Intelligent simulation model framework construction method

Abstract

The present invention relates to a method for constructing an intelligent simulation model framework, the method comprising: step S1, completing model label design; step S2, constructing a model system architecture specification; step S3, establishing a knowledge graph intelligent recommendation model based on the model label and the model system architecture specification; step S4, using the knowledge graph intelligent recommendation model to complete the generation and development of the simulation model. The present invention, through a label design method, constructs a multi-dimensional, multi-feature model system label library, forms a model system knowledge graph, and provides a label-based model system framework intelligent recommendation capability, thereby realizing the generation, development, and reconstruction of the simulation model, solving the problems of high model development learning cost, poor development efficiency, and low intelligence level.

Description

Technical Field

[0001] The present invention relates to the field of simulation and modeling technology, and in particular to a method for constructing an intelligent simulation model framework. Background Art

[0002] Currently, modeling and simulation technology is a key technology driving the development of modern high technology and building an innovative nation. It holds enormous potential and value in the fields of national defense and the national economy. Model frameworks are of significant engineering value in the construction of simulation models. Currently, model framework construction technology is rapidly gaining popularity in fields such as aviation, aerospace, shipbuilding, and weaponry. System modeling and simulation technology is widely used in defense and military enterprises and institutions, as well as in scientific research and other manufacturing industries.

[0003] Existing technologies lack unified model frameworks and specifications, and are highly complex. This results in high learning costs, long development cycles, low development efficiency, widespread siloed development, and low intelligence levels. This makes model commonality and reuse impossible, and the overall integrity of the model is not reflected. The model framework is not robust and complete, hindering its effectiveness. This increases repetitive work for model developers and prolongs system development time. Summary of the Invention

[0004] In order to solve the technical problems existing in the above-mentioned prior art, the purpose of the present invention is to provide a method for constructing an intelligent simulation model framework, which can solve the problems of high learning cost, poor development efficiency and low intelligence level of model development.

[0005] To achieve the above-mentioned object of the invention, the present invention provides a method for constructing an intelligent simulation model framework, comprising the following steps:

[0006] Step S1, complete model label design;

[0007] Step S2: Build model system architecture specifications;

[0008] Step S3: Establish a knowledge graph intelligent recommendation model based on the model label and the model system architecture specification;

[0009] Step S4: Use the knowledge graph intelligent recommendation model to complete the generation and development of the simulation model.

[0010] According to a technical solution of the present invention, step S1 specifically includes:

[0011] Use multi-level tree labels to design model category labels;

[0012] Describe the behavioral characteristics of each model in the form of labels, design based on the specific behavior of the model, and complete the model behavior label design;

[0013] Based on the specific parameter attributes of the model, it involves model parameter labels;

[0014] Design model rule labels based on a multi-level rule system;

[0015] Design model association relationship labels based on the command relationship and / or control relationship between models.

[0016] According to a technical solution of the present invention, in step S2, the model system architecture specification includes at least a basic framework for determining standards and specifications at the software development level and a business framework for determining business aspects of the model system.

[0017] According to a technical solution of the present invention, step S3 specifically includes:

[0018] Step S31: construct a tag library based on the model tags, and construct a tag knowledge graph based on the tag library;

[0019] Step S32: Generate or reconstruct the model system framework based on the model system architecture specification;

[0020] Step S33: Complete component modeling and obtain a knowledge graph intelligent recommendation model.

[0021] According to a technical solution of the present invention, in step S31, data of a knowledge graph is formed based on model types, behaviors, parameters, rules, and association relationship tags to construct a label knowledge graph;

[0022] The data is divided into structured data and unstructured data. The structured data at least includes: description of the simulation model entity status, actions, and combat effects; the unstructured data at least includes: related tasks and control instructions;

[0023] The tag knowledge graph is constructed in a bottom-up manner and stored using the Neo4j graph database.

[0024] According to a technical solution of the present invention, step S4 specifically includes:

[0025] Step S41: tag retrieval based on semantic understanding;

[0026] Step S42: Model matching based on knowledge graph;

[0027] Step S43: Complete the generation and development of the simulation model according to the matching results.

[0028] According to a technical solution of the present invention, in step S41, the model description information is used as a query to output entities or other labels that are closest to the text in the query statement, specifically including:

[0029] Step S411: Perform word segmentation on the user's model description information, decompose the sentence into search keywords, and match and convert them with a synonym dictionary;

[0030] Step S412: semantically expand the search keywords and construct a new search statement;

[0031] Step S413: perform dependency syntax analysis to convert it into a search statement corresponding to the graph;

[0032] Step S414: sort the obtained search results by relevance, and return the results that best meet the user's actual model building intention.

