Nuclear power engineering knowledge resource acquisition and processing method and system, storage medium and electronic equipment

Abstract

The invention relates to a nuclear power engineering knowledge resource collecting and processing method and system, a storage medium and electronic equipment, and the method comprises the following steps: collecting source data of different data sources, processing the source data to generate initial engineering knowledge data, and storing the initial engineering knowledge data in a nuclear power engineering knowledge base; screening the initial engineering knowledge data to obtain secondary engineering knowledge data resources; classifying the secondary engineering knowledge data resources to obtain classified data, and obtaining structured classified data; performing deep integration on the structured classification data to obtain integrated data; and releasing the integrated data through a service interface. According to the nuclear power engineering knowledge resource management system and method, efficient collection, classification and deep integration of nuclear power engineering knowledge resources can be achieved, a complete nuclear power engineering knowledge base is formed, the requirement for efficient utilization of the knowledge resources in the nuclear power industry can be met, meanwhile, the nuclear power engineering knowledge resources can be dynamically updated, and the reliability and real-time performance of data are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear power plant information management, and more specifically, to a method, a system, a storage medium, and an electronic device for collecting and processing nuclear power engineering knowledge resources. Background Art

[0002] The collection of nuclear power engineering knowledge resources is an important part of nuclear power knowledge resource services, mainly collecting information such as nuclear power industry news, enterprise dynamics, project information, and new technology applications, classifying and sorting the collected information, summarizing the information content, and pushing it to the corresponding service system after review. Professionals can obtain information by subscribing.

[0003] With the rapid development and wide application of nuclear power engineering technology, the related knowledge resources show the characteristics of being massive, multi-source, and heterogeneous. The existing means of collecting and processing knowledge resources often have problems such as low efficiency, incomplete coverage, and lagging updates, and cannot meet the high-efficiency utilization requirements of the nuclear power industry for knowledge resources. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method, a system, a storage medium, and an electronic device for collecting and processing nuclear power engineering knowledge resources in view of the problems existing in the prior art.

[0005] The technical solution adopted by the present invention to solve its technical problems is to construct a method for collecting and processing nuclear power engineering knowledge resources, including the following steps:

[0006] Collect source data from different data sources, process the source data to generate initial engineering knowledge data, and store the initial engineering knowledge data in a nuclear power engineering knowledge base;

[0007] Screen the initial engineering knowledge data to obtain secondary engineering knowledge data resources;

[0008] Classify the secondary engineering knowledge data resources to obtain classified data, and obtain structured classified data;

[0009] Deeply integrate the structured classified data to obtain integrated data;

[0010] Publish the integrated data through a service interface.

[0011] In the method for collecting and processing nuclear power engineering knowledge resources of the present invention, the step of collecting source data from different data sources, processing the source data to generate initial engineering knowledge data, and storing the initial engineering knowledge data in a nuclear power engineering knowledge base includes:

[0012] Collect multi-source data according to preset crawler rules to obtain source data from different data sources;

[0013] Identify and filter the source data to obtain nuclear power engineering data related to nuclear power engineering;

[0014] Deduplicate the nuclear power engineering data;

[0015] Perform error correction on the nuclear power engineering data after deduplication;

[0016] Format the nuclear power engineering data after error correction to obtain the initial engineering knowledge data;

[0017] Store the initial engineering knowledge data in the nuclear power engineering knowledge base.

[0018] In the nuclear power engineering knowledge resource collection and processing method of the present invention, the screening of the initial engineering knowledge data to obtain secondary engineering knowledge data resources includes:

[0019] Perform multi-dimensional evaluation on the initial engineering knowledge data based on a machine learning evaluation model to obtain high-quality resource data;

[0020] Perform personalized screening on the high-quality resource data to obtain the secondary engineering knowledge data resources.

