CN114860951A

CN114860951A - System and method for assisting in generating domain knowledge graph

Info

Publication number: CN114860951A
Application number: CN202210460560.XA
Authority: CN
Inventors: 陈德政
Original assignee: Individual
Current assignee: Individual
Priority date: 2022-04-24
Filing date: 2022-04-24
Publication date: 2022-08-05

Abstract

The invention discloses a system and a method for assisting in generating a domain knowledge graph, which comprises a basic library module, a knowledge graph assisting construction module, a submitted data integration processing module and a knowledge graph output module, wherein the basic library module comprises a knowledge construction model base, a knowledge construction algorithm base, a domain knowledge base and a knowledge graph output symbol base, and the knowledge construction model base, the knowledge construction algorithm base and the domain knowledge base are electrically connected with the knowledge graph assisting construction module; according to the invention, through the matching of the basic library module, the knowledge map auxiliary construction module, the submitted data integration processing module and the knowledge map output module, the basic library module comprises a knowledge construction model library, a knowledge construction algorithm library, a field knowledge library and a knowledge map output symbol library, and the quality of the finally generated knowledge map can be effectively ensured by adopting the preset knowledge construction model to expand knowledge.

Description

System and method for assisting in generating domain knowledge graph

Technical Field

The invention belongs to the technical field of knowledge maps, and particularly relates to a system and a method for assisting in generating a domain knowledge map.

Background

Knowledge Graph (Knowledge Graph), also known as Knowledge domain visualization or Knowledge domain mapping map, is a series of different graphs displaying the relationship between the Knowledge development process and the structure, describes Knowledge resources and carriers thereof by using visualization technology, and excavates, analyzes, constructs, draws and displays Knowledge and the mutual relation between the Knowledge resources and the carriers. The knowledge graph is a structured semantic knowledge base in nature, aims to describe various concepts and entities existing in the real world and the interrelation thereof, and can provide a practical and valuable reference for scientific research.

In the prior art, a knowledge graph is generally generated based on a thought-guiding graph and a concept map technology, or a knowledge graph is constructed by extracting related knowledge from network resources such as encyclopedic and the like; the Mind Map (Mind Map) expresses the relationship of each level of topics by using mutual membership and related hierarchical maps by using the skill of image-text repetition, and is an effective graphical Mind tool for expressing divergent thinking.

The Concept Map (Concept Map) is a network graphical representation of knowledge and relationships between knowledge, wherein the Concept is represented by nodes and the relationships between concepts are represented by connecting lines. By means of the thinking guide diagram, the concept diagram method or the software technology, the user can be well assisted to aim at a certain central knowledge theme, utilize the divergent thinking, mine other knowledge themes and the relation between the other knowledge themes and the central knowledge theme as much as possible, and show the knowledge themes in a tree-shaped and mesh structure diagram, so that a knowledge diagram with a clear center and convenience in memory and use can be generated from zero.

However, the knowledge graph is generated based on the thinking map and the concept map technology, and because the knowledge decomposition method utilizes divergent thinking and lacks standardization, concretionary and completeness, the randomness is stronger and is often limited by knowledge level, hierarchy and the like of a generator, the quality of the generated knowledge graph is often uneven in hierarchy, and the scale generation of the knowledge graph in the field is difficult;

by utilizing network resources such as encyclopedic and the like and through technical means such as big data, artificial intelligence and the like, the knowledge graph in the field can be quickly constructed. However, this solution faces two key difficulties. Firstly, the accuracy, scientificity and integrity of knowledge cannot be guaranteed by taking network resources such as encyclopedic and the like as data sources, especially in some advanced fields. Secondly, the knowledge extracted from the data of different sources and different structures is often disordered, a relatively formed knowledge graph can be finally constructed through a large amount of complex information processing in the later period, including complex operations such as manual classification and labeling, and the quality cannot be guaranteed. In addition, in the knowledge graph constructed by the method, data mapping of knowledge entities, relations and attributes is often performed only by using lines and the like, and the visualization is not strong.

To this end, we propose a system and method for assisting in generating domain knowledge maps to solve the existing problems described above.

