Intellectual property management system based on scientific research project

Abstract

The invention relates to the technical field of computer information, in particular to an intellectual property management system based on a scientific research project, and the system comprises a project intellectual property management module which is used for constructing a patentable knowledge graph of the scientific research project and obtaining a series of technical disclosure data; the high-value intellectual property cultivation module is used for establishing a multi-dimensional evaluation mechanism and obtaining a patent layout score; the technical disclosure management module is used for forming a technical disclosure library, performing patent retrieval and re-optimization integration, and forming a series of patent proposals; if the formed patent proposal is a batch proposal, inputting the batch proposal into the high-value intellectual property cultivation module again to obtain a new patent layout score; and performing sorting analysis according to the new patent layout score, and re-evaluating whether a high-value patent cultivation target can be achieved or not. By means of the system, automatic mining and systematic layout from technical achievements to patent proposals can be achieved, and quantitative evaluation is conducted on the patent layout value through a multi-dimensional evaluation mechanism.

Description

Technical Field

[0001] The present invention relates to the field of computer information technology, and in particular to an intellectual property management system based on scientific research projects. Background Art

[0002] Currently, innovative enterprises of all types apply for numerous patents annually to protect their innovations. Consequently, information management systems for patent data have become standard for managing massive amounts of patent data. Existing patent data management systems primarily manage enterprise patent information and primarily focus on existing patents. These systems include visual management of patent assets, early warning management of patent legal deadlines, cloud-based management of patent information, and interoperable management of patent data.

[0003] For example, in the prior art, there are Chinese invention patent documents with publication number CN113065844A, published on July 2, 2021; Chinese invention patent documents with publication number CN116069760A, published on May 5, 2023; and Chinese invention patent documents with publication number CN117670597A, published on March 8, 2024. These patent documents all involve patent data management and optimization of related functions.

[0004] However, these systems primarily manage existing patents and fail to fully cover the early stages of research projects, including intellectual property planning, patent discovery and deployment, and the cultivation of high-value intellectual property. For innovative companies, the importance of conducting early-stage intellectual property planning, patent discovery and deployment, and the cultivation of high-value intellectual property based on research projects is crucial.

[0005] Furthermore, during the early stages of intellectual property planning, technical personnel are often relied upon to draft technical briefing documents. This process presents the following problems: Many technical personnel lack a thorough understanding of the meaning and requirements of patents, making it difficult to assess which technological achievements or technical documents generated through research projects are suitable for patent formation. Furthermore, when developing patents, technical personnel often focus on drafting briefing documents for single technical points, lacking a systematic and holistic perspective. This results in a lack of scientific and systematic approach to patent formation.

[0006] Furthermore, subsequent evaluations of patents generated based on the aforementioned technical briefing documents are primarily based on the patents themselves. However, the commercialization of research results often requires a portfolio of intellectual property rights, primarily patents. Therefore, when developing an intellectual property portfolio around a scientific and technological achievement, patent managers must analyze the value of the patent portfolio to determine how to best achieve commercialization. However, existing technologies have yet to disclose a solution specifically addressing this need. Summary of the Invention

[0007] In order to solve the above technical problems, the present invention proposes an intellectual property management system based on scientific research projects. It can realize the automated mining and systematic layout from technological achievements to patent proposals based on scientific research projects, and quantitatively evaluate the value of patent layout through a multi-dimensional evaluation mechanism, thereby improving the output quality and efficiency of intellectual property rights and supporting the efficient transformation of scientific and technological achievements.

