Intelligent knowledge architecture graph construction method and system based on large model

Abstract

The invention discloses an intelligent knowledge architecture graph construction method and system based on a large model, and belongs to the technical field of artificial intelligence, and the method comprises the steps: obtaining a plurality of entities from a plurality of text blocks; classifying the entities and the relationships to obtain entity types and relationship types; extracting common characteristics of the entities, and generating entity types with attributes; generating a relation type triple in combination with the entity type with attributes, constructing a preliminary knowledge architecture graph according to the relation type triple, and adding and deleting nodes and edges to generate guidance suggestions; and extracting new entities and relationships from subsequent text blocks based on suggestions, updating the relationship type triple, and generating a final knowledge architecture graph when the maximum iteration round is reached. According to the method, a large model is used for replacing people to construct the knowledge architecture graph, the labor cost and the time cost are reduced, an iterative construction method is adopted, the demand tendency of a user is reasoned by using a small amount of modification of people on part of the knowledge architecture graph, and the accuracy and comprehensiveness of the knowledge architecture graph are ensured.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to a method and system for constructing an intelligent knowledge architecture diagram based on a large model. Background Art

[0002] With the advent of the era of big models, the automated construction of knowledge graphs has gradually become the focus of attention. The application of big models has automated the construction of knowledge graphs to a certain extent, but before building a knowledge graph, domain experts are still needed to design a comprehensive and accurate knowledge architecture diagram. The knowledge architecture diagram contains the common characteristics of entities and semantic relationships expected by users, namely entity types and relationship types. These entity types and relationship types will be used to guide the construction of subsequent knowledge graphs to ensure that the entities and semantic relationships contained in the knowledge graph meet the needs of users. The quality of the knowledge architecture diagram will directly affect the effect of the final knowledge graph.

[0003] However, the existing technology has the following shortcomings: First, the construction of existing knowledge architecture diagrams is usually carried out manually, and the construction efficiency is low; Second, the manually constructed knowledge architecture diagrams often omit key entity types and relationship types, resulting in incomplete information in the knowledge architecture diagram, which in turn affects the reliability and quality of the knowledge graph, resulting in the low accuracy and comprehensiveness of the constructed knowledge architecture diagram. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method and system for constructing an intelligent knowledge architecture diagram based on a large model, which can solve the problems of low construction efficiency, accuracy and comprehensiveness in the process of constructing a knowledge architecture diagram in the prior art.

[0005] In order to solve the above technical problems, this application is implemented as follows: In a first aspect, an embodiment of the present application provides a method for constructing an intelligent knowledge architecture diagram based on a large model, the method comprising: S1, obtaining multiple entities from a first text block among multiple sequentially connected text blocks; S2, obtain the semantic relationship between multiple entities and construct a preliminary knowledge architecture diagram; S3, adding and deleting nodes and edges of the preliminary knowledge architecture diagram to obtain a knowledge architecture diagram, and storing the added and deleted entity types in the database; S4. Based on the big model, the added and deleted entity types in the database are integrated to generate the guidance and suggestion text for the current round and update the iteration round. ; S5, when the iteration round At this time, based on The guidance text for the round starts from Get the first The entity of the round and the semantic relationship of the round, generate the relationship instance triples of the round; S6. Based on the large model, perform entity classification and semantic classification on the entity of the round and the semantic relationship of the round respectively, obtain the updated entity type and relationship type, and construct the updated relationship type triples; S7. Merge the relationship type triples of the round with the updated relationship type triples, obtain the preliminary knowledge architecture diagram of the round, and return to step S3 until the current iteration round reaches the preset maximum iteration round and stops the iteration, generating the final knowledge architecture diagram.

[0006] As an alternative implementation manner of the first aspect of the present application, the specific steps for constructing the preliminary knowledge architecture diagram include: constructing relationship instance triples based on semantic relationships and entities; performing entity classification and semantic classification on entities and semantic relationships respectively to obtain entity types and relationship types; obtaining common features from the text blocks where multiple entities corresponding to each entity type are located based on the large model to obtain entity types with attributes; constructing multiple relationship type triples based on the entity types with attributes, relationship types, and relationship instance triples, and obtaining the preliminary knowledge architecture diagram based on the relationship type triples.

