Methods, systems, and storage media for constructing advanced scientific and technological knowledge graphs in multiple languages

Abstract

The application provides a multi-source language front-end science and technology knowledge graph construction method and system and a storage medium, wherein the steps of the construction method comprise the following: firstly, automatically capturing multi-lingual front-end science and technology data information from the Internet; then, performing Chinese translation of the captured front-end science and technology data information in corresponding languages; then, performing data screening on the translated front-end science and technology data information to obtain Chinese version front-end science and technology data information; then, performing data processing and mining on the obtained Chinese version front-end science and technology data information, extracting keywords between Chinese texts and mining relationships between concepts; and finally, obtaining a front-end science and technology knowledge graph through a visualization tool. The application can avoid language barriers, automatically generate a dynamic front-end science and technology knowledge graph, enable the public to easily understand foreign front-end science and technology research, and provide a reference for research in related fields.

Description

Technical Field

[0001] This invention relates to the field of advanced technology acquisition technology, and in particular to a method, system and storage medium for constructing an advanced technology knowledge graph in multiple languages. Background Technology

[0002] With science and technology becoming increasingly important, cutting-edge technology has become a key development goal for various countries. Currently, cutting-edge technologies abroad are concentrated in countries such as the United States, Japan, and South Korea. Traditionally, to acquire these technologies, people have to manually collect and organize information from foreign websites, a long-term task requiring continuous updates. However, this manual collection and organization process is time-consuming, requires professionals from various fields, and is often hampered by language barriers, resulting in a significant lack of understanding of these technologies.

[0003] A knowledge graph, known in the library and information science field as knowledge domain visualization or knowledge domain mapping map, is a series of different graphics that display the development process and structural relationships of knowledge. It uses visualization technology to describe knowledge resources and their carriers, and to mine, analyze, construct, draw and display knowledge and the interrelationships between them.

[0004] Therefore, there is an urgent need for a method, system, and storage medium for constructing advanced scientific and technological knowledge graphs in multiple languages, which can avoid language barriers, automatically generate dynamic advanced scientific and technological knowledge graphs, enable the public to easily understand foreign advanced scientific and technological research, and provide reference for research in related fields. Summary of the Invention

[0005] The purpose of this invention is to provide a method, system, and storage medium for constructing advanced technology knowledge graphs in multiple languages, aiming to solve the problem of high costs in translating and systematizing advanced technologies.

[0006] To achieve the above objectives, in a first aspect, the present invention provides a method for constructing an advanced technology knowledge graph in multiple languages, the steps of which include:

[0007] S1: Automatically retrieves multilingual cutting-edge technology data and information from the Internet;

[0008] S2: Translate the cutting-edge technology data information captured in step S1 into Chinese in the corresponding language;

[0009] S3: Filter the translated advanced technology data to obtain the Chinese version of the advanced technology data.

[0010] S4: Perform data processing and mining on the Chinese version of advanced technology data information obtained in step S3, extract keywords between Chinese texts, and mine the relationships between concepts;

[0011] S5: Obtain knowledge graphs of cutting-edge technologies through visualization tools.

[0012] As a further improvement to the above solution, after obtaining the advanced technology knowledge graph, a web interactive system is constructed to make the advanced technology knowledge graph available on web pages.

[0013] As a further improvement to the above solution, the Web interactive system includes, but is not limited to, information search and retrieval, and opinion discussion.

[0014] As a further improvement to the above solution, the step of automatically retrieving multilingual cutting-edge technology data from the Internet in step S1 is as follows:

[0015] S11: Initialize the URLs to be crawled;

[0016] S12: Configure the web crawler;

[0017] S13: Make a request to the initialized URL; determine whether the response is successful. If the response is unsuccessful, return to step S11. If the response is successful, obtain the response data and store the response data.

[0018] As a further improvement to the above scheme, the data crawling source in step S1 is relevant cutting-edge technology information published on the Internet by various countries.

[0019] As a further improvement to the above solution, step S2, which involves translating the captured cutting-edge technology data into Chinese, includes:

[0020] S21: Perform morphological processing on the acquired advanced scientific and technological data information in Chinese and corresponding languages;

[0021] S22: Establish a parallel corpus for the corresponding language;

[0022] S23: Establish a corresponding parallel corpus of idioms in the corresponding scientific and technological fields.