[0008] The present invention is achieved by adopting the following technical solutions: An intellectual property management system based on scientific research projects, including: The project intellectual property management module is used to build a patentability knowledge map for scientific research projects and convert the technical foundation data of each scientific research project into a series of technical briefing materials; The high-value intellectual property cultivation module is used to establish a multi-dimensional evaluation mechanism, conduct a comprehensive evaluation of the patent layout of the series of technical briefing materials of each scientific research project output by the project intellectual property management module, and obtain the patent layout score of each scientific research project; The technical briefing management module is used to form a technical briefing library based on the series of technical briefing materials of each scientific research project, and conduct patentability search and re-optimization and integration according to the corresponding patent layout score to form a series of patent proposals; the patent proposals include single proposals and batch proposals; if the formed patent proposal is a batch proposal, the batch proposal will be re-entered into the high-value intellectual property cultivation module, and the patent layout will be comprehensively evaluated again to obtain a new patent layout score; and a ranking analysis will be carried out according to the new patent layout score to re-evaluate whether the high-value patent cultivation goal can be achieved.

[0009] Constructing a patentability knowledge graph for a scientific research project specifically includes the following steps: Step S1. Data acquisition and preprocessing; Step S2. Build and train a neural network-based entity-relationship extraction model; Step S3. Utilize the trained entity-relationship extraction model to extract multiple entities and their relationships, generate RDF triples of entity-relationship-entity, and store them in a graph database to construct a data-based patentability knowledge graph.

[0010] The data preprocessing specifically refers to: formatting the data and extracting information.

[0011] The entity-relationship extraction model is based on the pre-trained model BERT, which combines the location information of entities and relationships.

[0012] The method for obtaining the patent layout score is: calculate the scores of the six dimensions of the patent layout of each scientific research project, and take the weighted average as the patent layout score of each scientific research project; the six dimensions are layout completeness, layout effectiveness, layout accuracy, goal consistency, layout uniqueness and layout timeliness.

[0013] The layout integrity specifically refers to the completeness of the patent layout, the layout effectiveness specifically refers to the efficiency of the patent layout of the scientific research project, the layout accuracy refers to the accuracy of the patent layout in hitting the key technical points, the layout uniqueness refers to the duplication of the key technical points of the patent layout of the scientific research project with other patent layouts or single-point patent key technical points, the layout consistency specifically refers to the matching of the key technical points of the patent layout of the scientific research project with the company's strategic direction, and the layout timeliness specifically refers to: based on the goal of cultivating high-value patents, evaluate whether the layout can be completed within the specified time limit.

[0014] The score A for layout completeness is: by querying the technical pedigree of the scientific research project, checking whether the patent layout based on the scientific research project is complete: ; A score of B for layout effectiveness is: B=(number of layout patents / average number of layout patents) 100%; The score C for layout accuracy is: C=(number of key technical points hit / total number of key technical points) 100%; The score D for layout uniqueness is: D = (number of repetitions / total number of comparisons) 100%; The score E for layout consistency is: E=(Number of technical key points matching important branches / Total number of technical key points) 100%; The score F for layout timeliness is: .

[0015] The specific calculation method of patent layout score V is as follows: , Where, It is i The scores of the dimensions, It is i The weights of the dimensions are adjustable.

[0016] According to the corresponding patent layout score, patentability search and re-optimization and integration are carried out. Specifically, the patent layout is sorted according to the patent layout score, and the corresponding resource allocation and processing priority are determined according to the patent layout score; the patentability search is carried out on the patent layout according to the priority, and the patent layout is re-optimized and integrated based on the search results, patent application strategy and technical level.

[0017] Sorting and analyzing the new patent layout scores and re-evaluating whether the high-value patent cultivation goal can be achieved specifically refers to: sorting and analyzing the new patent layout scores, finding the patent layout that can achieve the high-value patent cultivation goal, and judging whether the patent layout that cannot achieve the high-value patent cultivation goal can be mined manually or supplementarily to ensure that the high-value patent cultivation goal can be achieved.

[0018] It also includes a proposal management module and a patent management module; the proposal management module is used to receive single proposal applications output by the technical briefing management module and batch proposal applications output by the high-value intellectual property cultivation module, and process the proposal applications; the patent management module is used to receive single proposals or batch proposal filing applications output by the proposal management module, form patent cases, and conduct patent management.