[0007] As an alternative implementation manner of the first aspect of the present application, the process of obtaining multiple sequentially connected text blocks includes: According to the number of iteration rounds input by the user, the large model evenly divides the input text into multiple sequentially connected text blocks. Starting from the second text block, each text block will retain one-tenth of the end of the previous text block as the connection part at the beginning of the current text block.

[0008] As an alternative implementation manner of the first aspect of the present application, the relationship types include: genus-species relationship, composition relationship, and location relationship.

[0009] As an alternative implementation manner of the first aspect of the present application, the preliminary knowledge architecture diagram is composed of multiple edges and multiple nodes. Among them, the nodes represent entity types, and the edges represent relationship types.

[0010] As an alternative implementation manner of the first aspect of the present application, the process of constructing multiple relationship type triples based on the entity types with attributes, relationship types, and relationship instance triples includes: ); Among them, respectively represent two different entity types, Represents the entity type 's list of attributes, Represents the entity type 's list of attributes, Represents the entity type and the entity type the semantic relationship between them, Represents the entity type the corresponding number of attributes.

[0011] As an alternative implementation of the first aspect of the present application, the common features represent those that appear more than or equal to a preset number of times in the text paragraphs corresponding to multiple entities of the same entity type according to the large model analysis, and are used to depict the static and dynamic characteristics of specific instances in the same entity type.

[0012] In a second aspect, an embodiment of the present application provides an intelligent knowledge architecture diagram construction system based on a large model, and the system includes: A text chunking module, configured to evenly chunk the user input text, obtain a plurality of sequentially connected text chunks, and obtain a plurality of entities from the first text chunk among the plurality of sequentially connected text chunks; A preliminary knowledge architecture diagram construction module, configured to obtain the semantic relationships between a plurality of entities and construct a preliminary knowledge architecture diagram; An artificial review and modification module, configured to add or delete nodes and edges of the preliminary knowledge architecture diagram to obtain a knowledge architecture diagram; A storage module, configured to store the added or deleted entity types in a database; A suggestion generation module, configured to fuse the added or deleted entity types stored in the database according to the large model to generate a guidance suggestion text; A knowledge architecture diagram update module, configured to iteratively update the knowledge architecture diagram according to the guidance suggestion text to generate a final knowledge architecture diagram.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, and the electronic device includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, and when the program or instruction is executed by the processor, the steps of the method as in the first aspect are implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a readable storage medium, and a program or instruction is stored on the readable storage medium, and when the program or instruction is executed by the processor, the steps of the method as in the first aspect are implemented.

[0015] Compared with the prior art, a method for constructing an intelligent knowledge architecture diagram based on a large model proposed in this application uses the large model to replace humans to construct the knowledge architecture diagram, significantly reducing the labor cost and time cost. In addition, this application adopts an iterative construction method, using a small number of modifications made by humans to a part of the knowledge architecture diagram to infer the user's demand tendency, ensuring the accuracy and comprehensiveness of the knowledge architecture diagram during the construction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flowchart of a method for constructing an intelligent knowledge architecture diagram based on a large model provided by the first embodiment of this application; Figure 2 is a schematic diagram of the knowledge architecture of a method for constructing an intelligent knowledge architecture diagram based on a large model provided by the first embodiment of this application; Figure 3 is a structural diagram of a system for constructing an intelligent knowledge architecture diagram based on a large model provided by the second embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this application without creative efforts shall fall within the protection scope of this application.

[0018] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application can be implemented in an order different from those illustrated or described herein. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally represents an "or" semantic relationship between the associated objects before and after.

[0019] Next, a method and system for constructing an intelligent knowledge architecture diagram based on a large model provided by the embodiments of this application will be described in detail in conjunction with the accompanying drawings through specific embodiments and their application scenarios.

[0020] Embodiment 1 Please refer to Figure 1 , which is a flowchart of a method for constructing an intelligent knowledge architecture diagram based on a large model proposed in the embodiments of this application. The proposed method includes steps S1 to S7.

[0021] Step S1: Obtain a plurality of entities from the first text block among a plurality of sequentially connected text blocks.

[0022] Specifically, the entity is a class object created for a preset entity class, and multiple sequentially connected text blocks are based on the number of iteration rounds input by the user. After that, the large model evenly divides the user input text into blocks. Starting from the second text block, each text block retains one-tenth of the end of the previous text block as the connection part at the beginning of the current text block. For example: when the user provides a 10,000-word text and requests ten iterations, the system will evenly cut the text into ten blocks, each block containing 1,100 words, where 100 words are the end part of the previous text block.