Disclosure of Invention

The present invention is directed to a system and method for assisting in generating a domain knowledge graph to solve the above-mentioned problems in the background art.

In order to achieve the purpose, the invention adopts the following technical scheme:

a system for assisting in generating a domain knowledge graph comprises a basic library module, a knowledge graph assisting construction module, a submitted data integration processing module and a knowledge graph output module, wherein the basic library module comprises a knowledge construction model base, a knowledge construction algorithm base, a domain knowledge base and a knowledge graph output symbol base;

the knowledge graph auxiliary construction module comprises knowledge subject setting, keyword extraction, knowledge construction model recommendation and selection and knowledge graph auxiliary construction; the submitted data integration processing module comprises basic identification of knowledge entities, a static space domain of the knowledge entities, a dynamic time domain of the knowledge entities, research domains of a plurality of knowledge entities and a contact system of the knowledge entities, and is used for integrating data submitted by a user and aiming at all node contents and a constructed model of a given knowledge topic; the knowledge graph output module is used for outputting the data processed by the submitted data integration processing module in a knowledge graph mode for a user to inquire, learn and use.

Preferably, the knowledge building model library includes a concept model, an attribute model, a characteristic model, a quantity model, an intuitive model, an emotion model, a structural model, a functional model, an upper model, a lower model, a parallel model, an overall model, a local model, a common model, a positive and negative model, an analysis model, a comprehensive model, an abstract model, a summary model, a generalization model, a transformation model, a similarity model, a difference model, a similarity model, a class shift model, an analogy model, a process model, a result model, a cause model, a background model, a condition model and a measure model, and is used for analyzing and building a certain knowledge entity in the field.

Preferably, the knowledge construction algorithm library comprises a concept algorithm, an attribute algorithm, a feature algorithm, a quantity algorithm, a visual algorithm, an emotion algorithm, a structural algorithm, a functional algorithm, an upper algorithm, a lower algorithm, a parallel algorithm, an overall algorithm, a local algorithm, a common algorithm, a positive and negative algorithm, an analysis algorithm, a comprehensive algorithm, an abstract algorithm, a summary algorithm, an induction algorithm, a deduction algorithm, an association algorithm, a imagination algorithm, a transformation algorithm, an identity algorithm, an exception algorithm, a similarity algorithm, a class shift algorithm, an analogy algorithm, a process algorithm, a result algorithm, a cause algorithm, a background algorithm, a condition algorithm and a measure algorithm, and is used for extracting the related content of a certain knowledge entity in the field from the field knowledge library.

Preferably, the domain knowledge base is a large domain knowledge base constructed by adopting manual addition or network acquisition and processing means through a knowledge construction model in a knowledge construction model base, and provides reference for a user in the process of establishing the domain knowledge map.

Preferably, the knowledge-graph output symbol library includes a central theme, a theme-type content, a descriptive content, a development process/stage, an item list, a content list, a connecting line, an arrow line, a concept, an attribute, a relation, a feature, an intrinsic feature, an extrinsic feature, a quantity, an intuition, an emotion, a structure, a constitution, an essence, a status, a function, an upper level, a lower level, a parallel level, a whole level, a local level, a common level, a positive and negative level, an analysis, a synthesis level, an abstraction level, a generalization level, a deduction level, an association level, an imagination level, a transformation level, a sameness level, an inequality level, a similarity level, a displacement level, an analogy level, a process, a result level, a cause, a background, a condition and a measure, and is used for symbolizing various relations in the domain knowledge graph.

Preferably, the knowledge-graph auxiliary construction module is used for generating a user specific domain knowledge graph, and specifically includes the following steps:

a1, setting a knowledge theme, which is used for a user to input the knowledge theme needing to generate the domain knowledge graph and using the knowledge theme as a primary node;

a2, extracting keywords, wherein the keywords are used for extracting the keywords of the knowledge subject of the domain knowledge graph input by the user;

a3, recommending and selecting a knowledge construction model, wherein the knowledge construction model is used for the system to recommend or the user to autonomously select the knowledge construction model through the keyword analysis of the acquired knowledge subject;

