Multi-source information fusion-based key point extraction method for medical and invasive resources

Abstract

The invention provides a multi-source information fusion-based key point extraction method for medical and invasive resources, and belongs to the technical field of key point extraction of medical and invasive resources. On the basis of multi-source heterogeneous data acquired by multiple parties, an original medical and invasive resource database is constructed, and medical and invasive resource statements are sorted according to an execution sequence of database operation statements to support efficient sorting and rapid screening analysis of data in the database by a user, so that the efficiency of subsequent data processing and information extraction is improved, and the user experience is improved. Core information is subjected to cross validation and complementary enhancement, structured integration of medical and invasive resources is realized, general rules, consensus cognition and core challenges in the field can be summarized on the basis of a constructed medical and invasive resource fusion model, and advantages and disadvantages of the medical and invasive resources in a database are deeply mined, so that a medical and invasive resource fusion model is established. The accuracy, adaptability and practicability of key point extraction of the medical and invasive resources under the background of multi-source information fusion are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of key points extraction of scientific and technological resources, and particularly relates to a method for extracting key points of scientific and technological resources based on multi-source information fusion. BACKGROUND

[0002] With the deepening of the policy support of the state for scientific development and technological service, the efficient collaboration of technological innovation and the sharing and use of scientific and technological resources have gradually formed a macro strategic direction of the integration development of technology industry and the landing of double-creation service projects. In order to better focus on industrial advantages, serve enterprise needs, and promote regional scientific and technological cooperation and industry-university-research-application, how to effectively use scientific and technological resources has become a key point. However, in practice, scientific and technological resources cover scientific and technological literature, patent achievements, global talents, listed companies, technical research reports and financial data and other types. These data are various in type, scattered in source, different in classification, and complex in data structure, and have large differences in underlying features. Therefore, it is difficult to realize the cross-platform convergence, standardized processing and structured fusion of data resources with multi-source and heterogeneous characteristics. Therefore, the resource utilization efficiency is not high, and the scientific research value discovery degree is not enough.

[0003] Under the background of technological innovation promoting economic transformation, scientific and technological resources are of great significance for promoting the deep integration of industry-university-research and the transformation of scientific and technological achievements to realize the innovative development of regional economy. However, the distribution of scientific and technological resources has the characteristics of multi-source and heterogeneity, and the data structure is not unified, the theme fusion degree is low, and the space-time distribution is inconsistent, which makes it difficult to exchange and share data and value mining. Therefore, the processing of scientific and technological resource data needs to solve the correctness and consistency of information description of unstructured scientific and technological achievements, semi-structured scientific and technological instances and structured scientific and technological objects, and realize the correlation analysis, dynamic integration and multi-source information fusion of cross-domain data after the structured processing of heterogeneous data.

[0004] The multi-source information fusion of scientific and technological resources refers to the core elements and intelligence conclusions extracted from massive information, which have key guiding significance and reference value for technological innovation activities. Using computer technology, mathematical models and algorithms, these heterogeneous, multi-dimensional and massive information are collaboratively processed, comprehensively analyzed and deeply mined, and finally a comprehensive judgment and knowledge more comprehensive, accurate and reliable than any single information source is formed. Different sources of data are integrated together to eliminate data redundancy and provide consistent and complete data views to support decision making, business analysis and business process optimization.

[0005] However, the existing scientific and technological resource key point extraction method has the problems of low screening and analysis efficiency and low key point extraction in the use process, cannot meet the massive multi-dimensional heterogeneous data fusion application, and is difficult to adapt to the requirement and extraction demand of scientific and technological resources under the background of multi-source information fusion. Therefore, it needs to be improved. SUMMARY

[0006] The embodiment of the application provides a scientific and technological resource point extraction method based on multi-source information fusion to improve the above problems.