[0023] Furthermore, when the system obtains multiple entities from the first text block, it filters them from the text block according to the user's needs. The user's needs are a text description and belong to the user's request. For example: the user inputs the requirement: "I need to build a knowledge graph about the principles and functions of operating systems". After the user inputs this requirement and sends it to the system, after the system receives the user's needs, it uses the large model to filter out the entities that meet this requirement from the first text block.

[0024] This application cuts the text into multiple blocks and constructs a knowledge architecture diagram in multiple rounds. Only one text block is processed in each round to construct a part of the knowledge architecture diagram, and then the user is allowed to modify this part of the knowledge architecture diagram. The system summarizes the modification information to guide the construction of the subsequent knowledge architecture diagram. In this way, the large model can better understand the user's needs during the construction process, so as to construct a comprehensive and accurate knowledge architecture diagram with less manual participation. This application retains one-tenth of the end of the previous text block as the connection part, which can also ensure the semantic coherence of the text blocks.

[0025] Step S2: Obtain the semantic relationships between multiple entities and construct a preliminary knowledge architecture diagram.

[0026] Specifically, the specific steps for constructing a preliminary knowledge architecture diagram include: constructing relationship instance triples based on semantic relationships and entities; performing entity classification and semantic classification on entities and semantic relationships respectively to obtain entity types and relationship types; obtaining entity types with attributes based on the common features of multiple entities corresponding to each entity type from the text blocks where they are located by using the large model; constructing multiple relationship type triples based on entity types with attributes, relationship types, and relationship instance triples, and obtaining a preliminary knowledge architecture diagram based on the relationship type triples.

[0027] Specifically, the specific process of constructing relationship instance triples based on semantic relationships and entities includes: the system uses the large model to find out whether there is a semantic relationship between every two entities from multiple sequentially connected text blocks. If there is a semantic relationship, it uses concise words to summarize the semantic relationship between them, and uses relationship instance triples ( , , ), where and represent two different entity types, represents the semantic relationship between these two entity types. For example: when the text block shows: "ChatGPT is an AI chatbot developed by OpenAI, capable of understanding and generating natural language.", since this text block contains two entities, "ChatGPT" and "AI chatbot", the large model can analyze the semantic relationship "belongs to" between the two, thus obtaining the relationship instance triple (ChatGPT, belongs to, AI chatbot).

[0028] Furthermore, when performing entity classification and semantic classification on entities and semantic relationships respectively to obtain entity types and relationship types, entity types include but are not limited to: teachers, doctors, companies, schools, occupations, etc., and relationship types include: genus-species relationship, composition relationship, and location relationship. Among them, the genus-species relationship means: A is B, the composition relationship means: A is a component of B, and the location relationship means: A is located at B. Among them, A and B represent two different entities.

[0029] Furthermore, based on the large model, common features are obtained from the text blocks of multiple entities corresponding to each entity type, resulting in entity types with attributes. Among them, common features refer to those that appear in the text paragraphs of multiple entities corresponding to the same entity type analyzed by the large model and whose occurrence times are greater than or equal to the preset times, and are used to describe the static and dynamic characteristics of specific instances in the same entity type. For example: for the entity type "student" corresponding to entities such as Zhang San and Li Si, the text paragraphs where they are located are respectively: "Zhang San is 17 years old this year, a student in Class 1, Grade 12, with student number 1023" and "Li Si is 18 years old this year, a student in Class 1, Grade 12, with student number 1024", and the system will infer class, age, and student number as the attributes of the entity type "student". The entity type with attributes can be expressed as: ; where et1 represents the entity type, represents the attribute list of the entity type et1, represents each different attribute of the entity type et1.

[0030] Furthermore, the specific process of constructing multiple relationship type triples based on the entity type with attributes, relationship types, and relationship instance triples, and obtaining the preliminary knowledge architecture diagram includes: taking the two entity types , , in the relationship instance triple ( and and the semantic relationship After replacing them with the corresponding entity types and relationship types with attributes respectively, the relationship type triples of the current round are obtained; multiple relationship type triples of the current round are combined to construct a preliminary knowledge architecture diagram. Among them, the relationship type triples of the current round are expressed as: ) Among them, respectively represent two different entity types, represents the entity type 's attribute list, represents the entity type 's attribute list, represents the entity type and the entity type 's semantic relationship, represents the number of attributes corresponding to the entity type .