a4, secondary node generation, which is used for the system to combine the acquired knowledge topic key words and the knowledge construction model finally determined by the user, and to acquire the matching knowledge topic key words from the domain knowledge base and the lower knowledge topics corresponding to the knowledge construction model as the reference of the user to construct the lower knowledge topics through the knowledge construction algorithm corresponding to the knowledge construction model, and the user determines the specific content of the node according to the specific reference content;

a5, repeating A2 to A4 according to the specific content determined by the secondary node, generating the tertiary node, and circulating the steps until the generation of the group of nodes is finished;

and A6, repeating A3 to A4, generating other secondary nodes different from the previous group, and generating each group of nodes according to A5 until new selection cannot be performed any more, wherein the domain knowledge graph is constructed in an auxiliary manner.

Preferably, when the secondary node is generated in step a4, the primary knowledge topic may be analyzed from different angles and aspects by using the same knowledge building model, and each building model is not necessarily used, and is specifically determined according to the attribute of the node, and the lower-level node is the same; when the generation of the secondary nodes is carried out, the recommendation of the system for constructing the model is carried out according to the following grouping:

A. constructing internal characteristic contents of the knowledge entity, wherein the internal characteristic contents comprise a concept model, an attribute model, a structure model, a local model and a lower model;

B. constructing external characteristic contents of the knowledge entity, wherein the external characteristic contents comprise a characteristic model, a visual model, a quantity model and an emotion model;

C. constructing dynamic development contents of knowledge entities, including a process model;

D. establishing knowledge entity rational knowledge content, including comprehensive model, analysis model, abstract model, general model, inductive model and deduction model;

E. establishing the existing position content of the knowledge entity, wherein the existing position content of the knowledge entity comprises a function model, a result model, a reason model, a background model, a condition model and a measure model;

F. establishing the contrast content of the knowledge entity, including a difference model, an identity model, a similar model, an analogy model and a class shift model;

G. the method comprises the following steps of establishing peripheral expansion contents of a knowledge entity, wherein the peripheral expansion contents comprise an upper model, a parallel model, an integral model, a common model, a positive and negative model, a transformation model, an association model and a imagery model.

Preferably, the basic identification of the knowledge entity mainly comprises the concept, attribute and research on the entity from the perspective of system theory; the static space domain of the knowledge entity is researched from the attribute of the entity and the structure and the function based on the system theory; the dynamic time domain of the knowledge entity is the research on the entity from the time perspective; the research domains of the knowledge entities are mainly carried out from three aspects of multi-entity generation, multi-entity research of the same system and multi-entity research of different systems; the relation system of the knowledge entities is mainly developed from the structural property of a system theory and the relevance of each element.

Preferably, in the domain knowledge graph finally output by the knowledge graph output module, various relations are displayed in a text mode or symbol conversion is performed through symbols in the domain knowledge graph output symbol library, so that the visual representation of the graph is improved.

Based on the system for assisting in generating the domain knowledge graph, the invention also provides a method for assisting in generating the domain knowledge graph, which comprises the following steps:

s1, a user firstly inputs the knowledge subject needing to generate the domain knowledge map as a primary node by means of pinyin, handwriting, voice input and the like through the setting operation of the knowledge subject in the knowledge map auxiliary construction module;

s2, after the user confirms the input, the keyword extraction operation will extract the keywords of the knowledge subjects of the domain knowledge graph set by the user;

s3, the system recommends or the user autonomously selects a knowledge construction model by analyzing the acquired knowledge topic keywords;

s4, determining a knowledge construction model by a user;

s5, the system combines the acquired knowledge topic key words and the knowledge construction model finally determined by the user, and acquires the matched knowledge topic key words from the domain knowledge base and the lower knowledge topic corresponding to the knowledge construction model as the reference of the user to construct the lower knowledge topic through the knowledge construction algorithm corresponding to the knowledge construction model;

s6, determining the specific content of the secondary node by the user according to the reference content given by the system;

s7, repeating S2-S6 after the secondary node is determined, generating the tertiary node, and circulating in the same way until the generation of the group of nodes is finished;

s8, repeating S3 to S7, generating other secondary nodes different from the previous group, and generating each group of nodes according to S7 until new selection can not be performed, and completing the auxiliary construction of the domain knowledge graph;

s9, the submitted data integration processing module processes the data submitted by the user;

and S10, outputting the final knowledge graph by the domain knowledge graph output module.

