency graph. According to the three processes of project development, project status, and intellectual property rights, the nodes of the achievement dependency graph are partitioned into a project development achievement dependency subgraph, a project status achievement dependency subgraph, and an intellectual property rights achievement dependency subgraph. Vectorizing the subgraphs provides a basis for feature learning while retaining the original information.

[0097] Extract features from the vectorized subgraphs, extract features related to achievement transformation, such as the completion time of R & D tasks, changes in project status, application time of intellectual property rights, etc., to form event-driven features, and use the event-driven features as the core to connect other vector data to establish relevant event-driven relationship chains.

[0098] In an alternative embodiment, hierarchical clustering is performed on the event-driven data, including the following steps:

[0099] Step S24: Calculate the node dependency of the event-driven relationship chain, and determine the clustering center from the event-driven relationship chain according to the node dependency;

[0100] Step S25: Use the k-nearest neighbor clustering algorithm to perform clustering calculation on the event-driven relationship chain starting from the clustering center, and update the event-driven relationship chain according to the clustering calculation result to obtain an updated event-driven relationship chain;

[0101] Step S26: Analyze the stop clustering condition for the updated event-driven relationship chain. If the stop clustering condition is not reached, use the updated event-driven relationship chain as the event-driven relationship chain and repeat steps S24 to S26.

[0102] In this embodiment, the selection of the clustering center is not random, but is determined based on the node dependency in the event-driven relationship chain. Through this dynamic center hierarchical clustering method, the feature vectors can be more effectively clustered and analyzed, so as to cluster the relevant data in the high-tech enterprise identification evidence chain.

[0103] In an alternative embodiment, association rule mining is performed on the achievement transformation-driven data, including the following steps:

[0104] Step S31: Obtain the historical high-tech enterprise identification evidence chain, and establish historical association rules using the historical high-tech enterprise identification evidence chain;

[0105] Step S32: Calculate the frequent values in the achievement transformation-driven data, arrange the achievement transformation-driven data from largest to smallest according to the frequent values, and generate a frequent-driven data set;

[0106] Step S33: Select the top N achievement transformation-driven data from the frequent-driven data set to form an association rule data set;

[0107] Step S34: Perform association rule matching between the association rule data set and the historical association rules, and determine the achievement transformation association rules according to the results of the association rule matching.

[0108] In an embodiment, based on the achievement transformation association rules, the R & D table, the project status table, and the intellectual property table are associated, including: extracting the fields related to the achievement transformation-driven data from the R & D table, the project status table, and the intellectual property table, and associating and combining the fields according to the achievement transformation association rules to form a high-tech enterprise identification evidence chain.

[0109] In one embodiment, the high-tech enterprise recognition detection model includes: a time node authentication module, an event node authentication module, and an integrity recognition module. The output channels of the time node authentication module and the event node authentication module are connected to the input channel of the integrity recognition module.

[0110] Using the above high-tech enterprise recognition detection model to recognize and detect the high-tech enterprise recognition evidence chain means performing time node authentication detection, event node authentication detection, and integrity authentication detection on the high-tech enterprise recognition evidence chain. Specifically, the time node authentication detection includes detecting the R & D time, the achievement transformation time, and the time related to intellectual property rights. The detection content includes whether the data is complete and whether there are errors in the sequence of time nodes, so as to ensure the accuracy and integrity of the evidence chain at the time node level. The event node authentication detection includes detecting event data such as the appraisal year, achievement name, project source, appraisal grade, appraisal status, and professional field in the project. The detection content includes whether the event data is complete and whether there is a correlation between the event data. This correlation can be determined through relevant dependency data such as the dependency relationship value between the event data. By performing event node authentication detection on the event data, the accuracy and integrity of the evidence chain at the event node level are ensured. After completing the time node authentication and event node authentication, evidence chain integrity authentication is performed to check the overall integrity of the evidence chain and the correlation between the time node data and the event node data, so as to ensure the overall integrity and correctness of the evidence chain. At this time, when both integrity and correctness are available, the high-tech enterprise recognition evidence chain is output; in the case of lack of integrity or correctness, the output content is the data lacking in the evidence chain.

[0111] The high-tech enterprise recognition result obtained after detection can be used to improve the high-tech enterprise recognition evidence chain and optimize the event-driven decomposition of the achievement transformation information.

[0112] Specifically, improving the high-tech enterprise recognition evidence chain includes supplementing the lacking evidence identified by the high-tech enterprise recognition model or correcting the wrong evidence.