[0031] Step S3: Add or delete nodes and edges of the preliminary knowledge architecture diagram to obtain the knowledge architecture diagram, and store the added or deleted entity types in the database.

[0032] Specifically, the preliminary knowledge architecture diagram consists of multiple edges and multiple nodes. Among them, the nodes represent entity types, and the edges represent relationship types. The specific steps of adding or deleting nodes and edges of the preliminary knowledge architecture diagram to obtain the knowledge architecture diagram and storing the added or deleted entity types in the database include: The system displays the preliminary knowledge architecture diagram of the current round to the user in the form of a directed graph, and the user reviews and modifies the preliminary knowledge architecture diagram of the current round (i.e., performs addition or deletion operations on nodes and edges) to obtain the knowledge architecture diagram of the current round. During the user's modification process, the system stores the added or deleted entity types by the user in the database.

[0033] During the user's review and modification process, the user will review and analyze each relationship type triple in the preliminary knowledge architecture diagram generated in each round, modify the incorrect relationship type triples. The system will record the user's modification information and infer suggestions based on these user modification information to guide the construction of the subsequent knowledge architecture diagram, making the knowledge architecture diagram generated in the subsequent round more accurate and comprehensive than the knowledge architecture diagram generated in the current round.

[0034] Step S4: Based on the large model, fuse the added or deleted entity types in the database to generate the guidance suggestion text of the current round and update the iteration round .

[0035] Specifically, the process of generating the guidance recommendation text for the current round by fusing the entity types added or deleted in the database based on the large model includes: The system reads the entity types added or deleted by the user from the database, and uses the large model to fuse the added or deleted entity types, and then generates recommendations to guide the construction of the knowledge architecture diagrams in the subsequent rounds. For example, if the user adds entity types such as teacher and doctor, and deletes entity types such as company and school, the system will analyze the added entity types, fuse out the entity type of occupation, and then generate a recommendation that "the user is interested in entity types of this occupation category". At the same time, the system will analyze the deleted entity types, fuse out the entity type of organization, and then generate a recommendation that "the user is not interested in entity types of this organization category". Meanwhile, update the current iteration round , and the specific process is: At the end of each iteration, the current iteration round is incremented by 1, that is, the relationship is satisfied: .

[0036] Step S5: When the iteration round is reached, obtain the entities of the th round and the semantic relationships of the th round from the th text block based on the guidance recommendation text of the th round, and generate the relationship instance triples of the th round.

[0037] Specifically, the process of generating the relationship instance triples of the th round includes: The system filters entities from the th text block according to the user requirements and the recommendations generated in the th round, obtains the two entities of the th round, then uses the large model to judge the semantic relationship between these two entities, obtains the semantic relationship of the th round, and obtains the relationship instance triples of the th round based on the two entities of the th round and the semantic relationship of the th round.

[0038] Step S6: Based on the large model, perform entity classification and semantic classification on the entities of the th round and the semantic relationships of the th round respectively, obtain the updated entity types and relationship types, and construct the updated relationship type triples.

[0039] Specifically, the specific process of obtaining the updated entity types and relationship types includes: The system extracts the existing entity types and relationship types from the knowledge architecture diagram generated in the th round, and then uses the large model to combine the entities of the th round and the Classify the semantic relationships of the round, and preferentially classify them into existing entity types and relationship types. Filter out entities and relationships that are not classified into existing entity types and relationship types (for example: there is an entity type of "teacher" in the existing entity types. When entities such as "Teacher Zhang" and "Teacher Yang" are obtained, these entities will be preferentially classified into the entity type of "teacher". Otherwise, in this round, "Teacher Zhang" and "Teacher Yang" may be classified into the entity type of "teacher" again. Since the meanings of "teacher" and "teacher" are essentially the same, redundant entity types will appear). Then classify these entities and relationships separately to obtain updated entity types and relationship types.

[0040] Step S7: Merge the relationship type triples of the round with the updated relationship type triples to obtain the preliminary knowledge architecture diagram of the round, and return to step S3 until the current iteration round stops iterating when reaching the preset maximum iteration round, and generates the final knowledge architecture diagram.

[0041] Specifically, the preset maximum number of iterations of the present invention is , if the current number of iterations , steps S3 to S7 will be repeated until the current number of iterations When it is, it means that the construction of the knowledge architecture diagram has reached the last round. At this time, the knowledge architecture diagram generated in the round is the final knowledge architecture diagram.