Compared with the prior art, the system and the method for assisting in generating the domain knowledge graph have the following advantages that:

1. the knowledge map quality generation method mainly comprises the steps that the basic library module, the knowledge map auxiliary construction module, the submitted data integration processing module and the knowledge map output module are matched, the basic library module comprises a knowledge construction model base, a knowledge construction algorithm base, a field knowledge base and a knowledge map output symbol base, and the quality of a finally generated knowledge map can be effectively guaranteed by adopting a preset knowledge construction model to expand knowledge.

2. According to the invention, through the matching of the set knowledge graph output symbol library and the knowledge graph output module, all data relations in the graph are replaced by corresponding specific symbols, so that the influence of the data relations on the data contents is reduced to the maximum extent, and the visual expression and the use value of the knowledge graph are greatly improved.

3. In the whole knowledge graph auxiliary construction process, the guiding function of a knowledge construction model, the reference content extraction capability of a knowledge construction algorithm and the strong support capability of an original knowledge base of a system are important, and the guidance of the knowledge construction model can effectively help a user to define the expansion direction of knowledge and reduce the influence on the knowledge graph construction due to the knowledge plane of the user to the maximum extent; the reference content is extracted through a knowledge construction algorithm, so that a user can be maximally assisted to develop more correct knowledge content; and the existence of the system knowledge base provides guarantee for the establishment of a high-quality knowledge graph to a certain extent.

Drawings

FIG. 1 is a block diagram of the system of the present invention;

FIG. 2 is a basic block diagram of the knowledge entity of the present invention;

FIG. 3 is a static spatial domain structure diagram of a knowledge entity of the present invention;

FIG. 4 is a diagram of a dynamic time domain structure of a knowledge entity of the present invention;

FIG. 5 is a research domain structure diagram of a plurality of knowledge entities of the present invention;

FIG. 6 is a diagram of a relationship architecture between knowledge entities of the present invention;

FIG. 7 is a schematic illustration of a portion of a symbol of a knowledge-graph output symbol library of the present invention;

FIG. 8 is another schematic diagram of a portion of a symbol of the knowledge-graph output symbol library of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The specific embodiments described herein are merely illustrative of the invention and do not delimit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The invention provides a system for assisting in generating a domain knowledge graph, which comprises a basic library module, a knowledge graph assisting construction module, a submitted data integration processing module and a knowledge graph output module, wherein the basic library module comprises a knowledge construction model base, a knowledge construction algorithm base, a domain knowledge base and a knowledge graph output symbol base;

the knowledge map auxiliary construction module comprises knowledge subject setting, keyword extraction, knowledge construction model recommendation and selection and knowledge map auxiliary construction; the submitted data integration processing module comprises basic identification of the knowledge entities, a static space domain of the knowledge entities, a dynamic time domain of the knowledge entities, research domains of a plurality of knowledge entities and a contact system of the knowledge entities, and is used for integrating data submitted by a user and aiming at all node contents and a constructed model of a given knowledge topic; the knowledge graph output module is used for outputting the data processed by the submitted data integration processing module in a knowledge graph mode for a user to inquire, learn and use, and various relations in the finally output domain knowledge graph are displayed in a character mode or are subjected to symbol conversion through symbols in a domain knowledge graph output symbol library so as to improve the visual representation of the graph.

The knowledge building model base comprises a concept model, an attribute model, a characteristic model, a quantity model, an intuitive model, an emotion model, a structure model, a function model, an upper model, a lower model, a parallel model, an integral model, a local model, a common model, a positive and negative model, an analysis model, a comprehensive model, an abstract model, a summary model, a transformation model, a samming model, a dissimilarity model, a similar model, a class shift model, an analogy model, a process model, a result model, a reason model, a background model, a condition model and a measure model, and is used for analyzing and building a certain knowledge entity in the field.

