A retrieval and graph analysis method based on a knowledge graph domain knowledge base

Abstract

The application provides a retrieval and graph analysis method based on a knowledge graph field knowledge base, comprising the following steps: storing knowledge graph field knowledge base content management data; constructing a knowledge graph field knowledge base retrieval function; storing knowledge graph field knowledge base knowledge construction data; building a knowledge graph field knowledge base graph construction function; and intelligently analyzing the knowledge graph field knowledge base graph. The retrieval and graph analysis method based on the knowledge graph field knowledge base, the device and the computer readable storage medium provided by the application optimize the display experience of content, reduce the complexity of search keywords of users, and ensure the accuracy of retrieval results under the premise of meeting functions.

Description

Technical Field

[0001] This invention relates to the field of knowledge graph technology, and more specifically, to a method, apparatus, and computer-readable storage medium for retrieval and graph analysis based on a knowledge graph domain knowledge base. Background Technology

[0002] The description of the background art in this invention pertains to related technologies and is used merely for illustration and to facilitate understanding of the invention. It should not be construed as the applicant explicitly believing or presuming that the invention was prior art on the filing date of the first application.

[0003] With the rapid development of deep learning methods, the extraction of textual information from natural language has also increased. Existing knowledge base platforms are mostly single-domain retrieval or knowledge construction platforms, lacking a data visualization model that combines knowledge base retrieval and knowledge graph construction. Furthermore, they are not very user-friendly for multi-domain applications, lack synonym / word cloud functionality, and have low data extraction accuracy. Moreover, most existing knowledge base platforms lack the integration of knowledge base retrieval and knowledge graphs; they either only support knowledge base retrieval or their knowledge graph construction and analysis only support structured data, failing to create multi-domain knowledge bases and lacking sufficient intelligence and flexibility. Therefore, combining domain-specific knowledge base retrieval and knowledge construction has a significant impact.

[0004] The current lack of knowledge graph platforms on the market that combine domain-specific knowledge base retrieval with graph analysis prevents the seamless transformation of unstructured text information into visualized graph data. It's well known that efficiency is greatly improved when content of interest can be found with minimal description and presented in a visually appealing graphical structure. Compared to text, graphs are more easily understood and key information is more readily grasped. Most current knowledge graph platforms are based on structured data or unstructured document libraries but lack graph analysis support. Furthermore, they cannot create word clouds of synonyms from different domains, impacting retrieval accuracy and recognition. For unstructured data, meeting the requirements for high precision, domain-specificity, and completeness is a prominent challenge facing current text retrieval and data analysis.

[0005] In summary, the shortcomings and deficiencies of existing technologies include: a lack of combined scenarios for knowledge base retrieval and knowledge construction; the platform is limited to a single domain and does not achieve domain diversification; the accuracy of retrieval and knowledge construction is not high, there is no domain synonym word cloud function, and the recognition rate of domain terminology synonyms is not high; the convenience and flexibility of knowledge base configuration are not high, and there is no permission configuration or multi-knowledge base service function.

[0006] To address the aforementioned technical problems, this invention proposes a retrieval and graph analysis method, device, and computer-readable storage medium based on a knowledge graph-based domain knowledge base. This results in a highly accurate, domain-specific knowledge base retrieval product and a knowledge graph analysis visualization platform. The developed knowledge graph-based knowledge base platform is used to construct a retrieval and graph analysis platform for domain knowledge bases, optimizing the retrieval process, improving retrieval accuracy, combining graph analysis, and enabling knowledge base data visualization. While fulfilling functional requirements, the invention optimizes the content display experience, reduces the complexity of user search keywords, and ensures the accuracy of search results. Summary of the Invention

[0007] This invention provides a method, device, and computer-readable storage medium for retrieval and graph analysis based on a knowledge graph-based domain knowledge base. It achieves a high-precision, domain-specific knowledge base retrieval product and realizes a knowledge graph analysis visualization platform. The developed knowledge graph-based knowledge base platform is used to construct a platform for domain knowledge base retrieval and graph analysis, optimizing the retrieval process, improving retrieval accuracy, combining graph analysis, and realizing knowledge base data visualization. While meeting functional requirements, it optimizes the content display experience, reduces the complexity of user search keywords, and ensures the accuracy of search results.