[0033] According to a technical solution of the present invention, in step S412, the process of semantically expanding the search keyword includes at least entity tag expansion, and the entity tag expansion includes similarity calculation between keywords and entities and similarity calculation between entities;

[0034] Among them, the similarity between keywords and entity tags is calculated by combining the literal similarity calculation method and the semantic similarity calculation method. The specific formula is:

[0035] S(K, E) = λS vec (K, E) + (1-λ) S lit (k, E) (1)

[0036] Among them, λ is the weight parameter; K is the keyword; E is the entity noun;

[0037] S vec (K, E) represents the vector space similarity between the retrieval keyword and the entity label, which is calculated as:

[0038]

[0039] Among them, k is the word vector corresponding to the search keyword, and e is the word vector corresponding to the entity name. The larger the cosine value, the smaller the angle between the two word vectors, and the higher the similarity between the words;

[0040] S lit (k, E) represents the literal similarity between the search keyword and the entity label, and the calculation formula is:

[0041]

[0042] Where M(K, E) represents the maximum length of the search keyword K and the entity name string, and L(K, E) represents the Levenshtein edit distance between the search keyword and the entity label;

[0043] According to formula (1), the semantic similarity between the search keyword and the entity name is obtained, and the top N entities with the highest similarity are selected as search expansion terms;

[0044] The number of common attributes between the entities is used to determine whether there is a relationship between two entities. altr (E1, E2) represents the attribute similarity between entity E1 and entity E2, and the specific formula is:

[0045]

[0046] Where I(E1, E2) represents the number of attributes shared by entities E1 and E2; U(E1, E2) represents the number of all attributes of entities E1 and E2;

[0047] Considering the distance between entity nodes and the number of common attributes between two nodes, the semantic similarity between entities can be expressed as:

[0048] S entity (E1, E2) = (1-μ)S altr (E1, E2) + μD(E1, E2) (5)

[0049] Where D(E1, E2) represents the shortest path between two entity nodes, and μ is a weight parameter.

[0050] According to a technical solution of the present invention, step S42 specifically includes:

[0051] Step S421: Based on the keyword tags extracted based on semantic understanding, query and filter the demand model from the knowledge graph through model matching of Cypher statements;

[0052] Step S422: Use a matching algorithm based on semantic features to sort the filtered models, and recommend models with high matching degrees to users as a basis for simulation model development.

[0053] According to a technical solution of the present invention, in step S422, the semantic feature-based matching recommendation algorithm constructs a feature vector based on the feature attribute values ​​of the simulation model, and calculates the similarity of the feature vectors between the two models to obtain the matching degree between the models. The similarity calculation formula based on semantic features is:

[0054]

[0055] SE1 and SE2 represent different simulation models, Lv (SE1, SE2), then calculate using the following formula:

[0056]

[0057] n is the number of features of the model; x 1i is the attribute value of the i-th feature of SE1; x 2i is the attribute value of the i-th feature of SE2.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The present invention proposes a method for constructing an intelligent simulation model framework, which extracts knowledge based on model categories, behaviors, parameters, rules, and associations, establishes a model system framework knowledge graph, realizes the extraction of demand model information labels and component model matching recommendations, and on this basis, combines the characteristics of the new model, performs flexible component configuration, completes the generation and development of the new model, improves the intelligence and reuse of the modeling process, and solves the problems of high learning cost, poor development efficiency, and low intelligence level in model development.

[0060] The present invention introduces multi-dimensional model label design including construction dimension, management dimension and usage dimension, segmentes the model information required by users based on intelligent recommendation of knowledge graph, extracts key labels, and realizes precise matching of simulation models through model matching based on Cypher statements and component model recommendation based on semantic features.

[0061] This invention is based on the model system architecture specification, including interface types, interface requirements, and protocol types. It primarily defines the standards and specifications for the business aspects of the model system, including command rules, field composition, basic protocols, and basic ports. When implementing, extending, or upgrading models, users build upon the foundation of the basic and business frameworks, thus achieving tag-based model system framework modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be derived from these drawings without inventive effort.

[0063] Figure 1 Schematically showing a schematic diagram of model category label dimensions in an embodiment of the present invention;

[0064] Figure 2Schematically showing a flow chart of label disambiguation and fusion in an embodiment of the present invention;

[0065] Figure 3 A schematic diagram of a basic knowledge graph in an implementation case according to the present invention is schematically shown;

[0066] Figure 4 Schematically showing a schematic diagram of an aircraft tag knowledge graph in an embodiment of the present invention;

[0067] Figure 5 Schematically illustrating a tag retrieval process based on semantic understanding in an embodiment of the present invention;

[0068] Figure 6 A diagram schematically showing an example of a Cypher query statement according to an embodiment of the present invention;

[0069] Figure 7 A schematic diagram schematically illustrates a process flow for constructing an intelligent simulation model framework according to an embodiment of the present invention;

[0070] Figure 8 A flowchart for constructing an intelligent simulation model framework according to an embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0071] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0072] like Figures 1 to 8 As shown, a method for constructing an intelligent simulation model framework of the present invention includes the following steps:

[0073] Step S1, complete model label design;

[0074] Step S2: Build model system architecture specifications;

[0075] Step S3: Establish a knowledge graph intelligent recommendation model based on the model label and the model system architecture specification;

[0076] Step S4: Use the knowledge graph intelligent recommendation model to complete the generation and development of the simulation model.