[0113] Specifically, optimizing the event-driven decomposition of the achievement transformation information includes analyzing the lacking information or wrong information identified by the high-tech enterprise recognition model and optimizing the dependency relationship between the achievement information fields according to the analysis results.

[0114] In summary, the results of the recognition detection are used for double feedback on the event-driven decomposition of the achievement transformation information and the high-tech enterprise recognition evidence chain. Through the double feedback mechanism, the improvement of the event-driven decomposition process and the supplementation of the lacking evidence in the high-tech enterprise certification evidence chain are realized.

[0115] Figure 2The structural schematic diagram of the achievement conversion management system for high-tech enterprise management provided in Embodiment 2 of the present invention is as follows Figure 2 As shown, the achievement conversion management system for high-tech enterprise management includes:

[0116] An information extraction module, configured to obtain high-tech enterprise certification materials, extract achievement conversion information from the high-tech enterprise certification materials, and generate an achievement information table; the achievement information table includes: a R & D table, a project status table, and an intellectual property table;

[0117] An event-driven module, configured to perform event-driven decomposition on the achievement conversion information to obtain event-driven data, and perform hierarchical clustering on the event-driven data to obtain achievement conversion-driven data;

[0118] A data association module, configured to perform association rule mining on the achievement conversion-driven data to generate achievement conversion association rules, and associate the R & D table, the project status table, and the intellectual property table based on the achievement conversion association rules to generate a high-tech enterprise certification evidence chain;

[0119] A certification detection module, configured to construct a high-tech enterprise certification detection model, and use the high-tech enterprise certification detection model to perform certification detection on the high-tech enterprise certification evidence chain to obtain a high-tech enterprise certification result.

[0120] Figure 3 The structural schematic diagram of an electronic device provided in Embodiment 3 of the present invention is as follows Figure 3 As shown, the electronic device includes a processor 21, a memory 22, an input device 23, and an output device 24; the number of processors 21 in the computer device may be one or more, Figure 3 Taking one processor 21 as an example; the processor 21, the memory 22, the input device 23, and the output device 24 in the electronic device may be connected through a bus or other means, Figure 3 Taking the connection through a bus as an example.

[0121] The memory 22, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules. The processor 21 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 22, that is, implements the achievement conversion management method for high-tech enterprise management in Embodiment 1.

[0122] The memory 22 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 22 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some instances, the memory 22 may further include a memory remotely provided with respect to the processor 21, and these remote memories may be connected to the electronic device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0123] The input device 23 may be used to receive user input such as an id and a password. The output device 24 is used to output a network configuration page.

[0124] Embodiment 4 of the present invention further provides a computer-readable storage medium, and the computer-executable instructions are used to implement the result conversion management method for high-tech enterprise management provided in Embodiment 1 when executed by a computer processor.

[0125] A storage medium containing computer-executable instructions provided in the embodiments of the present invention, the computer-executable instructions are not limited to the method operations provided in Embodiment 1, and may also execute related operations in the result conversion management method for high-tech enterprise management provided in any embodiment of the present invention.

[0126] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. The achievement conversion management method used in high-tech enterprise management is characterized by: The steps include: Step S1, obtaining high-tech enterprise certification information, extracting achievement conversion information from the high-tech enterprise certification information, and generating an achievement information table; the achievement information table includes: a research and development table, a project status table, and an intellectual property table; Step S2, performing event-driven decomposition on the achievement conversion information to obtain event-driven data, and performing hierarchical clustering on the event-driven data to obtain achievement conversion driven data; Step S3, performing association rule mining on the achievement conversion driving data to generate achievement conversion association rules, and associating the R&D table, the project status table and the intellectual property table based on the achievement conversion association rules to generate a high-tech enterprise identification evidence chain; Step S4: construct a high-tech enterprise identification detection model, and use the high-tech enterprise identification detection model to perform identification detection on the high-tech enterprise identification evidence chain to obtain the high-tech enterprise identification result; The event-driven decomposition of the achievement conversion information includes the following steps: Step S21, extracting achievement information fields from the achievement conversion information, and integrating the extracted achievement information fields into an achievement information field set; Step S22, traversing the achievement information field set, performing dependency analysis on the achievement information field set, and constructing an achievement dependency graph based on the dependency analysis result; Step S23, performing event-driven analysis on the achievement dependency graph, and forming an event-driven relationship chain according to the result of the event-driven analysis; Performing hierarchical clustering on the event-driven data includes the following steps: Step S24, calculating the node dependency of the event-driven relationship chain, and determining a cluster center from the event-driven relationship chain according to the node dependency; Step S25: using a k-nearest neighbor clustering algorithm to perform clustering calculation on the event-driven relationship chain with the cluster center as the starting point, and updating the event-driven relationship chain according to the clustering calculation result to obtain an updated event-driven relationship chain; Step S26: Perform a stop clustering condition analysis on the update event driven relationship chain. If the stop clustering condition is not met, repeat steps S24 to S26 by taking the update event driven relationship chain as the event driven relationship chain.