[0008] An embodiment of the first aspect of the present invention provides a retrieval and graph analysis method based on a knowledge graph domain knowledge base, comprising the following steps: storing knowledge graph domain knowledge base content management data; extracting unstructured natural language into structured data; identifying content information in the content and storing it in Elasticsearch; constructing a knowledge graph domain knowledge base retrieval function; employing Elasticsearch's full-text retrieval technology; configuring dynamic weight ratio conditions for querying; and using a combination of phrase matching and fuzzy query conditions for data retrieval; storing knowledge graph domain knowledge base knowledge construction data; extracting and labeling results from the structured natural language data using extraction models and semantic rules; identifying knowledge graph construction information within the data and storing it in Elasticsearch and ArrangoDB; building a knowledge graph domain knowledge base graph construction function; performing intelligent analysis using the knowledge graph domain knowledge base graph; performing intelligent analysis of the document library using knowledge models; and generating a stable model library after model training.

[0009] Preferably, in the step of storing the knowledge graph domain knowledge base content management data, the stored text content storage structure includes creation time, content type, paragraph ID, domain information, article title, paragraph title, and paragraph content.

[0010] Preferably, the steps for constructing the knowledge graph domain knowledge base retrieval function include the following operations: the application server and the parsing engine server perform initialization operations; the application server requests the original text parsing content from the front end; ElasticSearch obtains the original text parsing content from the application server and returns the original text parsing content to the application server; the front end renders the returned original text parsing content; the front end selects a model and rule base for pre-annotation and passes the pre-annotated content to the application server; the parsing engine server obtains the pre-annotated content from the application server; the parsing engine server performs model and rule base parsing; the application server obtains the annotation data from the parsing engine server; the front end obtains the annotation data from the application server and renders the page; the front end performs entity annotation, relation annotation, and tag annotation; the application server obtains the annotation option settings from the front end and determines whether the settings are successful; if the settings are successful, the front end performs synonym annotation and sends it to the application server, and the application server determines whether the saving is successful; if the saving is successful, the front end annotates the data, updates the document library, and sends it to the application server; the application server sends the updated identifier data to ElasticSearch; the application server returns operation success information to the front end.

[0011] Preferably, in the step of storing the knowledge construction data of the knowledge graph domain knowledge base, the stored knowledge graph data storage structure includes version information, domain information, word association array information, data coordinates, creation time, article ID, paragraph ID, and data attribute type.

[0012] Preferably, the word association array information includes synonym association information, similar word information, tagged word information, and segmented word information; the data attribute types include entity, relation, and event.

[0013] Preferably, the steps for building a knowledge graph construction function in the knowledge graph domain include the following operations: the front end sends the query knowledge graph construction annotation results to the retrieval server; ElasticSearch obtains the query knowledge graph construction annotation results through the retrieval server; page rendering and highlighting of annotation attribute words are passed to the front end; the front end allows clicking on words and expanding the graph, and passes this information to the retrieval server; based on the query words, the query words are concatenated and passed to ArangoDB; ArangoDB returns the graph traversal results to the retrieval server; page rendering, displaying the knowledge graph, and showing statistical information are passed to the front end.