[0019] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention first transforms the large amount of useful data generated by scientific research projects into patentable technical disclosure materials by constructing a patentable knowledge graph for these projects. For researchers lacking a patent mindset, this process can reduce the uncertainty and lag that can arise during manual technical disclosure mining. For researchers who are already proficient in technical disclosure mining, this process can reduce labor costs and make technical disclosure mining more scientific and systematic.

[0020] On this basis, the present invention further conducts a comprehensive evaluation of the patent layout of a series of technical briefing materials, so that patent managers can identify combinations that may produce high-value patents, determine the corresponding resource allocation and processing priority based on the score, optimize resource allocation, and improve overall work efficiency.

[0021] Furthermore, since the technical personnel of a scientific research project are each in charge of different technical branches, the overall patent planning and layout often require a certain overall view and patent protection strategy. The core invention points or common invention points need to be condensed and extracted from multiple technical branches. Therefore, the present invention forms a technical disclosure library to ensure that there are no omissions in technical inventions. Subsequently, through agencies or professionals, patentability searches and auxiliary layouts are carried out. According to the target needs of high-value patent cultivation, the patents are re-split and recombined to form a series of patent proposals to avoid missing technical points or duplication of work.

[0022] Finally, the batch proposals are re-entered into the high-value intellectual property cultivation module for another comprehensive evaluation of the patent layout. This can re-evaluate whether the target requirements can be achieved and determine whether further precipitation or optimization is needed. If the target has been basically achieved, it can be used as intellectual property support for achievement transformation, making the output and circulation of intellectual property more reasonable. In addition, this high-value intellectual property cultivation module can also solve the problems of high randomness and high operational difficulty of traditional patent layout.

[0023] In summary, this invention, through its progressive technical solutions, not only simplifies the patent mining process but also provides a systematic layout for patent mining in similar scientific research projects. Furthermore, the application of the high-value intellectual property cultivation module further enhances the scientific and rational nature of intellectual property management, ensuring the efficient output and circulation of intellectual property. This not only contributes to the successful transformation of scientific research projects but also provides solid support for technological innovation in related fields.

[0024] 2. The neural network-based entity-relationship extraction model employed in this invention demonstrates excellent performance in tasks such as relation extraction and joint extraction. Combining the strengths of pre-trained language models (such as BERT) and graph neural networks (GNNs), this model can efficiently identify potential technical entities and their semantic relationships from unstructured text related to scientific research projects, thereby generating structured knowledge representations and providing high-quality data support for the subsequent construction of patentability knowledge graphs.

[0025] Furthermore, the present invention can solve the problems of uncertainty, incompleteness and high personnel requirements of traditional technical briefing mining by introducing a patentability mining mechanism for scientific research projects based on graph neural networks and knowledge graphs.

[0026] 3. In the present invention, data preprocessing can not only quickly identify and extract technical data and other relevant auxiliary data that can be used to form patents in scientific research projects, but also provide a high-quality data foundation for subsequent entity-relationship extraction model training.

[0027] 4. Transformation of scientific research achievements is usually not a single patent, but rather a series of intellectual property portfolios centered around patents. Therefore, when planning the intellectual property layout around a scientific and technological achievement, patent managers need to evaluate and determine the reliability of the achievement transformation through a value analysis of the patent layout.

[0028] Therefore, the present invention proposes a high-value intellectual property cultivation module based on a multi-dimensional evaluation mechanism, which aims to calculate the patent layout score of each scientific research project through a systematic method, and provide an important reference basis for the cultivation and output of high-value intellectual property.

[0029] Specifically, this module comprehensively evaluates each research project's patent portfolio across six different dimensions, ensuring a comprehensive assessment of the patent portfolio's value and avoiding bias caused by a single metric. Furthermore, the module supports flexible weighting adjustments, allowing dynamic adjustments to the weights of each dimension based on the company's patent strategy needs. Finally, based on the calculated patent portfolio score, the research project's patent portfolio is ranked, helping to quickly identify intellectual property portfolios with high value potential.