[0007] To achieve the above object, the application adopts the following technical scheme: In a first aspect, the application provides a scientific and technological resource point extraction method based on multi-source information fusion, applied to an extraction terminal, and the method comprises the following steps: The extraction terminal acquires and caches original scientific and technological resource database information in multi-source heterogeneous data according to data attribute characteristics; According to the database operation statement and the original scientific and technological resource database information, information matching is performed to generate a target scientific and technological resource database set; Based on the target scientific and technological resource database set, semantic analysis and entity recognition are performed to identify main scientific and technological resource information in the database; The identified main scientific and technological resource information is cross-validated and complementarily enhanced to automatically fuse and calculate the data and construct a scientific and technological resource fusion model; Through the constructed scientific and technological resource fusion model, the internal scientific and technological resources are deeply analyzed, the core points of the scientific and technological resources are extracted, and a structured and normative description of the scientific and technological resources is formed; The structured and normative description of the scientific and technological resources is presented to decision makers in a visual manner.

[0008] In combination with the first aspect, in some embodiments, the extraction terminal acquires and caches original scientific and technological resource database information in multi-source heterogeneous data according to data attribute characteristics: Multi-source heterogeneous data of scientific and technological resources is acquired from multiple parties, the acquired multi-source heterogeneous data is taken as original scientific and technological resource database information, and the original scientific and technological resource database information is formed into a data set according to data attribute characteristics and format characteristics and is uniformly stored in a storage module.

[0009] In combination with the first aspect, in some embodiments, according to the database operation statement and the original scientific and technological resource database information, information matching is performed to generate a target scientific and technological resource database set: Based on the acquired original scientific and technological resource database information, information matching is performed on the data set through the database operation statement to form a matching information set; Based on the matching information set, the data is sorted according to the execution order of the database operation statement to form a target scientific and technological resource database set.

[0010] In combination with the first aspect, in some embodiments, based on the target scientific and technological resource database set, semantic analysis and entity recognition are performed to identify main scientific and technological resource information in the database: identify key scientific and technological resource entities in the information set within the target scientific and technological resource database set; identify scientific and technological resource relationships between entities, and obtain associated data of the key scientific and technological resource entities; and store the extracted scientific and technological resource entities, relationships and attributes in a structured form.

[0011] In combination with the first aspect, in some embodiments, the identified main scientific and technological resource information is cross-verified and complementarily enhanced for automatic data fusion calculation, and a scientific and technological resource fusion model is constructed: Cross-verify and complementarily enhance the obtained information, and associate it to the scientific and technological resource knowledge ontology; When the information from different sources is contradictory, the information is weighted and judged according to the timeliness; Based on time series analysis and scientific and technological resource topic model, the technical trend and research hotspot change of scientific and technological resources are analyzed and extracted; Using machine learning algorithm, construct a scientific and technological resource fusion model for technology value assessment, and predict the scientific and technological resource technology hot spot.

[0012] In combination with the first aspect, in some embodiments, through the constructed scientific and technological resource fusion model, the internal scientific and technological resources are deeply mined and analyzed, the core points are refined, and the structured and normative description of scientific and technological resources is formed: Based on the scientific and technological resource model and knowledge network after fusion, the general law, consensus and core challenge of scientific and technological resources are summarized; According to the difference analysis of different regions, the advantages and disadvantages of scientific and technological resources in the database are deeply mined; According to the advantages and disadvantages of scientific and technological resources, the core points are refined, and the structured data normative description of core requirements is formed.

[0013] In combination with the first aspect, in some embodiments, the structured data normative description is presented to the decision maker in a visualized way: The refined core requirements are presented to the decision maker in an intuitive and interactive way through knowledge graph visualization, heat map, technology roadmap or trend curve.

[0014] In combination with the first aspect, in some embodiments, the scientific and technological resource point extraction system of multi-source information fusion specifically includes the following steps: According to the data attribute characteristics, the original scientific and technological resource database information in the multi-source heterogeneous data is obtained and cached; Information matching is performed with the original scientific and technological resource database information to generate a target scientific and technological resource database set; Through semantic analysis and entity recognition, the main information in the database is identified; Cross-validation and complementary enhancement are performed according to the identified main scientific and technological resource information, and a scientific and technological resource fusion model is constructed. The scientific and technological resource core points are extracted through the constructed scientific and technological resource fusion model. The scientific and technological resource core points are presented to decision makers in a visual manner.

[0015] The third aspect of the embodiment of the application provides an electronic device, which comprises: At least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the system provided in the first aspect of the embodiment of the application.