[0021] In the nuclear power engineering knowledge resource collection and processing method of the present invention, the classification of the secondary engineering knowledge data resources to obtain classified data and obtaining structured classified data includes:

[0022] Determine the classification method;

[0023] Classify the secondary engineering knowledge data resources according to the classification method and the predefined nuclear power engineering knowledge system to obtain structured classified data.

[0024] In the nuclear power engineering knowledge resource collection and processing method of the present invention, the classification of the secondary engineering knowledge data resources according to the classification method and the predefined nuclear power engineering knowledge system to obtain structured classified data includes:

[0025] Screen the secondary engineering knowledge data resources based on the predefined nuclear power engineering knowledge system to obtain screened data;

[0026] Determine the classification model according to the classification method;

[0027] Classify the screened data based on the classification model to obtain the structured classified data.

[0028] In the method for collecting and processing nuclear power engineering knowledge resources according to the present invention, the step of deeply integrating the structured classification data to obtain integrated data includes:

[0029] Identifying the structured classification data to determine the text type of the structured classification data;

[0030] Based on the text type, performing deep integration to obtain the integrated data.

[0031] In the method for collecting and processing nuclear power engineering knowledge resources according to the present invention, the step of performing deep integration based on the text type to obtain the integrated data includes:

[0032] If the text type is unstructured text, constructing a knowledge graph;

[0033] If the text type is a core knowledge element, generating a knowledge summary;

[0034] If the text type is image data or video data, generating metadata.

[0035] The present invention also provides a nuclear power engineering knowledge resource collection and processing system, including:

[0036] A knowledge resource collection module, configured to collect source data of knowledge resources from different data sources, process the source data to generate initial engineering knowledge data, and store the initial engineering knowledge data in a nuclear power engineering knowledge base;

[0037] A knowledge resource screening module, configured to screen the initial engineering knowledge data to obtain secondary engineering knowledge data resources;

[0038] A knowledge resource classification module, configured to classify the secondary engineering knowledge data resources to obtain classification data, and perform structured processing on the classification data to obtain classified structured data;

[0039] A knowledge resource integration module, configured to deeply integrate the classified structured data to obtain integrated data;

[0040] A knowledge resource service interface module, configured to publish the integrated data through a service interface.

[0041] The present invention also provides a storage medium storing a computer program, which is suitable for being loaded by a processor to execute the steps of the above-mentioned method for collecting and processing nuclear power engineering knowledge resources.

[0042] The present invention also provides an electronic device, including a memory and a processor. A computer program is stored in the memory. The processor executes the steps of the nuclear power engineering knowledge resource collection and processing method as described above by calling the computer program stored in the memory.

[0043] Implementing the nuclear power engineering knowledge resource collection and processing method, system, storage medium and electronic device of the present invention has the following beneficial effects: Through the present invention, efficient collection, classification and in-depth integration of nuclear power engineering knowledge resources can be achieved, forming a complete nuclear power engineering knowledge base, which can meet the high-efficiency utilization requirements of the nuclear power industry for knowledge resources. At the same time, the nuclear power engineering knowledge resources can be dynamically updated to ensure the reliability and timeliness of the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention will be further described below in conjunction with the drawings and embodiments. In the drawings:

[0045] Figure 1 is a flowchart of the nuclear power engineering knowledge resource collection and processing method provided by the present invention;

[0046] Figure 2 is a schematic diagram of knowledge resource collection and processing provided by the present invention;

[0047] Figure 3 is a schematic diagram of knowledge resource screening provided by the present invention;

[0048] Figure 4 is a schematic diagram of knowledge resource classification provided by the present invention;

[0049] Figure 5 is a schematic diagram of in-depth integration of knowledge resources provided by the present invention;

[0050] Figure 6 is a schematic diagram of knowledge resource release provided by the present invention;

[0051] Figure 7 is a logical block diagram of the nuclear power engineering knowledge resource collection and processing system provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0053] The present invention firstly uses RPA (Robotic Process Automation, a new type of artificial intelligence virtual process automation robot) technology to automatically capture nuclear power engineering related content in a timely manner according to predefined rules, and clearly mark the source of the content. On this basis, it uses artificial intelligence to screen knowledge resources, establish a reasonable and effective classification scheme, integrate knowledge resources, highly summarize the content, and form a content summary of the knowledge resources. Through the knowledge resource service interface, the embedded application of knowledge resources in the business process is realized, and the resources are pushed to the people in need in a timely and proactive manner.