[0030] 5. The present invention also includes a proposal management module and a patent management module, which can solve the problem that the management of technical proposals before patent applications is not systematic, comprehensive, and targeted enough. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments, wherein: Figure 1 It is a structural schematic diagram of the present invention. DETAILED DESCRIPTION

[0032] Example 1 As a basic implementation mode of the present invention, the present invention includes an intellectual property management system based on scientific research projects, including a project intellectual property management module, a high-value intellectual property cultivation module and a technical briefing management module.

[0033] The project intellectual property management module is used to construct a patentability knowledge graph for scientific research projects and convert the technical foundation data of each scientific research project into a series of technical briefing materials. The high-value intellectual property cultivation module is used to establish a multi-dimensional evaluation mechanism, conduct a comprehensive patent layout evaluation of the series of technical briefing materials for each scientific research project output by the project intellectual property management module, and obtain a patent layout score for each scientific research project. The technical briefing management module is used to form a technical briefing library based on the series of technical briefing materials for each scientific research project, and conduct patentability searches and re-optimization and integration based on the corresponding patent layout scores to form a series of patent proposals.

[0034] Patent proposals include single proposals and batch proposals. If a batch proposal is generated, it will be re-entered into the High-Value Intellectual Property Cultivation Module for a comprehensive evaluation of the patent portfolio to obtain a new patent portfolio score. A ranking analysis based on the new patent portfolio score will be conducted to re-evaluate whether the goal of high-value patent cultivation can be achieved and determine whether further development or optimization is needed.

[0035] Example 2 As a preferred embodiment of the present invention, the present invention includes an intellectual property management system based on scientific research projects, including a project intellectual property management module, a high-value intellectual property cultivation module and a technical briefing management module.

[0036] The project intellectual property management module is used to build a patentability knowledge graph for scientific research projects and convert the technical foundation data of each scientific research project into a series of technical briefing materials. Specifically, building a patentability knowledge graph for scientific research projects includes the following steps: Step S1. Data acquisition and preprocessing; Step S2. Build and train a neural network-based entity-relationship extraction model; Step S3. Utilize the trained entity-relationship extraction model to extract multiple entities and their relationships, generate RDF triples of entity-relationship-entity, and store them in a graph database to construct a data-based patentability knowledge graph.

[0037] The High-Value Intellectual Property Cultivation Module is used to establish a multi-dimensional evaluation mechanism to conduct a comprehensive evaluation of the patent layout of each research project's series of technical briefing materials output by the Project Intellectual Property Management Module, thereby obtaining a patent layout score for each research project. The patent layout score is obtained by calculating the scores of six dimensions of each research project's patent layout and taking the weighted average of these scores as the patent layout score for each research project. The six dimensions are layout completeness, layout effectiveness, layout accuracy, goal consistency, layout uniqueness, and layout timeliness.

[0038] The technical briefing management module is used to form a technical briefing library based on a series of technical briefing materials of each scientific research project, and to conduct patentability search and re-optimization and integration based on the corresponding patent layout scores to form a series of patent proposals.

[0039] Patent proposals include single proposals and batch proposals. If a batch proposal is generated, it will be re-entered into the High-Value Intellectual Property Cultivation Module for a comprehensive evaluation of the patent portfolio to obtain a new patent portfolio score. A ranking analysis will be conducted based on the new patent portfolio score to re-evaluate whether the goal of high-value patent cultivation can be achieved.

[0040] Example 3 As another preferred embodiment of the present invention, the present invention includes an intellectual property management system based on scientific research projects, including a project intellectual property management module, a high-value intellectual property cultivation module, and a technical briefing management module. The project intellectual property management module is used to construct a patentability knowledge map of scientific research projects and convert the technical foundation data in each scientific research project into a series of technical briefing materials. The high-value intellectual property cultivation module is used to establish a multi-dimensional evaluation mechanism, conduct a comprehensive patent layout evaluation on the series of technical briefing materials of each scientific research project output by the project intellectual property management module, and obtain a patent layout score for each scientific research project.