[0077] Step S1 specifically includes: step S11, using multi-level tree tags to design model category labels;

[0078] For example, the category labels for airplanes include entity labels, action entities, aerial entities, and sports labels. At the same time, users can independently select the model type granularity to define labels. The finer the model classification granularity, the higher the accuracy of the category labels and the more accurate the knowledge graph intelligent recommendation. In the model category label, the model category label is mainly divided into three dimensions: model construction, management, and use. Figure 1 shown.

[0079] Define category labels based on the model construction dimension. The category labels for the model construction dimension can be divided into:

[0080] 1) Entity model; 2) Decision model; 3) Service model; 4) Action model; 5) Control model; 6) Physical model; 7) Algorithm model; 8) Interface object model.

[0081] Category labels are defined according to the model management dimension. The model management dimension category labels can be divided into: 1) aviation models; 2) aerospace models; 3) civil models; 4) military models; 5) behavioral rule models; 6) analysis and evaluation models.

[0082] Category labels are defined according to the model usage dimension, and the model usage dimension category labels can be divided into: 1) flight capability model; 2) management capability model; 3) information transmission capability model; 4) communication capability model; 5) confrontation capability model; 6) guarantee capability model.

[0083] Step S12: Describe the behavioral characteristics of each model in the form of a label. Design the model behavior label based on the specific behavior of the model. Model behavior labels are designed based on the specific behavior of the model. Each model's behavioral characteristics are described in the form of a label, including takeoff, landing, cruising, movement, patrol, support, and guarantee behaviors. When different models have the same behavior, only one behavior label is used. For example, if both passenger aircraft and drones share flight behavior, a unified flight label is used. When designing behavior labels, define a single model using a combination of multiple labels.

[0084] Step S13, based on the specific parameter attributes of the model, involves model parameter labels; model parameter labels, based on the specific parameter attributes of the model, adopt a multi-label combination design, such as: aircraft, including attributes such as position, attitude, and target characteristics, which are subdivided into longitude, latitude, and altitude according to position; and subdivided into dive attitude, roll attitude, yaw attitude, etc. according to attitude.

[0085] Step S14: Design model rule labels based on the multi-level rule system. Model rule labels are designed based on the multi-level rule system and must be defined within a semantic environment defined by universal syntax and semantics, using specific terms, graphics, symbols, and their specific arrangement. Model rule labels can be categorized into command planning rules, combat action rules, and so on.

[0086] Step S15: Design model association labels based on the command and / or control relationships between models. Model-to-model associations encompass actions such as command, control, and issuing instructions. Model association labels describe various relationships, including command and control relationships, using labels.

[0087] In step S2, a model system architecture specification is constructed.

[0088] Simulation model construction requires a foundational framework and a business framework. The foundational framework primarily defines standards and specifications for software development, including interface types, interface requirements, and protocol types. The business framework primarily defines standards and specifications for the business aspects of the model system, including command rules, field composition, basic protocols, and basic ports. When implementing, extending, or upgrading models, users build upon the foundational and business frameworks, thereby achieving a tag-based model system framework.

[0089] Modeling specifications refer to the standard framework and constraints for building models. The model system is based on the IOCE modeling specification (I is input, O is output, C is calculation, and E is event).

[0090] Configuration port: used to parameterize the key model. The model reads the information of the port to complete the initialization work. The configuration can be passed from one model to another to complete the configuration distribution within the model.

[0091] Data port: The data exchange port between models. The sender actively sends, the receiver receives asynchronously, and calls back the data response function to process the data.

[0092] Service Port: A remote method port between models. The initiator initiates a service call, and the server calls back the service response function, performs the service, and returns. The initiator continues to run after receiving the response. The platform provides system services such as creating new entities, establishing links, disconnecting links, requesting step size, obtaining simulation entity lists, obtaining port mapping lists, and opening new simulation branches.

[0093] Driver port: The model drives other or its own main callback function port to implement workflow serial, parallel, and logical judgment branches. It can drive the core computing functions within the model to complete business work.

[0094] State Port: This port retrieves or sets the model state. Data is read actively, i.e., "pull" data. Data publishers do not explicitly publish data. When data subscribers need state data, they use the GET method to obtain the port data without binding a response event. Data updaters can use the SET method to update state data.

[0095] In step S3, based on the model labels and the model architecture specifications, a knowledge graph intelligent recommendation model is established, specifically including:

[0096] Step S31: construct a tag library based on the model tags, and construct a tag knowledge graph based on the tag library;

[0097] For the simulation model to be constructed, there are corresponding tags, which constitute a tag library. The tag creation is used to create tags based on the tag design and in accordance with the tag format to form a tag library.