[0014] Preferably, the steps for intelligent analysis using a knowledge graph domain knowledge base graph include the following operations: initialization; the parsing engine server requests the model and rule base; the application server returns the model and rule base to the parsing engine server; the front-end creates and edits tasks to the application server; the application server determines whether the saving is successful; if the saving is successful, feedback is sent to the front-end, and the application server starts training; Elasticsearch obtains the original text set data and labeled data from the application server; Elasticsearch processes the data and returns it to the application server; the application server starts the training task and sends feedback to the parsing engine server; the parsing engine server returns the training task ID; the application server requests the training task progress from the parsing engine server; the parsing engine server performs model training. The parsing engine server generates the model and uploads the model file to atlas-oss; atlas-oss returns the model URL to the parsing engine server; the parsing engine server completes the training task and returns the model URL to the application server; the application server notifies the frontend that the training task is complete; the frontend can view the task details; the parsing engine server requests the training status and details from the application server; the parsing engine server returns the training status and details to the application server; the frontend displays the training status and details; the frontend requests to save the model; the application server saves the model to the parsing engine server; atlas-oss pulls the model and updates it; the parsing engine server obtains the updated model and passes it to the application server, completing the model update; the application server reports a successful operation to the frontend.

[0015] Preferably, in the step of building the knowledge graph domain knowledge base graph construction function, a combination of ElasticSearch and ArangoDB is used for retrieval and query. Based on the domain knowledge base retrieval results, related content knowledge is queried and stored in ElasticSearch data. The graph is constructed by highlighting words. By clicking on graph words on the page, starting from the query of related words, data is retrieved from ArangoDB and returned to form a knowledge graph graph.

[0016] A second aspect of the present invention also provides a retrieval and graph analysis device based on a knowledge graph domain knowledge base, comprising a memory and a processor; wherein the memory is used to store executable program code; and the processor is used to read the executable program code stored in the memory to execute the retrieval and graph analysis method based on the knowledge graph domain knowledge base.

[0017] A third aspect of the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements a retrieval and graph analysis method based on a knowledge graph domain knowledge base.

[0018] This invention provides a method, device, and computer-readable storage medium for retrieval and graph analysis based on a knowledge graph-based domain knowledge base. It achieves a high-precision, domain-specific knowledge base retrieval product and a knowledge graph analysis visualization platform. The developed knowledge graph-based knowledge base platform is used to construct a platform for domain knowledge base retrieval and graph analysis, optimizing the retrieval process, improving retrieval accuracy, combining graph analysis, and realizing knowledge base data visualization. While meeting functional requirements, it optimizes the content display experience, reduces the complexity of user search keywords, and ensures the accuracy of search results.

[0019] Additional aspects and advantages of the invention will become apparent in the following description or may be learned by practice of the invention. Attached Figure Description

[0020] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0021] Figure 1 A flowchart illustrating a retrieval and graph analysis method based on a knowledge graph domain knowledge base according to an embodiment of the present invention is shown.

[0022] Figure 2 A text content storage structure diagram of a retrieval and graph analysis method based on a knowledge graph domain knowledge base according to an embodiment of the present invention is shown.

[0023] Figure 3 This diagram illustrates the domain knowledge base retrieval sequence in the domain knowledge base retrieval and graph analysis method based on a knowledge graph according to an embodiment of the present invention.

[0024] Figure 4 This diagram illustrates the knowledge graph data storage structure in a knowledge graph-based domain knowledge base retrieval and graph analysis method according to an embodiment of the present invention.

[0025] Figure 5 This diagram illustrates the query sequence diagram for knowledge graph construction in a knowledge graph-based domain knowledge base retrieval and graph analysis method according to an embodiment of the present invention.

[0026] Figure 6 The diagram illustrates a timeline of the knowledge graph construction and training model in a knowledge graph-based domain knowledge base retrieval and graph analysis method according to an embodiment of the present invention.

[0027] Figure 7 This is a structural diagram of an embodiment of a knowledge graph retrieval and graph analysis device based on a knowledge base in the field of knowledge graphs, as described in this specification.