[0041] The technical briefing management module is used to create a technical briefing library based on the technical briefing materials of each research project. It then conducts patentability searches and re-optimization and integration based on the corresponding patent portfolio scores, forming a series of patent proposals. Specifically, the patent portfolios are sorted by their patent portfolio scores, and the corresponding resource allocation and processing priorities are determined based on the patent portfolio scores. Patent portfolios are then searched for patentability based on priority, and the patent portfolios are re-optimized and integrated based on the search results.

[0042] Patent proposals include single proposals and batch proposals. If a batch proposal is generated, it will be re-entered into the High-Value Intellectual Property Cultivation Module for a comprehensive evaluation of the patent portfolio to obtain a new patent portfolio score. A ranking analysis will be conducted based on the new patent portfolio score to reassess whether the goal of cultivating high-value patents can be achieved. This means finding a complete and reliable patent portfolio that can achieve the goal of cultivating high-value patents. It will also determine whether incomplete and reliable patent portfolios can be manually or supplemented to ensure that the goal of cultivating high-value patents can be achieved.

[0043] Example 4 As another preferred embodiment of the present invention, the present invention includes an intellectual property management system based on scientific research projects, Figure 1 , including project intellectual property management module, high-value intellectual property cultivation module, technical briefing management module, proposal management module and patent management module.

[0044] The project intellectual property management module is used to build a patentability knowledge map for scientific research projects and convert the technical foundation data of each scientific research project into a series of technical briefing materials. Specifically, it may include the following steps: Step S1. Data acquisition and preprocessing.

[0045] Data collection specifically refers to the collection of technical foundational data related to scientific research projects. For example, for aircraft landing gear maintenance research, this includes: ① Fault data, including fault time, fault component, component symptoms, fault description, and fault cause; ② Fault location, including shock absorbers, support struts, and retraction mechanisms; ③ Fault component symptoms, including vibration, oil leakage, fracture, and wear; and ④ Fault handling, including the repair principles, repair process, repair methods, and repair equipment.

[0046] By integrating the collected historical data, that is, integrating historical fault data, fault locations, fault component symptoms, and fault handling processes, it serves as the data source for constructing the patentability knowledge graph of this scientific research project.

[0047] Before building the knowledge graph, the collected historical text data is preprocessed to find technical data and other related auxiliary data that can subsequently form patents. The data preprocessing specifically refers to formatting the data and extracting information.

[0048] Specifically, data formatting involves converting files with inconsistent fonts and encodings into text files with a unified encoding format. Information extraction involves constructing a patentability knowledge graph involving multiple entity nodes, such as faulty components, component symptoms, and fault handling. Therefore, it's necessary to extract fault knowledge from original historical files (Excel, docx, doc, PDF) to obtain an entity list, which serves as training data for the entity-relationship extraction model.

[0049] Step S2. Construct and train a neural network-based entity-relationship extraction model. The entity-relationship extraction model is based on the pre-trained BERT model and combines entity and relationship extraction models with the location information of entities and relationships. It performs well for tasks such as relationship extraction and joint extraction. An entity-relationship dataset is manually constructed in advance, where the original fault data is divided into multiple entity categories: fault component, component symptom, fault description, fault handling, etc. Relationships can be expressed as: fault component - (occurrence) - component symptom, component symptom - (cause) - fault description, fault cause - (result) - fault description, fault handling - (resolution) - component symptom, etc. This can obtain RDF (Resource Description Framework) triples of entity-relationship-entity for training the entity-relationship extraction model.

[0050] Step S3. Utilize the trained entity-relationship extraction model to extract multiple entities and their relationships, generate RDF triples of entity-relationship-entity, and store them in a graph database to construct a data-based patentability knowledge graph.