[0098] 1) Tag editing

[0099] For the target simulation model, users can create various tags for the model. On the tag editing page, users can manually modify the automatically constructed tag attributes. The original tag file import time display and attachment download function are also provided, making it easy for users to manually verify and correct tags.

[0100] 2) New tag disambiguation and fusion based on NLTK similarity calculation

[0101] After completing the knowledge extraction of tags, the newly added structured tags cannot be directly imported into the tag library. The newly added tags need to be disambiguated and fused to eliminate the conflicts and similarities in the tag information before they can be updated into the library. The disambiguation and fusion processing process is as follows: Figure 2 shown.

[0102] a) Disambiguation

[0103] Tag disambiguation is the process of eliminating polysemy based on contextual information. This process can be achieved through tag matching and similarity calculation. To ensure that each tag in the tag library is unique, disambiguation is required. This involves searching for identical or similar tags within the existing tag library.

[0104] For similar tags, we can calculate text similarity based on the tag name, keywords, or description information to determine the similarity between the new tag and the existing tags, and select the one with the highest similarity as the disambiguation result. For tags involving multiple dimensions, we can use a multi-dimensional similarity calculation method to comprehensively consider the similarity between each dimension of the tag and use NLTK to disambiguate the new tags.

[0105] NLTK is a Python-based natural language processing toolkit for processing text data. The following is a summary of the steps for using NLTK:

[0106] First, install NLTK using pip. Then load the labeled text data you want to process into a Python program for preprocessing. This includes removing stop words, stemming, and vectorizing the text. These preprocessing steps make the text more standardized and comparable, thereby improving the accuracy of text similarity calculations.

[0107] Feature extraction is then used to convert the preprocessed text into feature vectors, a key step in calculating text similarity. Common feature extraction methods include the Bag of Words model, the TF-IDF model, and the Word2Vec model. These models convert text into numerical vectors for subsequent similarity calculations.

[0108] Next, you can use a weighted approach to adjust the weights of different features to more accurately determine text similarity. Disambiguation results are then selected based on the degree of similarity. A similarity threshold can be manually set in the backend. When the similarity exceeds the threshold, the two tags are considered similar and require disambiguation. This process can also consider other factors, such as the importance and historical nature of the tags, for a comprehensive judgment.

[0109] b) Fusion processing

[0110] After the disambiguation process, the disambiguation results need to be fused, that is, similar tags are merged into one and updated into the database.

[0111] First, the tag names, descriptions, and keywords must be retained. The names and descriptions of tags with the highest similarity are selected as the fused tag information. For tag attribute information, such as timelines, geographic information, and person information, various methods are used to fuse the information. Conflict detection and fusion are required to avoid duplicate or inconsistent information. For tag content information, the similarity and importance of the tags must be determined and fused. This can be accomplished using machine learning and natural language processing techniques.

[0112] Then all newly added tags are grouped according to their similarity. For each group of tags, one tag is selected as a representative, and other tags with higher similarity are merged to find ambiguities and inconsistencies in the tags. During the merging process, it is necessary to avoid duplication and conflict of information.

[0113] The merged labels are proofread to ensure their accuracy and completeness. During the proofreading process, attention should be paid to aspects such as the format, wording, and grammar of the labels to ensure that the labels comply with specifications and standards.

[0114] c) Update the storage

[0115] After disambiguation and fusion, the updated label information needs to be updated and stored in the database to ensure the integrity and accuracy of the label database. The update and storage process can be automated or manually reviewed to ensure the correctness of the label information.

[0116] Step S32: Generate or reconstruct the model system framework based on the model system architecture specification;

[0117] Step S33: Complete component modeling and obtain a knowledge graph intelligent recommendation model.

[0118] The basic unit of knowledge graph storage is a triple such as "entity-relationship-entity" or "entity-attribute-value pair". Entities are linked to each other through relationships to form a network-like knowledge structure. Figure 3 This is the simplest knowledge graph. M represents an entity or value pair, and L represents a relationship or attribute. Based on their coverage, knowledge graphs can be divided into open knowledge graphs and specialized knowledge graphs. Open knowledge graphs focus on breadth, striving to integrate more entities and encompass more knowledge.

[0119] Under the existing labeling design, the data for the knowledge graph is formed based on model type, behavior, parameters, rules, and relationship labels. This includes massive amounts of structured data describing the simulation model's entity states, actions, and operational effects, as well as a large amount of unstructured data such as related tasks and control instructions. These two components form the data sample set used to support knowledge graph construction. The knowledge graph construction process is completed in two steps: point identification and edge connection.

[0120] (1) Fixed point

[0121] "Fixing" refers to identifying nodes in the knowledge graph's network structure. Each node corresponds to an entity. The more complex the knowledge contained in the graph, the greater the number of nodes. Due to the large number of entities in the data sample, there is a large amount of redundant data. To more quickly obtain an accurate knowledge graph structure, knowledge graph nodes are labeled and, combined with specialized knowledge, relevant entities are identified.