[0028] Figure 8This is a structural diagram of an embodiment of a computer-readable storage medium for knowledge graph retrieval and graph analysis methods based on knowledge graph domain knowledge bases, as described in this specification. Detailed Implementation

[0029] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0030] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0031] The following discussion provides several embodiments of the invention. While each embodiment represents a single combination of the invention, different embodiments of the invention can be substituted or combined, and therefore the invention can also be considered to include all possible combinations of the same and / or different embodiments described. Thus, if one embodiment includes A, B, and C, and another embodiment includes a combination of B and D, then the invention should also be considered to include embodiments containing one or more other all other possible combinations of A, B, C, and D, even if such embodiments are not explicitly described in the following text.

[0032] Figure 1 A flowchart illustrating a retrieval and graph analysis method based on a knowledge graph domain knowledge base according to an embodiment of the present invention is shown. Figure 1 As shown, the retrieval and graph analysis method based on the knowledge graph domain knowledge base includes the following steps: Step S01, store the content management data of the knowledge graph domain knowledge base, extract unstructured natural language into structured data, identify the content information in the content and store it in Elasticsearch; Step S02, build the knowledge graph domain knowledge base retrieval function, use Elasticsearch's full-text search technology, configure dynamic weight ratio conditions for querying, and use a combination of phrase matching and fuzzy query conditions for data retrieval; Step S03, store the knowledge construction data of the knowledge graph domain knowledge base, extract the natural language after data structuring through extraction models and semantic rules to intelligently extract and annotate the results, identify the knowledge graph construction information in it and store it in Elasticsearch and ArangoDB; Step S04, build the knowledge graph construction function of the knowledge graph domain knowledge base; Step S05, use the knowledge graph domain knowledge base graph for intelligent analysis, use knowledge models to intelligently analyze the document library, and generate a stable model library after model training.

[0033] Figure 2 This diagram illustrates the text content storage structure of a knowledge graph-based domain knowledge base retrieval and graph analysis method according to an embodiment of the present invention. Figure 2 As shown, this describes the data storage for knowledge base content management in the knowledge graph domain. It extracts unstructured natural language into structured data, identifying and storing information such as article titles, paragraph headings, paragraph content, and synonyms in the content within Elasticsearch. Content is stored at the paragraph level as the smallest unit, with simultaneous synonym replacement for content terms. Each attribute is further divided into its own sub-attributes to facilitate more intelligent knowledge base analysis.

[0034] Figure 3 This diagram illustrates the domain knowledge base retrieval sequence in a knowledge graph-based domain knowledge base retrieval and graph analysis method according to an embodiment of the present invention; as shown... Figure 3 As shown, this demonstrates the knowledge base retrieval function in the knowledge graph domain. It employs ElasticSearch's full-text search technology, performing queries based on dynamically weighted conditions configured for content titles, paragraph titles, and paragraph content. Data retrieval utilizes a combination of phrase matching and fuzzy search criteria, and results can be sorted based on content parsing time and matching degree.

[0035] Figure 4 This diagram illustrates the knowledge graph data storage structure in a knowledge graph-based domain knowledge base retrieval and graph analysis method according to an embodiment of the present invention; as shown... Figure 4 As shown, this is a data storage method for knowledge graph knowledge base construction. After structuring the data, natural language extraction is used to intelligently extract and annotate the results through extraction models and semantic rules. The resulting knowledge graph construction information, such as entities, relationships, and events, is then stored in Elasticsearch and ArangoDB. Content storage is based on labeled attributes as the smallest unit, and is associated with paragraph information from content parsing. To further improve search accuracy, associated thesaurus word cloud data is also stored during storage.

[0036] Figure 5 This diagram illustrates a query sequence diagram for knowledge graph construction in a knowledge graph-based domain knowledge base retrieval and graph analysis method according to an embodiment of the present invention; as shown. Figure 5As shown, this is the knowledge graph construction function in the knowledge graph domain. It uses a combination of Elasticsearch and ArangoDB for retrieval and querying. Based on the search results from the domain knowledge base, it queries related content knowledge to construct and store Elasticsearch data, creating a graph with highlighted words. By clicking on words in the graph, users can search for related words as starting points, querying data in ArangoDB to form a knowledge graph. It also supports graph operations (K-layer expansion, full path, shortest path) and provides rich data statistics panels and query filtering rules.