[0051] Specifically, during data preprocessing, information extraction yields an entity list containing nodes such as fault location, symptoms, and treatment. This provides the vocabulary foundation for constructing the nodes in the knowledge graph. Based on a self-trained entity-relationship extraction model, we can extract RDF triples of entity-relationship-entity from fault handling data.

[0052] The constructed node and relationship knowledge is stored in the Neo4j graph database, a mature graph-structured database that facilitates node and edge management using the Cypher declarative query language. Neo4j also provides user-friendly visualization tools for intuitively inspecting the effectiveness of the knowledge graph construction. Neo4j's interfaces with deep learning frameworks such as TensorFlow will also provide technical support for subsequent graph representation learning. Based on the Neo4j graph database, a data-based patentability knowledge graph was constructed.

[0053] In summary, the project intellectual property management module collects, preprocesses, trains and constructs a knowledge graph of a large amount of useful data generated in scientific research projects, thereby realizing the construction of a patentability knowledge graph, providing a convenient way for automatic mining of technical briefing documents.

[0054] The High-Value Intellectual Property Cultivation Module is used to establish a multi-dimensional evaluation mechanism. It conducts a comprehensive patent portfolio evaluation of the series of technical briefing materials for each scientific research project output by the Project Intellectual Property Management Module, and obtains a patent portfolio score for each scientific research project. This helps patent managers identify combinations that may produce high-value patents, providing a reliable basis for the batch layout and output of high-value intellectual property. For example, when conducting intellectual property layout around a scientific and technological achievement, patent managers can use patent portfolio scoring analysis to evaluate and determine the reliability of the achievement's transformation.

[0055] Specifically, the patent portfolio score is obtained by calculating the scores of six dimensions of each research project's patent portfolio and taking the weighted average of these scores as the patent portfolio score for each research project. The six dimensions are portfolio completeness, portfolio effectiveness, portfolio accuracy, goal consistency, portfolio uniqueness, and portfolio timeliness.

[0056] Furthermore, the layout integrity specifically refers to the completeness of the patent layout. By querying the technical pedigree of the scientific research project, we can check whether the patent layout based on the scientific research project is complete, reflecting the standardization and completeness of the patent layout. Therefore, the score A of the layout integrity is: .

[0057] The effectiveness of the layout specifically refers to the efficiency of the patent layout of a scientific research project. This means that when a scientific research project is deployed, the total number of patents deployed accounts for the average number of patents deployed. For example, in the case of supporting the transformation of research results, the average number of patents deployed is 10. By comparing this with the average number of patents deployed, the effectiveness of the patent layout is reflected, and the value is a percentage. Therefore, the score B for the effectiveness of the layout is: B=(number of layout patents / average number of layout patents) 100%.

[0058] The layout accuracy refers to the accuracy of the patent layout in hitting the key technical points. Specifically, the patent manager compares the technical keywords pre-designated for the research project with the keywords in the patent layout to determine the degree of identity or similarity. The layout accuracy score C is a percentage and is calculated as follows: C=(number of key technical points hit / total number of key technical points) 100%.

[0059] The layout uniqueness refers to the duplication of the key technical points of the scientific research project patent layout with other patent layouts or single-point patent key technical points, reflecting the uniqueness of the layout patent. The score D of the layout uniqueness is a percentage, and the calculation method is: D = (number of repetitions / total number of comparisons) 100%.

[0060] Layout consistency specifically refers to the match between the key technical points of the scientific research project patent layout and the company's strategic direction. This process requires first confirming whether the key technical points of the patent layout come from the key branches of the company's technology map. If they do come from the key branches, their consistency is defined based on the degree of match with the key branches. The layout consistency score E is a percentage and is calculated as follows: E=(Number of technical key points matching important branches / Total number of technical key points) 100%.

[0061] The timeliness of layout specifically refers to: based on the target needs of high-value patent cultivation, such as application for achievement transformation projects, standard essential patent cultivation, etc., the technical leader of the scientific research project determines the timeliness of patent layout and determines the time limit for completion of the layout. If the layout is completed within the time limit, it is 1; if the layout is not completed within the time limit, it is 0. Specifically, the score F of layout timeliness is: .