[0016] The fourth aspect of the embodiment of the application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the system provided in the first aspect of the embodiment of the application.

[0017] In summary, the system and the device have the following technical effects: The application provides a scientific and technological resource point extraction method based on multi-source information fusion. The method is based on multi-source heterogeneous data obtained by multiple parties, constructs an original scientific and technological resource database, and sorts scientific and technological resource statements according to the execution order of database operation statements to support efficient sorting and rapid screening analysis of data in the database, thereby improving the efficiency of subsequent data processing and information extraction. In this process, through semantic analysis and entity recognition technology, the system can accurately identify key scientific and technological resource information in the database, cross-validate and complementally enhance the core information, and associate the core information to a preset scientific and technological resource knowledge ontology to realize the structured integration of scientific and technological resources. Further combined with time series analysis, the method can reveal the dynamic changes of technology development trends and research hotspots, support in-depth insight into the evolution path of scientific and technological resources, and based on the constructed scientific and technological resource fusion model, can summarize the universal laws, consensus cognition and core challenges in the field, and deeply mine the advantages and disadvantages of scientific and technological resources in the database, thereby significantly improving the accuracy, adaptability and practicality of scientific and technological resource point extraction in the context of multi-source information fusion, optimizing the rhetoric system of resource analysis, and expanding the application ability of the scientific and technological resource point extraction method in multiple scientific and technological scenes. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A flowchart of a scientific and technological resource point extraction method based on multi-source information fusion is provided for the embodiment of the application. DETAILED DESCRIPTION

[0019] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are some of the embodiments of the present application but not all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts should fall within the scope of the present application.

[0020] The present application embodiment proposes a multi-source information fusion scientific and technological resource key point extraction method, please refer to Figure 1 , applied to an extraction terminal, the method comprises: The extraction terminal acquires and caches original scientific and technological resource database information in multi-source heterogeneous data according to data attribute characteristics; According to the database operation statement and the original scientific and technological resource database information, information matching is performed to generate a target scientific and technological resource database set; Based on the target scientific and technological resource database set, the main scientific and technological resource information in the database is identified through semantic analysis and entity recognition; The identified main scientific and technological resource information is cross-validated and complementarily enhanced to automatically fuse and calculate the data, and a scientific and technological resource fusion model is constructed; Through the constructed scientific and technological resource fusion model, the internal scientific and technological resources are deeply mined and analyzed, the core points of the scientific and technological resources are extracted, and the structured and normative description of the scientific and technological resources is formed; The structured and normative description of the scientific and technological resources is presented to the decision maker in a visual way.

[0021] Based on multi-source heterogeneous data obtained by multiple parties, an original scientific and technological resource database is constructed, and scientific and technological resource statements are sorted according to the execution order of database operation statements to support users in efficiently sorting and quickly filtering and analyzing the data in the database, thereby improving the efficiency of subsequent data processing and information extraction. In this process, through semantic analysis and entity recognition technology, the system can accurately identify the key scientific and technological resource information in the database, cross-validate and complementally enhance these core information, and associate them to the preset scientific and technological resource knowledge ontology to realize the structured integration of scientific and technological resources. Further combined with time series analysis, this method can reveal the dynamic changes of technology development trend and research hotspot, support in-depth insight into the evolution path of scientific and technological resources, and based on the constructed scientific and technological resource fusion model, the universal law, consensus cognition and core challenge in the field can be summarized, and the advantages and disadvantages of the scientific and technological resources in the database are deeply mined, which significantly improves the accuracy, adaptability and practicality of scientific and technological resource key point extraction in the context of multi-source information fusion, optimizes the rhetoric system of resource analysis, and expands the application ability of scientific and technological resources in multiple scientific and technological scenarios.

[0022] The refining terminal acquires and caches original scientific and innovative resource database information in multi-source heterogeneous data according to data attribute characteristics: Multi-source heterogeneous data of scientific and innovative resources are acquired from multiple parties, and the acquired multi-source heterogeneous data are taken as original scientific and innovative resource database information, and a data set is formed according to data attribute characteristics and format characteristics and is uniformly stored in a storage module according to the original scientific and innovative resource database information; According to the database operation statement and the original scientific and innovative resource database information, a target scientific and innovative resource database set is generated: Based on the acquired original scientific and innovative resource database information, information matching is performed on the data set through the database operation statement to form a matching information set; Based on the matching information set, the data is sorted according to the execution order of the database operation statement to form a target scientific and innovative resource database set.