[0037] Figure 6 This diagram illustrates a time-series diagram of the knowledge graph construction and training model in a knowledge graph-based domain knowledge base retrieval and graph analysis method according to an embodiment of the present invention; as shown. Figure 6 As shown, this demonstrates intelligent analysis of knowledge base graphs in the knowledge graph domain. It employs knowledge models to intelligently analyze document databases. Different domain model databases, through continuous training on large volumes of documents, generate a stable model database. This database can then intelligently extract content entities, relationships, and event identifiers from the documents, reducing the time and effort required for manual labeling and significantly improving the labeling capabilities of the document database.

[0038] The retrieval and graph analysis method based on a knowledge graph domain knowledge base provided in this embodiment of the invention includes, in the step of storing the content management data of the knowledge graph domain knowledge base, the stored text content storage structure includes creation time, content type, paragraph ID, domain information, article title, paragraph title, and paragraph content.

[0039] The retrieval and graph analysis method based on a knowledge graph domain knowledge base provided in this invention includes the following steps for constructing a knowledge graph domain knowledge base retrieval function: The application server and the parsing engine server perform initialization operations; the application server requests the original text parsed content from the front end; ElasticSearch obtains the original text parsed content from the application server and returns it to the application server; the front end renders the returned original text parsed content; the front end selects a model and rule base for pre-annotation and transmits the pre-annotated content to the application server; the parsing engine server obtains the pre-annotated content from the application server; the parsing engine server... The application server parses the model and rule base; the application server retrieves the labeled data from the parsing engine server; the front end retrieves the labeled data from the application server and renders the page; the front end performs entity labeling, relationship labeling, and tag labeling; the application server retrieves the labeling option settings from the front end and determines whether the settings are successful; if the settings are successful, the front end performs synonym labeling and sends it to the application server, which determines whether the saving is successful; if the saving is successful, the front end annotates the data, updates the document library, and sends it to the application server; the application server sends the updated labeling data to Elasticsearch; the application server returns a success message to the front end.

[0040] The retrieval and graph analysis method based on a knowledge graph domain knowledge base provided in this embodiment of the invention includes the following in the step of storing knowledge construction data from the knowledge graph domain knowledge base: the stored knowledge graph data storage structure includes version information, domain information, word association array information, data coordinates, creation time, article ID, paragraph ID, and data attribute type.

[0041] The retrieval and graph analysis method based on a knowledge graph domain knowledge base provided in this embodiment of the invention includes word association array information such as synonym association information, similar word information, tagged word information, and segmented word information; data attribute types include entity, relation, and event.

[0042] The retrieval and graph analysis method based on a knowledge graph domain knowledge base provided in this invention includes the following steps for building a knowledge graph domain knowledge base graph construction function: The front end sends the query knowledge graph construction annotation results to the retrieval server; ElasticSearch obtains the query knowledge graph construction annotation results through the retrieval server; page rendering and highlighting of annotation attribute words are performed and transmitted to the front end; word clicks and graph expansion are performed through the front end and transmitted to the retrieval server; query words are concatenated and transmitted to ArangoDB; ArangoDB returns the graph traversal results to the retrieval server; page rendering, display of the knowledge graph, and display of statistical information are performed to the front end.