[0062] Finally, the weighted average is taken as the patent layout score V of each scientific research project: , Where, It is i The scores of the dimensions, It is i The weights of the dimensions can be adjusted according to the patent application targets for the year.

[0063] The technical briefing management module is used to create a technical briefing library based on the series of technical briefing materials for each research project. Because technical personnel within a research project are responsible for different technical branches, holistic patent planning and layout often require a certain overall perspective and patent protection strategy. Core or common inventions require condensing and extracting multiple technical branches. Therefore, the formation of a technical briefing library can ensure that no technical inventions are missed.

[0064] The technical briefing management module is also used to conduct patentability searches and re-optimize and integrate according to the corresponding patent layout scores to form a series of patent proposals. Specifically, the patent layout can be sorted according to the patent layout score, and the patent manager and others will decide the corresponding resource allocation and processing priority based on the patent layout score. The agency or professional can conduct a patentability search on the patent layout according to the priority. Based on the existing technology queried by the agency or professional, the search results are obtained, which can distinguish between creative technical points and technical points that have been disclosed by the existing technology. Based on the search results, patent application strategy and technical level, the technical briefing materials are further optimized and integrated to form a series of patent proposals.

[0065] The patent proposals include single proposals and batch proposals. If the patent proposal formed is a single proposal, the proposal process is triggered and a single proposal application is output. If the patent proposal formed is a batch proposal, the layout process is triggered, the batch proposal is re-entered into the high-value intellectual property cultivation module, and the patent layout is comprehensively evaluated again to obtain a new patent layout score. According to the new patent layout score, a ranking analysis is performed to re-evaluate whether the high-value patent cultivation goal can be achieved. Specifically, a complete and reliable patent layout can be quickly found, that is, a patent layout that can achieve the high-value patent cultivation goal. A patent layout that cannot achieve the high-value patent cultivation goal is an incomplete and reliable patent layout. It is further judged whether the incomplete and reliable patent layout can be manually or supplemented through mining, or through re-batch layout to ensure that the high-value patent cultivation goal can be achieved, so that a series of patents can be formed to support the achievement transformation project or standard essential patent cultivation. After the batch layout is finally completed, the proposal process is triggered and the batch proposal application is output.

[0066] The proposal management module is used to receive single proposal applications output by the technical briefing management module and batch proposal applications output by the high-value intellectual property cultivation module, process the proposal applications, and has a proposal query function.

[0067] The patent management module is used to receive the filing application of a single proposal or a batch of proposals output by the proposal management module, form a patent case, and perform subsequent patent management.

[0068] In summary, after reading the present invention document, ordinary technicians in this field can make various other corresponding transformation schemes based on the technical solutions and technical concepts of the present invention without creative mental work, which all fall within the scope of protection of the present invention.

Claims

1. An intellectual property management system based on scientific research projects, characterized by: include: The project intellectual property management module is used to build a patentability knowledge map for scientific research projects and convert the technical foundation data of each scientific research project into a series of technical briefing materials; The high-value intellectual property cultivation module is used to establish a multi-dimensional evaluation mechanism, conduct a comprehensive evaluation of the patent layout of the series of technical briefing materials of each scientific research project output by the project intellectual property management module, and obtain the patent layout score of each scientific research project; The technical briefing management module is used to form a technical briefing library based on the series of technical briefing materials of each scientific research project, and conduct patentability search and re-optimization and integration according to the corresponding patent layout score to form a series of patent proposals; the patent proposals include single proposals and batch proposals; if the formed patent proposal is a batch proposal, the batch proposal will be re-entered into the high-value intellectual property cultivation module, and the patent layout will be comprehensively evaluated again to obtain a new patent layout score; and a ranking analysis will be carried out according to the new patent layout score to re-evaluate whether the high-value patent cultivation goal can be achieved.