[0023] Based on the multi-source heterogeneous data acquired from multiple parties, a complete and comprehensive original scientific and innovative resource database is constructed, and intelligent sorting and priority division are performed on the scientific and innovative resource statement according to the logical execution order of the database operation statement, which significantly improves the efficient sorting and multi-dimensional rapid screening ability of users on the resources in the database, and lays a solid foundation for subsequent data processing and information extraction.

[0024] The application proposes a scientific and innovative resource point refining method based on multi-source information fusion, which identifies the main scientific and innovative resource information in the database through semantic analysis and entity recognition based on the target scientific and innovative resource database set: The key scientific and innovative resource entities in the information set are identified in the target scientific and innovative resource database set; The scientific and innovative resource relationships between entities are identified, and the associated data of the key scientific and innovative resource entities are obtained; The extracted scientific and innovative resource entities, relationships and attributes are stored in a structured form; The identified main scientific and innovative resource information is cross-verified and complementarily enhanced to automatically fuse and calculate the data, and a scientific and innovative resource fusion model is constructed: The acquired information is cross-verified and complementarily enhanced, and is associated to the scientific and innovative resource knowledge ontology; When different source information is contradictory, the information is weighted and judged according to the timeliness; Based on time series analysis and scientific and innovative resource topic model, the technical trend and research hotspot change of scientific and innovative resources are analyzed and extracted; A scientific and innovative resource fusion model for evaluating technical value is constructed by using a machine learning algorithm to predict the scientific and innovative resource technology hotspot.

[0025] By fusing semantic analysis and entity recognition technology, the system can accurately identify and extract key technical elements, research subjects and innovation achievements, and other core sci-tech resource information in the database. Relying on cross-source cross-validation and information complementary enhancement mechanism, the system performs consistency checking and integrity completion on the identified key information, and dynamically associates it to the preset sci-tech resource knowledge ontology with hierarchical structure, so as to realize the structured integration and semantic unified representation of sci-tech resources. By introducing time series analysis, the system quantitatively tracks the activity, research scale and diachronic change of the cooperation network of the technical theme, so as to clearly reveal the dynamic change law of the technical development trend and research hotspot, and effectively support the deep insight and forward-looking judgment of the evolution path of sci-tech resources.

[0026] By constructing the sci-tech resource fusion model, the sci-tech resources inside are deeply mined and analyzed, the core points are refined, and the structured and normative description of sci-tech resources is formed: Based on the fused sci-tech resource model and knowledge network, the general law, consensus and core challenge of sci-tech resources are summarized; According to the difference analysis of different regions, the advantages and disadvantages of sci-tech resources in the database are deeply mined; According to the advantages and disadvantages of sci-tech resources, the core points are refined, and the structured data normative description of the core requirements is formed.

[0027] Based on the constructed sci-tech resource multi-source fusion model, through deep machine learning and natural language processing technology, the general law, common technical bottleneck and consensus cognition of sci-tech resources are summarized by analyzing the massive heterogeneous data, and the core advantages and key disadvantages of sci-tech resources in the database are deeply mined and benchmarked, which significantly improves the accuracy, adaptability and practicality of sci-tech resource point extraction in the multi-source information fusion background. Further, the resource analysis rhetoric system and expression specification are optimized to adapt to the sci-tech resource requirement extraction demand in the multi-source information fusion background, and the practical application ability of the method in the multi-element sci-tech scene such as university scientific research management, enterprise research and development decision, industrial technology planning and government policy making is expanded.

[0028] Preferably, the structured data normative description is presented to the decision maker in a visual way: The refined core requirements are presented to the decision maker in an intuitive and interactive way through knowledge graph visualization, heat map, technology roadmap or trend curve.

[0029] The core advantages and key disadvantages of the refined scientific and technological resources after deep mining analysis are visualized through a knowledge graph, a heat map, a technology roadmap or a trend curve and reported or delivered to decision makers in an intuitive and interactive manner, so that the decision makers can clearly understand the core competitiveness and key short boards of the scientific and technological resources and immediately transform these insights into communication strategies for the outside and the inside, thereby greatly improving the communication efficiency and decision-making quality.