[0043] The retrieval and graph analysis method based on a knowledge graph domain knowledge base provided in this invention includes the following steps for intelligent analysis using a knowledge graph domain knowledge base: initialization; the parsing engine server requests the model and rule base; the application server returns the model and rule base to the parsing engine server; the front-end creates and edits tasks to the application server; the application server determines whether the saving is successful; if the saving is successful, feedback is sent to the front-end; the application server starts training; Elasticsearch obtains the original text set data and labeled data from the application server; Elasticsearch processes the data and returns it to the application server; the application server starts the training task and sends feedback to the parsing engine server; the parsing engine server returns the training task ID; the application server requests the training task progress from the parsing engine server. The parsing engine server trains the model; the parsing engine server generates the model and uploads the model file to atlas-oss; atlas-oss returns the model URL to the parsing engine server; the parsing engine server completes the training task and returns the model URL to the application server; the application server notifies the frontend that the training task is complete; the frontend can view the task details; the parsing engine server requests the training status and details from the application server; the parsing engine server returns the training status and details to the application server; the frontend displays the training status and details; the frontend requests to save the model; the application server saves the model to the parsing engine server; atlas-oss pulls the model and updates it; the parsing engine server obtains the updated model and passes it to the application server, completing the model update; the application server reports a successful operation to the frontend.

[0044] The retrieval and graph analysis method based on a knowledge graph domain knowledge base provided in this embodiment of the invention uses a combination of ElasticSearch and ArangoDB for retrieval queries in the step of building the knowledge graph domain knowledge base graph construction function. Based on the domain knowledge base retrieval results, it queries related content knowledge to construct and store ElasticSearch data, constructs a graph to highlight words, and allows users to click on graph words on the page, starting with the query of related words, and query data in ArangoDB to return and form a knowledge graph graph.

[0045] The retrieval and graph analysis method based on a knowledge graph-based domain knowledge base provided in this invention mainly includes knowledge base content management, knowledge base service management, model management, rule management, knowledge base annotation task, and graph construction data extraction. Those skilled in the art should understand that: user permission allocation is set based on a user center; model management and rule management identify annotation results, and regular expressions define the information extracted based on annotation items; the extraction model can predict and extract graph structure information; and the thesaurus word cloud management automatically replaces different domain synonyms in documents during intelligent parsing.

[0046] Compared with existing technologies, the retrieval and graph analysis method based on knowledge graph domain knowledge bases provided in this invention has the following advantages: it supports different knowledge base domains, adds synonym word cloud management, improves the universality of professional terms, can create multiple different knowledge graph-based domains according to actual needs, and supports deriving different knowledge graphs based on different knowledge graph ontology settings; it realizes the conversion of unstructured text information into data that can be used for knowledge base retrieval and can be associated with and converted into a data visualization platform for graph construction; the platform supports multiple knowledge base services and has dedicated access links. Specific content can be selected for knowledge base retrieval and graph construction, and permission configuration is added; based on knowledge extraction models and rule configurations, graph triplet data is extracted from knowledge base text information to form a graph analysis image.

[0047] Figure 7 This is a structural diagram of an embodiment of a knowledge graph retrieval and graph analysis device based on a knowledge base in the knowledge graph field, as described in this specification; see below for reference. Figure 7 This illustration shows a structural diagram of a knowledge graph-based domain knowledge base retrieval and graph analysis device 300 suitable for implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0048] like Figure 7As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0049] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0050] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 309, or installed from a storage device 308, or installed from a ROM 302. When the computer program is executed by the processing device 301, it performs the functions defined in the methods of embodiments of this disclosure.

[0051] Figure 8 This is a structural diagram of an embodiment of a computer-readable storage medium for knowledge graph retrieval and graph analysis methods based on knowledge bases in the field of knowledge graphs, as described in this specification. Figure 8 As shown, a computer-readable storage medium 40 according to an embodiment of the present disclosure stores non-transitory computer-readable instructions 41 thereon. When the non-transitory computer-readable instructions 41 are executed by a processor, all or part of the steps of the retrieval and graph analysis methods based on knowledge graph domain knowledge bases described in the foregoing embodiments of the present disclosure are performed.

[0052] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. 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 thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0053] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0054] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: construct a base page, the page code of which is used to build the environment required for the operation of the business page and / or implement the same workflow abstracted from similar business scenarios; construct one or more page templates, the page templates being used to provide code templates for implementing business functions in the business scenario; based on the corresponding page templates, through code conversion of the specific functions of each page in the business scenario, generate the final page code for each page in the business scenario; and merge the generated final page code of each page into the page code of the base page to generate the code for the business page.