2. The intellectual property management system based on scientific research projects according to claim 1, characterized in that: Constructing a patentability knowledge graph for a scientific research project specifically includes the following steps: Step S1. Data acquisition and preprocessing; Step S2. Build and train a neural network-based entity-relationship extraction model; Step S3. Utilize the trained entity-relationship extraction model to extract multiple entities and their relationships, generate RDF triples of entity-relationship-entity, and store them in a graph database to construct a data-based patentability knowledge graph.

3. The intellectual property management system based on scientific research projects according to claim 2, characterized in that: The data preprocessing specifically refers to: formatting the data and extracting information.

4. The intellectual property management system based on scientific research projects according to claim 2, characterized in that: The entity-relationship extraction model is based on the pre-trained model BERT, which combines the location information of entities and relationships.

5. The intellectual property management system based on scientific research projects according to claim 1, characterized in that: The method for obtaining the patent layout score is: calculate the scores of the six dimensions of the patent layout of each scientific research project, and take the weighted average as the patent layout score of each scientific research project; the six dimensions are layout completeness, layout effectiveness, layout accuracy, goal consistency, layout uniqueness and layout timeliness.

6. The intellectual property management system based on scientific research projects according to claim 5, characterized in that: The layout integrity specifically refers to the completeness of the patent layout, the layout effectiveness specifically refers to the efficiency of the patent layout of the scientific research project, the layout accuracy refers to the accuracy of the patent layout in hitting the key technical points, the layout uniqueness refers to the duplication of the key technical points of the patent layout of the scientific research project with other patent layouts or single-point patent key technical points, the layout consistency specifically refers to the matching of the key technical points of the patent layout of the scientific research project with the company's strategic direction, and the layout timeliness specifically refers to: based on the goal of cultivating high-value patents, evaluate whether the layout can be completed within the specified time limit.

7. The intellectual property management system based on scientific research projects according to claim 6, characterized in that: The score A for layout completeness is: by querying the technical pedigree of the scientific research project, checking whether the patent layout based on the scientific research project is complete: ； A score of B for layout effectiveness is: B=(number of layout patents / average number of layout patents) 100%; The score C for layout accuracy is: C=(number of key technical points hit / total number of key technical points) 100%; The score D for layout uniqueness is: D = (number of repetitions / total number of comparisons) 100%; The score E for layout consistency is: E=(Number of technical key points matching important branches / Total number of technical key points) 100%; The score F for layout timeliness is: 。 8. The intellectual property management system based on scientific research projects according to claim 7, characterized in that: The specific calculation method of patent layout score V is as follows: ， Where, It is i The scores of the dimensions, It is i The weights of the dimensions are adjustable.

9. The intellectual property management system based on scientific research projects according to claim 1, characterized in that: According to the corresponding patent layout score, patentability search and re-optimization and integration are carried out. Specifically, the patent layout is sorted according to the patent layout score, and the corresponding resource allocation and processing priority are determined according to the patent layout score; the patentability search is carried out on the patent layout according to the priority, and the patent layout is re-optimized and integrated based on the search results, patent application strategy and technical level.

10. The intellectual property management system based on scientific research projects according to claim 1, characterized in that: Sorting and analyzing the new patent layout scores and re-evaluating whether the goal of cultivating high-value patents can be achieved specifically refers to: Sorting and analyzing the new patent layout scores to find patent layouts that can achieve the goal of cultivating high-value patents, and judging whether the patent layouts that cannot achieve the goal of cultivating high-value patents can be mined manually or supplementarily to ensure that the goal of cultivating high-value patents can be achieved.

11. The intellectual property management system based on scientific research projects according to any one of claims 1 to 10, characterized in that: It also includes a proposal management module and a patent management module; the proposal management module is used to receive single proposal applications output by the technical briefing management module and batch proposal applications output by the high-value intellectual property cultivation module, and process the proposal applications; the patent management module is used to receive single proposals or batch proposal filing applications output by the proposal management module, form patent cases, and conduct patent management.

Images