The knowledge construction algorithm library comprises a concept algorithm, an attribute algorithm, a characteristic algorithm, a quantity algorithm, a visual algorithm, an emotion algorithm, a structure algorithm, a function algorithm, an upper algorithm, a lower algorithm, a parallel algorithm, a whole algorithm, a local algorithm, a common algorithm, a positive and negative algorithm, an analysis algorithm, a comprehensive algorithm, an abstract algorithm, a summary algorithm, an induction algorithm, a deduction algorithm, a association algorithm, a imagination algorithm, a transformation algorithm, an identity algorithm, an exception algorithm, a similar algorithm, a class shift algorithm, an analogy algorithm, a process algorithm, a result algorithm, a reason algorithm, a background algorithm, a condition algorithm and a measure algorithm, and is used for extracting the related content of a certain knowledge entity in the field from the field knowledge library.

The domain knowledge base is a large domain knowledge base which is built by adopting manual addition or network acquisition and processing means through a knowledge building model in a knowledge building model base, and provides reference for a user in the process of establishing the domain knowledge map.

The knowledge graph output symbol library comprises a central theme, theme type content, descriptive type content, development process/stage, an item list, a content list, a connecting line, an arrow line, a concept, an attribute, a relation, a characteristic, an internal characteristic, an external characteristic, a quantity, a intuition, emotion, a structure, a composition, an essence, a status, a function, an upper level, a lower level, a parallel level, a whole, a part, a common mode, a positive and negative mode, an analysis, a synthesis, an abstraction, a summarization, an induction, a deduction, an association, an imagination, a transformation mode, an identity, an exception, a similarity, a class shift, an analogy, a process, a result, a reason, a background, a condition and a measure, and is used for symbolizing various relations in the domain knowledge graph.

The knowledge graph auxiliary construction module is used for generating a user specific domain knowledge graph and specifically comprises the following steps:

a6, repeating A3 to A4, generating other secondary nodes different from the previous group, and generating each group of nodes according to A5 until new selection can not be performed any more, and completing the assisted construction of the domain knowledge graph.

When the secondary nodes are generated, the primary knowledge theme can be analyzed from different angles and aspects by using the same knowledge construction model, each construction model is not necessarily used, the specific use is determined according to the attribute of the node, and the lower nodes are the same; when the generation of the secondary nodes is carried out, the recommendation of the system for constructing the model is carried out according to the following grouping:

Basic identification of knowledge entities mainly includes concepts, attributes and researches on the entities from the perspective of system theory; as shown in FIG. 2, the attribute is the core content of the knowledge entity, including the nature of the entity and the relationship between the entity and other entities; the entity can be divided into an individual entity and a type entity according to the composition of the entity, wherein the type entity can be reflected by a concept; for type entities, classification studies are to be conducted; for individual entities, decomposition studies are to be performed on them; from the perspective of system theory, any entity is a system, and the research of the system focuses on the research on the structure and the function of the system; the system function is essentially its status or role in the environment, for a knowledge entity, i.e. the relationship of the entity to other entities; the structure of the system includes its constituent elements and the interrelationship between the elements, elements and systems, and for a knowledge entity, the nature of the entity.

The static space domain of the knowledge entity is researched from the attribute of the entity and the structure and the function based on the system theory; as shown in fig. 3, from the attributes of the knowledge entity, the characteristic features of the knowledge entity are studied, and the method is carried out from the internal aspect and the external aspect: the external features depend on the internal features to a certain extent, and visual perception can be performed; performing quantitative (quantity) analysis on the property characteristics of the knowledge entity; the emotional feedback of the people to the knowledge entity is analyzed on the basis of quantitative analysis and visual perception of the property and the characteristics of the knowledge entity, and a corresponding thought is further formed. Starting from the attributes of a knowledge entity, the relation between the knowledge entity and other entities is researched from two aspects of human and other entities: for humans, it is important to analyze its use; for other entities, it is necessary to analyze their role and meaning. From the perspective of the system theory, the functions of the human body are researched by combining the functions and meanings of the human body to human beings and other entities. From the perspective of a system theory, the structure is analyzed to determine the composition, essence, status and influence on internal characteristics; on the basis of analysis, abstracting to obtain essential attributes of the images; and by summarizing, obtain concepts, principles, algorithms, etc., thereof.