[0122] (2) Edge connection

[0123] Edges are the process of identifying relationships between entities in a knowledge graph. In theory, every node has a relationship, but the strength of the relationship between entities determines whether an edge is needed. The greater the number of entities in the graph and the more complex the knowledge, the more complex the edges between nodes. Relationships between entities are represented by directed edges, with the direction running from the starting point to the end point. When representing uncertain knowledge, each edge also has a probability value, indicating the probability that the edge actually exists. When constructing a knowledge graph, a set of data is first selected from the data sample set to form edges. The edge probabilities are statistically derived to form a preliminary knowledge graph structure.

[0124] The label knowledge graph is constructed in a bottom-up manner and stored in the Neo4j graph database. Neo4j is a high-performance NoSQL graph database that uses nodes and relationships to represent data. Nodes and relationships have attributes and can be labeled and classified using a tag library. Taking an airplane model as an example, the knowledge graph framework diagram based on Neo4j is shown below: Figure 4 .

[0125] With the aircraft model label entity as the center, a graph network is established with other label entities based on the model's category, behavior, parameters, rules, and association relationships. The aircraft model is labeled and managed according to the three dimensions of construction, management, and use. From the construction dimension, the aircraft model can be classified step by step according to components and types, such as: entity model-action entity model-air entity model-aircraft entity model. The above aircraft label knowledge graph is only an example framework diagram, and the specific construction should be based on the user's granularity label design and the label scale of the label library.

[0126] The knowledge graph intelligent recommendation model creates new tags based on the design of labels for model categories, actions, attributes, rules, and relationships. It then constructs a knowledge graph based on the label library, reconstructing the model system framework to achieve knowledge graph-based model information matching and intelligent model label recommendation, facilitating the development and design of new models. The knowledge graph intelligent recommendation model uses the Neo4j graph database as a carrier to build a labeled knowledge graph containing model categories, behaviors, parameters, and other types. Model categories, behaviors, and other features are formally described in the knowledge graph. Labels are extracted from user model information, and then a Cypher statement-based model matching and a semantic feature-based model recommendation algorithm are used to achieve precise matching of simulation models.

[0127] For numerical computational models, componentization technology is employed to develop various simulation models using a unified component development template. This ensures a unified code framework and compilation environment across different simulation models, providing a foundation for interaction between models. The simulation model employs object-oriented thinking, breaking down various equipment types into a series of universally applicable basic model components. Different types of components have their own functional definitions and inheritance relationships. Modelers flexibly configure components based on an intelligent recommendation model based on a knowledge graph, enabling the development and customization of specific models.

[0128] The component model template development function meets the needs of users to develop models independently, automatically generates code frameworks that comply with IOCE standards in multiple languages, simplifies the platform learning cost, and allows developers to focus on the implementation of business codes. The software can generate multi-language and multi-platform model frameworks. Based on the model framework, users can fill in the business code to complete the initial construction of the model. Different model frameworks can be generated for models of different business types, supporting multiple development languages ​​and multiple operating platforms. Users can write business codes in the model framework to form model components.

[0129] In step S4, the generation and development of the simulation model is completed using the knowledge graph intelligent recommendation model, which specifically includes:

[0130] Step S41: tag retrieval based on semantic understanding;

[0131] The tag retrieval service based on semantic understanding is based on users who have the need to develop models. The model description information is used as a query, and the entities or other tags that are closest to the text in the query statement are output. The retrieval process is as follows: First, the user's model description information is segmented, the statement is decomposed into retrieval keywords, and it is matched and converted with a synonym dictionary; secondly, the retrieval keywords are semantically expanded and new retrieval statements are constructed; then dependency syntactic analysis is performed to convert it into a retrieval statement corresponding to the graph; finally, the obtained retrieval results are sorted by relevance, and the result that best meets the user's actual model building intention is returned. The specific process is as follows Figure 5 shown.

[0132] 1) Search statement processing

[0133] a) Participle

[0134] General dictionaries cannot meet the word segmentation requirements for specialized texts. Therefore, we use HanLP, a Chinese word segmentation tool that supports custom dictionaries. We use tags from the knowledge graph to build specialized dictionaries to improve word segmentation performance.

[0135] b) Synonymous conversion

[0136] To address the problem of search failures caused by inconsistencies between search terms and knowledge graph labels, we leveraged the existing knowledge graph to analyze and compile statistics on the labels, and combined this with a general dictionary to build a synonym dictionary. This synonym dictionary can be used to convert search terms into synonyms, eliminating search failures caused by vocabulary discrepancies.