[0054] Specifically, refer to Figure 1 , Figure 1 A flow chart of a preferred embodiment of the method for collecting and processing nuclear power engineering knowledge resources provided by the present invention.

[0055] like Figure 1 As shown, the nuclear power engineering knowledge resource collection and processing method includes the following steps:

[0056] Step S101: collecting source data from different data sources, processing the source data to generate initial engineering knowledge data, and storing the initial engineering knowledge data in a nuclear power engineering knowledge base.

[0057] Optionally, in an embodiment of the present invention, if Figure 2 As shown, collecting source data from different data sources, generating initial engineering knowledge data after processing the source data, and storing the initial engineering knowledge data in the nuclear power engineering knowledge base includes: collecting multi-source data according to preset crawler rules to obtain source data from different data sources; identifying and filtering the source data to obtain nuclear power engineering data related to nuclear power engineering; deduplicating the nuclear power engineering data; performing error correction on the nuclear power engineering data that has completed the deduplication process; formatting the nuclear power engineering data that has completed the error correction process to obtain initial engineering knowledge data; and storing the initial engineering knowledge data in the nuclear power engineering knowledge base. In an embodiment of the present invention, the preset crawler rules are: assigning crawling priorities according to data, and identifying new content based on timestamps. This crawler technology can reduce duplicate requests.

[0058] Specifically, first, use the web crawler technology to collect data from different data sources (including but not limited to: data from Internet public websites, data from professional database APIs, data from open academic journals, data from conference paper databases, data from technical report databases, etc.), and capture data related to nuclear power engineering, such as various knowledge resources like text, images, videos, etc. At the same time, use intelligent recognition technology to identify and filter out irrelevant information. For example, identify and filter based on keywords (such as "reactor", "nuclear safety", etc.) and domain dictionaries (nuclear power engineering terminology library) to screen out valid data. Among them, the data types of the collected source data include but are not limited to: text (PDF / HTML / XML), images, videos, etc. At the same time, design dynamic parsing rules for data from different sources (such as web DOM parsing, API data extraction, PDF text extraction, video metadata capture, etc.). Among them, for unstructured text, extract the entity relationships of the knowledge graph to achieve structured storage, and for image / video data, perform metadata annotation. After the collection and recognition of the source data, it is also necessary to filter the source data (including processing such as deduplication, error correction, and formatting). Among them, deduplication is divided into deduplication based on content similarity and deduplication based on metadata or structure. Error correction includes text error correction (spelling, grammar); formatting includes unifying the data schema (converting heterogeneous data into a standard format such as JSON / XML; defining field constraints, such as "equipment model" must be a 10-digit alphanumeric combination); unifying the date format, physical units, and terms.

[0059] Step S102: Screen the initial engineering knowledge data to obtain secondary engineering knowledge data resources.

[0060] Optionally, in the embodiment of the present invention, screening the initial engineering knowledge data to obtain secondary engineering knowledge data resources includes: performing multi-dimensional evaluation on the initial engineering knowledge data based on a machine learning evaluation model to obtain high-quality resource data; performing personalized screening on the high-quality resource data to obtain secondary engineering knowledge data resources.

[0061] Specifically, such as Figure 3As shown in the figure, a knowledge resource quality evaluation model (i.e., a machine learning evaluation model) is constructed based on machine learning algorithms to evaluate the content quality, timeliness, authority, etc. of the initially collected knowledge data resources, so as to screen out high-quality resource data, that is, high-quality nuclear power engineering knowledge resources. At the same time, it also has functions such as keyword filtering and topic clustering to achieve personalized screening of resources according to user needs. Among them, the knowledge resource quality evaluation model includes: a text classification model BERT and a text similarity model Sentence-BERT. The text classification BERT is used to detect logical contradictions or technical errors in the text. The text similarity model Sentence-BERT is used to calculate the correlation score with the nuclear power theme, and a differential algorithm is used to compare the semantic differences between the new and old version documents based on the vector distance of Doc2Vec.