The dynamic time domain of a knowledge entity is the study of the entity from a temporal perspective; as shown in fig. 4, from the time point of view, a certain state of development of any entity is generated through a certain process under a certain reason; meanwhile, the existence of the system has a certain position in the external environment where the system is located and has influence on the generation or occurrence of other entities; among the factors causing the generation or occurrence of the knowledge entity, the major external environmental factors (background) and the favorable factors (conditions) with promotion effect are intensively researched; in addition, in order to ensure that the future development can be carried out according to the expected state, the research on measures is needed.

The research domains of a plurality of knowledge entities are mainly carried out from three aspects of multi-entity generation, multi-entity research of the same system and multi-entity research of different systems; as shown in fig. 5, for known knowledge entities, other entities can be derived through transformation, association, and imagination. In the same system, the integral characteristics of the whole system can be obtained by integrating multiple entities; through the induction of multiple entities, the general principle and conclusion of the system can be obtained; based on the induction, the general principles and conclusions can be deduced to derive other individual characteristics of the entity. In different systems, through comparison, the same (identity), similar and different (difference) characteristics of the different systems can be obtained; meanwhile, based on the same and similar characteristics, a new entity can be formed through class shifting; by analogy, the identity or similarity of other features can be deduced.

The contact system of knowledge entities is mainly developed from the structure of the system theory and the relevance of each element, and as shown in fig. 6, for any entity, the entity connected with the entity belongs to the inside or exists outside. Whether internal or external, can be attributed to a system, i.e., the entity itself is either a system or a part of a system. Therefore, for the connection between entities, we can abstract the connection into two basic connection ways by a structural analysis method from the viewpoint of system theory: whole to part, part to part. From the structural point of view of the system, to research the relationship between the entities, it needs to be done from three aspects of space, time and nature:

from a spatial perspective, the intra-system relationship is mainly represented by the relationship between the elements (parts) constituting the system and the system (whole). Because the system has types and individuals, the connection between them is mainly divided into four categories, namely, upper and lower connection, integral and local connection, parallel connection and common connection.

From a time perspective, the connections within the system are mainly represented by the connections between different stages (parts) of the system development and the whole development process (whole) of the system. Due to the sequence and irreversibility of the general system development stages, the connection between them is mainly a whole-part connection and a part-part connection which is embodied as a causal connection.

From the viewpoint of properties, the connection within the system is mainly represented by the connection between different properties (parts) of the system and the property of the system as a whole. From the correlation among the elements in the system, the relationship among the entities is researched, which mainly shows the following forms:

contradiction, which shows the contradiction relationship between elements and is embodied as the partial relation between positive and negative relation;

objectionability, which represents the mutual or juxtaposition relationship of the elements, and is expressed as a relationship between parts and parts;

inclusiveness, representing the relationship between the upper and lower positions or the whole and local parts of the elements, embodied as the whole and part relation;

the method is characterized by comprising the following steps of (1) completely associating, wherein the completely identical relationship among elements is shown and is embodied as the relationship between a part and a part of equivalent relationship;

the cross property shows the same relationship of elements under a certain angle, and the parts represented by similar relationship are related to parts.

s4, determining a knowledge construction model by a user;

s9, the submitted data integration processing module processes the submitted data of the user;

Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.

Claims

1. The utility model provides a system for supplementary field knowledge map that generates, includes basic library module, knowledge map supplementary construction module, submits data integration processing module and knowledge map output module, its characterized in that: the basic library module comprises a knowledge construction model library, a knowledge construction algorithm library, a field knowledge library and a knowledge map output symbol library, wherein the knowledge construction model library, the knowledge construction algorithm library and the field knowledge library are electrically connected with a knowledge map auxiliary construction module;

the knowledge graph auxiliary construction module comprises knowledge subject setting, keyword extraction, knowledge construction model recommendation and selection and knowledge graph auxiliary construction; the submitted data integration processing module comprises basic identification of knowledge entities, a static space domain of the knowledge entities, a dynamic time domain of the knowledge entities, research domains of a plurality of knowledge entities and a connection system of the knowledge entities, and is used for data integration processing of all node contents and a constructed model aiming at a given knowledge topic submitted by a user; the knowledge graph output module is used for outputting the data processed by the submitted data integration processing module in a knowledge graph mode for a user to inquire, learn and use.