[0023] As a further improvement to the above scheme, each type of advanced scientific and technological information in a non-Chinese language needs to undergo morphological processing in both Chinese and the corresponding language, and corresponding parallel corpora and parallel idiom corpora in the corresponding scientific and technological fields need to be established respectively.

[0024] As a further improvement to the above solution, when filtering the translated cutting-edge technology data, the data is filtered according to multiple dimensions, including but not limited to date, region, and field, by using keyword integration, and a corresponding dataset is constructed.

[0025] As a further improvement to the above scheme, in step S5, the construction of the advanced technology knowledge graph includes:

[0026] S51: Attribute Extraction

[0027] First, the system automatically extracts and identifies keywords, and categorizes them. Then, it sorts them according to time and constructs a timeline map based on time. Finally, it identifies and disambiguates the corresponding technical fields and unifies the classification standards.

[0028] S52: Relation Extraction

[0029] First, the relationships between cutting-edge technologies are listed and displayed in a graph; then, these relationships are defined and categorized, while potential relationships between different cutting-edge technologies are automatically generated.

[0030] S53: Content Updates and Maintenance

[0031] Continuously follow the forefront of technology, add or delete content as needed, and generate a dynamic process of knowledge graph evolution.

[0032] S54: Knowledge Graph Visualization

[0033] A knowledge graph is generated using keywords as nodes and the relationships between cutting-edge technologies as lines. The higher the frequency of a keyword, the larger the node and the greater its importance.

[0034] As a further improvement to the above solution, the display languages ​​of the advanced technology knowledge graph include, but are not limited to, Chinese, English, Korean, Japanese, and German, to meet the needs of different groups of people.

[0035] Secondly, this invention also provides a system for constructing advanced scientific and technological knowledge graphs based on multi-source language big data, comprising:

[0036] The Internet data acquisition module is used to collect cutting-edge technology information publicly available on foreign websites.

[0037] The translation module includes morphological processing units for Chinese and foreign languages, a parallel corpus unit for the corresponding foreign language, and a corresponding parallel idiom corpus for the corresponding scientific and technological field, which is used to perform professional translation of the cutting-edge scientific and technological information.

[0038] The feature embedding module is used to process and mine the translated cutting-edge technology information, and extract keyword features and relationship features between cutting-edge technologies.

[0039] The knowledge graph display module includes a knowledge representation unit, a knowledge storage unit, a knowledge reasoning unit, and a visualization unit. It is used to display the keywords obtained from the feature embedding module and the relationships between cutting-edge technologies as a graph in the form of nodes and lines.

[0040] Thirdly, the present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for constructing an advanced technology knowledge graph based on multi-source language big data.

[0041] Fourthly, the present invention also provides an electronic device, including at least a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program in the memory, implements the steps of the above-described method for constructing an advanced technology knowledge graph based on multi-source language big data.

[0042] Because the present invention adopts the above technical solutions, the beneficial effects of this application are as follows:

[0043] This invention provides a method for constructing a multi-language advanced technology knowledge graph. First, it automatically crawls advanced technology data from the internet in multiple languages. Then, it translates the crawled data into Chinese in the corresponding languages. Next, it filters the translated data to obtain a Chinese version. Then, it processes and mines the Chinese data to extract keywords and explore relationships between concepts. Finally, it uses visualization tools to obtain an advanced technology knowledge graph. This method automatically generates a dynamic advanced technology knowledge graph, enabling the public to easily understand foreign advanced technology research and providing a reference for research in related fields. Simultaneously, it incorporates multi-language translation for data crawling, avoiding language barriers in acquiring advanced technology data and ensuring the accessibility of advanced technology information published by various countries on the internet. Compared to traditional manual translation, it significantly reduces the cost of obtaining advanced technology information.

[0044] In some preferred embodiments, when filtering translated cutting-edge scientific and technological data, the data is filtered by multiple dimensions, including but not limited to date, region, and field, using keyword integration, and a corresponding dataset is constructed. This setup facilitates the categorized management of cutting-edge scientific and technological data from different countries, fields, and times, which is conducive to the formation of structured knowledge graphs and a clearer understanding of future evolution trends, thus providing learning and reference value for research in related fields in my country. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of the process for constructing a multi-source language advanced technology knowledge graph disclosed in this invention.

[0047] Figure 2 This is a schematic diagram of the process for automatically extracting multilingual cutting-edge technology data from the Internet, as disclosed in this invention.