[0042] Please refer to Figure 2 , Figure 2 is the schematic diagram of the knowledge architecture provided by the first embodiment of the present application, which is composed of multiple relationship type triples. Under the guidance of the pattern of (operating system, compliance, protocol), the large model can extract relationship type triples such as (Windows operating system, compliance, SMB protocol) and (Linux operating system, compliance, NFS protocol) from relevant text blocks.

[0043] The beneficial effect of an intelligent knowledge architecture diagram construction method based on a large model provided by the present application is that, first, the construction of the knowledge architecture diagram in the present application is divided into two processes, namely the construction of the current round and the round construction. The construction of each round includes extraction and classification, and manual review and modification. The round The construction is carried out under the guidance of the knowledge architecture diagram and suggestions generated in the previous round. In this way, the large model can better understand the user's needs during the construction process, so as to construct a comprehensive and accurate knowledge architecture diagram with less manual participation, greatly reducing the labor cost and time cost. Secondly, when generating the knowledge architecture diagram in each round of this application, the user can make minor modifications to some edges and nodes of the knowledge architecture diagram to infer the user's demand tendency. Modifying the edge means modifying the relationship type, and modifying the node means modifying the entity type. Through modification, the accuracy and comprehensiveness of the knowledge architecture diagram during the construction process can be ensured.

[0044] Embodiment 2 Please refer to Figure 3 , which shows the structure diagram of an intelligent knowledge architecture diagram construction system based on a large model provided by the second embodiment of this application, including: The text chunking module 100 is used to evenly chunk the user input text, obtain multiple sequentially connected text chunks, and obtain multiple entities from the first text chunk among the multiple sequentially connected text chunks; The preliminary knowledge architecture diagram construction module 200 is used to obtain the semantic relationships between multiple entities and construct a preliminary knowledge architecture diagram; The manual review and modification module 300 is used to add and delete nodes and edges of the preliminary knowledge architecture diagram to obtain a knowledge architecture diagram; The storage module 400 is used to store the added and deleted entity types in the database; The suggestion generation module 500 is used to fuse the added and deleted entity types stored in the database according to the large model to generate a guidance suggestion text; The knowledge architecture diagram update module 600 is used to iteratively update the knowledge architecture diagram according to the guidance suggestion text to generate a final knowledge architecture diagram.

[0045] The beneficial effects of an intelligent knowledge architecture diagram construction system based on a large model provided by this application are as follows. First, this application uses the text chunking module 100 to evenly chunk the input text, which can ensure the coherence of the semantics of each text chunk. Secondly, using the manual review and modification module 300 to add and delete nodes and edges of the preliminary knowledge architecture diagram to obtain a knowledge architecture diagram can infer the user's demand tendency by making minor modifications to some parts of the knowledge architecture diagram by humans, ensuring the accuracy and comprehensiveness of the knowledge architecture diagram during the construction process. Finally, using the suggestion generation module 500 to fuse the added and deleted entity types in the database to generate a guidance suggestion text can further enable the large model to better understand the user's needs during the construction process, so as to construct a comprehensive and accurate knowledge architecture diagram with less manual participation.

[0046] A system for constructing an intelligent knowledge architecture diagram based on a large model in an embodiment of the present application may be a device, or a component, an integrated circuit, or a chip in a terminal. The device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiments of the present application do not make specific limitations.

[0047] A system for constructing an intelligent knowledge architecture diagram based on a large model in an embodiment of the present application may be a device with an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems. The embodiments of the present application do not make specific limitations.

[0048] A system for constructing an intelligent knowledge architecture diagram based on a large model provided by an embodiment of the present application can implement Figures 1 to 2 each process implemented by a method for constructing an intelligent knowledge architecture diagram based on a large model in a method embodiment. To avoid repetition, it will not be elaborated here.