2. The system for assisting in generating a domain knowledge graph according to claim 1, wherein: the knowledge building model base comprises a concept model, an attribute model, a characteristic model, a quantity model, a visual model, an emotion model, a structure model, a function model, an upper model, a lower model, a parallel model, an integral model, a local model, a common model, a positive and negative model, an analysis model, a comprehensive model, an abstract model, a summary model, a transformation model, a similarity model, a difference model, a similar model, a class shift model, an analogy model, a process model, a result model, a reason model, a background model, a condition model and a measure model, and is used for analyzing and building a certain knowledge entity in the field.

3. The system for assisting in generating a domain knowledge graph according to claim 1, wherein: the knowledge construction algorithm library comprises a concept algorithm, an attribute algorithm, a characteristic algorithm, a quantity algorithm, a visual algorithm, an emotion algorithm, a structure algorithm, a function algorithm, an upper algorithm, a lower algorithm, a parallel algorithm, a whole algorithm, a local algorithm, a common algorithm, a positive and negative algorithm, an analysis algorithm, a comprehensive algorithm, an abstract algorithm, a summary algorithm, an induction algorithm, a deduction algorithm, a association algorithm, a imagination algorithm, a transformation algorithm, an identity algorithm, an exception algorithm, a similar algorithm, a class shift algorithm, an analogy algorithm, a process algorithm, a result algorithm, a reason algorithm, a background algorithm, a condition algorithm and a measure algorithm, and is used for extracting the related content of a certain knowledge entity in the field from the field knowledge library.

4. The system for assisting in generating a domain knowledge graph according to claim 1, wherein: the domain knowledge base is a large domain knowledge base which is built by adopting manual addition or network acquisition and processing means through a knowledge building model in a knowledge building model base, and provides reference for a user in the process of establishing a domain knowledge map.

5. The system for assisting in generating a domain knowledge graph according to claim 1, wherein: the knowledge graph output symbol library comprises a central theme, theme type content, descriptive type content, development process/stage, item list, content list, connecting line, arrow line, concept, attribute, relation, feature, intrinsic feature, extrinsic feature, quantity, intuition, emotion, structure, constitution, essence, status, function, upper level, lower level, parallel, whole, local, common, positive and negative, analysis, synthesis, abstraction, summarization, induction, deduction, association, imagination, transformation type, identity finding, difference finding, similarity, class shifting, analogy, process, result, reason, background, condition and measure, and is used for symbolizing various relations in the domain knowledge graph.

6. The system for assisting in generating a domain knowledge graph according to claim 5, wherein: the knowledge graph auxiliary construction module is used for generating a user specific domain knowledge graph and specifically comprises the following steps:

7. The system for assisting in generating a domain knowledge graph according to claim 6, wherein: when the secondary node is generated in the step a4, the primary knowledge topic can be analyzed from different angles and aspects by using the same knowledge construction model, and each construction model is not necessarily used, and is specifically determined according to the attribute of the node, and the lower node is the same; when the generation of the secondary nodes is carried out, the recommendation of the system for constructing the model is carried out according to the following grouping:

8. The system for assisting in generating a domain knowledge graph according to claim 1, wherein: the basic identification of the knowledge entity mainly comprises the concept, attribute and research on the entity from the perspective of system theory; the static space domain of the knowledge entity is researched from the attribute of the entity and the structure and the function based on the system theory; the dynamic time domain of the knowledge entity is the research on the entity from the time perspective; the research domains of the knowledge entities are mainly carried out from three aspects of multi-entity generation, multi-entity research of the same system and multi-entity research of different systems; the relation system of the knowledge entities is mainly developed from the structural property of a system theory and the relevance of each element.

9. The system for assisting in generating a domain knowledge graph according to claim 1, wherein: the knowledge map output module displays various relations in a character mode in the finally output domain knowledge map or performs symbol conversion through symbols in the domain knowledge map output symbol library so as to improve the visual representation of the map.

10. A method for assisting in generating a domain knowledge graph is characterized in that: the method comprises the following steps:

s4, determining a knowledge construction model by a user;