[0062] Step S103: Classify the secondary engineering knowledge data resources to obtain classified data and obtain structured classified data.

[0063] Optionally, in the embodiment of the present invention, classifying the secondary engineering knowledge data resources to obtain classified data and obtaining structured classified data includes: determining a classification method; classifying the secondary engineering knowledge data resources according to the classification method and the predefined nuclear power engineering knowledge system to obtain structured classified data. Among them, classifying the secondary engineering knowledge data resources according to the classification method and the predefined nuclear power engineering knowledge system to obtain structured classified data includes: screening the secondary engineering knowledge data resources based on the predefined nuclear power engineering knowledge system to obtain screened data; determining a classification model according to the classification method; classifying the screened data based on the classification model to obtain structured classified data.

[0064] Specifically, as Figure 4 shown in the figure, using the text classification technology of deep learning, according to the predefined nuclear power engineering knowledge system (including science and technology and information, engineering design, capital construction, quality and safety, communication management, etc., some contents are shown in Table 1), the screened secondary engineering knowledge data resources are classified into the corresponding knowledge categories to form structured classified data. At the same time, during the classification process, as Figure 2 shown in the figure, after determining the deep learning text classification model, automatically learn and adapt to the changes of the knowledge system (i.e., the predefined nuclear power engineering knowledge system) based on the classification decision, and maintain the dynamic update of the classification.

[0065] Table 1. Predefined Nuclear Power Engineering Knowledge System

[0066]

[0067]

[0068] Step S104: Deeply integrate the structured classification data to obtain integrated data.

[0069] Optionally, in the embodiments of the present invention, deeply integrating the structured classification data to obtain integrated data includes: identifying the structured classification data to determine the text type of the structured classification data; performing deep integration based on the text type to obtain integrated data. Among them, performing deep integration based on the text type to obtain integrated data includes: if the text type is unstructured text, constructing a knowledge graph; if the text type is core knowledge elements, generating a knowledge summary; if the text type is image data or video data, generating metadata.

[0070] Specifically, as Figure 5 shown, deeply integrating the classified knowledge resources may include, but is not limited to: associating similar or relevant knowledge entries, constructing a knowledge graph to reveal the internal connections between knowledge points; extracting core knowledge elements such as key concepts, formulas, and charts to generate a knowledge summary for easy and quick understanding and retrieval; removing duplicates and updating redundant or outdated knowledge to ensure the freshness and refinement of the content of the knowledge resources. Among them, the integrated data may include, but is not limited to: technical reports (structured fields: title, author, release date, key parameter table), academic papers (abstract, keywords, experimental data, references), regulations and standards (clause numbers, scope of application, revision history), nuclear power equipment drawings (annotations: equipment model, dimensions, materials), engineering site photos (metadata: shooting time, location, construction stage), etc.

[0071] Step S105: Publish the integrated data through a service interface.

[0072] Specifically, as Figure 6 shown, in the embodiments of the present invention, the integrated data obtained after deep integration can be stored in the nuclear power engineering knowledge base, and at the same time, standardized service interfaces for knowledge resource query, retrieval, subscription, etc. are provided, facilitating users to access and utilize the knowledge resources of the nuclear power engineering knowledge base at any time through various terminal devices. In addition, it also supports seamless integration with third-party platforms such as the knowledge management system and design management platform within the nuclear power, realizing the embedded application of knowledge resources in business processes.

[0073] Reference Figure 7 , Figure 7 is the logical block diagram of the nuclear power engineering knowledge resource acquisition and processing system provided by the present invention.