[0049] Optionally, an embodiment of the present application further provides an electronic device, including a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, it implements each process of the above method embodiment for constructing an intelligent knowledge architecture diagram based on a large model, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0050] An embodiment of the present application further provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by the processor, it implements each process of the above method embodiment for constructing an intelligent knowledge architecture diagram based on a large model, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0051] Among them, the processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes computer-readable storage media such as computer read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0052] It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article, or device including that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0053] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases, the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0054] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

Claims

1. A method for constructing an intelligent knowledge architecture diagram based on a large model, characterized in that: include: S1, obtaining a plurality of entities from a first text block among a plurality of sequentially connected text blocks; S2. Obtaining semantic relationships between the multiple entities and constructing a preliminary knowledge architecture diagram; S3, adding and deleting nodes and edges of the preliminary knowledge architecture diagram to obtain a knowledge architecture diagram, and storing the added and deleted entity types in a database; S4. Based on the big model, the added and deleted entity types in the database are integrated to generate the guidance and suggestion text for the current round and update the iteration round. ; S5, when the iteration round At this time, based on The guidance text for the round starts from Get the first The entity and the The semantic relationship of the round generates the The relation instance triple of the wheel; S6. Based on the large model The entity and the The semantic relations of the wheel are respectively subjected to entity classification and semantic classification to obtain updated entity types and relationship types, and to construct updated relationship type triples; S7, Merge The relationship type triplet of the first round and the updated relationship type triplet are obtained. The preliminary knowledge architecture diagram of the round is obtained, and the process returns to step S3 until the current iteration round. When the preset maximum number of iterations is reached, the iteration is stopped and the final knowledge architecture diagram is generated.

2. According to claim 1, a method for constructing an intelligent knowledge architecture diagram based on a large model is characterized in that: The specific steps of constructing the preliminary knowledge architecture diagram include: Constructing a relationship instance triple based on the semantic relationship and the entity; Performing entity classification and semantic classification on the entities and semantic relationships respectively to obtain entity types and relationship types; Based on the large model, common features are obtained from the text blocks where multiple entities corresponding to each entity type are located to obtain an entity type with attributes; A plurality of relationship type triplets are constructed based on the attributed entity type, the relationship type and the relationship instance triplets, and a preliminary knowledge architecture diagram is obtained based on the relationship type triplets.

3. According to the method for constructing an intelligent knowledge architecture diagram based on a large model according to claim 1, it is characterized in that: The process of obtaining the plurality of sequentially connected text blocks includes: According to the number of iterations input by the user, the large model evenly divides the input text into multiple sequentially connected text blocks. Starting from the second text block, each text block will retain one-tenth of the end of the previous text block as the connecting part at the beginning of the current text block.

4. According to claim 1, a method for constructing an intelligent knowledge architecture diagram based on a large model is characterized in that: The relationship types include: genus-species relationship, composition relationship and position relationship.

5. According to claim 2, a method for constructing an intelligent knowledge architecture diagram based on a large model is characterized in that: The preliminary knowledge architecture diagram consists of multiple edges and multiple nodes, wherein the nodes represent entity types and the edges represent relationship types.

6. The method for constructing an intelligent knowledge architecture diagram based on a large model according to claim 2, characterized in that: The process of constructing a plurality of relationship type triples based on the attributed entity type, the relationship type and the relationship instance triples includes: )； in, Represents two different entity types, Represents entity type A list of properties, Represents entity type A list of properties, Represents entity type and entity types The semantic relationship between Represents entity type The corresponding number of attributes.

7. The method for constructing an intelligent knowledge architecture diagram based on a large model according to claim 2, characterized in that: The common features represent the occurrence of multiple entities corresponding to the same entity type in a text paragraph greater than or equal to a preset number of times according to the large model analysis, and are used to characterize the static and dynamic features of specific instances in the same entity type.

8. An intelligent knowledge architecture diagram construction system based on a large model, characterized in that: The system comprises: A text slicing module is used to slice the user input text evenly, obtain a plurality of sequentially connected text blocks, and obtain a plurality of entities from a first text block among the plurality of sequentially connected text blocks; A preliminary knowledge architecture diagram construction module, used to obtain the semantic relationship between the plurality of entities and construct a preliminary knowledge architecture diagram; A manual review and modification module is used to add and delete nodes and edges of the preliminary knowledge architecture diagram to obtain a knowledge architecture diagram; The storage module is used to store the added and deleted entity types in the database; The suggestion generation module is used to fuse the added and deleted entity types stored in the database according to the big model and generate guidance suggestion text; The knowledge architecture diagram updating module is used to iteratively update the knowledge architecture diagram according to the guidance suggestion text to generate the final knowledge architecture diagram.

9. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of a method for constructing an intelligent knowledge architecture diagram based on a large model as described in any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the steps of a method for constructing an intelligent knowledge architecture diagram based on a large model as described in any one of claims 1-7 are implemented.

Images