[0137] 2) Semantic calculation method of multi-similarity fusion

[0138] a) Entity tag expansion

[0139] In extended search, entity tag expansion is a common implementation method. It can identify the potential needs of search users and enrich search results. This paper divides entity expansion into two cases: one is that the search keyword fails to successfully match the knowledge graph entity tag. In this case, it is necessary to calculate the similarity between the keyword and each entity in the knowledge graph to select entities with high similarity for search queries; the other is that the search keyword successfully matches an entity in the knowledge graph. In this case, it is necessary to calculate the similarity between the entity and other entities to select entities with high similarity to expand the search results.

[0140] (1) Method for calculating similarity between keywords and entities

[0141] Traditional methods based on literal similarity calculations primarily perform matching calculations based on the structure of the text itself, making it difficult to capture the semantic relationship between the two. To overcome this limitation, this paper proposes a method that combines literal and semantic similarity calculations to calculate the similarity between keywords and entity tags.

[0142] S(K, E) = λS vec (K, E) + (1-λ) S lit (k, E) (1)

[0143] Where: λ is the weight parameter; K is the keyword; E is the entity noun.

[0144] S vec (K, E) represents the vector space similarity between the retrieval keyword and the entity label, which is calculated as:

[0145]

[0146] Where k is the word vector corresponding to the search keyword, and e is the word vector corresponding to the entity name. A larger cosine value indicates a smaller angle between the two word vectors, and a higher similarity between the words.

[0147] S lit (k, E) represents the literal similarity between the search keyword and the entity label, and the calculation formula is:

[0148]

[0149] Where: M(K, E) represents the maximum length of the search keyword K and the entity name string. L(K, E) represents the Levenshtein edit distance between the search keyword and the entity label.

[0150] According to formula (1), the semantic similarity between the search keyword and the entity name is obtained, and the top N entities with the highest similarity are selected as the search expansion terms.

[0151] (2) Method for calculating similarity between entities

[0152] The more attributes an entity has, the more information it contains. The number of common attributes between two entities can be used to determine whether there is a relationship between them. The more common attributes between two entities, the more similar they are. altr (E1, E2) represents the attribute similarity between entities E1 and E2. The specific formula is as follows:

[0153]

[0154] Where: I(E1, E2) represents the number of common attributes of entities E1 and E2; U(E1, E2) represents the number of all attributes of entities E1 and E2.

[0155] Based on the distance between entity nodes and the number of common attributes between two nodes, the following method is proposed to calculate the semantic similarity between entities:

[0156] S entity (E1, E2) = (1-μ)S altr (E1, E2) + μD(E1, E2) (5)

[0157] Where: D(E1, E2) represents the shortest path between two entity nodes, and μ is the weight parameter.

[0158] b) Search statement conversion

[0159] Converting semantically understood search statements into Neo4j's Cypher query language is key to finding search results within the graph. Based on the characteristics of the knowledge graph, we use a question template matching method to convert search statements.

[0160] For some special query sentences (such as parameter comparison between weapons and equipment, multi-entity query, etc.), basic predicate attribute template matching cannot generate corresponding search statements. Therefore, the present invention has classified these sentences and designed specific matching templates. For example, when the identifiers such as "faster than..." or "heavier than..." appear in the search sentence, a corresponding Cypher statement will be generated and a WHERE statement will be added to perform a comparative query. When performing the search sentence conversion, first, a synonym conversion is performed according to a synonym dictionary, and then it is classified according to the keywords therein, and the query template is determined, and finally the corresponding Cypher statement is generated.

[0161] c) Sorting of search results

[0162] In order to enable users to quickly search for the information they need, the search results need to be sorted and returned to the user in descending order of relevance. Search results are divided into two types: ① Original query results: query results where the original sentence is directly matched to the answer in the graph after processing such as word segmentation and synonym conversion; ② Expanded query results: search results where the search sentence is expanded through entities. The algorithm for re-ranking the above two types of query results is as follows:

[0163] Input: Search text sentence Q

[0164] Output: retrieval result set R

[0165] 1) Perform semantic search on the search statement Q to obtain the original query result set R1 and the expanded query result set R2;

[0166] 2) If R1 is not empty, sort the result of R1 before the result of R2;

[0167] 3) If R1 is empty, the similarity of each result is calculated according to formula (1); otherwise, the similarity is calculated according to formula (5);

[0168] 4) Calculate the number of entities associated with each entity to measure the importance of the entity;

[0169] 5) A comprehensive linear weighting formula is used to calculate the entity semantic similarity and entity importance to obtain a comprehensive score for each search result;

[0170] 6) Sort by score in descending order and return the result R.

[0171] Step S42: Model matching based on knowledge graph;

[0172] By building a model knowledge graph, we can then perform model matching based on the knowledge graph. First, based on keyword tags extracted through semantic understanding, we query and filter the required models from the knowledge graph through model matching using Cypher statements. Then, we use a matching algorithm based on semantic features to sort the filtered models and recommend highly matched models to users as the basis for model development.

[0173] Step S421: Model matching based on Cypher statements.