2. The achievement conversion management method for high-tech enterprise management according to claim 1 is characterized in that: Performing dependency analysis on the achievement information field set and constructing an achievement dependency graph based on the dependency analysis result includes the following steps: Step S221: extracting an achievement information field from the achievement information field set as an information node, and calculating the correlation between the information node and other achievement information fields in the achievement information field set; Step S222: establishing an initial dependency relationship between the information node and other achievement information fields in the achievement information field set based on the correlation; Step S223, repeating step S221 to step S222 until the traversal of the achievement information field set is completed, and an initial achievement field dependency graph is generated; Step S224: performing dependency structure analysis on the initial achievement field dependency graph, and performing dependency relationship calculation on the initial achievement field dependency graph according to the result of the dependency structure analysis to obtain a dependency relationship value; Step S225: Utilize the dependency values ​​to perform dependency optimization on the initial achievement field dependency graph to obtain an achievement dependency graph.

3. The achievement conversion management method for high-tech enterprise management according to claim 2 is characterized in that: The calculation process of the dependency calculation is as follows: ； In the above formula, For the The result information field is the same as the The dependency of each outcome information field; For the The result information field is the same as the The field similarity of the result information fields; For the The result information field is the same as the The dependency value of each achievement information field; For the The result information field is the same as the The number of dependent connection channels between the result information fields; For the The dependency structure value of the dependent connection channel; For the The number of result information fields on the dependent connection channel; For the A set of result information fields on a dependent connection channel; For the A collection of result information fields on a dependent connection channel.

4. The achievement conversion management method for high-tech enterprise management according to claim 1 is characterized in that: Performing event-driven analysis on the achievement dependency graph includes the following steps: Step S231, dividing the achievement dependency graph into nodes based on the scientific and technological achievement process to generate a plurality of achievement dependency subgraphs; Step S232, vectorizing and representing a plurality of achievement dependency subgraphs to generate a plurality of vectorized achievement dependency subgraphs; Step S233, extracting features from a plurality of vectorized result dependency subgraphs to obtain event-driven features; Step S234: utilizing the event-driven feature to perform event-driven association on a plurality of vectorized outcome dependency subgraphs to form an event-driven relationship chain.

5. The achievement conversion management method for high-tech enterprise management according to claim 1 is characterized in that: Performing association rule mining on the achievement conversion driving data includes the following steps: Step S31, obtaining a historical high-tech enterprise identification evidence chain, and using the historical high-tech enterprise identification evidence chain to establish a historical association rule; Step S32, calculating the frequent values ​​in the achievement conversion driving data, arranging the achievement conversion driving data from large to small according to the frequent values, and generating a frequent driving data set; Step S33, selecting the first N achievement conversion driving data from the frequent driving data set to form an association rule data set; Step S34: performing association rule matching on the association rule data set and the historical association rule, and determining the achievement conversion association rule according to the result of the association rule matching.

6. The achievement conversion management system for high-tech enterprise management is characterized by: The achievement conversion management system is used to implement the achievement conversion management method for high-tech enterprise management as described in any one of claims 1 to 5, wherein the achievement conversion management system includes: An information extraction module is used to obtain high-tech enterprise certification data, extract achievement conversion information from the high-tech enterprise certification data, and generate an achievement information table; the achievement information table includes: a research and development table, a project status table, and an intellectual property table; An event-driven module, used for performing event-driven decomposition on the achievement conversion information to obtain event-driven data, and performing hierarchical clustering on the event-driven data to obtain achievement conversion driven data; A data association module is used to perform association rule mining on the achievement conversion driving data to generate achievement conversion association rules, and to associate the R&D table, the project status table and the intellectual property table based on the achievement conversion association rules to generate a high-tech enterprise identification evidence chain; The identification and detection module is used to build a high-tech enterprise identification and detection model, and use the high-tech enterprise identification and detection model to perform identification and detection on the high-tech enterprise identification evidence chain to obtain the high-tech enterprise identification results.

7. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the achievement conversion management method for high-tech enterprise management as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the achievement conversion management method for high-tech enterprise management as described in any one of claims 1 to 5.

Images