[0055] Alternatively, the aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: construct a base page, the page code of which is used to build the environment required for the operation of the business page and / or implement the same workflow abstracted from similar business scenarios; construct one or more page templates, the page templates being used to provide code templates for implementing business functions in the business scenario; based on the corresponding page templates, through code conversion of the specific functions of each page in the business scenario, generate the final page code for each page in the business scenario; and merge the generated final page code of each page into the page code of the base page to generate the code for the business page.

[0056] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0057] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0058] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0059] This invention provides a method, device, and computer-readable storage medium for retrieval and graph analysis based on a knowledge graph-based domain knowledge base. It combines knowledge graphs with domain knowledge bases, enabling the creation of multiple different knowledge graph ontology-based domains according to actual needs, without domain limitations. These domains can be used for knowledge base retrieval and knowledge graph construction. It offers comprehensive functionality, supports permission configuration, allows selection of specific knowledge content for retrieval and knowledge graph construction, and features a visual knowledge base retrieval interface linked to graph construction, providing rich data visualization. A rich domain thesaurus and word cloud significantly reduce repetitive work for domain experts in maintaining and managing the knowledge base, and performs synonym replacement during knowledge base retrieval, improving extraction accuracy. It supports extracting and structuring data from unstructured natural language text information, and then converting the structured data into knowledge graph data in one step, achieving data visualization from text information to graph display, making information more intuitive and comprehensive. While meeting functional requirements, it optimizes the content display experience, reduces the complexity of user search keywords, and ensures the accuracy of retrieval results.

[0060] In this invention, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance; the term "multiple" refers to two or more unless otherwise explicitly defined. The terms "install," "connect," "link," and "fix" should be interpreted broadly. For example, "connect" can be a fixed connection, a detachable connection, or an integral connection; "link" can be a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0061] In the description of this invention, it should be understood that the terms "upper" and "lower" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or unit referred to must have a specific orientation or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting this invention.