[0174] Cypher is the official query language of the Neo4j graph database. To perform model matching based on the knowledge graph, the required knowledge must first be retrieved from Neo4j using the Cypher language. Therefore, queries based on Cypher statements are an essential component for implementing model matching based on the knowledge graph. In order to provide rich model matching capabilities and meet diverse needs, multiple interfaces that provide different query matching functions are implemented based on Cypher statements, including strict matching based on node attributes, strict matching based on node relationships, fuzzy matching based on keywords in model descriptions, fuzzy matching based on node relationships, and direct matching of all model types. These interfaces receive the description information entered by the user and generate corresponding Cypher query statements. When matching the model, different interfaces will be executed based on the different model description information entered by the user. If the user selects fuzzy matching and the model description entered only includes the two pieces of information: the behavior type is patrol and the model category is aircraft, the fuzzy matching interface based on node relationships will be executed. This interface will generate the following: Figure 6 The Cypher query statement shown is:

[0175] Step S422: Matching recommendation based on semantic features.

[0176] The semantic feature-based matching recommendation algorithm constructs a feature vector based on the various attribute values ​​of the simulation model and calculates the similarity between the feature vectors of two models to determine the degree of matching between the models. According to the label type of the knowledge graph, the simulation model has the following characteristics: model type, behavior, parameters, rules, and associations.

[0177] The similarity calculation formula based on semantic features is:

[0178]

[0179] SE1 and SE2 represent different simulation models, L v (SE1, SE2), then calculate using the following formula:

[0180]

[0181] n is the number of features of the model; x1i is the attribute value of the i-th feature of SE1; x 2i is the attribute value of the i-th feature of SE2.

[0182] In terms of characteristic parameter values, since the characteristic parameters of the simulation model are mostly descriptive parameters rather than specific parameter values ​​represented by numbers, further processing is required for each different characteristic parameter to convert the non-numeric characteristic parameters into numerical types.

[0183] Take the model category feature as an example. Model categories are defined hierarchically based on granularity, with different scores assigned to different levels. For example, in the category label for an aircraft physical model, there are four different levels: physical model, action physical model, aerial physical model, and aircraft physical model. Each of these four levels is assigned a score of 1 for physical model, 2 for action physical model, 3 for aerial physical model, and 4 for aircraft physical model. These four scores represent the possible parameter values ​​for this feature attribute. The model matching value is calculated based on the parameter values ​​of multiple features. The highest matching level is achieved when the feature parameters are identical to the required model information description.

[0184] Depending on the model description information entered by the user and the matching method selected, the software executes different matching interfaces and returns matching results.

[0185] Step S43: Complete the generation and development of the simulation model according to the matching results.

[0186] Combining the knowledge graph database with the model descriptions of user needs, a semantic feature-based matching algorithm calculates model similarity. Using a TOP-K recommendation strategy, the current models are ranked from highest to lowest based on suitability, generating a recommended list of K corresponding models and sending it to the user for reference. Users can directly view labels such as model type, behavior, parameters, rules, and relationships. Based on this, combined with the characteristics of the new model, flexible component configuration is performed to complete the development of the new model.

[0187] The present invention provides a method for constructing an intelligent simulation model framework, the method comprising: step S1, completing model label design; step S2, constructing a model system architecture specification; step S3, establishing a knowledge graph intelligent recommendation model based on the model label and the model system architecture specification; step S4, using the knowledge graph intelligent recommendation model to complete the generation and development of the simulation model. The present invention, through a label design method, constructs a multi-dimensional, multi-feature model system label library, forms a model system knowledge graph, and provides a label-based model system framework intelligent recommendation capability, thereby realizing the generation, development, and reconstruction of the simulation model, solving the problems of high model development learning cost, poor development efficiency, and low intelligence level.

[0188] Furthermore, the present invention proposes a tag retrieval method based on semantic understanding, which solves the problem of intelligent extraction of tags from demand model information; proposes a model matching based on Cypher statements and a model recommendation algorithm based on semantic features, which solves the problem that developers find it difficult to carry out model design and development work proficiently and efficiently under the framework of a complex model system, and achieves intelligent recommendation, agile development, and reuse of models.

[0189] Furthermore, it should be noted that the present invention may be provided as a method, apparatus, or computer program product. Thus, embodiments of the present invention may take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media containing computer-usable program code.

[0190] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0191] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0192] It should also be noted that, in the present invention, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or terminal device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or also includes elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or terminal device comprising the element.