[0048] Figure 3 This is a structural block diagram of an embodiment of an advanced technology knowledge graph construction system based on multi-source language big data disclosed in this invention;

[0049] Figure 4 This is a schematic diagram of an advanced technology knowledge graph displayed on a webpage, using a multi-source language advanced technology knowledge graph construction method provided by the present invention.

[0050] The realization of the objective, functional characteristics and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] It should be noted that all directional indicators (such as up, down, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicator will also change accordingly.

[0053] The technical solutions of the various embodiments of the present invention can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0054] Example 1:

[0055] Reference Figure 1-4 This invention provides a method for constructing an advanced technology knowledge graph in multiple languages, the steps of which include:

[0056] S1: Automatically retrieves multilingual cutting-edge technology data and information from the Internet;

[0057] S2: Translate the cutting-edge technology data information captured in step S1 into Chinese in the corresponding language;

[0058] S3: Filter the translated advanced technology data to obtain the Chinese version of the advanced technology data.

[0059] S4: Perform data processing and mining on the Chinese version of advanced technology data information obtained in step S3, extract keywords between Chinese texts, and mine the relationships between concepts;

[0060] S5: Obtain knowledge graphs of cutting-edge technologies through visualization tools;

[0061] The method for constructing an advanced technology knowledge graph provided by this invention can automatically generate a dynamic advanced technology knowledge graph, enabling the public to easily understand foreign advanced technology research and providing reference for research in related fields. Simultaneously, it incorporates corresponding multi-language translation for data capture, avoiding language barriers in obtaining advanced technology data and information, and thus enabling access to advanced technology information published by various countries on the internet, ensuring data breadth. Compared to traditional manual translation, it significantly reduces the cost of obtaining advanced technology information.

[0062] As a preferred embodiment, after the advanced technology knowledge graph is constructed, a web interactive system is built to make the advanced technology knowledge graph available on a webpage; the content is displayed in the form of a webpage, and the web interactive system includes, but is not limited to, information search and retrieval, opinion discussion, etc., giving users the opportunity to express their ideas and participate in the construction of the graph; the website is easy to operate, and it is convenient to present multiple forms of models for users to choose from, intelligently generate charts, and quickly understand the main content.

[0063] In a preferred embodiment, step S1, which involves automatically retrieving multilingual cutting-edge technology data from the Internet, is as follows:

[0064] S11: Initialize the URLs to be crawled;

[0065] S12: Configure the web crawler;

[0066] S13: Make a request to the initialized URL; determine whether the response is successful. If the response is unsuccessful, return to step S11. If the response is successful, obtain the response data and store the response data. This setting enables real-time automatic data capture.

[0067] The content crawled includes text, video, images, and other data. The crawler is a program or script that automatically retrieves information from the World Wide Web according to predetermined rules. Traditional crawlers start from the URLs of one or more initial web pages, obtain the URLs on the initial web pages, and continuously extract new URLs from the current page and put them into a queue during the crawling process until the predetermined stopping conditions of the system are met.

[0068] This invention employs a focused crawler, which uses a webpage analysis algorithm to filter out irrelevant links, retaining useful links and placing them in a queue of URLs to be crawled. Then, based on a search strategy, it selects the next webpage URL to crawl from the queue, repeating the process until a certain system condition is met. Furthermore, all crawled webpages are stored by the system, analyzed, filtered, and indexed for later querying and retrieval. For focused crawlers, the analysis results obtained in this process may also provide feedback and guidance for subsequent crawling operations.

[0069] As a preferred embodiment, the data crawling source in step S1 is relevant cutting-edge technology information published by various countries on the Internet, especially the collection of cutting-edge ideas from information centers of technologically advanced countries such as the United States and Japan through the Internet. Therefore, it is necessary to translate the collected content into multiple languages, and the integrated result is divided into Chinese and foreign language parts.

[0070] In a preferred embodiment, step S2, which involves translating the captured cutting-edge technology data into Chinese, includes:

[0071] S21: Perform morphological processing on the acquired advanced scientific and technological data information in Chinese and corresponding languages;

[0072] S22: Establish a parallel corpus for the corresponding language;

[0073] S23: Establish a corresponding parallel corpus of idioms in the corresponding scientific and technological fields.