[0074] As Figure 7 shown, the nuclear power engineering knowledge resource acquisition and processing system includes:

[0075] The knowledge resource acquisition module 701 is used to acquire the source data of knowledge resources from different data sources, process the source data to generate initial engineering knowledge data, and store the initial engineering knowledge data in the nuclear power engineering knowledge base.

[0076] The knowledge resource screening module 702 is used to screen the initial engineering knowledge data to obtain secondary engineering knowledge data resources.

[0077] The knowledge resource classification module 703 is used to classify the secondary engineering knowledge data resources to obtain classified data, and perform structured processing on the classified data to obtain classified structured data.

[0078] The knowledge resource integration module 704 is used to deeply integrate the classified structured data to obtain integrated data.

[0079] The knowledge resource service interface module 705 is used to publish the integrated data through the service interface.

[0080] Specifically, the specific cooperation operation process between the units in the nuclear power engineering knowledge resource acquisition and processing system here can specifically refer to the above-mentioned nuclear power engineering knowledge resource acquisition and processing method, which will not be elaborated here.

[0081] The present invention provides a method for efficiently acquiring nuclear power engineering knowledge resources, which can automatically capture relevant content in a timely manner according to predetermined rules, effectively solve the problem of incomplete acquisition of nuclear power engineering knowledge resources, and realize the all-round and intelligent acquisition of knowledge resources. At the same time, through artificial intelligence, the collected knowledge resources are intelligently classified and deeply integrated, and knowledge services are embedded in the business process, reducing the repetitive and cumbersome sorting work, effectively meeting the high-efficiency utilization requirements of nuclear power design for knowledge resources, and realizing the accurate, dynamic classification and deep integration of knowledge resources.

[0082] Through the present invention, data is collected from multiple data sources such as the Internet, professional databases, academic journals, conference papers, and technical reports and integrated into a unified nuclear power engineering knowledge base. The data in the knowledge base is cleaned, classified, etc. through natural language processing technology, improving the quality and usability of the data, and realizing a more secure knowledge base establishment and update for nuclear power engineering knowledge requirements.

[0083] Furthermore, in view of the characteristics of nuclear power engineering knowledge resources, the present invention adopts a method based on the theme of the nuclear power engineering knowledge system for classification. Through deep learning of text data, text data features are extracted, and the results of classification and deep learning are integrated to form a complete nuclear power engineering knowledge base. The knowledge base data is regularly updated to achieve dynamic update in view of the dynamic changes of nuclear power engineering knowledge resources.

[0084] In addition, an electronic device according to the present invention includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to implement the nuclear power engineering knowledge resource acquisition and processing method as described in any one of the above. Specifically, according to an embodiment of the present invention, the process described with reference to the flowchart above can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the method shown in the flowchart. In such an embodiment, when the computer program is downloaded and installed by the electronic device and executed, it executes the above functions defined in the method of the embodiment of the present invention. The electronic device in the present invention can be a terminal such as a notebook, a desktop computer, a tablet computer, a smart phone, etc., or a server.

[0085] In addition, a storage medium according to the present invention has a computer program stored thereon, and when the computer program is executed by a processor, it implements the nuclear power engineering knowledge resource acquisition and processing method as described in any one of the above. Specifically, it should be noted that the above storage medium of the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or combined with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program codes. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or combined with an instruction execution system, apparatus, or device. The program codes contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0086] The above computer-readable medium may be included in the above electronic device; or it may exist independently without being assembled into the electronic device.

[0087] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the various embodiments, reference may be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference may be made to the description in the method section.

[0088] Those skilled in the art can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0089] The steps of the methods or algorithms described in combination with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0090] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. They do not limit the protection scope of the present invention. All equivalent changes and modifications made to the scope of the claims of the present invention shall fall within the scope covered by the claims of the present invention.