[0030] In combination with the first aspect, in some embodiments, the multi-source information fusion scientific and technological resource point refining system specifically comprises the following steps: Obtaining and caching original scientific and technological resource database information in multi-source heterogeneous data according to data attribute characteristics; Performing information matching on the original scientific and technological resource database information to generate a target scientific and technological resource database set; Identifying main information inside the database through semantic analysis and entity recognition; Cross-verification and complementary enhancement are performed according to the identified main scientific and technological resource information, and a scientific and technological resource fusion model is constructed; Scientific and technological resource core points are refined through the constructed scientific and technological resource fusion model; The scientific and technological resource core points are presented to decision makers in a visualized manner.

[0031] Based on the same inventive concept, the embodiments of the present application also propose an electronic device, which comprises: At least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the multi-source information fusion scientific and technological resource point refining method of the embodiments of the present application.

[0032] In addition, to achieve the above-mentioned purpose, the embodiments of the present application also propose a computer readable storage medium storing a computer program, and the computer program is executed by a processor to implement the multi-source information fusion scientific and technological resource point refining method of the embodiments of the present application.

[0033] The various constituent components of the electronic device will be specifically introduced as follows: The processor is the control center of the electronic device, and can be one processor or a combination of multiple processing elements. For example, the processor is one or more central processing units (CPUs), application specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present application, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs).

[0034] Optionally, the processor can execute various functions of the electronic device by running or executing software programs stored in the memory and calling data stored in the memory.

[0035] The memory is configured to store software programs for implementing the solutions of the present application, and the processor is configured to control the execution of the software programs. The specific implementation can refer to the above-mentioned system embodiments, and will not be described here.

[0036] Optionally, the memory can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program codes in the form of instructions or data structures and capable of being accessed by a computer, but not limited to the above. The memory can be integrated with the processor or exist independently and be coupled to the processor through the interface circuit of the electronic device, and the embodiments of the present application are not limited in this regard.

[0037] The transceiver is configured to communicate with a network device or a terminal device.

[0038] Optionally, the transceiver can include a receiver and a transmitter. The receiver is configured to implement the receiving function, and the transmitter is configured to implement the transmitting function.

[0039] Optionally, the transceiver can be integrated with the processor, or exist independently and be coupled with the processor through the interface circuit of the router, and the embodiments of the present application do not make a specific limitation hereon.

[0040] In addition, the technical effects of the electronic device can refer to the technical effects of the data transmission system described in the above system embodiments, which will not be described here again.

[0041] It should be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0042] It should also be understood that the memory in the embodiments of the present application can be volatile or nonvolatile memory, or can include both volatile and nonvolatile memory. Nonvolatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), used as external cache. By way of example, and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0043] The above-described embodiments can be implemented in whole or in part by software, hardware (such as a circuit), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0044] It should be understood that the term "and / or" herein merely describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents that the associated objects before and after it are in an "or" relationship, but it can also represent an "and / or" relationship, which can be understood according to the context before and after it.

[0045] In the present application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0046] It should be understood that in various embodiments of the present application, the size of the sequence number of each process described above does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0047] Those skilled in the art can realize the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be realized in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the particular application and design constraints. Those skilled in the art can realize the described functions by using different systems for each particular application, but such implementation does not need to be considered beyond the scope of the present application.

Claims

1. A method for extracting key points of scientific and technological resources by multi-source information fusion, characterized in that, The method is applied to a refining terminal, and the method comprises the following steps: The refining terminal acquires and caches original scientific and technological resource database information in multi-source heterogeneous data according to data attribute characteristics; Target scientific and technological resource database sets are generated by matching database operation statements with the original scientific and technological resource database information; Main scientific and technological resource information in the database is identified through semantic analysis and entity recognition based on the target scientific and technological resource database sets; Cross-validation and complementary enhancement are performed on the identified main scientific and technological resource information to automatically fuse and calculate the data and construct a scientific and technological resource fusion model; The scientific and technological resource fusion model is constructed, and the internal scientific and technological resources are deeply analyzed to refine core points of the scientific and technological resources and form a structured and normative description of the scientific and technological resources; The structured and normative description of the scientific and technological resources is presented to decision-makers in a visual manner.