[0074] As a preferred embodiment, each type of advanced scientific and technological information in a non-Chinese language needs to undergo morphological processing in both Chinese and the corresponding language, and corresponding parallel corpora and parallel idiom corpora in the corresponding scientific and technological fields are established respectively.

[0075] As a preferred embodiment, when filtering translated cutting-edge technology data, keyword integration is used to filter the data according to multiple dimensions, including but not limited to date, region, and field, and a corresponding dataset is constructed. Since the searched content has both homogeneity and diversity—although they are all cutting-edge technological concepts—they come from different countries, fields, and times. Categorizing and managing this content facilitates the formation of a structured knowledge graph and a clearer understanding of future trends.

[0076] In a preferred embodiment, step S5, the construction of the advanced technology knowledge graph includes:

[0077] S51: Attribute Extraction

[0078] First, the system automatically extracts and identifies keywords, categorizes them, and treats the extracted keywords as nodes. The higher the frequency of a keyword, the larger the node. Ultimately, the size of the node determines the importance of the relevant cutting-edge technology. Then, the nodes are sorted according to time and a timeline graph is constructed based on time. Finally, the corresponding technology fields are identified and disambiguated to unify the classification standards.

[0079] S52: Relation Extraction

[0080] First, the relationships between cutting-edge technologies are listed and displayed in a graph; then, these relationships are defined and categorized, while potential relationships between different cutting-edge technologies are automatically generated.

[0081] S53: Content Updates and Maintenance

[0082] Continuously follow the forefront of technology, add or delete content as needed, and generate a dynamic process of knowledge graph evolution.

[0083] S54: Knowledge Graph Visualization

[0084] Specific references Figure 4 The system generates a knowledge graph of cutting-edge technologies using keywords as nodes and relationships between these technologies as lines. The higher the frequency of a keyword, the larger the node and the greater its importance. Users can access the main content of the desired cutting-edge technology and its relationships with other cutting-edge technology projects by moving and clicking the mouse within the knowledge graph. The visualization is intuitive and concise, showing dynamic changes in real time, and users can freely select the display model. The analysis results are presented in multiple dimensions and with diverse display methods, including real-time dynamic models, geographical distribution models, and time-based display models.

[0085] As a preferred embodiment, the display language of the advanced technology knowledge graph includes, but is not limited to, Chinese, English, Korean, Japanese, German, etc., so that different groups of people can choose to meet their needs.

[0086] Example 2:

[0087] Secondly, participation Figure 3 The present invention also provides a system for constructing advanced scientific and technological knowledge graphs based on multi-source language big data, comprising:

[0088] The Internet data collection module is used to automatically collect cutting-edge technology information publicly available on foreign websites;

[0089] The translation module includes morphological processing units for Chinese and foreign languages, a parallel corpus unit for the corresponding foreign language, and a corresponding parallel idiom corpus for the corresponding scientific and technological field, which is used to perform professional translation of the cutting-edge scientific and technological information.

[0090] The feature embedding module is used to process and mine the translated cutting-edge technology information, and extract keyword features and relationship features between cutting-edge technologies.

[0091] The knowledge graph display module includes a knowledge representation unit, a knowledge storage unit, a knowledge reasoning unit, and a visualization unit. It is used to display the keywords obtained from the feature embedding module and the relationships between cutting-edge technologies in the form of nodes and lines as a graph.

[0092] The advanced technology knowledge graph construction system provided by this invention can collect publicly available advanced technology information from foreign networks in real time through an Internet data acquisition module. After being compiled and reviewed by a translation module, the information is structured and stored in a database. Multiple parallel corpora have been established, such as English, Korean, and Japanese corpora. The corresponding languages ​​are translated and localized. After feature embedding, the knowledge is represented, stored, reasoned, and visualized.

[0093] Example 3:

[0094] Thirdly, the present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for constructing an advanced technology knowledge graph based on multi-source language big data.

[0095] The aforementioned storage media may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device. It is understood that the storage media can be any machine-readable medium capable of storing program code, such as random access memory (RAM), magnetic disk, hard disk, solid-state disk (SSD), or non-volatile memory.

[0096] Those skilled in the art will understand that embodiments of the present invention can be provided as methods or storage media. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0097] Example 4:

[0098] Fourthly, the present invention also provides an electronic device, including at least a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program in the memory, implements the steps of the above-described method for constructing an advanced technology knowledge graph based on multi-source language big data.