[0193] Finally, it should be noted that the above is a preferred embodiment of the present invention. It should be noted that although the preferred embodiment of the present invention has been described, it is clear that those skilled in the art, once they understand the basic inventive concept of the present invention, can make various improvements and modifications without departing from the principles of the present invention. Such improvements and modifications should also be considered as within the scope of protection of the present invention. Therefore, the appended claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. A method for constructing an intelligent simulation model framework, characterized in that: The following steps are involved: Step S1, complete model label design; Step S2: Build model system architecture specifications; Step S3: Establish a knowledge graph intelligent recommendation model based on the model label and the model system architecture specification; Step S4: Using the knowledge graph intelligent recommendation model to complete the generation and development of the simulation model, specifically including: Step S41: Tag retrieval based on semantic understanding: using the model description information as a query, outputting entities or other tags that are closest to the text in the query statement, specifically including: Step S411: Perform word segmentation on the user's model description information, decompose the sentence into search keywords, and match and convert them with a synonym dictionary; Step S412: semantically expand the search keywords and construct a new search statement; Step S413: perform dependency syntax analysis to convert it into a search statement corresponding to the graph; Step S414: sort the obtained search results by relevance, and return the result that best meets the user's actual model building intention; Step S42: Model matching based on knowledge graph, specifically including: Step S421: Based on the keyword tags extracted based on semantic understanding, query and filter the demand model from the knowledge graph through model matching of Cypher statements; Step S422: sort the filtered models using a matching algorithm based on semantic features, and recommend models with high matching degrees to the user as a basis for simulation model development, specifically including: The matching recommendation algorithm based on semantic features constructs a feature vector based on the feature attribute values ​​of the simulation model, and calculates the similarity between the feature vectors of the two models to obtain the matching degree between the models. The similarity calculation formula based on semantic features is: Among them, SE1 and SE2 represent different simulation models, L v (SE1, SE2), then calculate using the following formula: n is the number of features of the model; x 1i is the attribute value of the i-th feature of SE1; x 2i is the attribute value of the i-th feature of SE2; Step S43: Complete the generation and development of the simulation model according to the matching results.

2. The intelligent simulation model framework construction method according to claim 1, characterized in that: The step S1 specifically includes: Use multi-level tree labels to design model category labels; Describe the behavioral characteristics of each model in the form of labels, design based on the specific behavior of the model, and complete the model behavior label design; Based on the specific parameter attributes of the model, it involves model parameter labels; Design model rule labels based on a multi-level rule system; Design model association relationship labels based on the command relationship and / or control relationship between models.

3. The intelligent simulation model framework construction method according to claim 2, characterized in that: In step S2, the model system architecture specification includes at least a basic framework for determining standards and specifications at the software development level and a business framework for determining business aspects of the model system.

4. The intelligent simulation model framework construction method according to claim 3, characterized in that: The step S3 specifically includes: Step S31: construct a tag library based on the model tags, and construct a tag knowledge graph based on the tag library; Step S32: Generate or reconstruct the model system framework based on the model system architecture specification; Step S33: Complete component modeling and obtain a knowledge graph intelligent recommendation model.

5. The intelligent simulation model framework construction method according to claim 4, characterized in that: In step S31, data of a knowledge graph is formed based on model types, behaviors, parameters, rules, and association relationship tags to construct a label knowledge graph; The data is divided into structured data and unstructured data. The structured data at least includes: description of the simulation model entity status, actions, and combat effects; the unstructured data at least includes: related tasks and control instructions; The tag knowledge graph is constructed in a bottom-up manner and stored using the Neo4j graph database.

6. The intelligent simulation model framework construction method according to claim 1, characterized in that: In step S412, the process of semantic expansion of the search keyword includes at least entity tag expansion, and the entity tag expansion includes similarity calculation between the keyword and the entity and similarity calculation between entities; Among them, the similarity between keywords and entity tags is calculated by combining the literal similarity calculation method and the semantic similarity calculation method. The specific formula is: S(K,E)=λS vec (K,E)+(1-λ)S lit (K,E) (1) Among them, λ is the weight parameter; K is the keyword; E is the entity noun; S vec (K, E) represents the vector space similarity between the retrieval keyword and the entity label, which is calculated as: Among them, k is the word vector corresponding to the search keyword, and e is the word vector corresponding to the entity name. The larger the cosine value, the smaller the angle between the two word vectors, and the higher the similarity between the words; S lit (K, E) represents the literal similarity between the search keyword and the entity label, and the calculation formula is: Where M(K,E) represents the maximum length of the search keyword K and the entity name string, and L(K,E) represents the Levenshtein edit distance between the search keyword and the entity label; According to formula (1), the semantic similarity between the search keyword and the entity name is obtained, and the top N entities with the highest similarity are selected as search expansion terms; The number of common attributes between the entities is used to determine whether there is a relationship between two entities. altr (E1, E2) represents the attribute similarity between entity E1 and entity E2, and the specific formula is: Where I(E1,E2) represents the number of attributes shared by entities E1 and E2; U(E1,E2) represents the number of all attributes of entities E1 and E2; Considering the distance between entity nodes and the number of common attributes between two nodes, the semantic similarity between entities can be expressed as: S entity (E1,E2)=(1-μ)S altr (E1,E2)+μD(E1,E2) (5) Among them, D(E1, E2) represents the shortest path between two entity nodes, and μ is the weight parameter.

Images