[0062] In the description of this specification, the terms "one embodiment," "some embodiments," "specific embodiment," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0063] The above are merely some embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A knowledge graph domain knowledge base-based retrieval and graph analysis method, characterized in that, Comprise the following steps: The knowledge graph field knowledge base content management data is stored, the non-structured natural language is extracted as structured data, the content information in the content is recognized and stored in ElasticSearch; The knowledge graph field knowledge base retrieval function is constructed, the full-text retrieval technology of ElasticSearch is adopted, the dynamic weight proportion condition is configured for query, the query condition combining phrase matching and fuzzy query is adopted for data retrieval; The knowledge graph field knowledge base knowledge construction data is stored, the structured natural language is extracted through the extraction model and semantic rules for intelligent extraction and annotation results, the knowledge graph construction information is recognized and stored in ElasticSearch and ArangoDB; The knowledge graph field knowledge base graph construction function is built; The knowledge graph field knowledge base graph is used for intelligent analysis, the knowledge model is used for intelligent analysis of the document library, and a stable model library is generated after model training, wherein the step of constructing the knowledge graph field knowledge base retrieval function comprises the following operations: The application service end and the parsing engine service end are initialized; The application service end requests the original text parsing content to the front end; ElasticSearch obtains the original text parsing content through the application service end, and returns the original text parsing content to the application service end; The front end renders the returned original text parsing content; The front end selects the model and rule library for pre-annotation, and transmits the pre-annotation content to the application service end; The parsing engine service end obtains the pre-annotation content from the application service end; The parsing engine service end performs model and rule library parsing; The application service end obtains the annotation data from the parsing engine service end; The front end obtains the annotation data from the application service end and renders the page; The front end performs entity annotation, relationship annotation and label annotation; The application service end obtains the annotation option setting from the front end, and judges whether the setting is successful; If the setting is successful, the front end performs synonym annotation and sends it to the application service end, and the application service end judges whether the saving is successful; If the saving is successful, the front end performs annotation data and updates the document library, and sends it to the application service end; The application service end sends the updated annotation data to ElasticSearch; The application service end returns the operation success information to the front end; The step of building the knowledge graph field knowledge base graph construction function comprises the following operations: The front end sends the query knowledge graph construction annotation result to the retrieval service end; ElasticSearch obtains the query knowledge graph construction annotation result through the retrieval service end; Page rendering and annotation attribute word highlighting display are transmitted to the front end; Through the front end, the word is clicked, the graph is expanded, and is transmitted to the retrieval service end; According to the query word, the query word is spliced and transmitted to ArangoDB; ArangoDB returns the graph traversal result to the retrieval service end; Page rendering, displaying knowledge graph and showing statistical information are transmitted to the front end. 2.The knowledge graph domain knowledge base based retrieval and graph analysis method according to claim 1, characterized in that, The stored text content storage structure includes creation time, content type, paragraph ID, domain information, article title, paragraph title, and paragraph content. 3.The knowledge graph domain knowledge base based retrieval and graph analysis method according to claim 1, characterized in that, The stored knowledge graph data storage structure includes version information, domain information, word association array information, data coordinates, creation time, article ID, paragraph ID, and data attribute type. 4.The knowledge graph domain knowledge base based retrieval and graph analysis method according to claim 3, characterized in that, The word association array information includes synonym association information, similar word information, marked word information, and segmented word information; and the data attribute type includes entity, relationship, and event. 5.The knowledge graph domain knowledge base based retrieval and graph analysis method according to claim 1, characterized in that, The step of performing intelligent analysis on the knowledge graph domain knowledge base graph includes the following operations: Initialization, parsing engine server requests for models and rule bases, and application server returns models and rule bases to the parsing engine server; Front-end new creation and editing tasks to the application server, and the application server judges whether the saving is successful; If the saving is successful, feedback to the front end, and the application server starts training; ElasticSearch obtains original text set data and labeled data on the application server; ElasticSearch returns the processed data to the application server; The application server starts training tasks and feeds back to the parsing engine server; The parsing engine server returns the training task ID; The application server requests the training task progress from the parsing engine server; The parsing engine server performs model training; The parsing engine server generates a model and uploads the model file to atlas-oss; The atlas-oss returns the model URL address to the parsing engine server; The parsing engine server completes the training task and returns the model URL address to the application server; The application server notifies the front end that the training task is completed; View task details through the front end; The parsing engine server requests training status and details from the application server; The parsing engine server returns the training status and details to the application server; The front end displays the training status and details; The front end requests to save the model; The application server saves the model to the parsing engine server; The atlas-oss pulls the model and performs model updating; The parsing engine server obtains the updated model and passes it to the application server, completing model updating; The application server feeds back to the front end that the operation is successful. 6.The knowledge graph domain knowledge base based retrieval and graph analysis method according to any one of claims 1-5, characterized in that, In the step of building the knowledge graph domain knowledge base graph construction function, ElasticSearch and ArangoDB are combined for retrieval and query, according to the domain knowledge base retrieval result, the associated content knowledge construction stored ElasticSearch data is queried, the graph construction word highlight display is performed, and the related word is queried as the starting point through page clicking graph words to return the knowledge graph graph formed by ArangoDB query data.

7. A knowledge graph domain knowledge base based search and graph analysis device comprising a memory and a processor; wherein, The memory is configured to store executable program codes; The processor is configured to read the executable program codes stored in the memory to execute the knowledge graph domain knowledge base-based retrieval and graph analysis method according to any one of claims 1-6.

8. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 7. The computer program is executed by a processor to implement the retrieval and graph analysis method based on the knowledge graph domain knowledge base according to any one of claims 1-6.

Images