2. The multi-source information fusion scientific and technological resource gist refining method according to claim 1, characterized in that, The refining terminal acquires and caches original scientific and technological resource database information in multi-source heterogeneous data according to data attribute characteristics: Multi-source heterogeneous data of scientific and technological resources are obtained from multiple parties, and the obtained multi-source heterogeneous data are taken as original scientific and technological resource database information, which is formed into a data set according to data attribute characteristics and format characteristics and is uniformly stored in a storage module.

3. The multi-source information fusion scientific and technological resource point extraction method according to claim 2, characterized in that, Target scientific and technological resource database sets are generated by matching database operation statements with the original scientific and technological resource database information: Based on the obtained original scientific and technological resource database information, the data set is matched by database operation statements to form a matching information set; Based on the matching information set, the data is sorted according to the execution order of the database operation statements to form the target scientific and technological resource database set.

4. The multi-source information fusion scientific and technological resource point extraction method according to claim 3, characterized in that, Main scientific and technological resource information in the database is identified through semantic analysis and entity recognition based on the target scientific and technological resource database sets: Key scientific and technological resource entities in the information set are identified in the target scientific and technological resource database set; The relationships between the scientific and technological resources are identified to obtain associated data of the key scientific and technological resource entities; The extracted scientific and technological resource entities, relationships and attributes are stored in a structured form.

5. The multi-source information fusion scientific and technological resource point extraction method according to claim 4, characterized in that, Cross-validation and complementary enhancement are performed on the identified main scientific and technological resource information to automatically fuse and calculate the data and construct a scientific and technological resource fusion model: The obtained information is cross-validated and complementarily enhanced and is associated to a scientific and technological resource knowledge ontology; When different source information is contradictory, weighted judgment is performed according to the timeliness of the information; Based on time series analysis and a scientific and technological resource topic model, the technical trends and research hotspot changes of the scientific and technological resources are analyzed and extracted; A technical value evaluation scientific and technological resource fusion model is constructed by using a machine learning algorithm.

6. The multi-source information fusion scientific and technological resource gist refining method according to claim 1, characterized in that, The scientific and technological resource fusion model is constructed, and the internal scientific and technological resources are deeply analyzed to refine core points and form a structured and normative description of the scientific and technological resources: Based on the fused scientific and technological resource model and knowledge network, the universal laws, consensus and core challenges of the scientific and technological resources are summarized; The advantages and disadvantages of the scientific and technological resources in the database are deeply analyzed according to the differences of different regions. According to the advantages and disadvantages of scientific and technological resources, core points are refined, and structured data is formed to describe the core requirements in a normative manner.

7. The multi-source information fusion scientific and technological resource gist refining method according to claim 1, characterized in that, The structured data is presented to the decision maker in a visual manner: The refined core requirements are presented to the decision maker in an intuitive and interactive manner through knowledge graph visualization, heat map, technology roadmap or trend curve.

8. A multi-source information fusion scientific and technological resource point extraction system, applied to the multi-source information fusion scientific and technological resource point extraction method of any one of claims 1-7, specifically comprising the following steps: According to the data attribute characteristics, the original scientific and technological resource database information in the multi-source heterogeneous data is obtained and cached; Information matching is performed with the original scientific and technological resource database information to generate a target scientific and technological resource database set; Through semantic analysis and entity recognition, the main information in the database is identified; According to the identified main scientific and technological resource information, cross-validation and complementary enhancement are performed, and a scientific and technological resource fusion model is constructed; Through the constructed scientific and technological resource fusion model, the core points of scientific and technological resources are refined; The core points of scientific and technological resources are presented to the decision maker in a visual manner.

9. An electronic device comprising: The memory, the processor and the computer program stored in the memory and executable on the processor, characterized in that the processor executes the program to realize the steps of the method of claim 8.

10. A computer-readable storage medium, the computer-readable storage medium storing computer-executable instructions, wherein, The computer executable instructions are used to make the computer execute the steps of the method of claim 8.

Images