[0099] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. All equivalent structural transformations made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A method for constructing a multi-source language cutting-edge science and technology knowledge graph, characterized in that, The steps include: S1: automatically scraping multilingual cutting-edge technology data information from the Internet; S2: performing Chinese translation of the cutting-edge technology data information scraped in step S1 in the corresponding language; In step S2, the step of performing Chinese translation of the scraped cutting-edge technology data information in the corresponding language includes: S21: performing morphological processing of the acquired cutting-edge technology data information in Chinese and the corresponding language; S22: establishing a parallel corpus of the corresponding language; S23: establishing a parallel corpus of the corresponding technology field; S3: performing data screening on the translated cutting-edge technology data information to obtain Chinese version cutting-edge technology data information; S4: performing data processing and mining on the Chinese version cutting-edge technology data information obtained in step S3, extracting keywords between Chinese texts, and mining relationships between concepts; S5: obtaining a cutting-edge technology knowledge graph through a visualization tool; In step S5, the construction of the cutting-edge technology knowledge graph includes: S51: attribute extraction First, the system automatically extracts key words, identifies key words, and classifies them; then, according to time sequence, a timeline graph is constructed with time as the main body; finally, the corresponding technology field is identified and disambiguated, and the classification standard is unified; S52: relationship extraction First, list the relationships between cutting-edge technologies and display them in the graph; then, define and classify the relationships, and automatically generate potential relationships between different cutting-edge technologies; S53: content update and maintenance Continuously follow up the cutting-edge technology, and add, delete or modify the content at any time to generate the dynamic change process of the knowledge graph; S54: knowledge graph visualization Generate a knowledge graph with keywords as nodes and relationships between cutting-edge technologies as lines. The higher the frequency of the keywords, the larger the node and the higher the importance. 2.The multi-source language front-end science and technology knowledge graph construction method of claim 1, wherein, After obtaining the cutting-edge technology knowledge graph, a Web interactive system is constructed, and the cutting-edge technology knowledge graph is opened on the webpage. 3.The multi-source language front-end science and technology knowledge graph construction method according to claim 1 or 2, characterized in that, In step S1, the steps of automatically scraping multilingual cutting-edge technology data information from the Internet are as follows: S11: initialize the URL to be crawled; S12: set the crawler; S13: initiate a request to the initialized URL; determine whether the response is successful, if not, return to step S11, if successful, obtain the response data and store the response data. 4.The multi-source language front-end science and technology knowledge graph construction method of claim 1, wherein, Each non-Chinese language cutting-edge technology information needs to be processed in Chinese and the corresponding language, and a corresponding parallel corpus and a parallel corpus of the corresponding technology field are established. 5.The multi-source language front-end science and technology knowledge graph construction method according to claim 1 or 2, characterized in that, When performing data screening on the translated cutting-edge technology data information, the cutting-edge technology data information is screened according to date, region, field and other dimensions in the form of keyword integration, and a corresponding data set is constructed. 6.The multi-source language front-end science and technology knowledge graph construction method according to claim 1 or 2, characterized in that, The display language of the cutting-edge technology knowledge graph is any one of Chinese, English, Korean, Japanese and German. 7.A system for constructing a cutting-edge science and technology knowledge graph based on multi-source language big data, characterized in that, It includes: An Internet data acquisition module for acquiring publicly available cutting-edge technology information on foreign networks; The translation module comprises a morphological processing unit for Chinese and foreign languages, a parallel corpus unit corresponding to the foreign language, and a corresponding parallel familiar corpus corresponding to the scientific and technological field, and is used for professional translation of the front-end scientific and technological information; The feature embedding module is used for data processing and mining of the translated front-end scientific and technological information, and extracts keyword features and relationship features between front-end sciences and technologies; The knowledge graph display module comprises a knowledge representation unit, a knowledge storage unit, a knowledge reasoning unit and a visualization unit, and is used for displaying the keyword features and the relationship between the front-end sciences and technologies obtained by the feature embedding module in the form of nodes and lines as a graph; The front-end scientific and technological knowledge graph construction system based on multi-source language big data adopts the steps of the front-end scientific and technological knowledge graph construction method of any one of claims 1-6.

8. A storage medium, characterized by The storage medium stores a computer program, and the computer program is executed by the processor to realize the steps of the front-end scientific and technological knowledge graph construction method of any one of claims 1-6.

Images