Claims

1. A method for collecting and processing nuclear power engineering knowledge resources, characterized in that, It includes the following steps: Collect the source data from different data sources, process the source data to generate initial engineering knowledge data, and store the initial engineering knowledge data in the nuclear power engineering knowledge base; Screen the initial engineering knowledge data to obtain secondary engineering knowledge data resources; Classify the secondary engineering knowledge data resources to obtain classified data, and obtain structured classified data; Deeply integrate the structured classified data to obtain integrated data; Publish the integrated data through a service interface.

2. The method for collecting and processing nuclear power engineering knowledge resources according to claim 1, wherein The step of collecting the source data from different data sources, processing the source data to generate initial engineering knowledge data, and storing the initial engineering knowledge data in the nuclear power engineering knowledge base includes: Collect multi-source data according to preset crawler rules to obtain source data from different data sources; Identify and filter the source data to obtain nuclear power engineering data related to nuclear power engineering; Perform duplicate removal processing on the nuclear power engineering data; Perform error correction processing on the nuclear power engineering data after duplicate removal; Perform formatting processing on the nuclear power engineering data after error correction to obtain the initial engineering knowledge data; Store the initial engineering knowledge data in the nuclear power engineering knowledge base.

3. The method for collecting and processing nuclear power engineering knowledge resources according to claim 1, wherein The step of screening the initial engineering knowledge data to obtain secondary engineering knowledge data resources includes: Perform multi-dimensional evaluation on the initial engineering knowledge data based on a machine learning evaluation model to obtain high-quality resource data; Perform personalized screening on the high-quality resource data to obtain the secondary engineering knowledge data resources.

4. The method for collecting and processing nuclear power engineering knowledge resources according to claim 1, characterized in that The step of classifying the secondary engineering knowledge data resources to obtain classified data and obtaining structured classified data includes: Determine the classification method; Classify the secondary engineering knowledge data resources according to the classification method and the predefined nuclear power engineering knowledge system to obtain structured classified data.

5. The method for collecting and processing nuclear power engineering knowledge resources according to claim 4, wherein The step of classifying the secondary engineering knowledge data resources according to the classification method and the predefined nuclear power engineering knowledge system to obtain structured classified data includes: Screen the secondary engineering knowledge data resources based on the predefined nuclear power engineering knowledge system to obtain screened data; Determine the classification model according to the classification method; Classify the screened data based on the classification model to obtain the structured classified data.

6. The method for collecting and processing nuclear power engineering knowledge resources according to claim 1, characterized in that The step of deeply integrating the structured classified data to obtain integrated data includes: Identify the structured classified data to determine the text type of the structured classified data; Perform deep integration based on the text type to obtain the integrated data.

7. The method for collecting and processing nuclear power engineering knowledge resources according to claim 6, wherein The step of performing deep integration based on the text type to obtain the integrated data includes: If the text type is unstructured text, construct a knowledge graph; If the text type is core knowledge elements, generate a knowledge summary; If the text type is image data or video data, generate metadata.

8. A nuclear power engineering knowledge resource collection and processing system, characterized in that, It includes: A knowledge resource collection module, which is used to collect the source data of knowledge resources from different data sources, process the source data to generate initial engineering knowledge data, and store the initial engineering knowledge data in the nuclear power engineering knowledge base; A knowledge resource screening module, which is used to screen the initial engineering knowledge data to obtain secondary engineering knowledge data resources; A knowledge resource classification module, which is used to classify the secondary engineering knowledge data resources to obtain classification data, and perform structured processing on the classification data to obtain classified structured data; A knowledge resource integration module, which is used to deeply integrate the classified structured data to obtain integrated data; A knowledge resource service interface module, which is used to publish the integrated data through a service interface.

9. A storage medium, characterized in that, The storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps of the nuclear power engineering knowledge resource acquisition and processing method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes a memory and a processor. A computer program is stored in the memory, and the processor executes the steps of the nuclear power engineering knowledge resource acquisition and processing method according to any one of claims 1 to 7 by calling the computer program stored in the memory.

Images